GPU Compute

AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) and NVIDIA GeForce GTX 1060 6GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2009080-FI-GPUCOMPUT34
Jump To Table - Results

View

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

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 2 Tests
HPC - High Performance Computing 5 Tests
Machine Learning 2 Tests
Multi-Core 3 Tests
NVIDIA GPU Compute 14 Tests
OpenCL 6 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
TITAN RTX
September 06 2020
  1 Hour, 24 Minutes
GTX 1070 Ti
September 06 2020
  1 Hour, 31 Minutes
GTX 970
September 06 2020
  2 Hours, 9 Minutes
GTX 1660 SUPER
September 07 2020
  1 Hour, 30 Minutes
GTX 980
September 07 2020
  1 Hour, 34 Minutes
GTX 1070
September 07 2020
  1 Hour, 26 Minutes
GTX 1080
September 07 2020
  1 Hour, 23 Minutes
GTX 980 Ti
September 07 2020
  1 Hour, 29 Minutes
RTX 2080 Ti
September 07 2020
  1 Hour, 24 Minutes
GTX 1060
September 08 2020
  1 Hour, 32 Minutes
Invert Hiding All Results Option
  1 Hour, 32 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):


GPU ComputeProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060AMD 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)NVIDIA TU102 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 11.0ext43840x2160Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz)NVIDIA GP104 HD AudioeVGA NVIDIA GeForce GTX 970 4GB (1163/3505MHz)NVIDIA GM204 HD AudioeVGA NVIDIA GeForce GTX 1660 SUPER 6GB (1530/7000MHz)NVIDIA TU116 HD AudioNVIDIA GeForce GTX 980 4GB (1126/3505MHz)NVIDIA GM204 HD AudioNVIDIA GeForce GTX 1070 8GB (1506/4006MHz)NVIDIA GP104 HD AudioNVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA GeForce GTX 980 Ti 6GB (999/3505MHz)NVIDIA GM200 HD AudioNVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TU102 HD AudioNVIDIA GeForce GTX 1060 6GB (1506/4006MHz)NVIDIA GP106 HD Audio5.4.0-47-generic (x86_64)OpenBenchmarking.orgCompiler Details- --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 Processor Details- Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013OpenCL Details- 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: 1280Python Details- Python 3.8.2Security Details- 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 1060Result OverviewPhoronix Test Suite100%213%326%439%552%MixbenchclpeakLeelaChessZeroMandelGPUOctaneBenchPlaidMLcl-memFAHBenchLuxCoreRender OpenCLFinanceBenchArrayFireGROMACSDarktableNAMD CUDARodiniaViennaCLDarmstadt Automotive Parallel Heterogeneous Suite

