NVIDIA Linux OpenCL CUDA RTX SUPER Compute

NVIDIA GeForce RTX SUPER Linux OpenCL/CUDA GPU compute benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1909299-AS-RTXSUPERC34
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
Performance Per
Dollar
Date
Run
  Test
  Duration
GTX 970
September 28 2019
  1 Hour, 51 Minutes
GTX 980
September 28 2019
  1 Hour, 51 Minutes
GTX 980 Ti
September 26 2019
  1 Hour, 46 Minutes
GTX 1060
September 27 2019
  1 Hour, 47 Minutes
GTX 1070
September 28 2019
  1 Hour, 41 Minutes
GTX 1070 Ti
September 27 2019
  1 Hour, 47 Minutes
GTX 1080
September 28 2019
  1 Hour, 37 Minutes
GTX 1080 Ti
September 28 2019
  1 Hour, 27 Minutes
GTX 1660
September 28 2019
  1 Hour, 47 Minutes
GTX 1660 Ti
September 28 2019
  1 Hour, 44 Minutes
RTX 2060
September 27 2019
  1 Hour, 35 Minutes
RTX 2060 SUPER
September 26 2019
  1 Hour, 38 Minutes
RTX 2070
September 27 2019
  1 Hour, 37 Minutes
RTX 2070 SUPER
September 26 2019
  1 Hour, 40 Minutes
RTX 2080
September 27 2019
  1 Hour, 36 Minutes
RTX 2080 SUPER
September 27 2019
  1 Hour, 38 Minutes
RTX 2080 Ti
September 29 2019
  1 Hour, 27 Minutes
TITAN RTX
September 27 2019
  1 Hour, 28 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 40 Minutes

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 Linux OpenCL CUDA RTX SUPER ComputeOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0802 BIOS)Intel Cannon Lake PCH16384MBSamsung SSD 970 EVO 250GBNVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz)NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)NVIDIA GeForce GTX 980 Ti 6GB (999/3505MHz)NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz)NVIDIA TITAN RTX 24GB (1350/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz)Zotac NVIDIA GeForce RTX 2080 8GB (795/810MHz)NVIDIA GeForce RTX 2060 6GB (1365/7000MHz)NVIDIA GeForce GTX 1060 6GB (1506/4006MHz)NVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz)eVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz)NVIDIA GeForce GTX 980 4GB (1126/3505MHz)ASUS NVIDIA GeForce GTX 1660 6GB (1530/4001MHz)NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)eVGA NVIDIA GeForce GTX 970 4GB (1163/3505MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)Realtek ALC1220Acer B286HKIntel I219-VUbuntu 19.045.3.0-999-generic (x86_64) 201909145.0.0-29-generic (x86_64)GNOME Shell 3.32.2X Server 1.20.4NVIDIA 435.214.6.0GCC 8.3.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelsDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionNVIDIA Linux OpenCL CUDA RTX SUPER Compute BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,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-offload-targets=nvptx-none --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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate performance- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2060 SUPER: GPU Compute Cores: 2176- GTX 980 Ti: GPU Compute Cores: 2816- RTX 2080 SUPER: GPU Compute Cores: 3072- TITAN RTX: GPU Compute Cores: 4608- RTX 2070: GPU Compute Cores: 2304- GTX 1070 Ti: GPU Compute Cores: 2432- RTX 2080: GPU Compute Cores: 2944- RTX 2060: GPU Compute Cores: 1920- GTX 1060: GPU Compute Cores: 1280- GTX 1080: GPU Compute Cores: 2560- GTX 1080 Ti: GPU Compute Cores: 3584- GTX 1660 Ti: GPU Compute Cores: 1536- GTX 980: GPU Compute Cores: 2048- GTX 1660: GPU Compute Cores: 1408- GTX 1070: GPU Compute Cores: 1920- GTX 970: GPU Compute Cores: 1664- RTX 2080 Ti: GPU Compute Cores: 4352- RTX 2070 SUPER, GTX 980 Ti, RTX 2080 SUPER, TITAN RTX, RTX 2070, GTX 1070 Ti, RTX 2080, RTX 2060, GTX 1060, GTX 1080, GTX 1080 Ti, GTX 1660 Ti, GTX 980, GTX 1660, GTX 1070, GTX 970, RTX 2080 Ti: Python 2.7.16 + Python 3.7.3 - l1tf: Not affected + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

RTX 2070 SUPERRTX 2060 SUPERGTX 980 TiRTX 2080 SUPERTITAN RTXRTX 2070GTX 1070 TiRTX 2080RTX 2060GTX 1060GTX 1080GTX 1080 TiGTX 1660 TiGTX 980GTX 1660GTX 1070GTX 970RTX 2080 TiLogarithmic Result OverviewPhoronix Test SuiteclpeakSHOC Scalable HeterOgeneous ComputingLuxMarkPlaidMLOctaneBenchcl-memFAHBenchDarktableRodiniaLeelaChessZeroNAMD CUDAJuliaGPUViennaCL

RTX 2070 SUPERRTX 2060 SUPERGTX 980 TiRTX 2080 SUPERTITAN RTXRTX 2070GTX 1070 TiRTX 2080RTX 2060GTX 1060GTX 1080GTX 1080 TiGTX 1660 TiGTX 980GTX 1660GTX 1070GTX 970RTX 2080 TiLogarithmic Per Watt Result OverviewPhoronix Test SuiteclpeakPlaidMLcl-memSHOC Scalable HeterOgeneous ComputingJuliaGPUViennaCLFAHBenchLuxMarkLeelaChessZeroOctaneBenchP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

