NVIDIA GPU Compute

Some benchmarks by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2009116-FI-GPUCOMPUT55
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 950
September 10 2020
  1 Hour, 38 Minutes
GTX 960
September 10 2020
  1 Hour, 43 Minutes
GTX 970
September 06 2020
  2 Hours, 9 Minutes
GTX 980
September 07 2020
  1 Hour, 34 Minutes
GTX 980 Ti
September 07 2020
  1 Hour, 29 Minutes
GTX TITAN X
September 09 2020
  1 Hour, 28 Minutes
GTX 1050 Ti
September 10 2020
  1 Hour, 48 Minutes
GTX 1060
September 08 2020
  1 Hour, 32 Minutes
GTX 1070
September 07 2020
  1 Hour, 26 Minutes
GTX 1070 Ti
September 06 2020
  1 Hour, 31 Minutes
GTX 1080
September 07 2020
  1 Hour, 23 Minutes
GTX 1650
September 09 2020
  1 Hour, 45 Minutes
GTX 1650 SUPER
September 08 2020
  1 Hour, 35 Minutes
GTX 1660
September 09 2020
  1 Hour, 47 Minutes
GTX 1660 SUPER
September 07 2020
  1 Hour, 30 Minutes
GTX 1660 Ti
September 09 2020
  1 Hour, 31 Minutes
RTX 2060
September 08 2020
  1 Hour, 42 Minutes
RTX 2060 SUPER
September 09 2020
  1 Hour, 25 Minutes
RTX 2070
September 09 2020
  1 Hour, 25 Minutes
RTX 2070 SUPER
September 08 2020
  1 Hour, 26 Minutes
RTX 2080
September 08 2020
  1 Hour, 25 Minutes
RTX 2080 SUPER
September 08 2020
  1 Hour, 39 Minutes
RTX 2080 Ti
September 07 2020
  1 Hour, 24 Minutes
TITAN RTX
September 06 2020
  1 Hour, 24 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 34 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 GPU ComputeOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600NVIDIA TITAN RTX 24GB (420/405MHz)Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz)eVGA NVIDIA GeForce GTX 970 4GB (1163/3505MHz)eVGA NVIDIA GeForce GTX 1660 SUPER 6GB (1530/7000MHz)NVIDIA GeForce GTX 980 4GB (1126/3505MHz)NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)NVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA GeForce GTX 980 Ti 6GB (999/3505MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA GeForce GTX 1060 6GB (1506/4006MHz)NVIDIA GeForce RTX 2060 6GB (1365/7000MHz)ASUS NVIDIA GeForce GTX 1650 SUPER 4GB (615/405MHz)NVIDIA GeForce RTX 2070 SUPER 8GB (450/405MHz)NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz)Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)eVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz)ASUS NVIDIA GeForce GTX 1660 6GB (1530/4001MHz)ASUS NVIDIA GeForce GTX 1650 4GB (1485/4001MHz)NVIDIA GeForce GTX TITAN X 12GB (1001/3505MHz)eVGA NVIDIA GeForce GTX 1050 Ti 4GB (1354/3504MHz)eVGA NVIDIA GeForce GTX 960 2GB (1277/3505MHz)eVGA NVIDIA GeForce GTX 950 2GB (1202/3304MHz)NVIDIA TU102 HD AudioNVIDIA GP104 HD AudioNVIDIA GM204 HD AudioNVIDIA TU116 HD AudioNVIDIA GM200 HD AudioNVIDIA GP106 HD AudioNVIDIA TU106 HD AudioNVIDIA TU104 HD AudioNVIDIA Device 10faNVIDIA GP107GL HD AudioNVIDIA GM206 HD AudioDELL P2415QRealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.4.0-45-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 450.664.6.0OpenCL 1.2 CUDA 11.0.2281.2.133GCC 9.3.0 + CUDA 11.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA GPU Compute BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013- TITAN RTX: GPU Compute Cores: 4608- GTX 1070 Ti: GPU Compute Cores: 2432- GTX 970: GPU Compute Cores: 1664- GTX 1660 SUPER: GPU Compute Cores: 1408- GTX 980: GPU Compute Cores: 2048- GTX 1070: GPU Compute Cores: 1920- GTX 1080: GPU Compute Cores: 2560- GTX 980 Ti: GPU Compute Cores: 2816- RTX 2080 Ti: GPU Compute Cores: 4352- GTX 1060: GPU Compute Cores: 1280- RTX 2060: GPU Compute Cores: 1920- GTX 1650 SUPER: GPU Compute Cores: 1280- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2080 SUPER: GPU Compute Cores: 3072- RTX 2080: GPU Compute Cores: 2944- RTX 2070: GPU Compute Cores: 2304- RTX 2060 SUPER: GPU Compute Cores: 2176- GTX 1660 Ti: GPU Compute Cores: 1536- GTX 1660: GPU Compute Cores: 1408- GTX 1650: GPU Compute Cores: 896- GTX TITAN X: GPU Compute Cores: 3072- GTX 1050 Ti: GPU Compute Cores: 768- GTX 960: GPU Compute Cores: 1024- GTX 950: GPU Compute Cores: 768- Python 3.8.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + 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 AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

TITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060RTX 2060GTX 1650 SUPERRTX 2070 SUPERRTX 2080 SUPERRTX 2080RTX 2070RTX 2060 SUPERGTX 1660 TiGTX 1660GTX 1650GTX TITAN XGTX 1050 TiGTX 960GTX 950Logarithmic Result OverviewPhoronix Test SuiteclpeakMandelGPUOctaneBenchcl-memFAHBenchLuxCoreRender OpenCLArrayFirePlaidMLGROMACSDarktableNAMD CUDARodiniaFinanceBenchLeelaChessZeroMixbenchViennaCLDarmstadt Automotive Parallel Heterogeneous Suite