GPU Computearrayfire: BLAS OpenCLarrayfire: Conjugate Gradient OpenCLcl-mem: Readcl-mem: Writecl-mem: Copyclpeak: Global Memory Bandwidthclpeak: Single-Precision Floatclpeak: Double-Precision Doubleclpeak: Integer Compute INTdarktable: Boat - OpenCLdarktable: Masskrug - OpenCLdarktable: Server Room - OpenCLdarktable: Server Rack - OpenCLdaphne: OpenCL - Euclidean Clusterdaphne: OpenCL - NDT Mappingdaphne: OpenCL - Points2Imagedaphne: NVIDIA CUDA - Euclidean Clusterdaphne: NVIDIA CUDA - NDT Mappingdaphne: NVIDIA CUDA - Points2Imagefahbench: financebench: Black-Scholes OpenCLfinancebench: Monte-Carlo OpenCLgromacs-gpu: Water Benchmarklczero: OpenCLluxcorerender-cl: LuxCore Benchmarkluxcorerender-cl: DLSCluxcorerender-cl: Rainbow Colors and Prismluxcorerender-cl: Foodmandelgpu: GPUmixbench: OpenCL - Single Precisionmixbench: OpenCL - Double Precisionmixbench: OpenCL - Integermixbench: NVIDIA CUDA - Single Precisionmixbench: NVIDIA CUDA - Double Precisionmixbench: NVIDIA CUDA - Half Precisionmixbench: NVIDIA CUDA - Integernamd-cuda: ATPase Simulation - 327,506 Atomsneatbench: GPUoctanebench: Total Scoreplaidml: Yes - Inference - Mobilenet - OpenCLplaidml: No - Training - Mobilenet - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - Inception V3 - OpenCLplaidml: No - Inference - DenseNet 201 - OpenCLplaidml: No - Inference - IMDB LSTM - OpenCLplaidml: No - Inference - VGG16 - OpenCLplaidml: No - Inference - VGG19 - OpenCLrodinia: OpenCL Myocyterodinia: OpenCL Particle Filterrodinia: NVIDIA CUDA GPU Myocyteviennacl: OpenCL LU FactorizationTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10605040.581.666567.7491.7322.7530.7914178.85548.2613783.931.4912.7920.7670.1032279.14343.6112538.2457870811434.17590.6329401.514070221292.15935.701277.2321217.117224244.995.9812.732.23480798376.615032.47454.3716979.9915103.61413.6632084.7914426.110.1919548.1324.5467692856.83198.372544.67355.85227.30775.69248.79196.6335.7674.25040.37376.64104304.763.814206.2198.2184.1198.186788.40242.702076.452.7412.9981.1660.1172223.78349.1213281.7676294191204.77137.13937.298754.2840124.25999472.242.555.380.98194875210.87018.90241.992157.316647.94240.92121.421887.610.22300141.6676551485.7899.641070.90159.43108.23331.84116.8992.8742.0817.79147.72269.18382457.735.400144.6136.3125.9144.563874.98137.481145.144.3114.6102.8620.1631928.88324.7011485.504137045979.3390.846014.196841.1885812.99551631.461.734.810.67113624502.04141.79137.201215.750.3607115.496.200864910.9173.25716.8297.8373.89203.0864.5351.1448.92013.18556.49860.19791765.012.642296.6240.7240.2276.354440.23172.494280.552.6073.0301.0820.1042175.96320.9713933.2739481651466.24563.1329306.127505907135.607315.271594.4380044.62973662.262.635.611.09200846066.45462.59144.305432.405440.74144.1410862.904866.610.23177135.6571341380.68111.391080.11135.31100.51298.7786.6168.8134.12711.48239.90568.15322826.164.904165.3159.1145.0165.294472.77159.721306.513.7644.5432.7300.1621976.41333.5211735.8414852981019.04102.366812.101749.2880023.27162651.631.935.110.78121139566.84683.96159.331389.900.3356617.3110.8143211053.4980.47810.50109.5082.21228.4672.2156.6050.55311.77459.47461.93622905.884.077206.2199.5183.3197.206093.02223.601695.792.7092.9741.1120.1172243.10345.4413045.8573943511231.44139.49748.968697.5462914.05297502.122.466.620.92184077179.76476.92224.822019.086174.80225.05113.321764.630.2402221.5132.8393541392.46103.791052.64151.71108.46314.8399.8879.1238.0038.20542.95566.20685091.863.387229.6225.6207.4223.148218.62298.462430.552.5462.9741.0950.1112345.38348.2913141.7294623901218.56151.56796.981921.6841524.634126622.132.454.230.99231826397.88520.97296.662655.588182.72296.09149.352326.090.2242624.6148.4720091665.7299.821154.13190.14112.28398.82131.34103.8337.9986.45743.19770.68802438.973.622266.0245.9217.8264.745512.89197.231612.523.0173.2271.3980.1641908.81339.2111829.864624498976.75115.77539.596660.5482493.85782832.002.366.590.92148357386.15844.90197.441711.030.29138143.5214321290.4889.281029.36138.3399.84267.8890.7471.1855.17410.07164.75864.53584836.621.677545.7449.5324.0506.9013536.25522.2213629.371.4922.7550.7590.1002268.23350.3713045.0309239411436.62606.7528816.817836895290.72496.020319.9141277.136218394.755.6712.332.23448915216.616061.09436.8116323.9414734.03409.4631492.2414103.790.19082310.8143992751.85187.732406.16353.54212.11753.75237.29187.9235.2354.41440.35275.78712856.385.000154.4148.1138.5147.664110.71150.681275.123.5173.1691.3010.1242076.48333.4711766.2918261271253.43102.268313.340894.0848653.18159331.531.785.410.65130290433.84355.28150.481354.144167.41151.6375.771187.720.3095791.732906987.0783.52775.73108.5679.13227.2371.7856.6238.11412.00242.70361.6530OpenBenchmarking.org