NVIDIA Linux OpenCL CUDA RTX SUPER Computeshoc: OpenCL - Max SP Flopsoctanebench: Total Scoreluxmark: GPU - Microphoneluxmark: GPU - Luxball HDRluxmark: GPU - Hotelfahbench: plaidml: Yes - Inference - NASNer Large - OpenCLplaidml: Yes - Inference - VGG19 - OpenCLplaidml: Yes - Inference - DenseNet 201 - OpenCLrodinia: OpenCL Myocyteplaidml: Yes - Inference - VGG16 - OpenCLclpeak: Double-Precision Doubleplaidml: No - Inference - VGG19 - OpenCLplaidml: Yes - Inference - Inception V3 - OpenCLlczero: OpenCLplaidml: No - Inference - VGG16 - OpenCLplaidml: No - Inference - Inception V3 - OpenCLplaidml: Yes - Inference - ResNet 50 - OpenCLnamd-cuda: ATPase Simulation - 327,506 Atomsplaidml: No - Inference - ResNet 50 - OpenCLplaidml: No - Inference - IMDB LSTM - OpenCLrodinia: OpenCL Particle Filtercl-mem: Readjuliagpu: GPUplaidml: Yes - Inference - Mobilenet - OpenCLcl-mem: Copycl-mem: Writeplaidml: No - Inference - Mobilenet - OpenCLdarktable: Masskrug - OpenCLclpeak: Integer Compute INTdarktable: Boat - OpenCLclpeak: Single-Precision Floatdarktable: Server Room - OpenCLviennacl: OpenCL LU Factorizationshoc: OpenCL - FFT SPclpeak: Global Memory Bandwidthshoc: OpenCL - MD5 HashRTX 2070 SUPERRTX 2060 SUPERGTX 980 TiRTX 2080 SUPERTITAN RTXRTX 2070GTX 1070 TiRTX 2080RTX 2060GTX 1060GTX 1080GTX 1080 TiGTX 1660 TiGTX 980GTX 1660GTX 1070GTX 970RTX 2080 Ti9869.34220.7620499297346565229.1255.2497.82190.0130.76123.20310.27122.32239.611604.21154.64215.85283.980.19501421.58499.696.82395.67275868151.172264.97291.87319.571649.173.718570.601.938502.710.8070.451088.17369.1121.788378.87205.2318509300936148205.2048.9680.82179.5130.42102.58263.11101.17219.76998.17128.22199.43250.980.19336374.71440.797.87395.67264172441.471983.82287.80333.201531.013.687023.071.957089.500.7569.17971.24367.9218.226213.97142.2011096168713885116.0230.6456.13111.4652.1371.26196.6068.47116.31466.8487.39135.14162.630.28675247.47270.009.95265.33195653728.471202.77216.83241.50990.124.121610.283.275538.751.5162.01725.98263.229.2212015.50233.5620164301796839256.8364.80115.44200.3830.63145.65378.98143.02301.112105.26180.45259.26327.800.19385468.70589.865.74436.27286818331.272437.48301.23345.771762.003.6910404.711.8210335.500.7971.471203.57405.0026.5617334.00322.7630756465469836301.9387.17162.05263.1331.69204.67547.97196.44373.713126.48247.83347.93433.810.18867648.36790.774.24566.70303198573.972842.38322.20495.372466.663.6613841.251.6414203.870.7472.961578.29528.8936.398528.70206.8818441300976150204.7149.9483.56176.4931.64105.60268.32103.89220.99999.75131.54198.03251.070.19440376.73446.237.75395.70267086274.531969.50284.43322.671516.963.677161.481.937198.640.7569.41976.78368.9618.777715.42141.3510259169254170138.2135.4173.12130.1538.7092.03242.6390.34147.04753.69114.03153.34205.850.22269294.36333.037.88205.27220447755.871371.21182.70190.031009.263.972076.932.936770.971.1764.68525.89197.2611.7010952.77222.8819916291646590242.7558.47105.54189.2831.65133.20345.81129.58268.331879.99164.05238.73305.760.19307441.24548.836.22395.70280162469.672292.38289.20331.501663.873.719660.921.908883.900.8070.961100.00368.4724.077320.73164.5213754216834833183.4141.1171.07154.1931.1189.55231.4488.04193.75704.69110.93167.87220.440.20250319.25389.408.90296.20251925176.901694.07237.77241.201232.473.735269.012.225329.070.8367.92818.44275.8616.044788.9291.447086122452648102.6123.1644.3791.0734.6956.07149.5854.7897.83262.4169.31104.44130.640.31789196.00224.8911.93153.50182188318.67908.43137.20144.57726.304.071267.893.654199.711.2858.67326.68146.627.269407.75147.988716137883807155.2240.3883.83143.5334.87106.09297.94101.00173.791146.75128.05184.80240.620.20978337.47399.006.49228.80237914974.401544.50205.93214.671123.853.942430.742.728314.291.0966.67614.69222.0914.2513230.77212.0413721216895649198.2556.64115.03191.3135.91145.42414.96138.68228.681886.30175.37257.55333.540.19669496.24523.984.96337.53262248899.332162.58283.20340.271672.733.923301.892.2911720.571.0569.09982.23328.9019.725893.41132.2811003161473805139.8134.1258.03114.5830.6773.18185.1273.35161.33420.0492.45140.05172.680.23185259.43315.8310.82250.23239300837.601394.05208.50208.671002.004.024775.452.924793.661.1566.06665.66234.6712.985052.73109.708914132463048102.8624.2443.6392.9247.3855.70159.6853.49101.92280.9968.95105.64142.140.33110203.91231.6611.69164.50181882709.77973.39143.40151.50759.435.741312.063.924476.693.1059.21458.35164.257.495329.84118.499794151623733126.6428.9952.52102.8330.9766.24168.4467.24137.66335.8684.83116.90156.500.25031228.14287.6811.87162.90230919642.131160.52145.37148.87814.654.014657.793.354610.011.1865.10452.89157.6011.877115.39132.869983172903870140.2933.0763.56127.0235.1080.27223.9176.89141.55642.1297.32147.17196.010.23957276.89315.378.26205.27216942144.931288.94182.00190.90987.693.921685.052.896269.491.1163.86478.54196.4710.614362.3195.60798511732273091.5321.4239.3479.7145.4849.76137.4747.7088.16207.8460.3294.72116.050.36368181.87204.3212.99142.10169258044.90841.48124.77132.60671.495.781140.294.423888.163.1656.95411.29143.486.5016656.20309.0428631429749215301.8984.97154.20254.4531.05194.83521.90186.19363.163032.10234.65343.49424.070.18909634.09758.214.39544.33299834728.802750.57324.40441.232335.463.6613609.331.6413532.740.7572.711485.73506.3334.91OpenBenchmarking.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 FlopsRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4K8K12K16K20KSE +/- 87.95, N = 3SE +/- 0.74, N = 3SE +/- 1.89, N = 3SE +/- 13.79, N = 3SE +/- 3.92, N = 3SE +/- 0.04, N = 3SE +/- 3.93, N = 3SE +/- 3.00, N = 3SE +/- 6.34, N = 3SE +/- 19.13, N = 3SE +/- 29.32, N = 3SE +/- 0.84, N = 3SE +/- 45.97, N = 3SE +/- 91.95, N = 3SE +/- 61.30, N = 3SE +/- 11.70, N = 3SE +/- 27.40, N = 3SE +/- 51.02, N = 316656.204362.317115.395329.845052.735893.4113230.779407.754788.927320.7310952.777715.428528.7017334.0012015.506213.978378.879869.341. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OctaneBench

OctaneBench is a test of the OctaneRender on the GPU and requires the use of NVIDIA CUDA. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterOctaneBench 4.00cTotal ScoreRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350309.0495.60132.86118.49109.70132.28212.04147.9891.44164.52222.88141.35206.88322.76233.56142.20205.23220.76

LuxMark

LuxMark is a multi-platform OpenGL benchmark using LuxRender. 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 3.1OpenCL Device: GPU - Scene: MicrophoneRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER7K14K21K28K35KSE +/- 21.50, N = 3SE +/- 2.00, N = 3SE +/- 4.91, N = 3SE +/- 1.33, N = 3SE +/- 18.25, N = 3SE +/- 2.33, N = 3SE +/- 19.33, N = 3SE +/- 1.20, N = 3SE +/- 1.53, N = 3SE +/- 3.84, N = 3SE +/- 11.68, N = 3SE +/- 15.50, N = 3SE +/- 26.44, N = 3SE +/- 168.12, N = 3SE +/- 108.17, N = 3SE +/- 49.74, N = 3SE +/- 43.34, N = 3SE +/- 16.84, N = 3286317985998397948914110031372187167086137541991610259184413075620164110961850920499

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER10K20K30K40K50KSE +/- 166.33, N = 3SE +/- 6.23, N = 3SE +/- 1.00, N = 3SE +/- 35.04, N = 3SE +/- 26.16, N = 3SE +/- 19.86, N = 3SE +/- 7.67, N = 3SE +/- 17.98, N = 3SE +/- 4.00, N = 3SE +/- 0.67, N = 3SE +/- 7.51, N = 3SE +/- 36.50, N = 3SE +/- 7.54, N = 3SE +/- 20.92, N = 3SE +/- 0.88, N = 3SE +/- 39.15, N = 3SE +/- 4.93, N = 3SE +/- 98.93, N = 3429741173217290151621324616147216891378812245216832916416925300974654630179168713009329734

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: HotelRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER2K4K6K8K10KSE +/- 4.37, N = 3SE +/- 1.86, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 3SE +/- 2.73, N = 3SE +/- 7.09, N = 3SE +/- 0.67, N = 3SE +/- 3.76, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 3.51, N = 3SE +/- 1.86, N = 3SE +/- 1.73, N = 3SE +/- 0.58, N = 3SE +/- 8.00, N = 3SE +/- 0.67, N = 3921527303870373330483805564938072648483365904170615098366839388561486565

FAHBench

FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350SE +/- 0.90, N = 3SE +/- 0.03, N = 3SE +/- 0.43, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.43, N = 3SE +/- 0.53, N = 3SE +/- 0.17, N = 3SE +/- 0.61, N = 3SE +/- 0.99, N = 3SE +/- 0.05, N = 3SE +/- 0.64, N = 3SE +/- 0.71, N = 3SE +/- 0.78, N = 3SE +/- 0.04, N = 3SE +/- 0.34, N = 3SE +/- 0.60, N = 3301.8991.53140.29126.64102.86139.81198.25155.22102.61183.41242.75138.21204.71301.93256.83116.02205.20229.12

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: NASNer Large - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER20406080100SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.25, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 384.9721.4233.0728.9924.2434.1256.6440.3823.1641.1158.4735.4149.9487.1764.8030.6448.9655.24

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4080120160200SE +/- 0.36, N = 3SE +/- 0.18, N = 3SE +/- 0.19, N = 3SE +/- 0.08, N = 3SE +/- 0.62, N = 4SE +/- 0.12, N = 3SE +/- 0.44, N = 3SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.44, N = 3SE +/- 0.03, N = 3SE +/- 0.35, N = 3SE +/- 0.48, N = 3SE +/- 0.21, N = 3SE +/- 0.77, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3154.2039.3463.5652.5243.6358.03115.0383.8344.3771.07105.5473.1283.56162.05115.4456.1380.8297.82

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 3SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3254.4579.71127.02102.8392.92114.58191.31143.5391.07154.19189.28130.15176.49263.13200.38111.46179.51190.01

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL MyocyteRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER1224364860SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 331.0545.4835.1030.9747.3830.6735.9134.8734.6931.1131.6538.7031.6431.6930.6352.1330.4230.761. (CXX) g++ options: -O2 -lOpenCL

