AMD NVIDIA Linux GPU OpenCL Compute

AMD Polaris and NVIDIA Pascal OpenCL benchmarks on Ubuntu 16.04 LTS Linux. Benchmarks by Michael Larabel for a future article on phoronix.com..

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1608190-KH-1608193LO70
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
Show Result Confidence Charts

Limit displaying results to tests within:

NVIDIA GPU Compute 3 Tests
OpenCL 4 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GeForce GTX 950
August 17 2016
 
GeForce GTX 960
August 18 2016
 
GeForce GTX 970
August 17 2016
 
GeForce GTX 980
August 17 2016
 
GeForce GTX 980 Ti
August 18 2016
 
GeForce GTX TITAN X Maxwell
August 18 2016
 
GeForce GTX 1060
August 17 2016
 
GeForce GTX 1070
August 17 2016
 
GeForce GTX 1080
August 17 2016
 
Radeon R9 285
August 18 2016
 
Radeon R9 290
August 18 2016
 
Radeon R9 Fury
August 18 2016
 
Radeon RX 460
August 18 2016
 
Radeon RX 470 OC
August 18 2016
 
Radeon RX 480
August 18 2016
 
Radeon R7 260X
August 18 2016
 
R9 Fury
August 19 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):


AMD NVIDIA Linux GPU OpenCL ComputeProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionGeForce GTX 950GeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN X MaxwellGeForce GTX 1060GeForce GTX 1070GeForce GTX 1080Radeon R9 285Radeon R9 290Radeon R9 FuryRadeon RX 460Radeon RX 470 OCRadeon RX 480Radeon R7 260XR9 FuryIntel Xeon E3-1280 v5 @ 4.00GHz (8 Cores)MSI C236A WORKSTATION (MS-7998) v1.0Intel Sky Lake16384MB4 x 120GB TOSHIBA-TR150 + Samsung SSD 950 PRO 256GBeVGA NVIDIA GeForce GTX 950 2048MB (1202/3304MHz)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 20160609ext43840x2160eVGA NVIDIA GeForce GTX 960 2048MB (1277/3505MHz)eVGA NVIDIA GeForce GTX 970 4096MB (1163/3505MHz)NVIDIA GeForce GTX 980 4096MB (1126/3505MHz)NVIDIA GeForce GTX 980 Ti 6144MB (999/3505MHz)NVIDIA GeForce GTX TITAN X 12288MB (1001/3505MHz)NVIDIA GeForce GTX 1060 6GB 6144MB (1506/4006MHz)NVIDIA GeForce GTX 1070 8192MB (1504/4006MHz)NVIDIA GeForce GTX 1080 8192MB (1612/5005MHz)XFX AMD Radeon R9 200 2048MB4.5.13448XFX AMD Radeon R9 200 4096MBSapphire AMD Radeon R9 Fury 4096MBAMD Radeon RX 460 2048MBSapphire AMD Radeon RX 470 4096MBAMD Radeon RX 480 8192MBSapphire AMD Radeon R7 200 2048MBIntel Core i5-6600 @ 3.90GHz (4 Cores)ASRock Z170 Pro4SIntel Sky Lake /DRAM120GB GOODRAM C50 + 32GB ADATA SP800 + 250GB Crucial_CT250MX2 + 1000GB Seagate ST1000DM003-1SB1Sapphire AMD Radeon R9 Fury 4096MBRealtek ALC892IPS224Xfce 4.121920x1080OpenBenchmarking.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 -vProcessor Details- GeForce GTX 950: Scaling Governor: intel_pstate performance- GeForce GTX 960: Scaling Governor: intel_pstate performance- GeForce GTX 970: Scaling Governor: intel_pstate performance- GeForce GTX 980: Scaling Governor: intel_pstate performance- GeForce GTX 980 Ti: Scaling Governor: intel_pstate performance- GeForce GTX TITAN X Maxwell: Scaling Governor: intel_pstate performance- GeForce GTX 1060: Scaling Governor: intel_pstate performance- GeForce GTX 1070: Scaling Governor: intel_pstate performance- GeForce GTX 1080: Scaling Governor: intel_pstate performance- Radeon R9 285: Scaling Governor: intel_pstate performance- Radeon R9 290: Scaling Governor: intel_pstate performance- Radeon R9 Fury: Scaling Governor: intel_pstate performance- Radeon RX 460: Scaling Governor: intel_pstate performance- Radeon RX 470 OC: Scaling Governor: intel_pstate performance- Radeon RX 480: Scaling Governor: intel_pstate performance- Radeon R7 260X: Scaling Governor: intel_pstate performance- R9 Fury: Scaling Governor: intel_pstate powersaveOpenCL Details- GeForce GTX 950: GPU Compute Cores: 768- 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 Maxwell: GPU Compute Cores: 3072- GeForce GTX 1060: GPU Compute Cores: 1280- GeForce GTX 1070: GPU Compute Cores: 1920- GeForce GTX 1080: GPU Compute Cores: 2560System Details- GeForce GTX 950: GPU Compute Cores: 768.- 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 Maxwell: GPU Compute Cores: 3072.- GeForce GTX 1060: GPU Compute Cores: 1280.- GeForce GTX 1070: GPU Compute Cores: 1920.- GeForce GTX 1080: GPU Compute Cores: 2560.Graphics Details- Radeon R9 285, Radeon R9 290, Radeon R9 Fury, Radeon RX 460, Radeon RX 470 OC, Radeon RX 480, Radeon R7 260X, R9 Fury: GLAMOR