NVIDIA GPU Computedarktable: Boat - OpenCLmixbench: NVIDIA CUDA - Half Precisionclpeak: Double-Precision Doublemandelgpu: GPUmixbench: OpenCL - Single Precisionclpeak: Single-Precision Floatplaidml: No - Inference - IMDB LSTM - OpenCLcl-mem: Readmixbench: OpenCL - Double Precisionclpeak: Global Memory Bandwidthmixbench: NVIDIA CUDA - Single Precisionoctanebench: Total Scorecl-mem: Writeplaidml: No - Inference - Mobilenet - OpenCLluxcorerender-cl: LuxCore Benchmarkluxcorerender-cl: DLSCplaidml: No - Inference - Inception V3 - OpenCLluxcorerender-cl: Foodplaidml: Yes - Inference - Mobilenet - OpenCLrodinia: OpenCL Particle Filterfahbench: plaidml: No - Inference - DenseNet 201 - OpenCLarrayfire: Conjugate Gradient OpenCLneatbench: GPUarrayfire: BLAS OpenCLmixbench: NVIDIA CUDA - Double Precisiondarktable: Server Room - OpenCLluxcorerender-cl: Rainbow Colors and Prismcl-mem: Copyplaidml: No - Inference - VGG19 - OpenCLgromacs-gpu: Water Benchmarkplaidml: No - Training - Mobilenet - OpenCLnamd-cuda: ATPase Simulation - 327,506 Atomsmixbench: OpenCL - Integerplaidml: No - Inference - VGG16 - OpenCLfinancebench: Monte-Carlo OpenCLclpeak: Integer Compute INTmixbench: NVIDIA CUDA - Integerlczero: OpenCLdarktable: Server Rack - OpenCLdarktable: Masskrug - OpenCLrodinia: OpenCL Myocyterodinia: NVIDIA CUDA GPU Myocyteviennacl: OpenCL LU Factorizationdaphne: NVIDIA CUDA - Euclidean Clusterdaphne: OpenCL - Euclidean Clusterdaphne: OpenCL - NDT Mappingdaphne: OpenCL - Points2Imagedaphne: NVIDIA CUDA - NDT Mappingdaphne: NVIDIA CUDA - Points2Imagefinancebench: Black-Scholes OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060RTX 2060GTX 1650 SUPERRTX 2070 SUPERRTX 2080 SUPERRTX 2080RTX 2070RTX 2060 SUPERGTX 1660 TiGTX 1660GTX 1650GTX TITAN XGTX 1050 TiGTX 960GTX 9501.49132084.79548.26480798376.615032.4714178.85775.69567.7454.37530.7915103.61324.546769491.72544.674.995.98355.852.232856.834.250292.1593227.301.66648.15040.58413.660.76712.73322.7196.637.117198.370.1919516979.99248.79277.23212113783.9314426.11224240.1032.79235.76740.37376.64101434.172279.14343.6112538.245787081590.6329401.5140702215.7012.741121.42242.70194875210.87018.906788.40331.84206.2241.99198.186647.94141.667655198.21070.902.242.55159.430.981485.787.791137.1393108.233.8144304.76240.921.1665.38184.192.874.25999.640.223002157.31116.89754.2840122076.451887.6199470.1172.99842.08147.72269.18381204.772223.78349.1213281.7676294197.2984.311137.48113624502.04141.793874.98203.08144.6137.20144.5696.200864136.3716.821.461.7397.830.67910.9113.18590.846073.895.40015.42457.732.8624.81125.951.142.99573.250.360711215.7564.53841.1885811145.1451630.1634.61048.92056.49860.1979979.331928.88324.7011485.50413704514.1962.60710862.90172.49200846066.45462.594440.23298.77296.6144.30276.355440.74135.657134240.71080.112.262.63135.311.091380.6811.482135.6073100.512.6421765.01144.141.0825.61240.268.814.629111.390.231775432.4086.61594.4380044280.554866.6173660.1043.03034.12739.90568.15321466.242175.96320.9713933.273948165563.1329306.12750590715.2713.764159.72121139566.84683.964472.77228.46165.3159.33165.29110.814321159.1810.501.631.93109.500.781053.4911.774102.366882.214.90417.32826.162.7305.11145.056.603.27180.470.335661389.9072.21749.2880021306.5162650.1624.54350.55359.47461.93621019.041976.41333.5211735.84148529812.1012.709113.32223.60184077179.76476.926093.02314.83206.2224.82197.206174.80132.839354199.51052.642.122.46151.710.921392.468.205139.4974108.464.07721.52905.88225.051.1126.62183.379.124.052103.790.240222019.0899.88697.5462911695.791764.6397500.1172.97438.00342.95566.20681231.442243.10345.4413045.8573943518.9682.546149.35298.46231826397.88520.978218.62398.82229.6296.66223.148182.72148.472009225.61154.132.132.45190.140.991665.726.457151.5679112.283.38724.65091.86296.091.0954.23207.4103.834.63499.820.224262655.58131.34921.6841522430.552326.09126620.1112.97437.99843.19770.68801218.562345.38348.2913141.7294623906.9813.017197.23148357386.15844.905512.89267.88266.0197.44264.74143.521432245.91029.362.002.36138.330.921290.4810.071115.775399.843.6222438.971.3986.59217.871.183.85789.280.291381711.0390.74660.5482491612.5282830.1643.22755.17464.75864.5358976.751908.81339.2111829.8646244989.5961.49231492.24522.22448915216.616061.0913536.25753.75545.7436.81506.9014734.03310.814399449.52406.164.755.67353.542.232751.854.414290.7249212.111.6774836.62409.460.75912.33324.0187.927.136187.730.1908216323.94237.29319.91412713629.3714103.79218390.1002.75535.23540.35275.78711436.622268.23350.3713045.030923941606.7528816.8178368956.0203.51775.77150.68130290433.84355.284110.71227.23154.4150.48147.664167.4191.732906148.1775.731.531.78108.560.65987.0712.002102.268379.135.0002856.38151.631.3015.41138.556.623.18183.520.309571354.1471.78894.0848651275.121187.7259330.1243.16938.11442.70361.65301253.432076.48333.4711766.29182612713.3402.09214646.46232.17252924048.77222.285417.55390.07297.4194.80276.947339.39166.098571258.71285.582.793.34172.731.171719.718.836178.4712125.232.65928.32321.09196.300.8447.97239.488.955.416125.330.206357275.33112.29528.3677445356.846539.81102900.1042.83534.90239.99973.30911468.392263.12332.0013398.060270468570.7730937.28262316312.5555.07010057.46157.98186025762.64943.064123.66269.17167.0132.75156.864993.9292.367839145.8740.171.361.61115.700.811080.4312.48782.052173.174.4451607.77133.882.9032.73143.861.854.12277.100.262114975.1877.981087.1681264128.394492.3251510.1214.75633.68639.93767.93301456.662143.59313.8012256.663207158534.8529380.30781584116.5777851.78019501.67308.86323061985.49630.838540.73500.26396.8259.11369.629754.99221.193748322.91712.753.694.44221.491.902287.036.837221.7284149.692.0713047.42260.970.82110.21292.1123.036.249154.740.196259696.38155.42400.3836258484.418722.28147300.0982.80434.77940.08574.44731444.272264.37338.6513076.859862793589.6330409.0647642218.2631.68023628.78376.32374422420.611758.6510264.38588.04437.6315.03405.9211685.95234.066446352.91815.923.624.38265.911.932432.735.718248.0118159.791.9003673.83315.610.8099.14301.7145.576.572158.820.1932911752.11183.53413.84512710266.7210562.99175010.0992.76434.20740.01276.10161448.462326.55344.1912974.465793761599.7030214.7556356346.8111.74221764.40345.11345359936.410812.529161.18544.54396.5290.13369.2310845.36224.387211338.11726.603.554.32243.511.872322.396.196235.5341151.992.07538.33358.20291.560.8189.24290.0130.236.536154.350.1926510930.56164.78406.0421229141.239732.48154420.0992.79435.08540.48774.72981441.292245.82341.8413228.140991558599.6429707.4414898257.6571.77616838.72267.79284631717.48357.967265.91444.84396.9226.65369.308435.23207.538286328.51575.653.494.17202.421.301996.607.767199.8719147.872.09735.82680.69226.210.77210.98284.4104.215.865153.030.203628362.86132.03377.7225007133.777540.28123110.1022.74435.51440.49972.56991462.962309.01339.1213499.166892694579.3629917.29572719310.2541.79416507.06261.89281931310.08159.157034.77438.26396.8222.15368.948264.66206.078943341.31585.763.544.20204.351.332012.377.914200.7664146.902.0832622.04221.800.77711.32288.0101.795.789154.810.200578218.02128.91367.0220036930.217348.91123350.1012.76334.55540.22472.50101475.242326.88338.0813476.343300533575.4530663.63830301310.4982.75711787.37184.34210891296.25821.194778.23313.08251.2155.78234.915888.78133.345223.91038.862.112.51143.221.071427.4310.847138.557898.993.0681877.32157.141.1665.01211.173.384.789108.060.228005803.6392.41654.8158654734.365271.3477330.1063.09134.41240.03870.02871465.392223.07321.7713606.962912993557.2029450.46232790214.3853.17310568.46168.56193795979.55259.294543.64289.42163.9141.25158.155313.33119.105265157.3858.902.202.56120.840.991199.6611.893125.615887.254.54118.61712.37141.361.1955.58145.967.744.41297.940.242905303.5185.46606.6998834338.674753.1158950.1133.09734.75840.06667.82001452.412174.72314.7113590.031350614552.6829594.88499253615.25912.4066948.33109.20132266243.93441.362673.64201.27108.791.77105.313474.1777.410218104.4573.671.511.7380.680.67814.5017.82375.813559.376.80812.81128.3992.373.6933.9399.242.323.25365.590.345033466.7253.35895.4304292641.383108.8431010.1854.32933.71539.89562.96071415.671983.67287.0712203.304555462517.1429148.73980909124.14528512.388219.42162891036.96463.106121.76294.10243.5221.88246.43154.420819237.61106.292.092.50148.840.981369.209.155123.1897105.393.9173699.513.6996.47214.475.734.08193.030.271031911.0197.40624.1757431757.8190660.1894.32453.83263.60365.9450956.541953.25339.7511498.2154879909.32312.30742.3984.6075842143.42561.982331.18130.6695.284.7892.342379.0155.43259391.2481.310.961.1360.920.46594.4121.26761.588949.717.7751639.0884.553.6773.9887.929.422.08457.130.53233771.5337.131214.994001719.46667.9025650.1924.29439.05343.28351.33811219.991759.04305.0711780.67548733224.36220012.40092.4179940246.72779.322604.97143.1581.593.0182.2358.90322977.7434.070.971.15213.490.44609.1618.40962.304145.548.9689.531303.043.6722.8472.810000000002.1540.50785828.804.911789.9924300.1914.28145.50952.33452.9206982.721778.01308.2811773.35493141619.51320012.39269.8761530230.32149.601974.96111.2590.369.7890.1851.15504584.9408.280.810.980.39508.6623.83452.694141.978.3499.541019.483.6843.2278.510000000001.8020.59513625.5510000000004.919593.7619820.1914.30745.53851.96547.2861980.331591.64294.1311764.70886620327.818867OpenBenchmarking.org