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4080120160200SE +/- 0.51, N = 3SE +/- 0.21, N = 3SE +/- 0.30, N = 3SE +/- 0.17, N = 3SE +/- 0.83, N = 4SE +/- 0.14, N = 3SE +/- 0.62, N = 3SE +/- 0.40, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.57, N = 3SE +/- 0.08, N = 3SE +/- 0.39, N = 3SE +/- 0.57, N = 3SE +/- 0.29, N = 3SE +/- 1.12, N = 3SE +/- 0.35, N = 3SE +/- 0.28, N = 3194.8349.7680.2766.2455.7073.18145.42106.0956.0789.55133.2092.03105.60204.67145.6571.26102.58123.20

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER120240360480600SE +/- 1.46, N = 3SE +/- 0.03, N = 3SE +/- 0.71, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 1.14, N = 3SE +/- 0.76, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.92, N = 3SE +/- 0.02, N = 3SE +/- 0.81, N = 3SE +/- 1.16, N = 3SE +/- 0.03, N = 3SE +/- 0.35, N = 3SE +/- 0.71, N = 3SE +/- 0.77, N = 3521.90137.47223.91168.44159.68185.12414.96297.94149.58231.44345.81242.63268.32547.97378.98196.60263.11310.271. (CXX) g++ options: -O3 -rdynamic -lOpenCL

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4080120160200SE +/- 0.41, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 3SE +/- 0.47, N = 3SE +/- 0.12, N = 3SE +/- 0.35, N = 3SE +/- 0.16, N = 3SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.42, N = 3SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.54, N = 3SE +/- 0.22, N = 3SE +/- 0.65, N = 3SE +/- 0.19, N = 3SE +/- 0.23, N = 3186.1947.7076.8967.2453.4973.35138.68101.0054.7888.04129.5890.34103.89196.44143.0268.47101.17122.32

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER80160240320400SE +/- 0.44, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 0.27, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.30, N = 3SE +/- 0.20, N = 3SE +/- 0.37, N = 3SE +/- 0.59, N = 3SE +/- 0.06, N = 3SE +/- 0.43, N = 3SE +/- 0.48, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3SE +/- 0.44, N = 3SE +/- 0.10, N = 3363.1688.16141.55137.66101.92161.33228.68173.7997.83193.75268.33147.04220.99373.71301.11116.31219.76239.61

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.22.0Backend: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER7001400210028003500SE +/- 8.77, N = 3SE +/- 1.93, N = 15SE +/- 12.32, N = 15SE +/- 4.05, N = 15SE +/- 2.79, N = 3SE +/- 5.83, N = 15SE +/- 32.29, N = 3SE +/- 14.70, N = 3SE +/- 3.68, N = 4SE +/- 1.84, N = 3SE +/- 21.60, N = 3SE +/- 8.69, N = 6SE +/- 16.93, N = 15SE +/- 28.21, N = 3SE +/- 29.82, N = 3SE +/- 5.67, N = 15SE +/- 18.12, N = 15SE +/- 17.64, N = 73032.10207.84642.12335.86280.99420.041886.301146.75262.41704.691879.99753.69999.753126.482105.26466.84998.171604.211. (CXX) g++ options: -lpthread

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER50100150200250SE +/- 0.50, N = 3SE +/- 0.05, N = 3SE +/- 0.17, N = 3SE +/- 0.21, N = 3SE +/- 0.79, N = 3SE +/- 0.24, N = 3SE +/- 0.62, N = 3SE +/- 0.38, N = 3SE +/- 0.12, N = 3SE +/- 0.32, N = 3SE +/- 0.73, N = 3SE +/- 0.06, N = 3SE +/- 0.43, N = 3SE +/- 0.40, N = 3SE +/- 0.28, N = 3SE +/- 1.36, N = 3SE +/- 0.34, N = 3SE +/- 0.29, N = 3234.6560.3297.3284.8368.9592.45175.37128.0569.31110.93164.05114.03131.54247.83180.4587.39128.22154.64

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER80160240320400SE +/- 0.38, N = 3SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 3SE +/- 0.38, N = 3SE +/- 0.10, N = 3SE +/- 0.23, N = 3SE +/- 0.57, N = 3SE +/- 0.06, N = 3SE +/- 0.29, N = 3SE +/- 0.42, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.25, N = 3SE +/- 0.07, N = 3343.4994.72147.17116.90105.64140.05257.55184.80104.44167.87238.73153.34198.03347.93259.26135.14199.43215.85

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER90180270360450SE +/- 1.04, N = 3SE +/- 0.00, N = 3SE +/- 0.28, N = 3SE +/- 0.31, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.42, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.16, N = 3SE +/- 0.60, N = 3SE +/- 0.08, N = 3SE +/- 0.53, N = 3SE +/- 0.70, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.48, N = 3SE +/- 0.71, N = 3424.07116.05196.01156.50142.14172.68333.54240.62130.64220.44305.76205.85251.07433.81327.80162.63250.98283.98

NAMD CUDA

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. This version of the NAMD test profile uses CUDA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.13ATPase Simulation - 327,506 AtomsRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.08180.16360.24540.32720.409SE +/- 0.00238, N = 3SE +/- 0.00026, N = 4SE +/- 0.00195, N = 3SE +/- 0.00287, N = 3SE +/- 0.00159, N = 3SE +/- 0.00192, N = 3SE +/- 0.00044, N = 3SE +/- 0.00088, N = 5SE +/- 0.00303, N = 3SE +/- 0.00147, N = 4SE +/- 0.00199, N = 3SE +/- 0.00075, N = 6SE +/- 0.00250, N = 3SE +/- 0.00297, N = 3SE +/- 0.00233, N = 3SE +/- 0.00105, N = 3SE +/- 0.00245, N = 3SE +/- 0.00245, N = 30.189090.363680.239570.250310.331100.231850.196690.209780.317890.202500.193070.222690.194400.188670.193850.286750.193360.19501

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER140280420560700SE +/- 0.63, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.47, N = 3SE +/- 0.72, N = 3SE +/- 0.32, N = 3SE +/- 0.07, N = 3SE +/- 0.39, N = 3SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.27, N = 3SE +/- 0.75, N = 3SE +/- 0.61, N = 3SE +/- 0.58, N = 3SE +/- 0.53, N = 3SE +/- 0.19, N = 3634.09181.87276.89228.14203.91259.43496.24337.47196.00319.25441.24294.36376.73648.36468.70247.47374.71421.58

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER2004006008001000SE +/- 1.01, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.50, N = 3SE +/- 0.15, N = 3SE +/- 0.74, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3SE +/- 0.37, N = 3SE +/- 1.63, N = 3SE +/- 0.49, N = 3SE +/- 0.21, N = 3SE +/- 2.25, N = 3SE +/- 1.47, N = 3SE +/- 0.56, N = 3SE +/- 0.31, N = 3SE +/- 0.67, N = 3758.21204.32315.37287.68231.66315.83523.98399.00224.89389.40548.83333.03446.23790.77589.86270.00440.79499.69

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL Particle FilterRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 34.3912.998.2611.8711.6910.824.966.4911.938.906.227.887.754.245.749.957.876.821. (CXX) g++ options: -O2 -lOpenCL

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: ReadRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER120240360480600SE +/- 0.38, N = 3SE +/- 1.50, N = 8SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.12, N = 3SE +/- 0.00, N = 3SE +/- 0.20, N = 3SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.25, N = 3SE +/- 0.40, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 3SE +/- 0.22, N = 3SE +/- 0.22, N = 3544.33142.10205.27162.90164.50250.23337.53228.80153.50296.20395.70205.27395.70566.70436.27265.33395.67395.671. (CC) gcc options: -O2 -flto -lOpenCL

JuliaGPU

JuliaGPU is an OpenCL benchmark with this version containing various PTS-specific enhancements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPURTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60M120M180M240M300MSE +/- 78810.54, N = 3SE +/- 383961.59, N = 3SE +/- 76295.47, N = 3SE +/- 197521.26, N = 3SE +/- 52667.10, N = 3SE +/- 495295.96, N = 3SE +/- 540298.84, N = 3SE +/- 341457.11, N = 3SE +/- 137674.47, N = 3SE +/- 121354.48, N = 3SE +/- 169596.23, N = 3SE +/- 97519.45, N = 3SE +/- 633693.84, N = 3SE +/- 489061.14, N = 3SE +/- 1165562.77, N = 3SE +/- 78142.08, N = 3SE +/- 369711.60, N = 3SE +/- 389272.10, N = 3299834728.80169258044.90216942144.93230919642.13181882709.77239300837.60262248899.33237914974.40182188318.67251925176.90280162469.67220447755.87267086274.53303198573.97286818331.27195653728.47264172441.47275868151.171. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER6001200180024003000SE +/- 13.82, N = 3SE +/- 1.43, N = 3SE +/- 4.57, N = 3SE +/- 1.34, N = 3SE +/- 2.37, N = 3SE +/- 2.77, N = 3SE +/- 7.35, N = 3SE +/- 4.27, N = 3SE +/- 2.37, N = 3SE +/- 3.62, N = 3SE +/- 4.68, N = 3SE +/- 0.80, N = 3SE +/- 5.21, N = 3SE +/- 4.02, N = 3SE +/- 6.75, N = 3SE +/- 1.24, N = 3SE +/- 10.89, N = 3SE +/- 4.73, N = 32750.57841.481288.941160.52973.391394.052162.581544.50908.431694.072292.381371.211969.502842.382437.481202.771983.822264.97

