NVIDIA GeForce RTX 30 Linux GPU Compute Benchmarks

NVIDIA GPU compute benchmarks on Linux 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 2104107-IB-GPUCOMPUT97
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

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 4 Tests
Game Development 2 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 2 Tests
Multi-Core 5 Tests
NVIDIA GPU Compute 21 Tests
OpenCL 5 Tests
Renderers 3 Tests
Server CPU Tests 2 Tests
Vulkan Compute 4 Tests
Common Workstation Benchmarks 2 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
RTX 2060
April 08 2021
  4 Hours, 45 Minutes
RTX 2060 SUPER
March 31 2021
  4 Hours, 35 Minutes
RTX 2070
April 03 2021
  4 Hours, 39 Minutes
RTX 2070 SUPER
March 30 2021
  4 Hours, 26 Minutes
RTX 2080
April 04 2021
  3 Hours, 26 Minutes
RTX 2080 SUPER
April 01 2021
  3 Hours, 20 Minutes
RTX 2080 Ti
April 01 2021
  3 Hours, 9 Minutes
TITAN RTX
April 02 2021
  3 Hours, 15 Minutes
RTX 3060
April 07 2021
  3 Hours, 18 Minutes
RTX 3060 Ti
March 30 2021
  2 Hours, 40 Minutes
RTX 3070
April 06 2021
  2 Hours, 34 Minutes
RTX 3080
March 29 2021
  2 Hours, 20 Minutes
RTX 3090
April 04 2021
  2 Hours, 9 Minutes
Invert Hiding All Results Option
  3 Hours, 26 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 GeForce RTX 30 Linux GPU Compute BenchmarksOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)ASUS ROG CROSSHAIR VIII HERO (3402 BIOS)AMD Starship/Matisse16GB1000GB Sabrent Rocket 4.0 Plus + 2000GBNVIDIA GeForce RTX 2060 6GBNVIDIA GeForce RTX 2060 SUPER 8GBASUS NVIDIA GeForce RTX 2070 8GBNVIDIA GeForce RTX 2070 SUPER 8GBZotac NVIDIA GeForce RTX 2080 8GBNVIDIA GeForce RTX 2080 SUPER 8GBNVIDIA GeForce RTX 2080 Ti 11GBNVIDIA TITAN RTX 24GBeVGA NVIDIA GeForce RTX 3060 12GBNVIDIA GeForce RTX 3060 Ti 8GBNVIDIA GeForce RTX 3070 8GBNVIDIA GeForce RTX 3080 10GBNVIDIA GeForce RTX 3090 24GBNVIDIA TU106 HD AudioNVIDIA TU104 HD AudioNVIDIA TU102 HD AudioNVIDIA Device 228eNVIDIA Device 228bNVIDIA Device 1aefASUS VP28URealtek RTL8125 2.5GbE + Intel I211Ubuntu 20.045.8.0-48-generic (x86_64)GNOME Shell 3.36.7X Server 1.20.9NVIDIA 460.674.6.0OpenCL 1.2 CUDA 11.2.1621.2.155GCC 9.3.0 + CUDA 11.2ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA GeForce RTX 30 Linux GPU Compute Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0xa201009- RTX 2060: GPU Compute Cores: 1920- RTX 2060 SUPER: GPU Compute Cores: 2176- RTX 2070: GPU Compute Cores: 2304- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2080: GPU Compute Cores: 2944- RTX 2080 SUPER: GPU Compute Cores: 3072- RTX 2080 Ti: GPU Compute Cores: 4352- TITAN RTX: GPU Compute Cores: 4608- RTX 3060: GPU Compute Cores: 3584- RTX 3060 Ti: GPU Compute Cores: 4864- RTX 3070: GPU Compute Cores: 5888- RTX 3080: GPU Compute Cores: 8704- RTX 3090: GPU Compute Cores: 10496- 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090Result OverviewPhoronix Test Suite100%188%276%364%452%BlenderChaos Group V-RAYclpeakOctaneBenchLuxCoreRender OpenCLRedShift DemoIndigoBenchMixbenchLeelaChessZeroFinanceBenchVkResampleHashcatRodiniaRealSR-NCNNSHOC Scalable HeterOgeneous Computingcl-memBetsy GPU CompressorViennaCLFAHBenchArrayFireWaifu2x-NCNN VulkanGROMACSNAMD CUDA