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 3.0.1Test: Boat - Acceleration: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3691215SE +/- 0.031, N = 4SE +/- 0.046, N = 4SE +/- 0.042, N = 4SE +/- 0.035, N = 4SE +/- 0.022, N = 4SE +/- 0.007, N = 8SE +/- 0.006, N = 9SE +/- 0.007, N = 10SE +/- 0.007, N = 10SE +/- 0.003, N = 10SE +/- 0.006, N = 10SE +/- 0.009, N = 10SE +/- 0.027, N = 7SE +/- 0.004, N = 9SE +/- 0.012, N = 8SE +/- 0.007, N = 10SE +/- 0.013, N = 8SE +/- 0.006, N = 9SE +/- 0.009, N = 9SE +/- 0.014, N = 8SE +/- 0.010, N = 9SE +/- 0.014, N = 7SE +/- 0.012, N = 8SE +/- 0.008, N = 912.39212.40012.30712.38812.4063.1732.7571.7941.7761.7421.6801.7805.0702.0923.5171.4923.0172.5462.7093.7642.6074.3112.7411.491

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Half PrecisionGTX 1050 TiGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 1080GTX 1070GTX 1660 SUPERGTX 1070 TiTITAN RTX7K14K21K28K35KSE +/- 0.01, N = 7SE +/- 0.56, N = 12SE +/- 53.59, N = 15SE +/- 0.43, N = 13SE +/- 1.95, N = 14SE +/- 1.36, N = 14SE +/- 10.25, N = 14SE +/- 15.07, N = 15SE +/- 1.10, N = 14SE +/- 0.94, N = 13SE +/- 7.32, N = 13SE +/- 0.02, N = 9SE +/- 601.15, N = 15SE +/- 0.10, N = 11SE +/- 0.02, N = 11SE +/- 15.42, N = 13SE +/- 0.07, N = 11SE +/- 939.79, N = 1542.396948.3310568.4611787.3716507.0616838.7221764.4023628.7819501.6710057.4614646.4675.7731492.24149.35113.3210862.90121.4232084.791. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 DoubleGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX120240360480600SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 4SE +/- 0.14, N = 3SE +/- 0.27, N = 3SE +/- 0.01, N = 3SE +/- 0.46, N = 3SE +/- 0.69, N = 3SE +/- 0.71, N = 3SE +/- 0.91, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.23, N = 3SE +/- 1.30, N = 3SE +/- 0.11, N = 3SE +/- 0.60, N = 3SE +/- 0.38, N = 4SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 1.32, N = 369.8792.4184.60219.42109.20168.56184.34261.89267.79345.11376.32308.86157.98232.17150.68522.22197.23298.46223.60159.72172.49137.48242.70548.261. (CXX) g++ options: -O3 -rdynamic -lOpenCL

MandelGPU

MandelGPU is an OpenCL benchmark and this test runs with the OpenCL rendering float4 kernel with a maximum of 4096 iterations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPUGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX100M200M300M400M500MSE +/- 40239.48, N = 3SE +/- 68943.82, N = 4SE +/- 67025.37, N = 4SE +/- 479054.57, N = 6SE +/- 92918.17, N = 6SE +/- 481764.73, N = 7SE +/- 340263.98, N = 7SE +/- 1074135.38, N = 8SE +/- 2064512.42, N = 8SE +/- 1245853.73, N = 9SE +/- 2703218.20, N = 9SE +/- 1663935.40, N = 9SE +/- 421595.14, N = 7SE +/- 1119740.36, N = 8SE +/- 339240.54, N = 6SE +/- 2765042.11, N = 10SE +/- 353641.55, N = 6SE +/- 528438.95, N = 8SE +/- 327094.24, N = 7SE +/- 4075144.18, N = 15SE +/- 173522.04, N = 7SE +/- 113731.50, N = 5SE +/- 459096.61, N = 7SE +/- 2829613.77, N = 1061530230.379940246.775842143.4162891036.9132266243.9193795979.5210891296.2281931310.0284631717.4345359936.4374422420.6323061985.4186025762.6252924048.7130290433.8448915216.6148357386.1231826397.8184077179.7121139566.8200846066.4113624502.0194875210.8480798376.61. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Single PrecisionGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3K6K9K12K15KSE +/- 0.35, N = 11SE +/- 1.32, N = 15SE +/- 1.64, N = 13SE +/- 9.14, N = 14SE +/- 0.54, N = 12SE +/- 5.87, N = 13SE +/- 6.62, N = 13SE +/- 2.35, N = 13SE +/- 10.00, N = 13SE +/- 14.62, N = 14SE +/- 8.02, N = 14SE +/- 4.39, N = 14SE +/- 1.39, N = 13SE +/- 6.45, N = 13SE +/- 2.22, N = 13SE +/- 66.33, N = 15SE +/- 4.87, N = 13SE +/- 11.17, N = 14SE +/- 12.17, N = 15SE +/- 23.81, N = 15SE +/- 8.38, N = 13SE +/- 0.70, N = 11SE +/- 2.95, N = 12SE +/- 619.26, N = 152149.602779.322561.986463.103441.365259.295821.198159.158357.9610812.5211758.659630.834943.067222.284355.2816061.095844.908520.976476.924683.965462.594141.797018.9015032.471. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 FloatGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3K6K9K12K15KSE +/- 28.68, N = 15SE +/- 19.60, N = 13SE +/- 51.80, N = 15SE +/- 71.02, N = 15SE +/- 21.41, N = 13SE +/- 27.06, N = 12SE +/- 56.79, N = 15SE +/- 85.70, N = 15SE +/- 92.93, N = 15SE +/- 73.37, N = 15SE +/- 38.81, N = 13SE +/- 77.74, N = 15SE +/- 49.35, N = 15SE +/- 67.09, N = 15SE +/- 76.28, N = 15SE +/- 177.79, N = 15SE +/- 62.62, N = 15SE +/- 104.59, N = 15SE +/- 112.12, N = 15SE +/- 36.45, N = 13SE +/- 43.47, N = 15SE +/- 48.39, N = 15SE +/- 3.15, N = 13SE +/- 206.22, N = 151974.962604.972331.186121.762673.644543.644778.237034.777265.919161.1810264.388540.734123.665417.554110.7113536.255512.898218.626093.024472.774440.233874.986788.4014178.851. (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: IMDB LSTM - Device: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX2004006008001000SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.30, N = 4SE +/- 0.34, N = 4SE +/- 0.07, N = 4SE +/- 0.06, N = 4SE +/- 0.28, N = 5SE +/- 0.29, N = 5SE +/- 0.58, N = 5SE +/- 0.50, N = 5SE +/- 0.28, N = 5SE +/- 0.08, N = 4SE +/- 0.19, N = 4SE +/- 0.09, N = 4SE +/- 1.41, N = 5SE +/- 0.57, N = 4SE +/- 0.35, N = 4SE +/- 0.44, N = 4SE +/- 0.41, N = 4SE +/- 0.17, N = 4SE +/- 0.11, N = 4SE +/- 0.07, N = 4SE +/- 0.80, N = 5111.25143.15130.66294.10201.27289.42313.08438.26444.84544.54588.04500.26269.17390.07227.23753.75267.88398.82314.83228.46298.77203.08331.84775.69

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: ReadGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX120240360480600SE +/- 0.00, N = 3SE +/- 0.80, N = 2SE +/- 0.00, N = 3SE +/- 0.20, N = 6SE +/- 0.04, N = 4SE +/- 0.02, N = 5SE +/- 0.07, N = 6SE +/- 0.13, N = 8SE +/- 0.10, N = 8SE +/- 0.42, N = 8SE +/- 0.11, N = 8SE +/- 0.09, N = 8SE +/- 0.04, N = 5SE +/- 0.08, N = 7SE +/- 0.02, N = 5SE +/- 0.13, N = 8SE +/- 0.17, N = 6SE +/- 0.08, N = 6SE +/- 0.03, N = 6SE +/- 0.08, N = 5SE +/- 0.07, N = 7SE +/- 0.02, N = 4SE +/- 0.03, N = 6SE +/- 0.13, N = 990.381.595.2243.5108.7163.9251.2396.8396.9396.5437.6396.8167.0297.4154.4545.7266.0229.6206.2165.3296.6144.6206.2567.71. (CC) gcc options: -O2 -flto -lOpenCL