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: CopyRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350SE +/- 0.40, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.15, N = 3SE +/- 0.25, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.00, N = 3SE +/- 0.24, N = 3SE +/- 0.67, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3324.40124.77182.00145.37143.40208.50283.20205.93137.20237.77289.20182.70284.43322.20301.23216.83287.80291.871. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER110220330440550SE +/- 0.35, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.28, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.40, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 1.00, N = 3SE +/- 1.39, N = 3SE +/- 0.54, N = 3SE +/- 0.06, N = 3SE +/- 0.82, N = 3SE +/- 0.43, N = 3441.23132.60190.90148.87151.50208.67340.27214.67144.57241.20331.50190.03322.67495.37345.77241.50333.20319.571. (CC) gcc options: -O2 -flto -lOpenCL

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER5001000150020002500SE +/- 6.28, N = 3SE +/- 0.75, N = 3SE +/- 1.57, N = 3SE +/- 1.38, N = 3SE +/- 0.24, N = 3SE +/- 0.86, N = 3SE +/- 5.20, N = 3SE +/- 1.27, N = 3SE +/- 0.63, N = 3SE +/- 2.11, N = 3SE +/- 4.17, N = 3SE +/- 0.73, N = 3SE +/- 1.46, N = 3SE +/- 13.68, N = 3SE +/- 2.80, N = 3SE +/- 0.07, N = 3SE +/- 1.59, N = 3SE +/- 1.25, N = 32335.46671.49987.69814.65759.431002.001672.731123.85726.301232.471663.871009.261516.962466.661762.00990.121531.011649.17

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Masskrug - Acceleration: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER1.30052.6013.90155.2026.5025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.665.783.924.015.744.023.923.944.073.733.713.973.673.663.694.123.683.71

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER3K6K9K12K15KSE +/- 57.62, N = 3SE +/- 19.67, N = 3SE +/- 24.36, N = 3SE +/- 32.97, N = 3SE +/- 0.38, N = 3SE +/- 64.34, N = 15SE +/- 29.87, N = 15SE +/- 26.46, N = 3SE +/- 13.36, N = 15SE +/- 63.11, N = 3SE +/- 4.11, N = 3SE +/- 0.72, N = 3SE +/- 84.78, N = 15SE +/- 156.59, N = 15SE +/- 83.79, N = 15SE +/- 23.09, N = 3SE +/- 76.65, N = 15SE +/- 81.60, N = 1513609.331140.291685.054657.791312.064775.453301.892430.741267.895269.019660.922076.937161.4813841.2510404.711610.287023.078570.601. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Boat - Acceleration: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.99451.9892.98353.9784.9725SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.644.422.893.353.922.922.292.723.652.221.902.931.931.641.823.271.951.93

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER3K6K9K12K15KSE +/- 207.30, N = 3SE +/- 40.24, N = 15SE +/- 3.03, N = 3SE +/- 7.83, N = 3SE +/- 46.38, N = 8SE +/- 61.47, N = 15SE +/- 5.50, N = 3SE +/- 3.14, N = 3SE +/- 1.88, N = 3SE +/- 77.72, N = 3SE +/- 7.41, N = 3SE +/- 7.63, N = 3SE +/- 81.15, N = 15SE +/- 228.75, N = 15SE +/- 124.22, N = 3SE +/- 44.36, N = 15SE +/- 84.87, N = 15SE +/- 76.18, N = 1513532.743888.166269.494610.014476.694793.6611720.578314.294199.715329.078883.906770.977198.6414203.8710335.505538.757089.508502.711. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Room - Acceleration: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.7111.4222.1332.8443.555SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 8SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.753.161.111.183.101.151.051.091.280.830.801.170.750.740.791.510.750.80

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 FactorizationRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER1632486480SE +/- 0.72, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.31, N = 3SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.60, N = 3SE +/- 0.26, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 372.7156.9563.8665.1059.2166.0669.0966.6758.6767.9270.9664.6869.4172.9671.4762.0169.1770.451. (CXX) g++ options: -rdynamic -lOpenCL

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: FFT SPRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER30060090012001500SE +/- 2.79, N = 3SE +/- 0.48, N = 3SE +/- 6.42, N = 4SE +/- 0.27, N = 3SE +/- 1.09, N = 3SE +/- 1.57, N = 3SE +/- 1.06, N = 3SE +/- 3.58, N = 3SE +/- 3.50, N = 7SE +/- 0.56, N = 3SE +/- 0.39, N = 3SE +/- 0.19, N = 3SE +/- 2.90, N = 3SE +/- 1.38, N = 3SE +/- 0.78, N = 3SE +/- 3.01, N = 3SE +/- 3.09, N = 3SE +/- 0.27, N = 31485.73411.29478.54452.89458.35665.66982.23614.69326.68818.441100.00525.89976.781578.291203.57725.98971.241088.171. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER110220330440550SE +/- 0.44, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 3SE +/- 0.71, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.66, N = 3SE +/- 0.08, N = 3SE +/- 0.52, N = 3SE +/- 0.11, N = 3SE +/- 0.33, N = 3506.33143.48196.47157.60164.25234.67328.90222.09146.62275.86368.47197.26368.96528.89405.00263.22367.92369.111. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER816243240SE +/- 0.12, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 334.916.5010.6111.877.4912.9819.7214.257.2616.0424.0711.7018.7736.3926.569.2218.2221.781. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350Min: 49.7 / Avg: 227.4 / Max: 374Min: 48.8 / Avg: 157.71 / Max: 306.3Min: 43.8 / Avg: 150.54 / Max: 286.9Min: 43.1 / Avg: 115.15 / Max: 262.4Min: 49.8 / Avg: 167.77 / Max: 329.4Min: 45.4 / Avg: 127.55 / Max: 273.9Min: 49.6 / Avg: 207.86 / Max: 380Min: 44.9 / Avg: 162.99 / Max: 328.3Min: 44.3 / Avg: 128.45 / Max: 269.5Min: 46.1 / Avg: 153.75 / Max: 303.8Min: 47.5 / Avg: 181.54 / Max: 342.9Min: 48.6 / Avg: 131.89 / Max: 259.9Min: 46 / Avg: 164.53 / Max: 321.3Min: 50.6 / Avg: 227.86 / Max: 371.4Min: 46 / Avg: 173.42 / Max: 330.5Min: 53.6 / Avg: 199.07 / Max: 370.3Min: 45.4 / Avg: 158.95 / Max: 312Min: 45.5 / Avg: 134.05 / Max: 323.3

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER1632486480Min: 31 / Avg: 60.94 / Max: 77Min: 28 / Avg: 52.34 / Max: 68Min: 28 / Avg: 61.94 / Max: 76Min: 28 / Avg: 56.71 / Max: 77Min: 29 / Avg: 68.53 / Max: 81Min: 30 / Avg: 50.73 / Max: 65Min: 34 / Avg: 67.92 / Max: 84Min: 30 / Avg: 63.66 / Max: 77Min: 30 / Avg: 58.15 / Max: 74Min: 32 / Avg: 57.94 / Max: 72Min: 30 / Avg: 66.02 / Max: 83Min: 39 / Avg: 48.41 / Max: 61Min: 28 / Avg: 58.64 / Max: 77Min: 37 / Avg: 62.01 / Max: 80Min: 34 / Avg: 53.35 / Max: 70Min: 36 / Avg: 71.62 / Max: 85Min: 29 / Avg: 54.33 / Max: 75Min: 27 / Avg: 43.67 / Max: 69