NVIDIA GeForce RTX 30 Linux GPU Compute Benchmarksblender: Barbershop - NVIDIA OptiXlczero: OpenCLblender: Pabellon Barcelona - CUDAredshift: blender: Classroom - CUDAoctanebench: Total Scoreblender: Pabellon Barcelona - NVIDIA OptiXgromacs-gpu: Water Benchmarkluxcorerender-cl: Foodfahbench: blender: Classroom - NVIDIA OptiXblender: Fishy Cat - CUDAluxcorerender-cl: LuxCore Benchmarkluxcorerender-cl: DLSCv-ray: NVIDIA CUDA GPUv-ray: NVIDIA RTX GPUblender: Fishy Cat - NVIDIA OptiXindigobench: OpenCL GPU - Bedroomindigobench: OpenCL GPU - Supercarrealsr-ncnn: 4x - Yesblender: BMW27 - CUDAvkresample: 2x - Doubleclpeak: Double-Precision Doubleblender: BMW27 - NVIDIA OptiXviennacl: OpenCL BLAS - dGEMM-TTnamd-cuda: ATPase Simulation - 327,506 Atomsviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dDOTviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - sCOPYviennacl: OpenCL BLAS - dGEMM-NTluxcorerender-cl: Rainbow Colors and Prismviennacl: OpenCL BLAS - dGEMM-NNshoc: OpenCL - Texture Read Bandwidthrealsr-ncnn: 4x - Novkresample: 2x - Singlebetsy: ETC2 RGB - Highestbetsy: ETC1 - Highestrodinia: OpenCL Particle Filterhashcat: SHA-512hashcat: SHA1hashcat: MD5waifu2x-ncnn: 2x - 3 - Yescl-mem: Readhashcat: TrueCrypt RIPEMD160 + XTScl-mem: Writecl-mem: Copyshoc: OpenCL - GEMM SGEMM_Nhashcat: 7-Ziparrayfire: Conjugate Gradient OpenCLclpeak: Integer Compute INTshoc: OpenCL - Triadshoc: OpenCL - Reductionshoc: OpenCL - FFT SPclpeak: Single-Precision Floatclpeak: Global Memory Bandwidthshoc: OpenCL - MD5 Hashfinancebench: Black-Scholes OpenCLmixbench: OpenCL - Single Precisionmixbench: OpenCL - Integermixbench: OpenCL - Double Precisionshoc: OpenCL - S3DRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 30901812.3112248583.12477304.55193.72607208.095.7891.20183.8393150.10140.642.783.3047465875.055.58218.37985.64574.50349.257231.5336.920.179142913082802532122182177.912201035.4212.76527.2229.4016.7838.98910511714298233357143258673714295.852297.4310388251.7239.32451.994422822.6595393.4912.6239263.281801.4985390.85275.9916.311619.7763337223.667256.56195.67147.5631790.0714537544.98380301.61243.271628194.576.2711.32207.6500145.23121.413.604.1849073465.227.34723.22975.84163.92309.018263.4730.970.1666638840336832926324927624811.232491106.3011.51322.2478.4426.0817.99111863857149307085714291733285715.382396.9349878335.1286.93046.364939822.0826949.7912.7589317.728963.1256982.39368.5318.366216.4142008240.308197.38221.54188.8771844.7614829556.87378308.95243.280503198.296.3581.29205.5287149.28122.943.564.1447871064.447.37923.45975.11164.95303.671267.8431.250.1614538840136732126025227125410.972551064.2811.37322.2848.3605.9397.89012170428579511900000299063285715.373396.8357513321.8283.43114.475029552.0957048.6512.7737317.460967.6167259.99368.4718.719415.9918392.728354.50226.00193.4271015.8417409357.54350172.25264.486018134.866.7531.79229.315091.1996.993.594.3076196256.977.72024.51863.63251.27263.373308.5428.520.151403864023663252602932812899.862901133.9310.41919.5017.5235.6367.018142097142911107042857350967285714.890396.8426357318.7290.83319.275903902.0708612.7512.7814323.2711087.478583.14369.4521.815112.8079773.719693.07260.38199.281987.7318781354.15342169.00262.52907134.577.1111.86246.180988.1297.203.554.2374390350.677.74324.89559.53551.68234.437345.9726.583240.148333884043703172503322793279.293291114.909.44218.9946.8284.9716.257156218571412219442857385484714294.672396.8462213331.2290.13349.366357602.0749246.8512.7697317.8481098.168890.45369.1624.323511.83110940.4210825.09290.29196.927925.5521050345.65323160.65266.684229128.997.3911.90262.070383.4796.203.614.3275692647.427.98225.69054.19950.66215.024376.3225.743540.146144274404043282503572883529.243571165.168.92617.4366.2274.6115.784173568571413554400000428575428574.437437.5535927348.6300.63725.027187271.90010291.5012.8073328.7711203.3410284.15405.5626.624310.52511866.9211714.43314.09213.058916.0927639285.52247152.86352.027289104.118.1782.19298.642774.8172.454.655.63928124536.0711.03333.37144.52938.49155.569522.2819.520.1440851852147840532248330847312.344761187.967.86014.7585.1383.8514.464224774285717685385714551863142863.965545.6656675449.5321.64831.948926801.69013256.8912.8851370.5011487.9513380.02507.0635.34599.31116375.1616219.08432.17271.700969.5827299297.11246161.80363.872047109.027.0182.08292.399279.0373.364.695.67892123236.6311.16333.66643.32938.74152.755515.0219.944720.1662352051647738930545629646812.924741169.727.55714.1826.8754.702224934285717755985714555546000004.013545.3654338476.8306.34975.628948871.68813017.2112.8550350.9711574.8513624.14504.5136.28929.13517145.6716892.91439.29289.596863.8718456319.41305128.50288.473165122.256.0862.06180.369878.4885.644.515.53784105958.228.42025.65672.19844.35377.589209.5624.381940.1628132532831130228919927119913.262011256.4311.18223.3529.7346.4499.7639789714297713342857228292714295.259315.8300188296.4266.72772.304302552.5185737.4424.3577306.317934.05912487.45314.2315.225016.66200013135.076602.45177.72171.800549.7925920217.7824085.48382.7713186.047.5052.99236.553554.7561.995.917.251185154841.9811.45934.01153.99031.92263.987303.9017.820.1390439939836235732429229229217.722932119.258.84617.6696.7904.9746.968141212857111092171429329189857144.541393.1428390383.3297.03438.495886912.0918364.5424.7052324.7091152.9116008.65389.0021.693112.97618832.999593.81255.14211.882462.6029208190.0522876.26410.55825376.967.6573.36266.101648.1654.266.497.931341171535.7112.89037.23050.03128.99223.669360.4416.100.1415139639736535732534129434118.923422121.568.40017.5166.0304.2935.979166518571413107471429386413571434.307393.1503400379.8296.93775.876860002.09010229.1824.6655325.8451135.1420059.00389.0825.528510.46422115.6911288.37300.72218.501400.0836733147.5416661.63560.12128556.729.1273.96318.649936.4341.807.879.591650215124.6217.39345.99234.39622.18149.531537.2411.644920.1313863059254746837349735050122.314942204.206.42811.4044.5233.3454.386239856666718934633333554587000003.620666.0710567641.3354.56181.239846251.56115094.0225.2918387.7291915.3829322.87662.1637.40027.61630534.4417004.83385.83339.907336.9938623120.3514151.43678.244246.759.2004.66343.360530.4634.599.1611.151964262020.3720.77852.86129.67118.47122.897656.289.726000.1355072265060750437559936660326.336012237.775.8569.2754.0003.0163.767286544285722679671429666688428573.451825.6850275741.1363.48144.8111445401.48518024.3425.4663391.9582348.6735070.69811.9244.43706.30535766.2718323.71500.47429.333OpenBenchmarking.org