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX100200300400500SE +/- 0.12, N = 11SE +/- 0.07, N = 12SE +/- 0.02, N = 12SE +/- 0.07, N = 14SE +/- 0.01, N = 12SE +/- 0.14, N = 13SE +/- 0.12, N = 13SE +/- 0.01, N = 13SE +/- 0.11, N = 15SE +/- 0.56, N = 14SE +/- 0.08, N = 15SE +/- 0.00, N = 14SE +/- 0.15, N = 13SE +/- 0.00, N = 13SE +/- 0.23, N = 13SE +/- 0.56, N = 15SE +/- 0.12, N = 13SE +/- 0.15, N = 14SE +/- 0.06, N = 13SE +/- 0.18, N = 13SE +/- 0.22, N = 13SE +/- 0.16, N = 13SE +/- 0.08, N = 14SE +/- 1.13, N = 1469.7893.0184.78221.8891.77141.25155.78222.15226.65290.13315.03259.11132.75194.80150.48436.81197.44296.66224.82159.33144.30137.20241.99454.371. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 BandwidthGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX110220330440550SE +/- 0.02, N = 13SE +/- 0.01, N = 13SE +/- 0.07, N = 11SE +/- 0.09, N = 9SE +/- 0.06, N = 12SE +/- 0.06, N = 11SE +/- 0.12, N = 12SE +/- 0.06, N = 13SE +/- 0.05, N = 13SE +/- 0.07, N = 13SE +/- 0.14, N = 13SE +/- 0.10, N = 13SE +/- 0.02, N = 13SE +/- 0.15, N = 12SE +/- 0.04, N = 10SE +/- 0.46, N = 12SE +/- 0.13, N = 15SE +/- 0.11, N = 15SE +/- 0.04, N = 11SE +/- 0.01, N = 13SE +/- 0.16, N = 12SE +/- 0.02, N = 12SE +/- 0.01, N = 11SE +/- 0.05, N = 1390.1882.2392.34246.43105.31158.15234.91368.94369.30369.23405.92369.62156.86276.94147.66506.90264.74223.14197.20165.29276.35144.56198.18530.791. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Single PrecisionGTX 1050 TiGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 1080GTX 1070GTX 1660 SUPERGTX 1070 TiTITAN RTX3K6K9K12K15KSE +/- 0.33, N = 7SE +/- 0.12, N = 12SE +/- 0.26, N = 13SE +/- 2.28, N = 13SE +/- 0.94, N = 14SE +/- 0.92, N = 14SE +/- 56.09, N = 15SE +/- 134.69, N = 15SE +/- 5.98, N = 14SE +/- 0.29, N = 13SE +/- 3.59, N = 13SE +/- 1.19, N = 9SE +/- 556.93, N = 15SE +/- 3.04, N = 11SE +/- 30.05, N = 15SE +/- 0.25, N = 13SE +/- 2.31, N = 11SE +/- 595.40, N = 152379.013474.175313.335888.788264.668435.2310845.3611685.959754.994993.927339.394167.4114734.038182.726174.805440.746647.9415103.611. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 ScoreGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX7014021028035051.1658.9055.43154.4277.41119.11133.35206.08207.54224.39234.07221.1992.37166.1091.73310.81143.52148.47132.84110.81135.6696.20141.67324.55

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: WriteGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX110220330440550SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 6SE +/- 0.02, N = 4SE +/- 0.04, N = 5SE +/- 0.14, N = 6SE +/- 0.29, N = 8SE +/- 0.29, N = 8SE +/- 0.51, N = 8SE +/- 0.27, N = 8SE +/- 0.29, N = 8SE +/- 0.04, N = 5SE +/- 0.46, N = 7SE +/- 0.02, N = 5SE +/- 0.21, N = 8SE +/- 0.14, N = 6SE +/- 0.09, N = 6SE +/- 0.03, N = 6SE +/- 0.20, N = 5SE +/- 0.36, N = 7SE +/- 0.15, N = 4SE +/- 0.03, N = 6SE +/- 0.97, N = 984.977.791.2237.6104.4157.3223.9341.3328.5338.1352.9322.9145.8258.7148.1449.5245.9225.6199.5159.1240.7136.3198.2491.71. (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: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX5001000150020002500SE +/- 0.17, N = 6SE +/- 0.05, N = 6SE +/- 0.34, N = 6SE +/- 0.79, N = 8SE +/- 0.31, N = 7SE +/- 0.61, N = 7SE +/- 0.87, N = 8SE +/- 1.35, N = 8SE +/- 1.79, N = 8SE +/- 1.77, N = 8SE +/- 1.80, N = 9SE +/- 1.66, N = 8SE +/- 0.61, N = 7SE +/- 2.01, N = 8SE +/- 0.68, N = 7SE +/- 1.58, N = 8SE +/- 0.66, N = 8SE +/- 0.60, N = 8SE +/- 1.14, N = 8SE +/- 0.69, N = 7SE +/- 1.11, N = 8SE +/- 0.28, N = 7SE +/- 0.27, N = 8SE +/- 2.36, N = 8408.28434.07481.311106.29573.67858.901038.861585.761575.651726.601815.921712.75740.171285.58775.732406.161029.361154.131052.64810.501080.11716.821070.902544.67

LuxCoreRender OpenCL

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on OpenCL accelerators/GPUs. The alternative luxcorerender test profile is for CPU execution due to a difference in tests, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1.12282.24563.36844.49125.614SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 30.810.970.962.091.512.202.113.543.493.553.623.691.362.791.534.752.002.132.121.632.261.462.244.99

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1.34552.6914.03655.3826.7275SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, 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 = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 30.981.151.132.501.732.562.514.204.174.324.384.441.613.341.785.672.362.452.461.932.631.732.555.98

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: Inception V3 - Device: OpenCLGTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX80160240320400SE +/- 110.03, N = 12SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.22, N = 3SE +/- 0.31, N = 3SE +/- 0.29, N = 3SE +/- 0.29, N = 3SE +/- 0.40, N = 4SE +/- 0.38, N = 4SE +/- 0.32, N = 3SE +/- 0.13, N = 3SE +/- 0.31, N = 3SE +/- 0.19, N = 3SE +/- 0.25, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.23, N = 3SE +/- 0.62, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.19, N = 3213.4960.92148.8480.68120.84143.22204.35202.42243.51265.91221.49115.70172.73108.56353.54138.33190.14151.71109.50135.3197.83159.43355.85

LuxCoreRender OpenCL

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on OpenCL accelerators/GPUs. The alternative luxcorerender test profile is for CPU execution due to a difference in tests, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX0.50181.00361.50542.00722.509SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 4SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 30.390.440.460.980.670.991.071.331.301.871.931.900.811.170.652.230.920.990.920.781.090.670.982.23

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: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX6001200180024003000SE +/- 0.31, N = 5SE +/- 0.57, N = 6SE +/- 0.93, N = 6SE +/- 3.21, N = 7SE +/- 0.63, N = 7SE +/- 1.27, N = 7SE +/- 1.12, N = 7SE +/- 3.83, N = 8SE +/- 3.47, N = 8SE +/- 2.80, N = 7SE +/- 6.26, N = 8SE +/- 2.51, N = 8SE +/- 0.88, N = 6SE +/- 0.92, N = 7SE +/- 2.10, N = 6SE +/- 1.82, N = 7SE +/- 2.34, N = 5SE +/- 1.79, N = 7SE +/- 3.20, N = 7SE +/- 0.78, N = 6SE +/- 0.83, N = 7SE +/- 0.24, N = 6SE +/- 0.31, N = 7SE +/- 1.27, N = 8508.66609.16594.411369.20814.501199.661427.432012.371996.602322.392432.732287.031080.431719.71987.072751.851290.481665.721392.461053.491380.68910.911485.782856.83

