AMDGPU-PRO 17.40 ROCm, NVIDIA 384.98 12-Way NVIDIA AMD GPU Linux OpenCL Comparison

Radeon and NVIDIA Linux OpenCL compute comparison for a future article on Phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1711111-AL-OPENCLING78
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
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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

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
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Radeon RX 580
November 11 2017
 
Radeon R9 Fury
November 11 2017
 
Radeon RX Vega 56
November 11 2017
 
Radeon RX Vega 64
November 11 2017
 
GeForce GTX 980 Ti
November 10 2017
 
GeForce GTX 1050
November 10 2017
 
GeForce GTX 1050 Ti
November 10 2017
 
GeForce GTX 1060
November 10 2017
 
GeForce GTX 1070
November 10 2017
 
GeForce GTX 1070 Ti
November 10 2017
 
GeForce GTX 1080
November 10 2017
 
GeForce GTX 1080 Ti
November 10 2017
 
Invert Behavior (Only Show Selected Data)
 

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):


AMDGPU-PRO 17.40 ROCm, NVIDIA 384.98 12-Way NVIDIA AMD GPU Linux OpenCL ComparisonProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionOpenCLGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 FuryIntel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads)ASUS PRIME Z370-AIntel Device 3ec216384MB525GB Crucial_CT525MX3 + Samsung SSD 950 PRO 256GBNVIDIA GeForce GTX 1060 6GB 6144MB (1506/4006MHz)Realtek GenericDELL P2415QIntel ConnectionUbuntu 17.044.10.0-38-generic (x86_64)Unity 7.5.0X Server 1.19.3NVIDIA 384.984.5.01.0.42GCC 6.3.0 20170406ext43840x2160eVGA NVIDIA GeForce GTX 1050 Ti 4096MB (1354/3504MHz)NVIDIA GeForce GTX 1070 8192MB (1506/4006MHz)Zotac NVIDIA GeForce GTX 1070 Ti 8192MB (1480/4006MHz)NVIDIA GeForce GTX 1080 8192MB (1607/5005MHz)NVIDIA GeForce GTX 1080 Ti 11264MB (1480/5508MHz)Zotac NVIDIA GeForce GTX 1050 2048MB (1354/3504MHz)NVIDIA GeForce GTX 980 Ti 6144MB (999/3505MHz)AMD Radeon RX Vega 8176MBamdgpu 1.3.994.5.13496OpenCL 2.0 AMD-APP (2482.3)MSI AMD Radeon RX 580 8192MBmodesetting 1.19.3Sapphire AMD Radeon 4096MBOpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --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=auto --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=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-target-system-zlib --with-tune=generic -v Processor Details- Scaling Governor: intel_pstate performanceOpenCL Details- GeForce GTX 1060: GPU Compute Cores: 1280- GeForce GTX 1050 Ti: GPU Compute Cores: 768- GeForce GTX 1070: GPU Compute Cores: 1920- GeForce GTX 1070 Ti: GPU Compute Cores: 2432- GeForce GTX 1080: GPU Compute Cores: 2560- GeForce GTX 1080 Ti: GPU Compute Cores: 3584- GeForce GTX 1050: GPU Compute Cores: 640- GeForce GTX 980 Ti: GPU Compute Cores: 2816System Details- GeForce GTX 1060: GPU Compute Cores: 1280.- GeForce GTX 1050 Ti: GPU Compute Cores: 768.- GeForce GTX 1070: GPU Compute Cores: 1920.- GeForce GTX 1070 Ti: GPU Compute Cores: 2432.- GeForce GTX 1080: GPU Compute Cores: 2560.- GeForce GTX 1080 Ti: GPU Compute Cores: 3584.- GeForce GTX 1050: GPU Compute Cores: 640.- GeForce GTX 980 Ti: GPU Compute Cores: 2816.Kernel Details- Radeon RX Vega 56, Radeon RX Vega 64, Radeon RX 580, Radeon R9 Fury: amdgpu.vm_fragment_size=9Graphics Details- Radeon RX Vega 56, Radeon RX Vega 64, Radeon RX 580, Radeon R9 Fury: GLAMOR

GeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 FuryResult OverviewPhoronix Test Suite100%205%310%414%519%JuliaGPUViennaCLcl-memLuxMarkSHOC Scalable HeterOgeneous Computing

GeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 FuryPer Watt Result OverviewPhoronix Test Suite100%151%202%253%304%SHOC Scalable HeterOgeneous ComputingLuxMarkLuxMarkLuxMarkOpenCL - Max SP FlopsGPU - HotelGPU - Luxball HDRGPU - Microphone