OctaneBench

OpenBenchmarking.orgWatts, Fewer Is BetterOctaneBench 4.00cSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 51.7 / Avg: 322.94 / Max: 355.5Min: 50.8 / Avg: 160.22 / Max: 180Min: 86 / Avg: 157.88 / Max: 173.8Min: 46.3 / Avg: 127.11 / Max: 144.7Min: 53.6 / Avg: 178.66 / Max: 203.2Min: 47.1 / Avg: 145.79 / Max: 161.1Min: 130.6 / Avg: 236.94 / Max: 265Min: 48.3 / Avg: 167.77 / Max: 228.3Min: 44.9 / Avg: 120.33 / Max: 135.2Min: 49.8 / Avg: 188.5 / Max: 218.2Min: 50 / Avg: 239.21 / Max: 278.1Min: 52.2 / Avg: 132.45 / Max: 182.7Min: 47.1 / Avg: 215.17 / Max: 242.1Min: 55.3 / Avg: 326.69 / Max: 357.7Min: 47.8 / Avg: 225.1 / Max: 261.8Min: 128.3 / Avg: 220.62 / Max: 240Min: 46.5 / Avg: 210.53 / Max: 232.6Min: 49 / Avg: 211.57 / Max: 245.6

OpenBenchmarking.orgScore Per Watt, More Is BetterOctaneBench 4.00cTotal ScoreRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.24080.48160.72240.96321.2040.960.600.840.930.610.910.890.880.760.870.931.070.960.991.040.640.971.04

LeelaChessZero

OpenBenchmarking.orgWatts, Fewer Is BetterLeelaChessZero 0.22.0System Power Consumption MonitorGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350Min: 82.3 / Avg: 164.63 / Max: 252.9Min: 71.9 / Avg: 152.4 / Max: 214.7Min: 46.5 / Avg: 118.46 / Max: 180.4Min: 51.8 / Avg: 153.94 / Max: 247.5Min: 47.9 / Avg: 134.26 / Max: 195.9Min: 106.6 / Avg: 215.46 / Max: 320.5Min: 48.8 / Avg: 161.47 / Max: 252.9Min: 47.2 / Avg: 138.37 / Max: 187.2Min: 49.1 / Avg: 147.07 / Max: 231.4Min: 52.8 / Avg: 175.13 / Max: 286.6Min: 52 / Avg: 128.59 / Max: 197.7Min: 48.6 / Avg: 172.95 / Max: 253.7Min: 53.3 / Avg: 197.7 / Max: 371.4Min: 47.5 / Avg: 170.9 / Max: 315Min: 59.1 / Avg: 216.14 / Max: 319.4Min: 45.5 / Avg: 151.83 / Max: 241.9Min: 47.2 / Avg: 178.69 / Max: 276

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.22.0Backend: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4812162014.001.264.212.841.833.138.757.101.904.7910.735.865.7815.8112.322.166.578.98

PlaidML

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 52.9 / Avg: 251.39 / Max: 354Min: 75.4 / Avg: 201.26 / Max: 220.7Min: 84.2 / Avg: 180.68 / Max: 209.8Min: 46 / Avg: 160.67 / Max: 185.8Min: 55.7 / Avg: 208.34 / Max: 246.7Min: 48.3 / Avg: 167.7 / Max: 196.3Min: 55.7 / Avg: 245.95 / Max: 321.1Min: 89.9 / Avg: 209.47 / Max: 253.5Min: 45.1 / Avg: 170.04 / Max: 188.8Min: 50.1 / Avg: 192.21 / Max: 230.7Min: 49.9 / Avg: 230.45 / Max: 288.2Min: 52.4 / Avg: 180.41 / Max: 207.7Min: 49.7 / Avg: 197.21 / Max: 252.5Min: 53.2 / Avg: 260.22 / Max: 361.7Min: 49.5 / Avg: 224.18 / Max: 302.6Min: 119.7 / Avg: 273.57 / Max: 330.8Min: 55 / Avg: 193.52 / Max: 240.6Min: 47.5 / Avg: 199.98 / Max: 276.8

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.16880.33760.50640.67520.8440.740.240.430.420.260.440.560.480.320.460.560.500.530.750.640.250.520.61

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 52.7 / Avg: 239.16 / Max: 354.3Min: 94.5 / Avg: 195.88 / Max: 219.3Min: 50 / Avg: 172.78 / Max: 208.8Min: 45.6 / Avg: 146.27 / Max: 182Min: 90.4 / Avg: 213.83 / Max: 251.4Min: 46.4 / Avg: 163.81 / Max: 195.7Min: 51.8 / Avg: 234.29 / Max: 318.4Min: 46.2 / Avg: 209.24 / Max: 254.3Min: 69.4 / Avg: 166.46 / Max: 190Min: 48.4 / Avg: 179.22 / Max: 228.5Min: 48.9 / Avg: 201.23 / Max: 285.7Min: 52.3 / Avg: 169.99 / Max: 205.7Min: 48.4 / Avg: 193.79 / Max: 250.6Min: 52.4 / Avg: 239.94 / Max: 363Min: 47.7 / Avg: 218.91 / Max: 299.1Min: 56.5 / Avg: 270.73 / Max: 328.7Min: 53.3 / Avg: 181.51 / Max: 239.5Min: 47.2 / Avg: 191.71 / Max: 276.3

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.23180.46360.69540.92721.1590.980.310.560.580.320.560.750.610.420.620.820.670.681.030.820.320.710.81

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER50100150200250Min: 52.6 / Avg: 166.27 / Max: 275.3Min: 94.4 / Avg: 160.18 / Max: 203.4Min: 50.4 / Avg: 132.86 / Max: 187.3Min: 46.3 / Avg: 96.5 / Max: 135.8Min: 100 / Avg: 162.49 / Max: 218.7Min: 46.6 / Avg: 100.43 / Max: 150.5Min: 48.5 / Avg: 142.23 / Max: 208.8Min: 46.3 / Avg: 122.88 / Max: 159.6Min: 49.2 / Avg: 125.65 / Max: 186.5Min: 56.5 / Avg: 138.96 / Max: 215.1Min: 52.4 / Avg: 128.8 / Max: 152Min: 51.8 / Avg: 130.6 / Max: 207.8Min: 57.1 / Avg: 192.1 / Max: 249.1Min: 54.9 / Avg: 136.39 / Max: 187.2Min: 49.2 / Avg: 136.18 / Max: 192.6

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER1.14532.29063.43594.58125.72654.561.282.372.981.433.143.002.811.833.103.952.593.685.094.521.413.233.67

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 83.3 / Avg: 172.91 / Max: 233.2Min: 89.6 / Avg: 153.55 / Max: 208.4Min: 46.3 / Avg: 119.8 / Max: 159.7Min: 53 / Avg: 176.69 / Max: 244.6Min: 47.9 / Avg: 141.14 / Max: 182.8Min: 56.4 / Avg: 186.43 / Max: 312.7Min: 48.4 / Avg: 149.71 / Max: 246.6Min: 45.9 / Avg: 132.6 / Max: 182.3Min: 48.6 / Avg: 147.64 / Max: 221.8Min: 52 / Avg: 137.63 / Max: 231.8Min: 52.2 / Avg: 140.17 / Max: 177.3Min: 47.5 / Avg: 122.1 / Max: 239.9Min: 52.7 / Avg: 128.84 / Max: 167.9Min: 49.4 / Avg: 162.94 / Max: 270.3Min: 129.1 / Avg: 233.7 / Max: 292Min: 55.4 / Avg: 144.71 / Max: 231.4Min: 46.8 / Avg: 145.98 / Max: 249.6

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER1.13182.26363.39544.52725.6593.701.051.801.901.151.842.662.251.482.163.212.103.095.033.181.062.592.89

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 51.8 / Avg: 206.66 / Max: 321.6Min: 81.4 / Avg: 182.54 / Max: 219.9Min: 84.3 / Avg: 149.15 / Max: 206.1Min: 46.3 / Avg: 123.06 / Max: 152.7Min: 56.7 / Avg: 188.31 / Max: 242.7Min: 46.3 / Avg: 136.65 / Max: 177.5Min: 128 / Avg: 191.53 / Max: 304Min: 84.7 / Avg: 196.13 / Max: 242.5Min: 46.9 / Avg: 150.12 / Max: 180Min: 47.6 / Avg: 150.66 / Max: 214.3Min: 49.4 / Avg: 176.08 / Max: 254.9Min: 51.1 / Avg: 141.76 / Max: 172.5Min: 49.8 / Avg: 167.7 / Max: 230.4Min: 56.2 / Avg: 178.56 / Max: 327.6Min: 49.6 / Avg: 170.73 / Max: 255.1Min: 126.5 / Avg: 220.09 / Max: 281.6Min: 54.4 / Avg: 162.79 / Max: 223.8Min: 49.5 / Avg: 161.34 / Max: 234.9

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.43880.87761.31641.75522.1941.660.520.990.950.561.021.340.940.701.111.361.081.181.951.520.611.231.34

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER61218243022.635.209.659.565.5311.2010.229.357.5911.6714.1611.3014.8423.2316.606.6412.9819.70