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX400800120016002000SE +/- 0.62, N = 3SE +/- 0.39, N = 3SE +/- 3.33, N = 3SE +/- 0.36, N = 3SE +/- 0.79, N = 3SE +/- 0.76, N = 3SE +/- 0.51, N = 3SE +/- 0.15, N = 3SE +/- 2.14, N = 3SE +/- 0.73, N = 3SE +/- 0.48, N = 3SE +/- 2.26, N = 3SE +/- 0.70, N = 31812.311790.071844.761015.84987.73925.55916.09863.87549.79462.60400.08336.99969.58
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX30060090012001500Min: 1811.62 / Avg: 1812.31 / Max: 1813.55Min: 1789.68 / Avg: 1790.07 / Max: 1790.84Min: 1840.86 / Avg: 1844.76 / Max: 1851.39Min: 1015.28 / Avg: 1015.84 / Max: 1016.51Min: 986.16 / Avg: 987.73 / Max: 988.6Min: 924.57 / Avg: 925.55 / Max: 927.04Min: 915.49 / Avg: 916.09 / Max: 917.11Min: 863.6 / Avg: 863.87 / Max: 864.13Min: 546.56 / Avg: 549.79 / Max: 553.84Min: 461.87 / Avg: 462.6 / Max: 464.06Min: 399.29 / Avg: 400.08 / Max: 400.96Min: 334.65 / Avg: 336.99 / Max: 341.51Min: 968.29 / Avg: 969.58 / Max: 970.71