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 OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106011002200330044005500SE +/- 17.72, N = 4SE +/- 1.17, N = 4SE +/- 1.45, N = 4SE +/- 3.01, N = 4SE +/- 10.36, N = 4SE +/- 4.04, N = 4SE +/- 10.96, N = 4SE +/- 8.83, N = 4SE +/- 13.92, N = 4SE +/- 2.50, N = 45040.584304.762457.731765.012826.162905.885091.862438.974836.622856.381. (CXX) g++ options: -rdynamic

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601.2152.433.6454.866.075SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 9SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.004, N = 10SE +/- 0.002, N = 10SE +/- 0.006, N = 10SE +/- 0.005, N = 10SE +/- 0.003, N = 101.6663.8145.4002.6424.9044.0773.3873.6221.6775.0001. (CXX) g++ options: -rdynamic

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: ReadTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060120240360480600SE +/- 0.13, N = 9SE +/- 0.03, N = 6SE +/- 0.02, N = 4SE +/- 0.07, N = 7SE +/- 0.08, N = 5SE +/- 0.03, N = 6SE +/- 0.08, N = 6SE +/- 0.17, N = 6SE +/- 0.13, N = 8SE +/- 0.02, N = 5567.7206.2144.6296.6165.3206.2229.6266.0545.7154.41. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060110220330440550SE +/- 0.97, N = 9SE +/- 0.03, N = 6SE +/- 0.15, N = 4SE +/- 0.36, N = 7SE +/- 0.20, N = 5SE +/- 0.03, N = 6SE +/- 0.09, N = 6SE +/- 0.14, N = 6SE +/- 0.21, N = 8SE +/- 0.02, N = 5491.7198.2136.3240.7159.1199.5225.6245.9449.5148.11. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106070140210280350SE +/- 0.08, N = 9SE +/- 0.03, N = 6SE +/- 0.02, N = 4SE +/- 0.05, N = 7SE +/- 0.02, N = 5SE +/- 0.02, N = 6SE +/- 0.02, N = 6SE +/- 0.07, N = 6SE +/- 0.10, N = 8SE +/- 0.02, N = 5322.7184.1125.9240.2145.0183.3207.4217.8324.0138.51. (CC) gcc options: -O2 -flto -lOpenCL

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 BandwidthTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060110220330440550SE +/- 0.05, N = 13SE +/- 0.01, N = 11SE +/- 0.02, N = 12SE +/- 0.16, N = 12SE +/- 0.01, N = 13SE +/- 0.04, N = 11SE +/- 0.11, N = 15SE +/- 0.13, N = 15SE +/- 0.46, N = 12SE +/- 0.04, N = 10530.79198.18144.56276.35165.29197.20223.14264.74506.90147.661. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10603K6K9K12K15KSE +/- 206.22, N = 15SE +/- 3.15, N = 13SE +/- 48.39, N = 15SE +/- 43.47, N = 15SE +/- 36.45, N = 13SE +/- 112.12, N = 15SE +/- 104.59, N = 15SE +/- 62.62, N = 15SE +/- 177.79, N = 15SE +/- 76.28, N = 1514178.856788.403874.984440.234472.776093.028218.625512.8913536.254110.711. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060120240360480600SE +/- 1.32, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.38, N = 4SE +/- 0.60, N = 3SE +/- 0.11, N = 3SE +/- 1.30, N = 3SE +/- 0.23, N = 3548.26242.70137.48172.49159.72223.60298.46197.23522.22150.681. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10603K6K9K12K15KSE +/- 169.21, N = 15SE +/- 0.30, N = 10SE +/- 8.78, N = 10SE +/- 6.44, N = 12SE +/- 1.81, N = 8SE +/- 6.03, N = 12SE +/- 7.00, N = 10SE +/- 8.22, N = 9SE +/- 23.37, N = 12SE +/- 10.83, N = 1513783.932076.451145.144280.551306.511695.792430.551612.5213629.371275.121. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Darktable

OpenBenchmarking.orgWatts, Fewer Is BetterDarktableGPU Power Consumption MonitorTITAN RTX4080120160200Min: 24.51 / Avg: 72.14 / Max: 236.96

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktableGPU Temperature MonitorTITAN RTX1020304050Min: 40 / Avg: 42.66 / Max: 48

OpenBenchmarking.orgWatts, Fewer Is BetterDarktableGPU Power Consumption MonitorTITAN RTX20406080100Min: 24.52 / Avg: 56.98 / Max: 89.35

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktableGPU Temperature MonitorTITAN RTX918273645Min: 41 / Avg: 42.09 / Max: 43