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 select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX612182430SE +/- 0.028, N = 3SE +/- 0.055, N = 3SE +/- 0.027, N = 3SE +/- 0.038, N = 5SE +/- 0.004, N = 3SE +/- 0.015, N = 4SE +/- 0.016, N = 5SE +/- 0.008, N = 6SE +/- 0.005, N = 6SE +/- 0.008, N = 7SE +/- 0.006, N = 7SE +/- 0.011, N = 6SE +/- 0.021, N = 4SE +/- 0.004, N = 5SE +/- 0.012, N = 4SE +/- 0.009, N = 8SE +/- 0.092, N = 5SE +/- 0.018, N = 6SE +/- 0.019, N = 6SE +/- 0.058, N = 4SE +/- 0.009, N = 5SE +/- 0.026, N = 4SE +/- 0.006, N = 6SE +/- 0.008, N = 823.83418.40921.2679.15517.82311.89310.8477.9147.7676.1965.7186.83712.4878.83612.0024.41410.0716.4578.20511.77411.48213.1857.7914.2501. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

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 2.3.2GTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX60120180240300SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.31, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.42, N = 3SE +/- 0.32, N = 3SE +/- 0.34, N = 3SE +/- 0.92, N = 3SE +/- 0.82, N = 3SE +/- 1.06, N = 3SE +/- 0.21, N = 3SE +/- 0.54, N = 3SE +/- 0.16, N = 3SE +/- 1.17, N = 3SE +/- 0.33, N = 3SE +/- 0.41, N = 3SE +/- 0.46, N = 3SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.85, N = 352.6962.3061.59123.1975.81125.62138.56200.77199.87235.53248.01221.7382.05178.47102.27290.72115.78151.57139.50102.37135.6190.85137.14292.16

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: DenseNet 201 - Device: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX50100150200250SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.25, N = 341.9745.5449.71105.3959.3787.2598.99146.90147.87151.99159.79149.6973.17125.2379.13212.1199.84112.28108.4682.21100.5173.89108.23227.30

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3691215SE +/- 0.002, N = 10SE +/- 0.002, N = 10SE +/- 0.005, N = 10SE +/- 0.007, N = 10SE +/- 0.003, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.002, N = 10SE +/- 0.003, N = 10SE +/- 0.005, N = 10SE +/- 0.006, N = 10SE +/- 0.002, N = 10SE +/- 0.004, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 9SE +/- 0.001, N = 10SE +/- 0.001, N = 108.3498.9687.7753.9176.8084.5413.0682.0832.0972.0751.9002.0714.4452.6595.0001.6773.6223.3874.0774.9042.6425.4003.8141.6661. (CXX) g++ options: -rdynamic

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: GPUGTX 950GTX 960GTX 1650GTX 1660RTX 2070RTX 2080RTX 2060GTX 1080GTX 1070GTX 980GTX 970TITAN RTX1122334455SE +/- 0.02, N = 13SE +/- 0.01, N = 13SE +/- 0.05, N = 13SE +/- 0.06, N = 13SE +/- 0.26, N = 13SE +/- 0.11, N = 15SE +/- 0.23, N = 14SE +/- 0.04, N = 13SE +/- 0.13, N = 13SE +/- 0.04, N = 13SE +/- 0.05, N = 13SE +/- 0.02, N = 139.549.5312.8018.6035.8038.3028.3024.6021.5017.3015.4048.10

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX11002200330044005500SE +/- 1.10, N = 4SE +/- 0.80, N = 4SE +/- 1.56, N = 4SE +/- 10.31, N = 4SE +/- 1.92, N = 4SE +/- 1.22, N = 4SE +/- 3.15, N = 4SE +/- 4.79, N = 4SE +/- 11.45, N = 4SE +/- 10.88, N = 4SE +/- 9.77, N = 4SE +/- 1.43, N = 4SE +/- 1.69, N = 4SE +/- 5.03, N = 4SE +/- 2.50, N = 4SE +/- 13.92, N = 4SE +/- 8.83, N = 4SE +/- 10.96, N = 4SE +/- 4.04, N = 4SE +/- 10.36, N = 4SE +/- 3.01, N = 4SE +/- 1.45, N = 4SE +/- 1.17, N = 4SE +/- 17.72, N = 41019.481303.041639.083699.511128.391712.371877.322622.042680.693358.203673.833047.421607.772321.092856.384836.622438.975091.862905.882826.161765.012457.734304.765040.581. (CXX) g++ options: -rdynamic

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Double PrecisionGTX 1050 TiGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 1080GTX 1070GTX 1660 SUPERGTX 1070 TiTITAN RTX90180270360450SE +/- 0.03, N = 7SE +/- 0.06, N = 12SE +/- 0.10, N = 13SE +/- 0.08, N = 13SE +/- 0.23, N = 14SE +/- 0.27, N = 14SE +/- 0.22, N = 15SE +/- 0.96, N = 15SE +/- 0.15, N = 15SE +/- 0.13, N = 13SE +/- 0.01, N = 13SE +/- 0.00, N = 9SE +/- 10.76, N = 15SE +/- 0.03, N = 11SE +/- 0.10, N = 11SE +/- 0.66, N = 15SE +/- 0.35, N = 11SE +/- 15.67, N = 1584.5592.37141.36157.14221.80226.21291.56315.61260.97133.88196.30151.63409.46296.09225.05144.14240.92413.661. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 3.0.1Test: Server Room - Acceleration: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX0.83231.66462.49693.32924.1615SE +/- 0.006, N = 7SE +/- 0.009, N = 8SE +/- 0.008, N = 7SE +/- 0.008, N = 7SE +/- 0.003, N = 7SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.002, N = 11SE +/- 0.006, N = 8SE +/- 0.001, N = 11SE +/- 0.002, N = 10SE +/- 0.002, N = 11SE +/- 0.002, N = 10SE +/- 0.003, N = 10SE +/- 0.004, N = 10SE +/- 0.004, N = 8SE +/- 0.002, N = 10SE +/- 0.017, N = 8SE +/- 0.001, N = 10SE +/- 0.002, N = 113.6843.6723.6773.6993.6931.1951.1660.7770.7720.8180.8090.8212.9030.8441.3010.7591.3981.0951.1122.7301.0822.8621.1660.767

LuxCoreRender OpenCL

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on OpenCL accelerators/GPUs. The alternative luxcorerender test profile is for CPU execution due to a difference in tests, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 4SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 12SE +/- 0.13, N = 12SE +/- 0.18, N = 43.222.843.986.473.935.585.0111.3210.989.249.1410.212.737.975.4112.336.594.236.625.115.614.815.3812.73

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsGTX 950GTX 960GTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970TITAN RTX2004006008001000414.87288.09346.43290.51416.11502.09689.61642.98728.37831.53754.61399.75553.15280.521013.20327.28406.50348.12249.04497.00223.07962.08

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: CopyGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX70140210280350SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.11, N = 6SE +/- 0.00, N = 4SE +/- 0.17, N = 5SE +/- 0.06, N = 6SE +/- 0.06, N = 8SE +/- 0.09, N = 8SE +/- 0.06, N = 8SE +/- 0.05, N = 8SE +/- 0.07, N = 8SE +/- 0.00, N = 5SE +/- 0.06, N = 7SE +/- 0.02, N = 5SE +/- 0.10, N = 8SE +/- 0.07, N = 6SE +/- 0.02, N = 6SE +/- 0.02, N = 6SE +/- 0.02, N = 5SE +/- 0.05, N = 7SE +/- 0.02, N = 4SE +/- 0.03, N = 6SE +/- 0.08, N = 978.572.887.9214.499.2145.9211.1288.0284.4290.0301.7292.1143.8239.4138.5324.0217.8207.4183.3145.0240.2125.9184.1322.71. (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: VGG19 - Device: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX200M400M600M800M1000MSE +/- 0.01, N = 3SE +/- 1.11, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.22, N = 3SE +/- 0.29, N = 3SE +/- 0.39, N = 3SE +/- 0.62, N = 3SE +/- 0.36, N = 3SE +/- 0.24, N = 3SE +/- 0.13, N = 3SE +/- 0.29, N = 3SE +/- 0.16, N = 3SE +/- 0.60, N = 3SE +/- 1.20, N = 3SE +/- 0.31, N = 3SE +/- 0.13, N = 3SE +/- 0.61, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.42, N = 41000000000.001000000000.0029.4275.7342.3267.7473.38101.79104.21130.23145.57123.0361.8588.9556.62187.9271.18103.8379.1256.6068.8151.1492.87196.63