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: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX8K16K24K32K40KSE +/- 40.29, N = 3SE +/- 59.97, N = 3SE +/- 73.63, N = 3SE +/- 31.66, N = 3SE +/- 72.61, N = 3SE +/- 98.63, N = 3SE +/- 120.07, N = 3SE +/- 95.55, N = 3SE +/- 104.85, N = 3SE +/- 49.53, N = 3SE +/- 210.78, N = 3SE +/- 98.56, N = 3SE +/- 211.49, N = 3122481453714829174091878121050276391845625920292083673338623272991. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX7K14K21K28K35KMin: 12173 / Avg: 12248 / Max: 12311Min: 14450 / Avg: 14537 / Max: 14652Min: 14748 / Avg: 14829 / Max: 14976Min: 17351 / Avg: 17409 / Max: 17460Min: 18698 / Avg: 18781.33 / Max: 18926Min: 20886 / Avg: 21050.33 / Max: 21227Min: 27497 / Avg: 27639.33 / Max: 27878Min: 18270 / Avg: 18456 / Max: 18587Min: 25783 / Avg: 25920 / Max: 26126Min: 29116 / Avg: 29207.67 / Max: 29286Min: 36380 / Avg: 36732.67 / Max: 37109Min: 38457 / Avg: 38622.67 / Max: 38798Min: 26909 / Avg: 27298.67 / Max: 276361. (CXX) g++ options: -flto -pthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650SE +/- 1.13, N = 3SE +/- 0.40, N = 3SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.48, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3583.12544.98556.87357.54354.15345.65285.52319.41217.78190.05147.54120.35297.11
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX100200300400500Min: 580.86 / Avg: 583.12 / Max: 584.35Min: 544.19 / Avg: 544.98 / Max: 545.39Min: 556.59 / Avg: 556.87 / Max: 557.06Min: 357.45 / Avg: 357.54 / Max: 357.68Min: 354.04 / Avg: 354.15 / Max: 354.23Min: 345.43 / Avg: 345.65 / Max: 345.79Min: 284.58 / Avg: 285.52 / Max: 286.15Min: 319.38 / Avg: 319.41 / Max: 319.44Min: 217.74 / Avg: 217.78 / Max: 217.82Min: 190.04 / Avg: 190.05 / Max: 190.06Min: 147.35 / Avg: 147.54 / Max: 147.64Min: 120.23 / Avg: 120.35 / Max: 120.41Min: 296.77 / Avg: 297.11 / Max: 297.37