OpenBenchmarking.orgWatts, Fewer Is BetterDarktableGPU Power Consumption MonitorTITAN RTX306090120150Min: 24.59 / Avg: 62.16 / Max: 145.89

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktableGPU Temperature MonitorTITAN RTX918273645Min: 40 / Avg: 41.68 / Max: 43

OpenBenchmarking.orgWatts, Fewer Is BetterDarktableGPU Power Consumption MonitorTITAN RTX1224364860Min: 24.5 / Avg: 39.6 / Max: 59.07

OpenBenchmarking.orgCelsius, Fewer Is BetterDarktableGPU Temperature MonitorTITAN RTX918273645Min: 39 / Avg: 39.79 / Max: 41

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Boat - Acceleration: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10600.971.942.913.884.85SE +/- 0.008, N = 9SE +/- 0.012, N = 8SE +/- 0.014, N = 7SE +/- 0.010, N = 9SE +/- 0.014, N = 8SE +/- 0.009, N = 9SE +/- 0.006, N = 9SE +/- 0.013, N = 8SE +/- 0.007, N = 10SE +/- 0.012, N = 81.4912.7414.3112.6073.7642.7092.5463.0171.4923.517

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Masskrug - Acceleration: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601.03732.07463.11194.14925.1865SE +/- 0.011, N = 8SE +/- 0.016, N = 8SE +/- 0.022, N = 7SE +/- 0.011, N = 8SE +/- 0.023, N = 7SE +/- 0.008, N = 8SE +/- 0.011, N = 8SE +/- 0.012, N = 8SE +/- 0.009, N = 9SE +/- 0.009, N = 82.7922.9984.6103.0304.5432.9742.9743.2272.7553.169

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Server Room - Acceleration: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10600.6441.2881.9322.5763.22SE +/- 0.002, N = 11SE +/- 0.001, N = 10SE +/- 0.017, N = 8SE +/- 0.002, N = 10SE +/- 0.004, N = 8SE +/- 0.004, N = 10SE +/- 0.003, N = 10SE +/- 0.002, N = 10SE +/- 0.002, N = 11SE +/- 0.002, N = 100.7671.1662.8621.0822.7301.1121.0951.3980.7591.301

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Server Rack - Acceleration: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10600.03690.07380.11070.14760.1845SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.001, N = 15SE +/- 0.000, N = 13SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 130.1030.1170.1630.1040.1620.1170.1110.1640.1000.124

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: OpenCL - Kernel: Euclidean ClusterTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10605001000150020002500SE +/- 9.59, N = 5SE +/- 0.67, N = 5SE +/- 1.83, N = 4SE +/- 3.67, N = 5SE +/- 2.91, N = 5SE +/- 7.62, N = 5SE +/- 5.86, N = 5SE +/- 5.50, N = 4SE +/- 5.93, N = 5SE +/- 3.33, N = 52279.142223.781928.882175.961976.412243.102345.381908.812268.232076.481. (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 MappingTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106080160240320400SE +/- 1.41, N = 3SE +/- 2.01, N = 3SE +/- 0.82, N = 3SE +/- 2.54, N = 3SE +/- 0.61, N = 3SE +/- 2.24, N = 3SE +/- 1.38, N = 3SE +/- 2.08, N = 3SE +/- 0.87, N = 3SE +/- 0.67, N = 3343.61349.12324.70320.97333.52345.44348.29339.21350.37333.471. (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: Points2ImageTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10603K6K9K12K15KSE +/- 36.56, N = 3SE +/- 112.38, N = 3SE +/- 123.30, N = 3SE +/- 16.13, N = 3SE +/- 75.04, N = 3SE +/- 180.15, N = 3SE +/- 90.00, N = 3SE +/- 62.20, N = 3SE +/- 70.09, N = 3SE +/- 136.54, N = 312538.2513281.7711485.5013933.2711735.8413045.8613141.7311829.8613045.0311766.291. (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: Euclidean ClusterTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106030060090012001500SE +/- 2.28, N = 4SE +/- 7.67, N = 3SE +/- 2.99, N = 3SE +/- 0.96, N = 4SE +/- 1.10, N = 3SE +/- 4.73, N = 3SE +/- 2.36, N = 3SE +/- 15.93, N = 3SE +/- 0.89, N = 4SE +/- 8.38, N = 31434.171204.77979.331466.241019.041231.441218.56976.751436.621253.431. (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 MappingTITAN RTXGTX 1660 SUPERRTX 2080 Ti130260390520650SE +/- 5.64, N = 3SE +/- 4.39, N = 3SE +/- 2.73, N = 3590.63563.13606.751. (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: Points2ImageTITAN RTXGTX 1660 SUPERRTX 2080 Ti6K12K18K24K30KSE +/- 203.08, N = 3SE +/- 284.42, N = 3SE +/- 496.68, N = 329401.5129306.1328816.821. (CXX) g++ options: -O3 -m64 -std=c++11 -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 2.3.2TITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106060120180240300SE +/- 0.85, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.46, N = 3SE +/- 0.41, N = 3SE +/- 0.33, N = 3SE +/- 1.17, N = 3SE +/- 0.16, N = 3292.16137.1490.85135.61102.37139.50151.57115.78290.72102.27