GeForce GTX 950GeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN X MaxwellGeForce GTX 1060GeForce GTX 1070GeForce GTX 1080Radeon R9 285Radeon R9 290Radeon R9 FuryRadeon RX 460Radeon RX 470 OCRadeon RX 480Radeon R7 260XR9 FuryResult OverviewPhoronix Test Suite100%329%559%788%1017%MixbenchLuxMarkLuxMarkMixbenchIntegerGPU - Luxball HDRGPU - MicrophoneSingle Precision

AMD NVIDIA Linux GPU OpenCL Computeshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthshoc: OpenCL - Triadmixbench: Single Precisionmixbench: Double Precisionshoc: OpenCL - Max SP Flopsshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashmixbench: Integerjuliagpu: GPUmandelbulbgpu: GPUluxmark: GPU - Luxball HDRluxmark: GPU - Microphoneluxmark: GPU - Hotelfinancebench: Black-Scholes OpenCLGeForce GTX 950GeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN X MaxwellGeForce GTX 1060GeForce GTX 1070GeForce GTX 1080Radeon R9 285Radeon R9 290Radeon R9 FuryRadeon RX 460Radeon RX 470 OCRadeon RX 480Radeon R7 260XR9 Fury12.4513.20244.0310.832153.3870.302210.69115.102.70633.3367614640.4737190054.6759883116112226.7112.4813.20270.3510.742788.5092.972943.15123.933.86837.7082726348.8044815450.0362693177129717.7812.4813.14284.3111.364157.94137.334336.29209.225.461222.22107959473.8358806852.00110215873184614.0812.4913.17331.4311.454747.21159.025019.38212.196.241405.02117722561.5063820883.30122216111198310.6612.4313.15349.4211.685874.35197.786173.34203.377.741727.27132005802.9771117240.8015216798125158.9512.4313.22354.0111.696585.34221.826885.13203.768.391924.27140161877.9776108478.6315666830924977.8512.4713.21369.7111.364407.44151.944785.98214.665.631367.78114733414.7762160246.30114595204211211.2112.4813.23451.9611.706502.90226.757080.77294.608.372008.75143250390.9777948508.2315839735030837.7912.5313.19521.9211.828556.64300.169389.10327.7811.802688.91164343285.1389708762.4712513655729336.0312.9512.54162.348.421764.933275.6216.703.77648.24850440448.938.21251.576.014585.084776.9845.455.521575.6315344691412.9412.96221.964.006597.137130.6436.656.041358.2719564879411.506.847.1476.633.121718.132119.7634.042.37425.185455287612.9612.37156.228.344891.215145.0927.794.681021.881273270309.2112.9612.68162.743.985516.275805.7827.375.171152.821418077987.5511.529.2797.957.05841.282028.0920.372.36328.77464923126724.13449.371428.801993090227.72OpenBenchmarking.org

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringRadeon RX 460Radeon R7 260XGeForce GTX 1060GeForce GTX 950GeForce GTX 960Radeon RX 480Radeon RX 470 OCRadeon R9 285GeForce GTX 1070GeForce GTX 970GeForce GTX 1080GeForce GTX 980Radeon R9 FuryRadeon R9 290GeForce GTX 980 TiGeForce GTX TITAN X Maxwell50100150200250Min: 44.4 / Avg: 76.79 / Max: 98.7Min: 48.3 / Avg: 84.62 / Max: 110.7Min: 38.4 / Avg: 106.15 / Max: 162.5Min: 43.2 / Avg: 106.98 / Max: 146Min: 43.8 / Avg: 110.57 / Max: 167.4Min: 57.4 / Avg: 128.01 / Max: 184.2Min: 52.9 / Avg: 132.38 / Max: 199.1Min: 54.2 / Avg: 132.75 / Max: 179Min: 40.4 / Avg: 133.78 / Max: 202.8Min: 46.2 / Avg: 138 / Max: 213.1Min: 40 / Avg: 145.64 / Max: 243.4Min: 45.9 / Avg: 149.24 / Max: 231.6Min: 55.1 / Avg: 154.66 / Max: 234.6Min: 63.1 / Avg: 163.82 / Max: 246.2Min: 49.5 / Avg: 182.17 / Max: 277.6Min: 50.3 / Avg: 193.1 / Max: 303.2