RedShift Demo

This is a test of MAXON's RedShift demo build that currently requires NVIDIA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX100200300400500SE +/- 1.86, N = 3SE +/- 1.67, N = 3SE +/- 1.76, N = 3SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 1.33, N = 3SE +/- 1.20, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3477380378350342323247305240228166141246
OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX80160240320400Min: 475 / Avg: 477.33 / Max: 481Min: 378 / Avg: 379.67 / Max: 383Min: 375 / Avg: 377.67 / Max: 381Min: 348 / Avg: 350 / Max: 353Min: 340 / Avg: 342 / Max: 345Min: 322 / Avg: 323.33 / Max: 326Min: 245 / Avg: 246.67 / Max: 249Min: 304 / Avg: 305 / Max: 307Min: 239 / Avg: 240.33 / Max: 243Min: 227 / Avg: 228 / Max: 230Min: 165 / Avg: 166 / Max: 167Min: 140 / Avg: 140.67 / Max: 142Min: 245 / Avg: 245.67 / Max: 247

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX70140210280350SE +/- 0.53, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 3304.55301.61308.95172.25169.00160.65152.86128.5085.4876.2661.6351.43161.80
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX60120180240300Min: 303.99 / Avg: 304.55 / Max: 305.61Min: 301.48 / Avg: 301.61 / Max: 301.69Min: 308.91 / Avg: 308.95 / Max: 308.98Min: 171.91 / Avg: 172.25 / Max: 172.44Min: 168.85 / Avg: 169 / Max: 169.09Min: 160.42 / Avg: 160.65 / Max: 160.88Min: 152.85 / Avg: 152.86 / Max: 152.87Min: 128.47 / Avg: 128.5 / Max: 128.54Min: 85.38 / Avg: 85.48 / Max: 85.55Min: 76.23 / Avg: 76.26 / Max: 76.28Min: 61.52 / Avg: 61.63 / Max: 61.7Min: 51.3 / Avg: 51.43 / Max: 51.51Min: 161.34 / Avg: 161.8 / Max: 162.13

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 2020.1Total ScoreRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX150300450600750193.73243.27243.28264.49262.53266.68352.03288.47382.77410.56560.12678.24363.87

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX50100150200250SE +/- 0.02, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3208.09194.57198.29134.86134.57128.99104.11122.2586.0476.9656.7246.75109.02
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX4080120160200Min: 208.06 / Avg: 208.09 / Max: 208.12Min: 194.12 / Avg: 194.57 / Max: 194.92Min: 197.92 / Avg: 198.29 / Max: 198.68Min: 134.78 / Avg: 134.86 / Max: 134.92Min: 134.46 / Avg: 134.57 / Max: 134.75Min: 128.95 / Avg: 128.99 / Max: 129.02Min: 103.95 / Avg: 104.11 / Max: 104.25Min: 122.13 / Avg: 122.25 / Max: 122.4Min: 85.92 / Avg: 86.04 / Max: 86.14Min: 76.94 / Avg: 76.96 / Max: 76.97Min: 56.63 / Avg: 56.72 / Max: 56.76Min: 46.6 / Avg: 46.75 / Max: 46.89Min: 108.98 / Avg: 109.02 / Max: 109.08