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 52.9 / Avg: 210.77 / Max: 350.6Min: 89.6 / Avg: 193.7 / Max: 220.3Min: 70.7 / Avg: 170.23 / Max: 208.9Min: 45.5 / Avg: 136.67 / Max: 171.6Min: 53.3 / Avg: 201.25 / Max: 246.9Min: 48.2 / Avg: 154.23 / Max: 191.6Min: 120.6 / Avg: 236.48 / Max: 318.6Min: 91.2 / Avg: 194.23 / Max: 252.2Min: 45.9 / Avg: 157.15 / Max: 187.3Min: 48.9 / Avg: 179.62 / Max: 228Min: 52.6 / Avg: 181.66 / Max: 277.7Min: 51.9 / Avg: 158.16 / Max: 196.1Min: 48.7 / Avg: 189.06 / Max: 250.5Min: 52.8 / Avg: 227.24 / Max: 356.3Min: 49.1 / Avg: 194.92 / Max: 278.5Min: 71.2 / Avg: 244.52 / Max: 316.6Min: 57.1 / Avg: 209.61 / Max: 237.5Min: 47.2 / Avg: 198.27 / Max: 271.7

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.16430.32860.49290.65720.82150.730.200.370.380.220.380.490.430.280.400.580.460.440.710.590.230.390.49

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 52.7 / Avg: 188.04 / Max: 345.4Min: 51.5 / Avg: 184.27 / Max: 233.4Min: 47.7 / Avg: 162.2 / Max: 207.3Min: 45.6 / Avg: 137.8 / Max: 169.2Min: 69.1 / Avg: 196.2 / Max: 247.2Min: 47.3 / Avg: 151.58 / Max: 191.5Min: 118 / Avg: 235.58 / Max: 316.5Min: 88.2 / Avg: 189.28 / Max: 251.8Min: 45.8 / Avg: 152.31 / Max: 187.6Min: 48.1 / Avg: 163.79 / Max: 226.4Min: 54.1 / Avg: 173.35 / Max: 273.1Min: 95.2 / Avg: 160.1 / Max: 191.4Min: 48.1 / Avg: 174.02 / Max: 249.3Min: 53.8 / Avg: 216.91 / Max: 353.5Min: 49.4 / Avg: 181.31 / Max: 274.6Min: 55.1 / Avg: 244.29 / Max: 316.2Min: 54 / Avg: 187.95 / Max: 233.7Min: 46.7 / Avg: 187.65 / Max: 267.6

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.2340.4680.7020.9361.171.040.270.490.480.280.480.620.560.370.550.770.570.610.940.800.290.550.66

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER50100150200250Min: 52.4 / Avg: 173.16 / Max: 273Min: 52.1 / Avg: 148.78 / Max: 190.2Min: 48.3 / Avg: 135.38 / Max: 188.6Min: 45.8 / Avg: 106.92 / Max: 138.1Min: 53.5 / Avg: 157.67 / Max: 213.1Min: 48.2 / Avg: 115.16 / Max: 152Min: 109.8 / Avg: 203.83 / Max: 255.3Min: 49.1 / Avg: 151.63 / Max: 200.9Min: 45.7 / Avg: 125.77 / Max: 157.6Min: 49 / Avg: 134.34 / Max: 190.3Min: 51.5 / Avg: 146.49 / Max: 216.5Min: 53.5 / Avg: 128.35 / Max: 157.6Min: 51.5 / Avg: 138.71 / Max: 203.8Min: 52.7 / Avg: 173.29 / Max: 277.5Min: 48.8 / Avg: 141.86 / Max: 214.3Min: 57 / Avg: 191.08 / Max: 247.4Min: 55.8 / Avg: 142.16 / Max: 204.9Min: 49.1 / Avg: 124.58 / Max: 203.3

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.34430.68861.03291.37721.72151.470.540.940.960.590.990.940.950.721.151.291.011.271.521.410.581.261.53

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 50.4 / Avg: 231.53 / Max: 336Min: 94.8 / Avg: 192.64 / Max: 216.8Min: 83.7 / Avg: 182.29 / Max: 211.2Min: 44.8 / Avg: 135.27 / Max: 159.9Min: 99.4 / Avg: 199.9 / Max: 241.3Min: 46.5 / Avg: 154.44 / Max: 184.5Min: 107 / Avg: 238.78 / Max: 315.7Min: 48.2 / Avg: 203.49 / Max: 246Min: 75.4 / Avg: 157.49 / Max: 178.6Min: 48.1 / Avg: 176.3 / Max: 224.1Min: 49.7 / Avg: 201.32 / Max: 272.7Min: 51.4 / Avg: 151.49 / Max: 175.5Min: 48 / Avg: 190.9 / Max: 247Min: 51.3 / Avg: 235.38 / Max: 341.7Min: 46.7 / Avg: 204.84 / Max: 277Min: 124.3 / Avg: 237.03 / Max: 284.6Min: 54.2 / Avg: 192.58 / Max: 235.4Min: 46.5 / Avg: 184.51 / Max: 249.7

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: NASNer Large - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.08330.16660.24990.33320.41650.370.110.180.210.120.220.240.200.150.230.290.230.260.370.320.130.250.30

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER50100150200250Min: 51.5 / Avg: 167.74 / Max: 291.7Min: 81.7 / Avg: 163.48 / Max: 201.2Min: 77.9 / Avg: 157.58 / Max: 202.6Min: 44.8 / Avg: 109.89 / Max: 143.5Min: 52.8 / Avg: 183.08 / Max: 228.8Min: 47.3 / Avg: 117.8 / Max: 162Min: 55.7 / Avg: 189.84 / Max: 284.9Min: 94.6 / Avg: 159.56 / Max: 227.4Min: 68.7 / Avg: 129.36 / Max: 164Min: 47.9 / Avg: 142.09 / Max: 199.4Min: 50.7 / Avg: 139.72 / Max: 234.8Min: 51.5 / Avg: 131.42 / Max: 162.8Min: 49 / Avg: 148.17 / Max: 210.6Min: 55.6 / Avg: 169.21 / Max: 293Min: 48.5 / Avg: 147.96 / Max: 225.2Min: 127.5 / Avg: 205.03 / Max: 260.5Min: 54.4 / Avg: 144.26 / Max: 207.2Min: 47.9 / Avg: 135.09 / Max: 211.7

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.5761.1521.7282.3042.882.530.711.241.420.781.471.761.511.011.552.191.571.692.562.220.791.742.10

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER50100150200250Min: 50.7 / Avg: 178.03 / Max: 280Min: 72.9 / Avg: 158.81 / Max: 190.7Min: 70.5 / Avg: 148.83 / Max: 185.2Min: 44.4 / Avg: 112.99 / Max: 143Min: 99.3 / Avg: 168.06 / Max: 211.7Min: 46.7 / Avg: 122.59 / Max: 164Min: 125.6 / Avg: 201.87 / Max: 257Min: 84.5 / Avg: 158.48 / Max: 204.6Min: 55.5 / Avg: 124.66 / Max: 155.7Min: 48.8 / Avg: 144.1 / Max: 197.4Min: 49 / Avg: 153.24 / Max: 230.1Min: 51 / Avg: 131.33 / Max: 154.1Min: 47.6 / Avg: 141.04 / Max: 207.9Min: 51.1 / Avg: 182.86 / Max: 282.6Min: 48.4 / Avg: 151.02 / Max: 226.9Min: 128.3 / Avg: 193.81 / Max: 239.9Min: 53 / Avg: 147.84 / Max: 203.6Min: 46.6 / Avg: 139.53 / Max: 205.1

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.4590.9181.3771.8362.2952.040.560.951.220.611.321.131.100.781.341.751.121.572.041.990.601.491.72

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER61218243026.716.9812.3514.797.1716.0615.2114.029.5718.2026.2114.1621.3522.1925.067.6720.6824.75

cl-mem

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.83481.66962.50443.33924.1743.461.071.541.611.032.332.021.641.442.242.741.763.713.132.851.482.612.60

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.86631.73262.59893.46524.33153.381.051.681.691.192.672.101.901.342.763.261.863.283.373.851.763.093.47

clpeak

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorGTX 1660 TiGTX 1080 TiGTX 1060RTX 2070TITAN RTXRTX 2080 SUPERRTX 2060 SUPERRTX 2070 SUPER70140210280350Min: 46.4 / Avg: 77.81 / Max: 158.1Min: 52.4 / Avg: 199.89 / Max: 328.7Min: 66.2 / Avg: 117.06 / Max: 191Min: 47.8 / Avg: 135.68 / Max: 254.5Min: 52.5 / Avg: 207.88 / Max: 366.7Min: 47.9 / Avg: 144.19 / Max: 288.8Min: 47.4 / Avg: 86.98 / Max: 242.5Min: 47.5 / Avg: 141.91 / Max: 279.4