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthGeForce GTX 1080GeForce GTX 1070GeForce GTX 1060GeForce GTX 950GeForce GTX 960GeForce GTX 980GeForce GTX 970GeForce GTX 980 TiRadeon R9 FuryGeForce GTX TITAN X MaxwellRadeon R9 290Radeon RX 480Radeon RX 470 OCRadeon R9 285Radeon R7 260XRadeon RX 4600.95851.9172.87553.8344.79254.263.763.742.432.422.282.272.011.991.951.821.641.481.401.241.02

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadRadeon RX 480Radeon RX 470 OCRadeon R9 285Radeon R9 FuryGeForce GTX 1080GeForce GTX 980GeForce GTX 1070GeForce GTX 970GeForce GTX 960GeForce GTX 1060GeForce GTX 950GeForce GTX TITAN X MaxwellGeForce GTX 980 TiRadeon R7 260XRadeon R9 290Radeon RX 4603691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.93, N = 3SE +/- 0.00, N = 312.9612.9612.9512.9412.5312.4912.4812.4812.4812.4712.4512.4312.4311.528.936.841. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackGeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 1060GeForce GTX 960GeForce GTX 950GeForce GTX 1080GeForce GTX 980GeForce GTX 980 TiGeForce GTX 970Radeon R9 FuryRadeon RX 480Radeon R9 285Radeon RX 470 OCRadeon R7 260XRadeon R9 290Radeon RX 4603691215SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.46, N = 3SE +/- 0.22, N = 3SE +/- 0.30, N = 3SE +/- 0.24, N = 3SE +/- 1.53, N = 3SE +/- 1.36, N = 3SE +/- 0.00, N = 313.2313.2213.2113.2013.2013.1913.1713.1513.1412.9612.6812.5412.379.278.217.141. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthGeForce GTX 1080GeForce GTX 1070GeForce GTX 1060GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 980GeForce GTX 970GeForce GTX 960Radeon R9 290GeForce GTX 950Radeon R9 FuryRadeon RX 480Radeon R9 285Radeon RX 470 OCRadeon R7 260XRadeon RX 460110220330440550SE +/- 0.40, N = 3SE +/- 0.97, N = 3SE +/- 1.18, N = 3SE +/- 2.25, N = 3SE +/- 0.27, N = 3SE +/- 0.23, N = 3SE +/- 0.51, N = 3SE +/- 0.25, N = 3SE +/- 1.94, N = 3SE +/- 0.50, N = 3SE +/- 1.10, N = 3SE +/- 0.23, N = 3SE +/- 1.03, N = 3SE +/- 0.37, N = 3SE +/- 0.15, N = 3SE +/- 0.57, N = 3521.92451.96369.71354.01349.42331.43284.31270.35251.57244.03221.96162.74162.34156.2297.9576.631. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadGeForce GTX 1080GeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 980GeForce GTX 1060GeForce GTX 970GeForce GTX 950GeForce GTX 960Radeon R9 285Radeon RX 470 OCRadeon R7 260XRadeon R9 290Radeon R9 FuryRadeon RX 480Radeon RX 4603691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 3SE +/- 0.85, N = 3SE +/- 0.33, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 311.8211.7011.6911.6811.4511.3611.3610.8310.748.428.347.056.014.003.983.121. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2016-06-06Benchmark: Single PrecisionGeForce GTX 1080R9 FuryRadeon R9 FuryGeForce GTX TITAN X MaxwellGeForce GTX 1070GeForce GTX 980 TiRadeon RX 480Radeon RX 470 OCGeForce GTX 980Radeon R9 290GeForce GTX 1060GeForce GTX 970GeForce GTX 960GeForce GTX 950Radeon R9 285Radeon RX 460Radeon R7 260X2K4K6K8K10KSE +/- 198.39, N = 3SE +/- 0.37, N = 3SE +/- 1.05, N = 3SE +/- 8.77, N = 3SE +/- 85.54, N = 3SE +/- 8.48, N = 3SE +/- 0.43, N = 3SE +/- 0.41, N = 3SE +/- 1.51, N = 3SE +/- 0.85, N = 3SE +/- 4.04, N = 3SE +/- 2.04, N = 3SE +/- 1.13, N = 3SE +/- 0.18, N = 3SE +/- 193.76, N = 3SE +/- 260.96, N = 3SE +/- 45.05, N = 38556.646724.136597.136585.346502.905874.355516.274891.214747.214585.084407.444157.942788.502153.381764.931718.13841.281. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsGeForce GTX 1080GeForce GTX 1070GeForce GTX 1060Radeon RX 480Radeon R9 FuryGeForce GTX TITAN X MaxwellRadeon RX 470 OCGeForce GTX 980 TiGeForce GTX 980GeForce GTX 970Radeon R9 290Radeon RX 460GeForce GTX 960Radeon R9 285Radeon R7 260XGeForce GTX 950153045607567.3456.4447.0341.5737.8936.0535.0234.5334.3932.9931.5626.9426.7023.9823.5020.80