FinanceBench

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

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106048121620SE +/- 0.002, N = 15SE +/- 0.003, N = 15SE +/- 0.003, N = 15SE +/- 0.001, N = 14SE +/- 0.023, N = 15SE +/- 0.209, N = 15SE +/- 0.003, N = 15SE +/- 0.156, N = 15SE +/- 0.002, N = 14SE +/- 0.317, N = 155.7017.29814.19615.27112.1018.9686.9819.5966.02013.3401. (CXX) g++ options: -O3 -lOpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Monte-Carlo OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10602004006008001000SE +/- 1.20, N = 8SE +/- 0.22, N = 8SE +/- 1.03, N = 7SE +/- 0.49, N = 8SE +/- 0.37, N = 8SE +/- 0.41, N = 7SE +/- 0.48, N = 7SE +/- 0.29, N = 8SE +/- 0.60, N = 8SE +/- 0.45, N = 7277.23754.28841.19594.44749.29697.55921.68660.55319.91894.081. (CXX) g++ options: -O3 -lOpenCL

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringTITAN RTXGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106060120180240300Min: 24.02 / Avg: 126.58 / Max: 312.98Min: 15.21 / Avg: 95.21 / Max: 176.52Min: 10.68 / Avg: 67.65 / Max: 128.36Min: 15.1 / Avg: 102.77 / Max: 192.38Min: 6.84 / Avg: 82.21 / Max: 159.92Min: 6.47 / Avg: 92.36 / Max: 196.24Min: 15.33 / Avg: 131.28 / Max: 252.57Min: 5.74 / Avg: 124.11 / Max: 273.84Min: 6.24 / Avg: 64.43 / Max: 128.04

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601632486480Min: 35 / Avg: 55.61 / Max: 78Min: 32 / Avg: 45.46 / Max: 58Min: 33 / Avg: 52.58 / Max: 74Min: 33 / Avg: 55.48 / Max: 68Min: 31 / Avg: 65.22 / Max: 80Min: 29 / Avg: 59.81 / Max: 78Min: 28 / Avg: 61.17 / Max: 83Min: 30 / Avg: 70.66 / Max: 85Min: 29 / Avg: 56.11 / Max: 78Min: 32 / Avg: 52.77 / Max: 69

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 BenchmarkTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060246810SE +/- 0.005, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.007, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.020, N = 2SE +/- 0.003, N = 37.1174.2592.9954.6293.2714.0524.6343.8577.1363.1811. (CXX) g++ options: -O3 -lpthread -ldl -lrt -lm

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: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10605K10K15K20K25KSE +/- 20.50, N = 3SE +/- 36.50, N = 3SE +/- 54.30, N = 3SE +/- 43.89, N = 3SE +/- 85.75, N = 3SE +/- 57.21, N = 3SE +/- 28.99, N = 3SE +/- 55.16, N = 3SE +/- 28.32, N = 322424994751637366626597501266282832183959331. (CXX) g++ options: -flto -pthread

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 BenchmarkTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601.12282.24563.36844.49125.614SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 12SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 34.992.241.462.261.632.122.132.004.751.53MIN: 0.32 / MAX: 5.69MIN: 0.27 / MAX: 2.52MIN: 0.12 / MAX: 1.68MIN: 0.27 / MAX: 2.54MIN: 0.27 / MAX: 1.83MIN: 0.27 / MAX: 2.4MIN: 0.27 / MAX: 2.39MIN: 0.27 / MAX: 2.27MIN: 0.32 / MAX: 5.39MIN: 0.23 / MAX: 1.72