OpenBenchmarking.orgGIOPS Per Watt, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER30609012015054.769.1923.8979.948.4461.3816.5226.8210.8363.25123.0725.5952.7866.5872.169.0080.7460.39

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4080120160200Min: 50.3 / Avg: 197 / Max: 217.1Min: 93.6 / Avg: 140.29 / Max: 146.2Min: 46 / Avg: 117.77 / Max: 137.1Min: 43.9 / Avg: 97.25 / Max: 106.6Min: 51.6 / Avg: 146.12 / Max: 159.1Min: 46.4 / Avg: 107.92 / Max: 119.4Min: 51.6 / Avg: 166.5 / Max: 193Min: 46.2 / Avg: 135.52 / Max: 152.6Min: 44.7 / Avg: 102.22 / Max: 117.3Min: 47.9 / Avg: 126.06 / Max: 143Min: 49.8 / Avg: 153.89 / Max: 172.5Min: 51 / Avg: 113.26 / Max: 124.1Min: 46.9 / Avg: 137.5 / Max: 151.9Min: 51.5 / Avg: 203.24 / Max: 225.1Min: 47.6 / Avg: 151.43 / Max: 166.9Min: 128.4 / Avg: 179.97 / Max: 191.4Min: 47.1 / Avg: 142.14 / Max: 150.8Min: 47 / Avg: 137.66 / Max: 150.3

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.60751.2151.82252.433.03752.650.981.901.731.091.722.492.201.461.842.252.141.952.702.501.091.852.25

OpenBenchmarking.orgWatts, Fewer Is BetterclpeakSystem Power Consumption MonitorGTX 970GTX 980GTX 1660 TiRTX 2070TITAN RTXGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 51.4 / Avg: 98.78 / Max: 148.8Min: 52.5 / Avg: 122.69 / Max: 181.1Min: 45.5 / Avg: 67.18 / Max: 127.1Min: 48.2 / Avg: 96.86 / Max: 180.2Min: 50.6 / Avg: 137.09 / Max: 308.7Min: 54.9 / Avg: 131.87 / Max: 194.2Min: 46.6 / Avg: 63.45 / Max: 103Min: 47.5 / Avg: 69.91 / Max: 138.9

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 2080 TiGTX 970GTX 1070GTX 980GTX 1660 TiGTX 1080RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER50100150200250222.0939.3670.6336.4971.3589.11109.2079.2584.4674.32103.6184.4942.00111.74121.62

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER36912159.151.522.633.161.652.242.732.261.845.091.923.336.184.862.024.885.41

JuliaGPU

OpenBenchmarking.orgSamples/sec Per Watt, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPURTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER600K1200K1800K2400K3000K1910018.661275493.931809790.272790569.691325997.882880366.361682592.711906369.991658141.692469451.172691799.292260229.902271141.791923116.672379445.261099178.252670026.702632329.69

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGHash/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashGTX 970GTX 1660GTX 980GTX 1660 TiGTX 1080GTX 1060RTX 2060RTX 2080RTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2070 SUPER0.08330.16660.24990.33320.41650.050.260.080.260.150.110.120.210.150.370.320.040.30

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070GTX 980 TiRTX 2060 SUPERRTX 2070 SUPER4812162011.545.126.235.705.4512.257.977.874.0013.2315.466.368.676.9217.5915.58

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350Min: 51.3 / Avg: 217.17 / Max: 360Min: 80.6 / Avg: 148.92 / Max: 222.7Min: 78 / Avg: 141.46 / Max: 206.4Min: 44.5 / Avg: 106.24 / Max: 161Min: 97.6 / Avg: 160.93 / Max: 243.5Min: 46.4 / Avg: 118.75 / Max: 170.7Min: 49.6 / Avg: 199.67 / Max: 326.6Min: 94 / Avg: 157.13 / Max: 259.6Min: 74.8 / Avg: 119.53 / Max: 184.8Min: 47 / Avg: 145.37 / Max: 229.5Min: 48.7 / Avg: 171.33 / Max: 292.2Min: 50.5 / Avg: 125.61 / Max: 179.8Min: 47.9 / Avg: 149.29 / Max: 251.7Min: 52 / Avg: 223.03 / Max: 367Min: 47 / Avg: 164.08 / Max: 318.6Min: 126.9 / Avg: 193.91 / Max: 298.6Min: 46.8 / Avg: 148.63 / Max: 238Min: 47.1 / Avg: 150.09 / Max: 265.5

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER2040608010076.6929.2950.3050.1731.4049.6366.2659.8740.0650.3663.9361.4357.1377.7273.2332.0556.3865.76

cl-mem

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.72681.45362.18042.90723.6343.230.961.351.581.041.961.621.651.252.662.281.532.442.172.831.452.432.82

ViennaCL

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.3150.630.9451.261.5751.310.660.801.080.791.100.590.701.000.730.710.711.351.351.180.601.400.90

Rodinia

OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 2.4System Power Consumption MonitorGTX 970GTX 1660GTX 980GTX 1660 TiGTX 1060RTX 2060GTX 1070 TiGTX 980 TiRTX 2070 SUPER4080120160200Min: 50.5 / Avg: 141.83 / Max: 190Min: 45.1 / Avg: 88.85 / Max: 116.6Min: 52.6 / Avg: 156.47 / Max: 203.2Min: 46 / Avg: 107.04 / Max: 129.7Min: 44.7 / Avg: 111.27 / Max: 154.1Min: 47.6 / Avg: 121.91 / Max: 156.6Min: 50.3 / Avg: 101.74 / Max: 149.4Min: 54.7 / Avg: 167.04 / Max: 233.5Min: 47 / Avg: 103.36 / Max: 166

OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 2.4System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER306090120150Min: 51.1 / Avg: 152.87 / Max: 162.6Min: 85.4 / Avg: 117.57 / Max: 120.9Min: 70.9 / Avg: 107.97 / Max: 112.9Min: 45.5 / Avg: 90.35 / Max: 95.7Min: 88.8 / Avg: 119.77 / Max: 124.7Min: 45.9 / Avg: 98.53 / Max: 104.6Min: 53.3 / Avg: 137.65 / Max: 146.3Min: 47.4 / Avg: 113.6 / Max: 118.7Min: 62.8 / Avg: 97.17 / Max: 100.8Min: 46.6 / Avg: 112.18 / Max: 123.5Min: 49.5 / Avg: 131.08 / Max: 142Min: 49.1 / Avg: 105.1 / Max: 108.7Min: 48.1 / Avg: 122.39 / Max: 128.3Min: 51.9 / Avg: 158.82 / Max: 169.5Min: 46.6 / Avg: 123.16 / Max: 135.3Min: 110.1 / Avg: 153.24 / Max: 157.4Min: 46.3 / Avg: 122.27 / Max: 129.5Min: 46.4 / Avg: 116.19 / Max: 128.7

LuxMark

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350Min: 54.2 / Avg: 341.41 / Max: 361Min: 50.9 / Avg: 198.98 / Max: 206.3Min: 48.8 / Avg: 197.56 / Max: 206Min: 46.7 / Avg: 154.16 / Max: 157.9Min: 51.4 / Avg: 215.19 / Max: 226.6Min: 47.2 / Avg: 169.1 / Max: 176.4Min: 55.9 / Avg: 282.16 / Max: 295.6Min: 47.9 / Avg: 205.71 / Max: 214.4Min: 45.7 / Avg: 155.74 / Max: 161.6Min: 50.4 / Avg: 210.86 / Max: 220.4Min: 52.6 / Avg: 269.03 / Max: 281.5Min: 51.1 / Avg: 162.66 / Max: 167.9Min: 51.8 / Avg: 241 / Max: 251.5Min: 57.7 / Avg: 358.16 / Max: 371Min: 50.8 / Avg: 249.5 / Max: 264.2Min: 57.2 / Avg: 255.39 / Max: 271.7Min: 47.9 / Avg: 233.07 / Max: 242.2Min: 47.6 / Avg: 241.53 / Max: 254.1

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: HotelRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER61218243026.9913.7219.5924.2214.1622.5020.0218.5117.0022.9224.5025.6425.5227.4627.4115.2126.3827.18