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2016-06-06Benchmark: Double PrecisionR9 FuryGeForce GTX 1080GeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 980GeForce GTX 1060GeForce GTX 970GeForce GTX 960GeForce GTX 950100200300400500SE +/- 0.00, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.65, N = 3SE +/- 0.25, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3449.37300.16226.75221.82197.78159.02151.94137.3392.9770.301. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsGeForce GTX 1080Radeon R9 FuryGeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiRadeon RX 480Radeon RX 470 OCGeForce GTX 980GeForce GTX 1060Radeon R9 290GeForce GTX 970Radeon R9 285GeForce GTX 960GeForce GTX 950Radeon RX 460Radeon R7 260X2K4K6K8K10KSE +/- 18.40, N = 3SE +/- 0.31, N = 3SE +/- 17.78, N = 3SE +/- 4.90, N = 3SE +/- 16.67, N = 3SE +/- 0.27, N = 3SE +/- 0.30, N = 3SE +/- 2.08, N = 3SE +/- 13.64, N = 3SE +/- 0.49, N = 3SE +/- 0.64, N = 3SE +/- 0.30, N = 3SE +/- 0.74, N = 3SE +/- 0.17, N = 3SE +/- 9.80, N = 3SE +/- 0.38, N = 39389.107130.647080.776885.136173.345805.785145.095019.384785.984776.984336.293275.622943.152210.692119.762028.091. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPGeForce GTX 1080GeForce GTX 1070GeForce GTX 1060GeForce GTX 980GeForce GTX 970GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 960GeForce GTX 950Radeon R9 290Radeon R9 FuryRadeon RX 460Radeon RX 470 OCRadeon RX 480Radeon R7 260XRadeon R9 28570140210280350SE +/- 0.85, N = 3SE +/- 0.63, N = 3SE +/- 0.46, N = 3SE +/- 0.45, N = 3SE +/- 0.49, N = 3SE +/- 1.14, N = 3SE +/- 0.52, N = 3SE +/- 0.52, N = 3SE +/- 0.17, N = 3SE +/- 13.07, N = 3SE +/- 0.29, N = 3SE +/- 6.49, N = 3SE +/- 0.20, N = 3SE +/- 0.73, N = 3SE +/- 10.55, N = 3SE +/- 0.32, N = 3327.78294.60214.66212.19209.22203.76203.37123.93115.1045.4536.6534.0427.7927.3720.3716.701. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashGeForce GTX 1080GeForce GTX TITAN X MaxwellGeForce GTX 1070GeForce GTX 980 TiGeForce GTX 980Radeon R9 FuryGeForce GTX 1060Radeon R9 290GeForce GTX 970Radeon RX 480Radeon RX 470 OCGeForce GTX 960Radeon R9 285GeForce GTX 950Radeon RX 460Radeon R7 260X3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.25, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 311.808.398.377.746.246.045.635.525.465.174.683.863.772.702.372.361. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2016-06-06Benchmark: IntegerGeForce GTX 1080GeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiRadeon R9 290R9 FuryGeForce GTX 980GeForce GTX 1060Radeon R9 FuryGeForce GTX 970Radeon RX 480Radeon RX 470 OCGeForce GTX 960Radeon R9 285GeForce GTX 950Radeon RX 460Radeon R7 260X6001200180024003000SE +/- 2.27, N = 3SE +/- 27.29, N = 3SE +/- 2.12, N = 3SE +/- 4.84, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 2.17, N = 3SE +/- 0.55, N = 3SE +/- 44.24, N = 3SE +/- 1.90, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.54, N = 3SE +/- 0.09, N = 3SE +/- 0.60, N = 3SE +/- 1.34, N = 3SE +/- 37.53, N = 32688.912008.751924.271727.271575.631428.801405.021367.781358.271222.221152.821021.88837.70648.24633.33425.18328.771. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