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601.34552.6914.03655.3826.7275SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 12SE +/- 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 = 35.982.551.732.631.932.462.452.365.671.78MIN: 4.3 / MAX: 6.07MIN: 2.31 / MAX: 2.62MIN: 0.43 / MAX: 1.81MIN: 2.55 / MAX: 2.68MIN: 1.74 / MAX: 1.98MIN: 2.29 / MAX: 2.51MIN: 2.29 / MAX: 2.5MIN: 2.29 / MAX: 2.42MIN: 5.22 / MAX: 5.74MIN: 1.64 / MAX: 1.82

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10603691215SE +/- 0.18, N = 4SE +/- 0.13, N = 12SE +/- 0.10, N = 12SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 4SE +/- 0.01, N = 312.735.384.815.615.116.624.236.5912.335.41MIN: 11.95 / MAX: 14MIN: 1.63 / MAX: 5.69MIN: 1.5 / MAX: 5.09MIN: 5.07 / MAX: 5.86MIN: 4.25 / MAX: 5.29MIN: 5.17 / MAX: 6.91MIN: 3.57 / MAX: 4.38MIN: 5.89 / MAX: 6.88MIN: 11.33 / MAX: 12.81MIN: 4.66 / MAX: 5.64

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10600.50181.00361.50542.00722.509SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 12SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.230.980.671.090.780.920.990.922.230.65MIN: 0.25 / MAX: 2.7MIN: 0.24 / MAX: 1.14MIN: 0.12 / MAX: 0.81MIN: 0.25 / MAX: 1.26MIN: 0.23 / MAX: 0.88MIN: 0.23 / MAX: 1.06MIN: 0.24 / MAX: 1.15MIN: 0.23 / MAX: 1.06MIN: 0.32 / MAX: 2.65MIN: 0.22 / MAX: 0.74

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: GPUTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060100M200M300M400M500MSE +/- 2829613.77, N = 10SE +/- 459096.61, N = 7SE +/- 113731.50, N = 5SE +/- 173522.04, N = 7SE +/- 4075144.18, N = 15SE +/- 327094.24, N = 7SE +/- 528438.95, N = 8SE +/- 353641.55, N = 6SE +/- 2765042.11, N = 10SE +/- 339240.54, N = 6480798376.6194875210.8113624502.0200846066.4121139566.8184077179.7231826397.8148357386.1448915216.6130290433.81. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsTITAN RTXGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10602004006008001000962.08223.07497.00249.04348.12406.50327.281013.20280.52