AMDGPU-PRO 17.40 ROCm, NVIDIA 384.98 12-Way NVIDIA AMD GPU Linux OpenCL Comparisonshoc: OpenCL - Max SP Flopsshoc: OpenCL - Texture Read Bandwidthshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Triaddarktable: Boat - OpenCLdarktable: Masskrug - OpenCLdarktable: Server Room - OpenCLluxmark: GPU - Luxball HDRluxmark: GPU - Microphoneluxmark: GPU - Hotelcl-mem: Readcl-mem: Writecl-mem: Copyjuliagpu: GPUviennacl: OpenCL LU FactorizationGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury4854377.95333.307.3111.944.234.601.281165053802108153.40140139.10121054859.2056.092702.95303.88197.934.1111.4613.3813.775.8772663706134294.2085.2086.8081114034.5047.557256.76451.38481.0910.6012.183.384.291.091624374302871205.40191.80186.70149885098.2059.669127.64503.41514.9713.8012.183.324.281.091615177473213205.50190.60186.5017146526663.249593.38524.60582.5614.3012.283.214.291.081289964573164229215.60208.90176402393.6063.5813411.90598.58990.4719.9012.462.724.221.0220163100373884338.10336.30317.10202544036.4065.242123.34267.71197.203.2411.4424.8913.466.2265863383113495.1086.3087.106715780843.416250.35351.98652.049.2812.263.714.491.511506983672495266.20238.80216.50138987453.5059.2410702.80377.52917.7314.2312.4721871110723750339.10321.90304.70331818340.6041.4712923.60431.291072.7816.9911.9423328126304262397.20378.20363.90348619117.2042.586261.97216.56521.557.7312.023.574.180.821450072682540208.40177.30174.90248225442.3014.137141.33249.34793.708.8411.393.084.271.052071183522489448.20381.60330.70269983077.7024.55OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury3K6K9K12K15K4854.002702.957256.769127.649593.3813411.902123.346250.3510702.8012923.606261.977141.331. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury153045607540.8927.9052.0559.7662.4666.3521.8132.5242.8141.4539.8336.83

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury60120180240300Min: 38.9 / Avg: 118.7 / Max: 163.6Min: 50 / Avg: 96.89 / Max: 107Min: 41.5 / Avg: 139.43 / Max: 169.9Min: 73.1 / Avg: 152.73 / Max: 248.4Min: 69.1 / Avg: 153.58 / Max: 182.1Min: 114.3 / Avg: 202.15 / Max: 323.2Min: 56.9 / Avg: 97.37 / Max: 116.1Min: 104 / Avg: 192.19 / Max: 240.9Min: 62.8 / Avg: 250.03 / Max: 273.6Min: 62.6 / Avg: 311.77 / Max: 357.7Min: 51.8 / Avg: 157.21 / Max: 212.5Min: 51.4 / Avg: 193.91 / Max: 296.3

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury130260390520650377.95303.88451.38503.41524.60598.58267.71351.98377.52431.29216.56249.341. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury2004006008001000333.30197.93481.09514.97582.56990.47197.20652.04917.731072.78521.55793.701. (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 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury5101520257.314.1110.6013.8014.3019.903.249.2814.2316.997.738.841. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury369121511.9411.4612.1812.1812.2812.4611.4412.2612.4711.9412.0211.391. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

Darktable

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.2.1Test: Boat - Acceleration: OpenCLGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX 580Radeon R9 Fury6121824304.2313.383.383.323.212.7224.893.713.573.08

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.2.1Test: Masskrug - Acceleration: OpenCLGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX 580Radeon R9 Fury481216204.6013.774.294.284.294.2213.464.494.184.27

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.2.1Test: Server Room - Acceleration: OpenCLGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX 580Radeon R9 Fury2468101.285.871.091.091.081.026.221.510.821.05

LuxMark

LuxMark is a multi-platform OpenGL benchmark using LuxRender / SLG2. LuxMark supports targeting different OpenCL devices and has multiple scenes available for rendering. LuxMark is a fully open-source OpenCL program with real-world rendering examples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: Luxball HDRGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury5K10K15K20K25K1165072661624316151128992016365861506921871233281450020711

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: Luxball HDRGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury2040608010077.8363.9389.3986.5672.3681.6159.0162.2585.8272.8279.6590.99