GROMACS

The CUDA version of the Gromacs molecular dynamics package. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX246810SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.000, N = 3SE +/- 0.005, N = 3SE +/- 0.005, N = 3SE +/- 0.010, N = 3SE +/- 0.006, N = 3SE +/- 0.016, N = 3SE +/- 0.013, N = 3SE +/- 0.015, N = 3SE +/- 0.041, N = 3SE +/- 0.008, N = 3SE +/- 0.004, N = 3SE +/- 0.008, N = 3SE +/- 0.003, N = 3SE +/- 0.020, N = 2SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.007, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.005, N = 31.8022.1542.0844.0813.2534.4124.7895.7895.8656.5366.5726.2494.1225.4163.1817.1363.8574.6344.0523.2714.6292.9954.2597.1171. (CXX) g++ options: -O3 -lpthread -ldl -lrt -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: No - Mode: Training - Network: Mobilenet - Device: OpenCLGTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX4080120160200SE +/- 0.02, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.17, N = 3SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 357.1393.0365.5997.94108.06154.81153.03154.35158.82154.7477.10125.3383.52187.7389.2899.82103.7980.47111.3973.2599.64198.37

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 2.14ATPase Simulation - 327,506 AtomsGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX0.13390.26780.40170.53560.6695SE +/- 0.00145, N = 3SE +/- 0.00332, N = 3SE +/- 0.00392, N = 3SE +/- 0.00182, N = 4SE +/- 0.00088, N = 3SE +/- 0.00142, N = 4SE +/- 0.00217, N = 4SE +/- 0.00060, N = 4SE +/- 0.00191, N = 4SE +/- 0.00054, N = 4SE +/- 0.00097, N = 4SE +/- 0.00025, N = 4SE +/- 0.00061, N = 4SE +/- 0.00144, N = 4SE +/- 0.00077, N = 3SE +/- 0.00046, N = 4SE +/- 0.00163, N = 4SE +/- 0.00174, N = 4SE +/- 0.00276, N = 4SE +/- 0.00291, N = 3SE +/- 0.00026, N = 4SE +/- 0.00170, N = 3SE +/- 0.00101, N = 4SE +/- 0.00134, N = 40.595130.507850.532330.271030.345030.242900.228000.200570.203620.192650.193290.196250.262110.206350.309570.190820.291380.224260.240220.335660.231770.360710.223000.19195

Mixbench

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

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX4K8K12K16K20KSE +/- 0.55, N = 15SE +/- 0.81, N = 12SE +/- 2.02, N = 12SE +/- 1.23, N = 14SE +/- 0.52, N = 12SE +/- 0.61, N = 13SE +/- 50.53, N = 15SE +/- 2.40, N = 13SE +/- 1.82, N = 13SE +/- 1.20, N = 14SE +/- 11.48, N = 14SE +/- 1.47, N = 14SE +/- 0.38, N = 13SE +/- 14.13, N = 13SE +/- 2.70, N = 14SE +/- 11.06, N = 14SE +/- 1.27, N = 13SE +/- 6.51, N = 15SE +/- 0.96, N = 13SE +/- 5.50, N = 15SE +/- 7.30, N = 13SE +/- 0.40, N = 13SE +/- 0.83, N = 14SE +/- 63.55, N = 15625.55828.80771.531911.013466.725303.515803.638218.028362.8610930.5611752.119696.384975.187275.331354.1416323.941711.032655.582019.081389.905432.401215.752157.3116979.991. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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: OpenCLGTX 950GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX200M400M600M800M1000MSE +/- 0.01, N = 3SE +/- 0.47, N = 3SE +/- 0.16, N = 3SE +/- 0.30, N = 3SE +/- 0.25, N = 3SE +/- 0.38, N = 3SE +/- 0.51, N = 3SE +/- 0.81, N = 3SE +/- 0.37, N = 3SE +/- 0.33, N = 3SE +/- 0.16, N = 3SE +/- 0.40, N = 3SE +/- 0.22, N = 3SE +/- 0.64, N = 3SE +/- 0.87, N = 3SE +/- 0.42, N = 3SE +/- 0.18, N = 3SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.54, N = 41000000000.0037.1397.4053.3585.4692.41128.91132.03164.78183.53155.4277.98112.2971.78237.2990.74131.3499.8872.2186.6164.53116.89248.79

FinanceBench

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

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Monte-Carlo OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX30060090012001500SE +/- 0.024977, N = 9SE +/- 0.042376, N = 9SE +/- 0.754451, N = 7SE +/- 0.570026, N = 8SE +/- 2.023658, N = 7SE +/- 0.790748, N = 8SE +/- 0.519549, N = 8SE +/- 1.739449, N = 8SE +/- 0.935750, N = 8SE +/- 0.614932, N = 8SE +/- 0.455030, N = 8SE +/- 0.343146, N = 8SE +/- 0.533801, N = 7SE +/- 1.146962, N = 8SE +/- 0.445319, N = 7SE +/- 0.595119, N = 8SE +/- 0.287953, N = 8SE +/- 0.481963, N = 7SE +/- 0.409086, N = 7SE +/- 0.367985, N = 8SE +/- 0.488651, N = 8SE +/- 1.034930, N = 7SE +/- 0.217923, N = 8SE +/- 1.197236, N = 84.9190004.9110001214.994001624.175743895.430429606.699883654.815865367.022003377.722500406.042122413.845127400.3836251087.168126528.367744894.084865319.914127660.548249921.684152697.546291749.288002594.438004841.188581754.284012277.2321211. (CXX) g++ options: -O3 -lOpenCL

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 INTGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3K6K9K12K15KSE +/- 4.46, N = 15SE +/- 3.50, N = 9SE +/- 10.24, N = 15SE +/- 10.01, N = 9SE +/- 1.93, N = 13SE +/- 10.20, N = 12SE +/- 49.36, N = 15SE +/- 81.72, N = 15SE +/- 83.63, N = 15SE +/- 51.79, N = 12SE +/- 58.52, N = 13SE +/- 66.40, N = 12SE +/- 41.07, N = 15SE +/- 65.66, N = 15SE +/- 10.83, N = 15SE +/- 23.37, N = 12SE +/- 8.22, N = 9SE +/- 7.00, N = 10SE +/- 6.03, N = 12SE +/- 1.81, N = 8SE +/- 6.44, N = 12SE +/- 8.78, N = 10SE +/- 0.30, N = 10SE +/- 169.21, N = 15593.76789.99719.461757.812641.384338.674734.366930.217133.779141.2310266.728484.414128.395356.841275.1213629.371612.522430.551695.791306.514280.551145.142076.4513783.931. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Mixbench

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

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: IntegerGTX 1050 TiGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 1080GTX 1070GTX 1660 SUPERGTX 1070 TiTITAN RTX3K6K9K12K15KSE +/- 0.18, N = 7SE +/- 0.11, N = 12SE +/- 0.22, N = 13SE +/- 0.35, N = 13SE +/- 49.03, N = 15SE +/- 0.55, N = 14SE +/- 7.76, N = 14SE +/- 1.56, N = 14SE +/- 0.98, N = 14SE +/- 0.38, N = 13SE +/- 4.65, N = 13SE +/- 2.01, N = 9SE +/- 264.51, N = 15SE +/- 1.56, N = 11SE +/- 3.28, N = 11SE +/- 4.94, N = 15SE +/- 0.87, N = 11SE +/- 458.60, N = 15667.903108.844753.115271.347348.917540.289732.4810562.998722.284492.326539.811187.7214103.792326.091764.634866.611887.6114426.111. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 0.26Backend: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX5K10K15K20K25KSE +/- 16.29, N = 3SE +/- 10.44, N = 3SE +/- 2.73, N = 3SE +/- 27.94, N = 3SE +/- 6.17, N = 3SE +/- 3.38, N = 3SE +/- 56.77, N = 3SE +/- 61.94, N = 3SE +/- 70.73, N = 3SE +/- 77.45, N = 3SE +/- 79.08, N = 3SE +/- 28.58, N = 3SE +/- 19.16, N = 3SE +/- 64.75, N = 3SE +/- 28.32, N = 3SE +/- 55.16, N = 3SE +/- 28.99, N = 3SE +/- 57.21, N = 3SE +/- 85.75, N = 3SE +/- 43.89, N = 3SE +/- 54.30, N = 3SE +/- 36.50, N = 3SE +/- 20.50, N = 31982243025659066310158957733123351231115442175011473051511029059332183982831266297506265736651639947224241. (CXX) g++ options: -flto -pthread