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 PrecisionTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10603K6K9K12K15KSE +/- 619.26, N = 15SE +/- 2.95, N = 12SE +/- 0.70, N = 11SE +/- 8.38, N = 13SE +/- 23.81, N = 15SE +/- 12.17, N = 15SE +/- 11.17, N = 14SE +/- 4.87, N = 13SE +/- 66.33, N = 15SE +/- 2.22, N = 1315032.477018.904141.795462.594683.966476.928520.975844.9016061.094355.281. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 1060100200300400500SE +/- 1.13, N = 14SE +/- 0.08, N = 14SE +/- 0.16, N = 13SE +/- 0.22, N = 13SE +/- 0.18, N = 13SE +/- 0.06, N = 13SE +/- 0.15, N = 14SE +/- 0.12, N = 13SE +/- 0.56, N = 15SE +/- 0.23, N = 13454.37241.99137.20144.30159.33224.82296.66197.44436.81150.481. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10604K8K12K16K20KSE +/- 63.55, N = 15SE +/- 0.83, N = 14SE +/- 0.40, N = 13SE +/- 7.30, N = 13SE +/- 5.50, N = 15SE +/- 0.96, N = 13SE +/- 6.51, N = 15SE +/- 1.27, N = 13SE +/- 11.06, N = 14SE +/- 2.70, N = 1416979.992157.311215.755432.401389.902019.082655.581711.0316323.941354.141. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Single PrecisionTITAN RTXGTX 1070 TiGTX 1660 SUPERGTX 1070GTX 1080RTX 2080 TiGTX 10603K6K9K12K15KSE +/- 595.40, N = 15SE +/- 2.31, N = 11SE +/- 0.25, N = 13SE +/- 30.05, N = 15SE +/- 3.04, N = 11SE +/- 556.93, N = 15SE +/- 1.19, N = 915103.616647.945440.746174.808182.7214734.034167.411. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Double PrecisionTITAN RTXGTX 1070 TiGTX 1660 SUPERGTX 1070GTX 1080RTX 2080 TiGTX 106090180270360450SE +/- 15.67, N = 15SE +/- 0.35, N = 11SE +/- 0.66, N = 15SE +/- 0.10, N = 11SE +/- 0.03, N = 11SE +/- 10.76, N = 15SE +/- 0.00, N = 9413.66240.92144.14225.05296.09409.46151.631. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Half PrecisionTITAN RTXGTX 1070 TiGTX 1660 SUPERGTX 1070GTX 1080RTX 2080 TiGTX 10607K14K21K28K35KSE +/- 939.79, N = 15SE +/- 0.07, N = 11SE +/- 15.42, N = 13SE +/- 0.02, N = 11SE +/- 0.10, N = 11SE +/- 601.15, N = 15SE +/- 0.02, N = 932084.79121.4210862.90113.32149.3531492.2475.771. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: IntegerTITAN RTXGTX 1070 TiGTX 1660 SUPERGTX 1070GTX 1080RTX 2080 TiGTX 10603K6K9K12K15KSE +/- 458.60, N = 15SE +/- 0.87, N = 11SE +/- 4.94, N = 15SE +/- 3.28, N = 11SE +/- 1.56, N = 11SE +/- 264.51, N = 15SE +/- 2.01, N = 914426.111887.614866.611764.632326.0914103.791187.721. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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 AtomsTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10600.08120.16240.24360.32480.406SE +/- 0.00134, N = 4SE +/- 0.00101, N = 4SE +/- 0.00170, N = 3SE +/- 0.00026, N = 4SE +/- 0.00291, N = 3SE +/- 0.00276, N = 4SE +/- 0.00174, N = 4SE +/- 0.00163, N = 4SE +/- 0.00046, N = 4SE +/- 0.00077, N = 30.191950.223000.360710.231770.335660.240220.224260.291380.190820.30957

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: GPUTITAN RTXGTX 970GTX 980GTX 1070GTX 10801122334455SE +/- 0.02, N = 13SE +/- 0.05, N = 13SE +/- 0.04, N = 13SE +/- 0.13, N = 13SE +/- 0.04, N = 1348.115.417.321.524.6

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 ScoreTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106070140210280350324.55141.6796.20135.66110.81132.84148.47143.52310.8191.73

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: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10606001200180024003000SE +/- 1.27, N = 8SE +/- 0.31, N = 7SE +/- 0.24, N = 6SE +/- 0.83, N = 7SE +/- 0.78, N = 6SE +/- 3.20, N = 7SE +/- 1.79, N = 7SE +/- 2.34, N = 5SE +/- 1.82, N = 7SE +/- 2.10, N = 62856.831485.78910.911380.681053.491392.461665.721290.482751.85987.07

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Training - Network: Mobilenet - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10604080120160200SE +/- 0.21, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.06, N = 3198.3799.6473.25111.3980.47103.7999.8289.28187.7383.52

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10605001000150020002500SE +/- 2.36, N = 8SE +/- 0.27, N = 8SE +/- 0.28, N = 7SE +/- 1.11, N = 8SE +/- 0.69, N = 7SE +/- 1.14, N = 8SE +/- 0.60, N = 8SE +/- 0.66, N = 8SE +/- 1.58, N = 8SE +/- 0.68, N = 72544.671070.90716.821080.11810.501052.641154.131029.362406.16775.73

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106080160240320400SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.62, N = 3SE +/- 0.23, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.25, N = 3SE +/- 0.19, N = 3355.85159.4397.83135.31109.50151.71190.14138.33353.54108.56

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106050100150200250SE +/- 0.25, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.21, N = 3SE +/- 0.02, N = 3227.30108.2373.89100.5182.21108.46112.2899.84212.1179.13

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10602004006008001000SE +/- 0.80, N = 5SE +/- 0.07, N = 4SE +/- 0.11, N = 4SE +/- 0.17, N = 4SE +/- 0.41, N = 4SE +/- 0.44, N = 4SE +/- 0.35, N = 4SE +/- 0.57, N = 4SE +/- 1.41, N = 5SE +/- 0.09, N = 4775.69331.84203.08298.77228.46314.83398.82267.88753.75227.23