JuliaGPU

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGeForce GTX 1080GeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 980GeForce GTX 1060GeForce GTX 970GeForce GTX 960GeForce GTX 95040M80M120M160M200MSE +/- 413616.13, N = 3SE +/- 70686.86, N = 3SE +/- 140800.69, N = 3SE +/- 172847.35, N = 3SE +/- 182338.25, N = 3SE +/- 291564.71, N = 3SE +/- 474968.42, N = 3SE +/- 462038.74, N = 3SE +/- 109829.25, N = 3164343285.13143250390.97140161877.97132005802.97117722561.50114733414.77107959473.8382726348.8067614640.471. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

OpenBenchmarking.orgSamples/sec Per Watt, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGeForce GTX 1080GeForce GTX 1070GeForce GTX 1060GeForce GTX 970GeForce GTX 980GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 960GeForce GTX 950300K600K900K1200K1500K1492898.881364506.031258904.56904351.51901570.45834214.13828315.02786780.08640150.26

MandelbulbGPU

MandelbulbGPU is an OpenCL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterMandelbulbGPU 1.0pts1OpenCL Device: GPUGeForce GTX 1080GeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiGeForce GTX 980GeForce GTX 1060GeForce GTX 970GeForce GTX 960GeForce GTX 95020M40M60M80M100MSE +/- 419322.49, N = 3SE +/- 473735.75, N = 3SE +/- 202155.32, N = 3SE +/- 608054.60, N = 3SE +/- 2971.36, N = 3SE +/- 289951.05, N = 3SE +/- 104185.29, N = 3SE +/- 60575.76, N = 3SE +/- 13927.02, N = 389708762.4777948508.2376108478.6371117240.8063820883.3062160246.3058806852.0044815450.0337190054.671. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

OpenBenchmarking.orgSamples/sec Per Watt, More Is BetterMandelbulbGPU 1.0pts1OpenCL Device: GPUGeForce GTX 1080GeForce GTX 1070GeForce GTX 1060GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX 960GeForce GTX TITAN X MaxwellGeForce GTX 950200K400K600K800K1000K802942.60749144.72711704.22563553.92563390.57463103.37452300.59446973.89386239.70

LuxMark

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: MicrophoneGeForce GTX 1070Radeon RX 480GeForce GTX 1060Radeon R9 FuryGeForce GTX 1080Radeon RX 470 OCGeForce GTX 970GeForce GTX 980 TiGeForce GTX 980GeForce GTX TITAN X MaxwellRadeon R9 290Radeon RX 460GeForce GTX 960GeForce GTX 950Radeon R9 285Radeon R7 260X112233445548.0445.7443.0742.6542.1939.4736.9736.5735.5235.0631.9330.1525.8925.3024.6923.92

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: Luxball HDRR9 FuryRadeon R9 FuryGeForce GTX 1070GeForce GTX TITAN X MaxwellRadeon R9 290GeForce GTX 980 TiRadeon RX 480Radeon RX 470 OCGeForce GTX 1080GeForce GTX 980GeForce GTX 1060GeForce GTX 970Radeon R9 285GeForce GTX 960GeForce GTX 950Radeon RX 460Radeon R7 260X4K8K12K16K20KSE +/- 93.11, N = 3SE +/- 79.45, N = 3SE +/- 73.73, N = 3SE +/- 44.68, N = 3SE +/- 16.65, N = 3SE +/- 143.18, N = 3SE +/- 71.34, N = 3SE +/- 63.01, N = 3SE +/- 12.12, N = 3SE +/- 71.17, N = 3SE +/- 4.26, N = 3SE +/- 26.69, N = 3SE +/- 33.31, N = 3SE +/- 4.33, N = 3SE +/- 14.86, N = 3SE +/- 14.50, N = 3SE +/- 11.78, N = 319930195641583915666153441521614180127321251312221114591102185046269598854554649

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: Luxball HDRGeForce GTX 1070Radeon R9 FuryGeForce GTX 1060Radeon RX 480GeForce GTX 1080Radeon RX 470 OCGeForce GTX 980 TiGeForce GTX 980Radeon R9 290GeForce GTX TITAN X MaxwellGeForce GTX 970Radeon RX 460Radeon R9 285GeForce GTX 960GeForce GTX 950Radeon R7 260X2040608010094.9187.8283.5580.3276.3468.1066.8965.3364.9264.1263.5456.3448.6447.7147.5846.20