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 3.0.1Test: Server Rack - Acceleration: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX0.04320.08640.12960.17280.216SE +/- 0.004, N = 15SE +/- 0.004, N = 15SE +/- 0.004, N = 15SE +/- 0.003, N = 15SE +/- 0.000, N = 13SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 15SE +/- 0.000, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 13SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.000, N = 13SE +/- 0.001, N = 15SE +/- 0.000, N = 13SE +/- 0.000, N = 130.1910.1910.1920.1890.1850.1130.1060.1010.1020.0990.0990.0980.1210.1040.1240.1000.1640.1110.1170.1620.1040.1630.1170.103

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Masskrug - Acceleration: OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1.07012.14023.21034.28045.3505SE +/- 0.011, N = 7SE +/- 0.023, N = 7SE +/- 0.014, N = 7SE +/- 0.019, N = 7SE +/- 0.018, N = 7SE +/- 0.012, N = 8SE +/- 0.012, N = 8SE +/- 0.015, N = 9SE +/- 0.009, N = 9SE +/- 0.019, N = 8SE +/- 0.014, N = 9SE +/- 0.009, N = 8SE +/- 0.023, N = 7SE +/- 0.014, N = 8SE +/- 0.009, N = 8SE +/- 0.009, N = 9SE +/- 0.012, N = 8SE +/- 0.011, N = 8SE +/- 0.008, N = 8SE +/- 0.023, N = 7SE +/- 0.011, N = 8SE +/- 0.022, N = 7SE +/- 0.016, N = 8SE +/- 0.011, N = 84.3074.2814.2944.3244.3293.0973.0912.7632.7442.7942.7642.8044.7562.8353.1692.7553.2272.9742.9744.5433.0304.6102.9982.792

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 select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL MyocyteGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1224364860SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.22, N = 3SE +/- 0.23, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 345.5445.5139.0553.8333.7234.7634.4134.5635.5135.0934.2134.7833.6934.9038.1135.2455.1738.0038.0050.5534.1348.9242.0835.771. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: NVIDIA CUDA GPU MyocyteGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1428425670SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 3SE +/- 0.03, N = 351.9752.3343.2863.6039.9040.0740.0440.2240.5040.4940.0140.0939.9440.0042.7040.3564.7643.2042.9659.4739.9156.5047.7240.371. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

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 FactorizationGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX20406080100SE +/- 0.19, N = 10SE +/- 0.19, N = 10SE +/- 0.14, N = 10SE +/- 0.23, N = 11SE +/- 0.21, N = 11SE +/- 0.25, N = 11SE +/- 0.37, N = 11SE +/- 0.24, N = 11SE +/- 0.47, N = 11SE +/- 0.38, N = 11SE +/- 0.41, N = 11SE +/- 0.44, N = 11SE +/- 0.27, N = 11SE +/- 0.29, N = 11SE +/- 0.32, N = 11SE +/- 0.39, N = 11SE +/- 0.25, N = 11SE +/- 0.21, N = 11SE +/- 0.23, N = 11SE +/- 0.29, N = 11SE +/- 0.37, N = 11SE +/- 0.20, N = 10SE +/- 0.38, N = 11SE +/- 0.57, N = 1147.2952.9251.3465.9562.9667.8270.0372.5072.5774.7376.1074.4567.9373.3161.6575.7964.5470.6966.2161.9468.1560.2069.1876.641. (CXX) g++ options: -rdynamic -lOpenCL

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: NVIDIA CUDA - Kernel: Euclidean ClusterGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX30060090012001500SE +/- 13.18, N = 3SE +/- 1.80, N = 3SE +/- 6.85, N = 3SE +/- 0.86, N = 3SE +/- 0.94, N = 4SE +/- 2.01, N = 4SE +/- 1.42, N = 4SE +/- 1.47, N = 4SE +/- 1.75, N = 4SE +/- 2.02, N = 4SE +/- 2.29, N = 4SE +/- 2.13, N = 4SE +/- 2.43, N = 4SE +/- 2.06, N = 4SE +/- 8.38, N = 3SE +/- 0.89, N = 4SE +/- 15.93, N = 3SE +/- 2.36, N = 3SE +/- 4.73, N = 3SE +/- 1.10, N = 3SE +/- 0.96, N = 4SE +/- 2.99, N = 3SE +/- 7.67, N = 3SE +/- 2.28, N = 4980.33982.721219.99956.541415.671452.411465.391475.241462.961441.291448.461444.271456.661468.391253.431436.62976.751218.561231.441019.041466.24979.331204.771434.171. (CXX) g++ options: -O3 -m64 -std=c++11 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenCL - Kernel: Euclidean ClusterGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX5001000150020002500SE +/- 1.01, N = 4SE +/- 2.79, N = 4SE +/- 6.06, N = 4SE +/- 3.18, N = 4SE +/- 8.11, N = 4SE +/- 9.93, N = 5SE +/- 6.33, N = 5SE +/- 4.74, N = 5SE +/- 9.09, N = 5SE +/- 4.22, N = 5SE +/- 6.61, N = 5SE +/- 4.72, N = 5SE +/- 1.34, N = 5SE +/- 6.16, N = 5SE +/- 3.33, N = 5SE +/- 5.93, N = 5SE +/- 5.50, N = 4SE +/- 5.86, N = 5SE +/- 7.62, N = 5SE +/- 2.91, N = 5SE +/- 3.67, N = 5SE +/- 1.83, N = 4SE +/- 0.67, N = 5SE +/- 9.59, N = 51591.641778.011759.041953.251983.672174.722223.072326.882309.012245.822326.552264.372143.592263.122076.482268.231908.812345.382243.101976.412175.961928.882223.782279.141. (CXX) g++ options: -O3 -m64 -std=c++11 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenCL - Kernel: NDT MappingGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX80160240320400SE +/- 1.45, N = 3SE +/- 2.15, N = 3SE +/- 1.02, N = 3SE +/- 1.91, N = 3SE +/- 1.36, N = 3SE +/- 0.15, N = 3SE +/- 2.24, N = 3SE +/- 1.17, N = 3SE +/- 2.26, N = 3SE +/- 1.78, N = 3SE +/- 0.33, N = 3SE +/- 0.37, N = 3SE +/- 0.20, N = 3SE +/- 0.47, N = 3SE +/- 0.67, N = 3SE +/- 0.87, N = 3SE +/- 2.08, N = 3SE +/- 1.38, N = 3SE +/- 2.24, N = 3SE +/- 0.61, N = 3SE +/- 2.54, N = 3SE +/- 0.82, N = 3SE +/- 2.01, N = 3SE +/- 1.41, N = 3294.13308.28305.07339.75287.07314.71321.77338.08339.12341.84344.19338.65313.80332.00333.47350.37339.21348.29345.44333.52320.97324.70349.12343.611. (CXX) g++ options: -O3 -m64 -std=c++11 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenCL - Kernel: Points2ImageGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX3K6K9K12K15KSE +/- 66.71, N = 3SE +/- 85.88, N = 3SE +/- 128.29, N = 3SE +/- 57.16, N = 3SE +/- 175.10, N = 3SE +/- 28.64, N = 3SE +/- 35.36, N = 3SE +/- 146.98, N = 3SE +/- 35.39, N = 3SE +/- 56.40, N = 3SE +/- 64.15, N = 3SE +/- 194.60, N = 3SE +/- 155.29, N = 3SE +/- 87.49, N = 3SE +/- 136.54, N = 3SE +/- 70.09, N = 3SE +/- 62.20, N = 3SE +/- 90.00, N = 3SE +/- 180.15, N = 3SE +/- 75.04, N = 3SE +/- 16.13, N = 3SE +/- 123.30, N = 3SE +/- 112.38, N = 3SE +/- 36.56, N = 311764.7111773.3511780.6811498.2212203.3013590.0313606.9613476.3413499.1713228.1412974.4713076.8612256.6613398.0611766.2913045.0311829.8613141.7313045.8611735.8413933.2711485.5013281.7712538.251. (CXX) g++ options: -O3 -m64 -std=c++11 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: NVIDIA CUDA - Kernel: NDT MappingGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060RTX 2080 TiGTX 1660 SUPERTITAN RTX130260390520650SE +/- 0.81, N = 3SE +/- 0.21, N = 3SE +/- 3.12, N = 3SE +/- 0.39, N = 3SE +/- 2.81, N = 3SE +/- 1.76, N = 3SE +/- 1.09, N = 3SE +/- 0.12, N = 3SE +/- 1.45, N = 3SE +/- 0.63, N = 3SE +/- 2.73, N = 3SE +/- 4.39, N = 3SE +/- 5.64, N = 3517.14552.68557.20575.45579.36599.64599.70589.63534.85570.77606.75563.13590.631. (CXX) g++ options: -O3 -m64 -std=c++11 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: NVIDIA CUDA - Kernel: Points2ImageGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060RTX 2080 TiGTX 1660 SUPERTITAN RTX7K14K21K28K35KSE +/- 329.31, N = 7SE +/- 269.28, N = 15SE +/- 392.98, N = 5SE +/- 226.31, N = 3SE +/- 471.75, N = 3SE +/- 430.26, N = 4SE +/- 273.74, N = 15SE +/- 401.47, N = 5SE +/- 220.88, N = 3SE +/- 339.25, N = 14SE +/- 496.68, N = 3SE +/- 284.42, N = 3SE +/- 203.08, N = 329148.7429594.8829450.4630663.6429917.3029707.4430214.7630409.0629380.3130937.2828816.8229306.1329401.511. (CXX) g++ options: -O3 -m64 -std=c++11 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1632486480Min: 29 / Avg: 62.51 / Max: 82Min: 27 / Avg: 61.47 / Max: 74Min: 28 / Avg: 52.14 / Max: 68Min: 32 / Avg: 70.56 / Max: 85Min: 27 / Avg: 49.62 / Max: 67Min: 30 / Avg: 51.27 / Max: 76Min: 29 / Avg: 48.98 / Max: 66Min: 33 / Avg: 53.72 / Max: 74Min: 29 / Avg: 54.87 / Max: 76Min: 28 / Avg: 62.06 / Max: 83Min: 28 / Avg: 49.61 / Max: 73Min: 29 / Avg: 50.76 / Max: 71Min: 30 / Avg: 50.85 / Max: 66Min: 29 / Avg: 51.56 / Max: 73Min: 32 / Avg: 52.77 / Max: 69Min: 29 / Avg: 56.11 / Max: 78Min: 30 / Avg: 70.66 / Max: 85Min: 28 / Avg: 61.17 / Max: 83Min: 29 / Avg: 59.81 / Max: 78Min: 31 / Avg: 65.22 / Max: 80Min: 33 / Avg: 55.48 / Max: 68Min: 33 / Avg: 52.58 / Max: 74Min: 32 / Avg: 45.46 / Max: 58Min: 35 / Avg: 55.61 / Max: 78