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106050100150200250SE +/- 0.54, N = 4SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.42, N = 3SE +/- 0.87, N = 3SE +/- 0.64, N = 3SE +/- 0.22, N = 3248.79116.8964.5386.6172.2199.88131.3490.74237.2971.78

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10604080120160200SE +/- 0.42, N = 4SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.61, N = 3SE +/- 0.13, N = 3SE +/- 0.31, N = 3SE +/- 1.20, N = 3SE +/- 0.60, N = 3SE +/- 0.16, N = 3196.6392.8751.1468.8156.6079.12103.8371.18187.9256.62

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 MyocyteTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601224364860SE +/- 0.08, N = 3SE +/- 0.24, N = 3SE +/- 0.26, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 335.7742.0848.9234.1350.5538.0038.0055.1735.2438.111. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10603691215SE +/- 0.008, N = 8SE +/- 0.006, N = 6SE +/- 0.026, N = 4SE +/- 0.009, N = 5SE +/- 0.058, N = 4SE +/- 0.019, N = 6SE +/- 0.018, N = 6SE +/- 0.092, N = 5SE +/- 0.009, N = 8SE +/- 0.012, N = 44.2507.79113.18511.48211.7748.2056.45710.0714.41412.0021. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: NVIDIA CUDA GPU MyocyteTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 10601428425670SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 340.3747.7256.5039.9159.4742.9643.2064.7640.3542.701. (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 FactorizationTITAN RTXGTX 1070 TiGTX 970GTX 1660 SUPERGTX 980GTX 1070GTX 1080GTX 980 TiRTX 2080 TiGTX 106020406080100SE +/- 0.57, N = 11SE +/- 0.38, N = 11SE +/- 0.20, N = 10SE +/- 0.37, N = 11SE +/- 0.29, N = 11SE +/- 0.23, N = 11SE +/- 0.21, N = 11SE +/- 0.25, N = 11SE +/- 0.39, N = 11SE +/- 0.32, N = 1176.6469.1860.2068.1561.9466.2170.6964.5475.7961.651. (CXX) g++ options: -rdynamic -lOpenCL

62 Results Shown

ArrayFire:
  BLAS OpenCL
  Conjugate Gradient OpenCL
cl-mem:
  Read
  Write
  Copy
clpeak:
  Global Memory Bandwidth
  Single-Precision Float
  Double-Precision Double
  Integer Compute INT
Darktable:
  GPU Power Consumption Monitor
  GPU Temp Monitor
  GPU Power Consumption Monitor
  GPU Temp Monitor
  GPU Power Consumption Monitor
  GPU Temp Monitor
  GPU Power Consumption Monitor
  GPU Temp Monitor
Darktable:
  Boat - OpenCL
  Masskrug - OpenCL
  Server Room - OpenCL
  Server Rack - OpenCL
Darmstadt Automotive Parallel Heterogeneous Suite:
  OpenCL - Euclidean Cluster
  OpenCL - NDT Mapping
  OpenCL - Points2Image
  NVIDIA CUDA - Euclidean Cluster
  NVIDIA CUDA - NDT Mapping
  NVIDIA CUDA - Points2Image
FAHBench
FinanceBench:
  Black-Scholes OpenCL
  Monte-Carlo OpenCL
GPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Celsius
GROMACS
LeelaChessZero
LuxCoreRender OpenCL:
  LuxCore Benchmark
  DLSC
  Rainbow Colors and Prism
  Food
MandelGPU
Meta Performance Per Watts
Mixbench:
  OpenCL - Single Precision
  OpenCL - Double Precision
  OpenCL - Integer
  NVIDIA CUDA - Single Precision
  NVIDIA CUDA - Double Precision
  NVIDIA CUDA - Half Precision
  NVIDIA CUDA - Integer
NAMD CUDA
NeatBench
OctaneBench
PlaidML:
  Yes - Inference - Mobilenet - OpenCL
  No - Training - Mobilenet - OpenCL
  No - Inference - Mobilenet - OpenCL
  No - Inference - Inception V3 - OpenCL
  No - Inference - DenseNet 201 - OpenCL
  No - Inference - IMDB LSTM - OpenCL
  No - Inference - VGG16 - OpenCL
  No - Inference - VGG19 - OpenCL
Rodinia:
  OpenCL Myocyte
  OpenCL Particle Filter
  NVIDIA CUDA GPU Myocyte
ViennaCL