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: HotelGeForce GTX 1070GeForce GTX 1080GeForce GTX 1060GeForce GTX 980 TiGeForce GTX TITAN X MaxwellGeForce GTX 970GeForce GTX 980GeForce GTX 960GeForce GTX 9504812162016.8115.4114.6910.7810.5210.4410.349.018.38

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: MicrophoneR9 FuryRadeon R9 FuryGeForce GTX TITAN X MaxwellGeForce GTX 980 TiRadeon RX 480GeForce GTX 1070Radeon RX 470 OCRadeon R9 290GeForce GTX 1080GeForce GTX 980GeForce GTX 970GeForce GTX 1060Radeon R9 285GeForce GTX 960GeForce GTX 950Radeon RX 460Radeon R7 260X2K4K6K8K10KSE +/- 9.60, N = 3SE +/- 39.47, N = 3SE +/- 9.00, N = 3SE +/- 1.73, N = 3SE +/- 1.20, N = 3SE +/- 8.69, N = 3SE +/- 0.33, N = 3SE +/- 9.39, N = 3SE +/- 1.76, N = 3SE +/- 0.88, N = 3SE +/- 5.57, N = 3SE +/- 2.40, N = 3SE +/- 18.84, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 390228794830979817798735070306914655761115873520440443177311628762312

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: HotelGeForce GTX 1070GeForce GTX 1080GeForce GTX 980 TiGeForce GTX TITAN X MaxwellGeForce GTX 1060GeForce GTX 980GeForce GTX 970GeForce GTX 960GeForce GTX 9507001400210028003500SE +/- 0.58, N = 3SE +/- 2.00, N = 3SE +/- 37.43, N = 3SE +/- 3.61, N = 3SE +/- 1.20, N = 3SE +/- 4.00, N = 3SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3308329332515249721121983184612971122

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLGeForce GTX 1080Radeon RX 480R9 FuryGeForce GTX 1070GeForce GTX TITAN X MaxwellGeForce GTX 980 TiRadeon RX 470 OCGeForce GTX 980GeForce GTX 1060Radeon R9 FuryGeForce GTX 970GeForce GTX 960GeForce GTX 950612182430SE +/- 0.01, N = 3SE +/- 0.22, N = 3SE +/- 1.27, N = 6SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.22, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 2.57, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 1.69, N = 36.037.557.727.797.858.959.2110.6611.2111.5014.0817.7826.711. (CXX) g++ options: -O3 -lOpenCL

LuxMark

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.0System Power Consumption MonitorRadeon RX 460Radeon R7 260XGeForce GTX 950GeForce GTX 960GeForce GTX 1060GeForce GTX 1080GeForce GTX 1070GeForce GTX 970Radeon R9 285Radeon RX 480Radeon RX 470 OCGeForce GTX 980Radeon R9 FuryGeForce GTX 980 TiRadeon R9 290GeForce GTX TITAN X Maxwell50100150200250Min: 44.4 / Avg: 96.82 / Max: 98.7Min: 48.9 / Avg: 100.63 / Max: 103.2Min: 43.2 / Avg: 125.85 / Max: 131.1Min: 98.5 / Avg: 131.39 / Max: 133.5Min: 133.4 / Avg: 137.14 / Max: 138.9Min: 40 / Avg: 163.91 / Max: 170.1Min: 40.4 / Avg: 166.89 / Max: 173.7Min: 86.2 / Avg: 173.44 / Max: 177.1Min: 54.2 / Avg: 174.83 / Max: 179Min: 58.6 / Avg: 176.55 / Max: 184.2Min: 54.3 / Avg: 186.97 / Max: 199.1Min: 45.9 / Avg: 187.08 / Max: 194Min: 55.4 / Avg: 222.78 / Max: 234.6Min: 59.5 / Avg: 227.47 / Max: 238Min: 63.2 / Avg: 236.36 / Max: 246.2Min: 50.3 / Avg: 244.33 / Max: 254.9