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringGTX 950GTX 960GTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970TITAN RTX60120180240300Min: 8.46 / Avg: 57.65 / Max: 109.21Min: 8.45 / Avg: 64.56 / Max: 143.77Min: 16.01 / Avg: 139.4 / Max: 257.78Min: 5.55 / Avg: 37.62 / Max: 70.94Min: 6.72 / Avg: 45.57 / Max: 122.32Min: 7.22 / Avg: 59.54 / Max: 132.74Min: 9.27 / Avg: 88.74 / Max: 180.97Min: 7.57 / Avg: 85.38 / Max: 180.92Min: 13.71 / Avg: 103.45 / Max: 219.93Min: 8.85 / Avg: 91.93 / Max: 248.16Min: 14.36 / Avg: 96.17 / Max: 217.58Min: 6.47 / Avg: 47.87 / Max: 99.24Min: 9.59 / Avg: 74.07 / Max: 165.3Min: 6.24 / Avg: 64.43 / Max: 128.04Min: 5.74 / Avg: 124.11 / Max: 273.84Min: 15.33 / Avg: 131.28 / Max: 252.57Min: 6.47 / Avg: 92.36 / Max: 196.24Min: 6.84 / Avg: 82.21 / Max: 159.92Min: 15.1 / Avg: 102.77 / Max: 192.38Min: 10.68 / Avg: 67.65 / Max: 128.36Min: 15.21 / Avg: 95.21 / Max: 176.52Min: 24.02 / Avg: 126.58 / Max: 312.98

FinanceBench

OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-06-06GPU Temperature MonitorGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX1326395265Min: 50 / Avg: 52.52 / Max: 57Min: 52 / Avg: 53.6 / Max: 55Min: 38 / Avg: 40.3 / Max: 43Min: 58 / Avg: 60.14 / Max: 63Min: 34 / Avg: 35.36 / Max: 37Min: 36 / Avg: 37.72 / Max: 40Min: 36 / Avg: 37.83 / Max: 39Min: 38 / Avg: 39.66 / Max: 42Min: 38 / Avg: 39.74 / Max: 42Min: 45 / Avg: 46.84 / Max: 49Min: 37 / Avg: 38.31 / Max: 40Min: 37 / Avg: 38.3 / Max: 40Min: 39 / Avg: 39.86 / Max: 41Min: 37 / Avg: 38.7 / Max: 41Min: 40 / Avg: 42.76 / Max: 46Min: 42 / Avg: 43.96 / Max: 46Min: 59 / Avg: 61.76 / Max: 66Min: 46 / Avg: 47.39 / Max: 50Min: 43 / Avg: 48.67 / Max: 50Min: 50 / Avg: 51.97 / Max: 54Min: 45 / Avg: 46.81 / Max: 49Min: 39 / Avg: 39.35 / Max: 40Min: 39 / Avg: 39.94 / Max: 41Min: 41 / Avg: 42.67 / Max: 44

OpenBenchmarking.orgWatts, Fewer Is BetterFinanceBench 2016-06-06GPU Power Consumption MonitorGTX 950GTX 960GTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970TITAN RTX1632486480Min: 10.57 / Avg: 23.48 / Max: 38.35Min: 26.23 / Avg: 31.11 / Max: 39.27Min: 73.14 / Avg: 77.07 / Max: 78.94Min: 5.79 / Avg: 10.62 / Max: 17.61Min: 6.77 / Avg: 12.6 / Max: 20.59Min: 7.58 / Avg: 14.8 / Max: 25.66Min: 9.85 / Avg: 24.96 / Max: 41.32Min: 8.3 / Avg: 20.71 / Max: 37.14Min: 15.36 / Avg: 31.49 / Max: 51.96Min: 9 / Avg: 29.32 / Max: 48.16Min: 14.56 / Avg: 28.59 / Max: 46.88Min: 6.65 / Avg: 13.23 / Max: 20.93Min: 9.59 / Avg: 21.32 / Max: 35.76Min: 24.02 / Avg: 28.54 / Max: 34.93Min: 6.58 / Avg: 29.78 / Max: 53.12Min: 69.22 / Avg: 77.38 / Max: 86.25Min: 34.48 / Avg: 37.96 / Max: 41.35Min: 30.74 / Avg: 38.09 / Max: 44.91Min: 44.36 / Avg: 47.75 / Max: 49.96Min: 11.38 / Avg: 21.68 / Max: 35Min: 43.88 / Avg: 46.25 / Max: 48.4Min: 24.7 / Avg: 38.84 / Max: 59.62

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLGTX 950GTX 960GTX 1050 TiGTX TITAN XGTX 1650GTX 1660GTX 1660 TiRTX 2060 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERRTX 2060GTX 1060RTX 2080 TiGTX 980 TiGTX 1080GTX 1070GTX 980GTX 1660 SUPERGTX 970GTX 1070 TiTITAN RTX714212835SE +/- 0.453232, N = 15SE +/- 0.303704, N = 15SE +/- 0.748737, N = 15SE +/- 0.004731, N = 14SE +/- 0.002491, N = 14SE +/- 0.001244, N = 14SE +/- 0.001932, N = 14SE +/- 0.015324, N = 15SE +/- 0.001589, N = 14SE +/- 0.001547, N = 14SE +/- 0.003249, N = 15SE +/- 0.014259, N = 15SE +/- 0.001228, N = 14SE +/- 0.000959, N = 14SE +/- 0.317433, N = 15SE +/- 0.001717, N = 14SE +/- 0.156028, N = 15SE +/- 0.003290, N = 15SE +/- 0.209293, N = 15SE +/- 0.022523, N = 15SE +/- 0.001295, N = 14SE +/- 0.003094, N = 15SE +/- 0.003359, N = 15SE +/- 0.001983, N = 1527.81886719.51320024.3622009.32300024.14528515.25900014.38500010.49800010.2540007.6570006.8110008.26300016.57778512.55500013.3400006.0200009.5960006.9810008.96800012.10100015.27100014.1960007.2980005.7010001. (CXX) g++ options: -O3 -lOpenCL