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.0System Power Consumption MonitorGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury60120180240300Min: 86.9 / Avg: 149.68 / Max: 155.8Min: 61.2 / Avg: 113.65 / Max: 117Min: 80.3 / Avg: 181.7 / Max: 190.9Min: 85.6 / Avg: 186.58 / Max: 194.4Min: 86 / Avg: 178.27 / Max: 185.1Min: 117.7 / Avg: 247.08 / Max: 256.7Min: 56.6 / Avg: 111.62 / Max: 114.8Min: 119.9 / Avg: 242.06 / Max: 250.3Min: 192.4 / Avg: 254.85 / Max: 276.2Min: 64.7 / Avg: 320.36 / Max: 336.9Min: 52.4 / Avg: 182.06 / Max: 201.3Min: 94.2 / Avg: 227.63 / Max: 241.9

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: MicrophoneGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury3K6K9K12K15K538037067430774764571003733838367110721263072688352

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: MicrophoneGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury102030405039.7334.8045.1945.5538.7943.9531.9236.6244.6940.9743.2542.72

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.0System Power Consumption MonitorGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury60120180240300Min: 38.6 / Avg: 135.41 / Max: 142.2Min: 36.6 / Avg: 106.5 / Max: 111.7Min: 41.7 / Avg: 164.43 / Max: 172.7Min: 45.3 / Avg: 170.09 / Max: 179.1Min: 40.7 / Avg: 166.47 / Max: 174.4Min: 47.7 / Avg: 228.36 / Max: 239.7Min: 36.8 / Avg: 105.98 / Max: 111.1Min: 50.6 / Avg: 228.51 / Max: 239.3Min: 122.2 / Avg: 247.77 / Max: 263.6Min: 68.1 / Avg: 308.3 / Max: 332.6Min: 54 / Avg: 168.06 / Max: 180.1Min: 69.1 / Avg: 195.52 / Max: 211

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: HotelGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury9001800270036004500210813422871321331643884113424953750426225402489

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.0OpenCL Device: GPU - Scene: HotelGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury4812162013.3711.5814.9716.1615.5814.9710.0610.3815.6913.7614.0712.79

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.0System Power Consumption MonitorGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury60120180240300Min: 90.8 / Avg: 157.64 / Max: 163.2Min: 37 / Avg: 115.85 / Max: 121.6Min: 50.4 / Avg: 191.85 / Max: 202.1Min: 45.2 / Avg: 198.87 / Max: 210.9Min: 40.6 / Avg: 203.13 / Max: 212.7Min: 47.8 / Avg: 259.41 / Max: 276.4Min: 37.2 / Avg: 112.78 / Max: 118.8Min: 88.6 / Avg: 240.44 / Max: 253.6Min: 64.1 / Avg: 239.06 / Max: 257.4Min: 67.3 / Avg: 309.79 / Max: 336.4Min: 53.8 / Avg: 180.54 / Max: 202.4Min: 55.6 / Avg: 194.55 / Max: 219.8

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury100200300400500153.4094.20205.40205.50229.00338.1095.10266.20339.10397.20208.40448.201. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury80160240320400140.0085.20191.80190.60215.60336.3086.30238.80321.90378.20177.30381.601. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury80160240320400139.1086.80186.70186.50208.90317.1087.10216.50304.70363.90174.90330.701. (CC) gcc options: -O2 -flto -lOpenCL

JuliaGPU

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury70M140M210M280M350M121054859.2081114034.50149885098.20171465266.00176402393.60202544036.4067157808.00138987453.50331818340.60348619117.20248225442.30269983077.701. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile uses ViennaCL OpenCL support and runs the included computational benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury153045607556.0947.5559.6663.2463.5865.2443.4159.2441.4742.5814.1324.551. (CXX) g++ options: -rdynamic -lOpenCL

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringGeForce GTX 1060GeForce GTX 1050 TiGeForce GTX 1070GeForce GTX 1070 TiGeForce GTX 1080GeForce GTX 1080 TiGeForce GTX 1050GeForce GTX 980 TiRadeon RX Vega 56Radeon RX Vega 64Radeon RX 580Radeon R9 Fury60120180240300Min: 38.5 / Avg: 113.75 / Max: 163.6Min: 36.4 / Avg: 91.32 / Max: 148.3Min: 40.9 / Avg: 135.13 / Max: 202.1Min: 44.6 / Avg: 143.93 / Max: 248.4Min: 39.9 / Avg: 143.08 / Max: 212.7Min: 45.3 / Avg: 191.14 / Max: 323.2Min: 35.5 / Avg: 93.14 / Max: 164.4Min: 48.8 / Avg: 183.62 / Max: 282.5Min: 62.8 / Avg: 197.85 / Max: 276.2Min: 62.6 / Avg: 237.02 / Max: 357.7Min: 51.6 / Avg: 133.26 / Max: 212.5Min: 51.4 / Avg: 153.02 / Max: 296.3