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.0System Power Consumption MonitorRadeon RX 460Radeon R7 260XGeForce GTX 1060GeForce GTX 960GeForce GTX 950GeForce GTX 1070GeForce GTX 1080GeForce GTX 970Radeon R9 285Radeon RX 480GeForce GTX 980Radeon RX 470 OCRadeon R9 FuryRadeon R9 290GeForce GTX 980 TiGeForce GTX TITAN X Maxwell4080120160200Min: 46.3 / Avg: 95.39 / Max: 97.6Min: 50.8 / Avg: 96.65 / Max: 99.3Min: 40 / Avg: 120.84 / Max: 124.1Min: 44 / Avg: 122.71 / Max: 126.1Min: 76 / Avg: 123.15 / Max: 126.8Min: 43.2 / Avg: 153.01 / Max: 155.8Min: 42.3 / Avg: 155.42 / Max: 159.2Min: 47.2 / Avg: 158.84 / Max: 165.2Min: 71.6 / Avg: 163.81 / Max: 169.2Min: 67.3 / Avg: 170.49 / Max: 176.8Min: 48.4 / Avg: 172.06 / Max: 181.7Min: 69.3 / Avg: 178.13 / Max: 187.5Min: 57.9 / Avg: 206.19 / Max: 213.3Min: 78.6 / Avg: 216.57 / Max: 227.2Min: 66.1 / Avg: 218.21 / Max: 223.9Min: 66.4 / Avg: 237.03 / Max: 242.6

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.0System Power Consumption MonitorRadeon RX 460Radeon R9 FuryRadeon R7 260XRadeon RX 480Radeon RX 470 OCRadeon R9 285Radeon R9 290GeForce GTX 950GeForce GTX 1060GeForce GTX 960GeForce GTX 970GeForce GTX 1070GeForce GTX 1080GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN X Maxwell50100150200250Min: 55.3 / Avg: 62.12 / Max: 67.3Min: 58.3 / Avg: 70.63 / Max: 77.6Min: 66.1 / Avg: 71.26 / Max: 79.3Min: 60.3 / Avg: 73.58 / Max: 77Min: 68.5 / Avg: 74.85 / Max: 88.6Min: 71.4 / Avg: 81.13 / Max: 95.3Min: 81.8 / Avg: 84.84 / Max: 87.8Min: 43.9 / Avg: 133.94 / Max: 140.1Min: 72.9 / Avg: 143.73 / Max: 147.8Min: 44.4 / Avg: 143.88 / Max: 146.8Min: 46.9 / Avg: 176.81 / Max: 181.4Min: 42.9 / Avg: 183.4 / Max: 188.3Min: 42.3 / Avg: 190.35 / Max: 194.9Min: 47.8 / Avg: 191.79 / Max: 199.2Min: 51.6 / Avg: 233.39 / Max: 243.6Min: 53.7 / Avg: 237.45 / Max: 253.9

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRadeon RX 460Radeon R7 260XGeForce GTX 1060GeForce GTX 950GeForce GTX 960GeForce GTX 1070GeForce GTX 970Radeon R9 285GeForce GTX 1080Radeon RX 480GeForce GTX 980Radeon RX 470 OCRadeon R9 290GeForce GTX 980 TiRadeon R9 FuryGeForce GTX TITAN X Maxwell50100150200250Min: 45.4 / Avg: 78.7 / Max: 90.1Min: 50.1 / Avg: 86.31 / Max: 110.7Min: 39.8 / Avg: 101.76 / Max: 162.5Min: 100.1 / Avg: 106.29 / Max: 146Min: 102.5 / Avg: 110.22 / Max: 167.4Min: 42.1 / Avg: 125.46 / Max: 191Min: 46.9 / Avg: 131.44 / Max: 203.8Min: 85.3 / Avg: 136.57 / Max: 156.9Min: 41.6 / Avg: 139.42 / Max: 239.6Min: 58.1 / Avg: 139.65 / Max: 184.1Min: 132.6 / Avg: 145.97 / Max: 231.6Min: 67.1 / Avg: 146.91 / Max: 166.5Min: 64.8 / Avg: 151.38 / Max: 196.5Min: 51.2 / Avg: 178.77 / Max: 277.6Min: 58.1 / Avg: 188.21 / Max: 219Min: 56.7 / Avg: 190.99 / Max: 303.2

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRadeon RX 460Radeon R7 260XGeForce GTX 1060Radeon RX 480GeForce GTX 950Radeon RX 470 OCRadeon R9 FuryGeForce GTX 960Radeon R9 285GeForce GTX 1070GeForce GTX 1080GeForce GTX 970Radeon R9 290GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN X Maxwell4080120160200Min: 46.1 / Avg: 75.1 / Max: 82.4Min: 50 / Avg: 78.73 / Max: 88.9Min: 39.6 / Avg: 98.87 / Max: 114.5Min: 63.6 / Avg: 99.32 / Max: 121.2Min: 43.9 / Avg: 100.35 / Max: 118.2Min: 56.8 / Avg: 105.47 / Max: 125.8Min: 58.6 / Avg: 111.6 / Max: 141.3Min: 105.6 / Avg: 111.63 / Max: 118.8Min: 73.3 / Avg: 115.8 / Max: 147.4Min: 41.9 / Avg: 120.3 / Max: 141Min: 41.9 / Avg: 122.51 / Max: 141.9Min: 46.4 / Avg: 125.36 / Max: 145.2Min: 92.8 / Avg: 138.33 / Max: 188.2Min: 107.6 / Avg: 145.23 / Max: 159.1Min: 51 / Avg: 173.78 / Max: 208Min: 100.1 / Avg: 181.34 / Max: 220.2