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 55.9 / Avg: 318.95 / Max: 337.2Min: 51.9 / Avg: 177.8 / Max: 184.4Min: 49 / Avg: 170.27 / Max: 177.6Min: 46 / Avg: 137.52 / Max: 142.7Min: 51 / Avg: 193.46 / Max: 203.7Min: 48 / Avg: 156.46 / Max: 161.4Min: 52.7 / Avg: 237.89 / Max: 245.4Min: 49.1 / Avg: 173.32 / Max: 180.3Min: 45.6 / Avg: 138.57 / Max: 144.8Min: 48.6 / Avg: 190.73 / Max: 198.4Min: 53.8 / Avg: 241.11 / Max: 251.4Min: 50.1 / Avg: 145.89 / Max: 150.4Min: 51.5 / Avg: 219.74 / Max: 234.1Min: 60.2 / Avg: 337.98 / Max: 356.9Min: 47.8 / Avg: 225.09 / Max: 235.4Min: 112.5 / Avg: 234.81 / Max: 244.3Min: 49.8 / Avg: 222.76 / Max: 232.3Min: 47.6 / Avg: 220.93 / Max: 232.4

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: MicrophoneRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER2040608010089.7744.9158.6371.2246.0870.3357.6850.2951.1472.1182.6070.3283.9291.0089.5847.2583.0992.78

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 53.9 / Avg: 326.39 / Max: 340.7Min: 52.2 / Avg: 180.29 / Max: 185.6Min: 48.6 / Avg: 181.94 / Max: 188.2Min: 45.9 / Avg: 139.49 / Max: 144Min: 87.7 / Avg: 195.16 / Max: 205Min: 48.2 / Avg: 157.16 / Max: 163.8Min: 107.7 / Avg: 245.73 / Max: 254Min: 75.8 / Avg: 180.11 / Max: 185.5Min: 76 / Avg: 146.92 / Max: 152Min: 47.4 / Avg: 192.86 / Max: 200.8Min: 52.5 / Avg: 244.9 / Max: 255.3Min: 52.3 / Avg: 151.74 / Max: 155.9Min: 50.1 / Avg: 230.98 / Max: 243.5Min: 53.7 / Avg: 338.9 / Max: 360.6Min: 49.4 / Avg: 230.52 / Max: 238Min: 130.4 / Avg: 238.82 / Max: 247.5Min: 47.2 / Avg: 229.14 / Max: 241Min: 47.5 / Avg: 217.27 / Max: 227.7

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER306090120150131.6665.0795.03108.7067.87102.7588.2676.5583.34112.43119.09111.54130.30137.34130.9270.64131.33136.85

NAMD CUDA

OpenBenchmarking.orgWatts, Fewer Is BetterNAMD CUDA 2.13System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER70140210280350Min: 53.9 / Avg: 251.92 / Max: 374Min: 51.3 / Avg: 258.19 / Max: 306.3Min: 48.2 / Avg: 206.59 / Max: 286.9Min: 44.9 / Avg: 177.54 / Max: 262.4Min: 52.6 / Avg: 238.95 / Max: 329.4Min: 47.7 / Avg: 177.22 / Max: 273.9Min: 55.3 / Avg: 266.23 / Max: 380Min: 48.6 / Avg: 253.18 / Max: 326.9Min: 45.2 / Avg: 198.8 / Max: 269.5Min: 46.1 / Avg: 197.89 / Max: 303.8Min: 52.9 / Avg: 238.49 / Max: 342.9Min: 50.3 / Avg: 198.82 / Max: 259.9Min: 50 / Avg: 202.69 / Max: 321.3Min: 54.3 / Avg: 214.96 / Max: 367.7Min: 48.8 / Avg: 219.44 / Max: 330.5Min: 55.9 / Avg: 272.91 / Max: 370.3Min: 48.4 / Avg: 233.81 / Max: 312Min: 47.2 / Avg: 198.42 / Max: 323.3

FAHBench

OpenBenchmarking.orgWatts, Fewer Is BetterFAHBench 2.3.2System Power Consumption MonitorRTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER60120180240300Min: 49.7 / Avg: 218.05 / Max: 323.3Min: 48.8 / Avg: 147.69 / Max: 193Min: 43.8 / Avg: 145.58 / Max: 193.2Min: 46.5 / Avg: 114.3 / Max: 152.8Min: 49.8 / Avg: 159.19 / Max: 211.9Min: 47.6 / Avg: 127.19 / Max: 170.3Min: 77.6 / Avg: 195.24 / Max: 264.4Min: 44.9 / Avg: 154.62 / Max: 208.2Min: 66.3 / Avg: 124.04 / Max: 159.6Min: 45.7 / Avg: 151.46 / Max: 214.2Min: 47.5 / Avg: 176.01 / Max: 263Min: 49.1 / Avg: 125.16 / Max: 155Min: 46 / Avg: 158.7 / Max: 226.7Min: 52.5 / Avg: 226.18 / Max: 324.2Min: 64 / Avg: 177.55 / Max: 252.2Min: 56.3 / Avg: 186.17 / Max: 244.4Min: 48.5 / Avg: 161.35 / Max: 226.3Min: 46.6 / Avg: 161.4 / Max: 230

OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterFAHBench 2.3.2RTX 2080 TiGTX 970GTX 1070GTX 1660GTX 980GTX 1660 TiGTX 1080 TiGTX 1080GTX 1060RTX 2060RTX 2080GTX 1070 TiRTX 2070TITAN RTXRTX 2080 SUPERGTX 980 TiRTX 2060 SUPERRTX 2070 SUPER0.32630.65260.97891.30521.63151.380.620.961.110.651.101.021.000.831.211.381.101.291.331.450.621.271.42

94 Results Shown

SHOC Scalable HeterOgeneous Computing
OctaneBench
LuxMark:
  GPU - Microphone
  GPU - Luxball HDR
  GPU - Hotel
FAHBench
PlaidML:
  Yes - Inference - NASNer Large - OpenCL
  Yes - Inference - VGG19 - OpenCL
  Yes - Inference - DenseNet 201 - OpenCL
Rodinia
PlaidML
clpeak
PlaidML:
  No - Inference - VGG19 - OpenCL
  Yes - Inference - Inception V3 - OpenCL
LeelaChessZero
PlaidML:
  No - Inference - VGG16 - OpenCL
  No - Inference - Inception V3 - OpenCL
  Yes - Inference - ResNet 50 - OpenCL
NAMD CUDA
PlaidML:
  No - Inference - ResNet 50 - OpenCL
  No - Inference - IMDB LSTM - OpenCL
Rodinia
cl-mem
JuliaGPU
PlaidML
cl-mem:
  Copy
  Write
PlaidML
Darktable
clpeak
Darktable
clpeak
Darktable
ViennaCL
SHOC Scalable HeterOgeneous Computing
clpeak
SHOC Scalable HeterOgeneous Computing
System Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Celsius
  System Power Consumption Monitor:
    Watts
  Total Score:
    Score Per Watt
  System Power Consumption Monitor:
    Watts
  OpenCL:
    Nodes Per Second Per Watt
  System Power Consumption Monitor:
    Watts
  No - Inference - VGG19 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  No - Inference - VGG16 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  No - Inference - IMDB LSTM - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  No - Inference - ResNet 50 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  No - Inference - Inception V3 - OpenCL:
    FPS Per Watt
  No - Inference - Mobilenet - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  Yes - Inference - VGG19 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  Yes - Inference - VGG16 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  Yes - Inference - DenseNet 201 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  Yes - Inference - NASNer Large - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  Yes - Inference - ResNet 50 - OpenCL:
    FPS Per Watt
  System Power Consumption Monitor:
    Watts
  Yes - Inference - Inception V3 - OpenCL:
    FPS Per Watt
  Yes - Inference - Mobilenet - OpenCL:
    FPS Per Watt
  Write:
    GB/s Per Watt
  Read:
    GB/s Per Watt
  System Power Consumption Monitor:
    Watts
  Integer Compute INT:
    GIOPS Per Watt
  System Power Consumption Monitor:
    Watts
  Double-Precision Double:
    GFLOPS Per Watt
  System Power Consumption Monitor:
    Watts
  Single-Precision Float:
    GFLOPS Per Watt
  Global Memory Bandwidth:
    GBPS Per Watt
  GPU:
    Samples/sec Per Watt
  OpenCL - MD5 Hash:
    GHash/s Per Watt
  OpenCL - FFT SP:
    GFLOPS Per Watt
  System Power Consumption Monitor:
    Watts
  OpenCL - Max SP Flops:
    GFLOPS Per Watt
  Copy:
    GB/s Per Watt
  OpenCL LU Factorization:
    GFLOPS Per Watt
  System Power Consumption Monitor:
    Watts
    Watts
    Watts
  GPU - Hotel:
    Score Per Watt
  System Power Consumption Monitor:
    Watts
  GPU - Microphone:
    Score Per Watt
  System Power Consumption Monitor:
    Watts
  GPU - Luxball HDR:
    Score Per Watt
  System Power Consumption Monitor:
    Watts
    Watts
  :
    Ns Per Day Per Watt