JuliaGPU

OpenBenchmarking.orgWatts, Fewer Is BetterJuliaGPU 1.2pts1System Power Consumption MonitorRadeon RX 460Radeon R9 FuryRadeon R7 260XRadeon RX 470 OCRadeon RX 480GeForce GTX 1060GeForce GTX 1070GeForce GTX 960GeForce GTX 950Radeon R9 285GeForce GTX 1080GeForce GTX 970Radeon R9 290GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN X Maxwell306090120150Min: 51.6 / Avg: 58.46 / Max: 60.5Min: 57.3 / Avg: 75.59 / Max: 98.1Min: 50.6 / Avg: 77.24 / Max: 81.5Min: 55.4 / Avg: 80.42 / Max: 84.3Min: 58.8 / Avg: 84.51 / Max: 90.3Min: 38.7 / Avg: 91.14 / Max: 102.2Min: 41 / Avg: 104.98 / Max: 118.9Min: 44.3 / Avg: 105.15 / Max: 112.5Min: 81.9 / Avg: 105.62 / Max: 108.9Min: 55.8 / Avg: 106.08 / Max: 124.3Min: 40.7 / Avg: 110.08 / Max: 129.2Min: 46.6 / Avg: 119.38 / Max: 129.1Min: 65.3 / Avg: 130.24 / Max: 152.5Min: 102.3 / Avg: 130.58 / Max: 137.8Min: 115.3 / Avg: 159.37 / Max: 171.9Min: 133.8 / Avg: 168.02 / Max: 180

MandelbulbGPU

OpenBenchmarking.orgWatts, Fewer Is BetterMandelbulbGPU 1.0pts1System Power Consumption MonitorRadeon RX 460Radeon R9 FuryRadeon RX 470 OCRadeon R7 260XGeForce GTX 1060Radeon RX 480GeForce GTX 950GeForce GTX 960GeForce GTX 1070GeForce GTX 970GeForce GTX 1080GeForce GTX 980Radeon R9 285Radeon R9 290GeForce GTX 980 TiGeForce GTX TITAN X Maxwell306090120150Min: 45.6 / Avg: 60.06 / Max: 62.8Min: 57.3 / Avg: 76.06 / Max: 83.7Min: 55 / Avg: 76.23 / Max: 83.5Min: 50 / Avg: 77.5 / Max: 83Min: 59.2 / Avg: 87.34 / Max: 99.4Min: 88 / Avg: 88.59 / Max: 89.4Min: 44.1 / Avg: 96.29 / Max: 105.4Min: 80.8 / Avg: 99.08 / Max: 106.9Min: 68.1 / Avg: 104.05 / Max: 117.1Min: 48.2 / Avg: 104.35 / Max: 122.8Min: 70.2 / Avg: 111.73 / Max: 125.8Min: 52.8 / Avg: 113.28 / Max: 132.7Min: 113.8 / Avg: 114.86 / Max: 116.5Min: 141.1 / Avg: 144.95 / Max: 147.4Min: 130.3 / Avg: 153.57 / Max: 166Min: 164 / Avg: 170.28 / Max: 175.1

31 Results Shown

System Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  OpenCL - Texture Read Bandwidth
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Bus Speed Download
  OpenCL - Bus Speed Readback
  OpenCL - Texture Read Bandwidth
  OpenCL - Triad
Mixbench
SHOC Scalable HeterOgeneous Computing
Mixbench
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Max SP Flops
  OpenCL - FFT SP
  OpenCL - MD5 Hash
Mixbench
JuliaGPU
JuliaGPU
MandelbulbGPU
MandelbulbGPU:
  GPU
  GPU - Microphone
LuxMark
LuxMark:
  GPU - Luxball HDR
  GPU - Hotel
LuxMark:
  GPU - Microphone
  GPU - Hotel
FinanceBench
LuxMark:
  System Power Consumption Monitor:
    Watts
    Watts
    Watts
    Watts
    Watts
    Watts
    Watts