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 BenchmarkRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215SE +/- 0.004, N = 3SE +/- 0.015, N = 3SE +/- 0.024, N = 3SE +/- 0.036, N = 3SE +/- 0.031, N = 3SE +/- 0.023, N = 3SE +/- 0.015, N = 3SE +/- 0.017, N = 3SE +/- 0.047, N = 3SE +/- 0.052, N = 3SE +/- 0.125, N = 3SE +/- 0.011, N = 2SE +/- 0.011, N = 35.7896.2716.3586.7537.1117.3918.1786.0867.5057.6579.1279.2007.0181. (CXX) g++ options: -O3 -lpthread -ldl -lrt -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215Min: 5.78 / Avg: 5.79 / Max: 5.8Min: 6.25 / Avg: 6.27 / Max: 6.3Min: 6.31 / Avg: 6.36 / Max: 6.4Min: 6.7 / Avg: 6.75 / Max: 6.82Min: 7.06 / Avg: 7.11 / Max: 7.17Min: 7.36 / Avg: 7.39 / Max: 7.43Min: 8.16 / Avg: 8.18 / Max: 8.21Min: 6.06 / Avg: 6.09 / Max: 6.12Min: 7.42 / Avg: 7.5 / Max: 7.58Min: 7.58 / Avg: 7.66 / Max: 7.76Min: 8.95 / Avg: 9.13 / Max: 9.37Min: 9.19 / Avg: 9.2 / Max: 9.21Min: 7 / Avg: 7.02 / Max: 7.041. (CXX) g++ options: -O3 -lpthread -ldl -lrt -lm

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: FoodRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1.04852.0973.14554.1945.2425SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 4SE +/- 0.03, N = 7SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 31.201.321.291.791.861.902.192.062.993.363.964.662.08MIN: 0.21 / MAX: 1.43MIN: 0.23 / MAX: 1.59MIN: 0.21 / MAX: 1.55MIN: 0.09 / MAX: 2.3MIN: 0.21 / MAX: 2.29MIN: 0.21 / MAX: 2.38MIN: 0.23 / MAX: 2.7MIN: 0.22 / MAX: 2.57MIN: 0.2 / MAX: 3.75MIN: 0.2 / MAX: 4.25MIN: 0.26 / MAX: 4.99MIN: 0.29 / MAX: 5.93MIN: 0.22 / MAX: 2.61
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX246810Min: 1.19 / Avg: 1.2 / Max: 1.21Min: 1.3 / Avg: 1.32 / Max: 1.34Min: 1.29 / Avg: 1.29 / Max: 1.3Min: 1.07 / Avg: 1.79 / Max: 1.89Min: 1.84 / Avg: 1.86 / Max: 1.89Min: 1.87 / Avg: 1.9 / Max: 1.93Min: 2.18 / Avg: 2.19 / Max: 2.19Min: 2.03 / Avg: 2.06 / Max: 2.09Min: 2.89 / Avg: 2.99 / Max: 3.05Min: 3.2 / Avg: 3.36 / Max: 3.45Min: 3.93 / Avg: 3.96 / Max: 4.02Min: 4.61 / Avg: 4.66 / Max: 4.69Min: 2.04 / Avg: 2.08 / Max: 2.12

FAHBench

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

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX70140210280350SE +/- 0.11, N = 3SE +/- 0.51, N = 3SE +/- 0.10, N = 3SE +/- 0.19, N = 3SE +/- 0.36, N = 3SE +/- 0.26, N = 3SE +/- 3.72, N = 3SE +/- 0.11, N = 3SE +/- 0.45, N = 3SE +/- 0.55, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 3SE +/- 0.36, N = 3183.84207.65205.53229.32246.18262.07298.64180.37236.55266.10318.65343.36292.40
OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX60120180240300Min: 183.64 / Avg: 183.84 / Max: 184.02Min: 206.94 / Avg: 207.65 / Max: 208.64Min: 205.39 / Avg: 205.53 / Max: 205.73Min: 229.02 / Avg: 229.31 / Max: 229.68Min: 245.78 / Avg: 246.18 / Max: 246.9Min: 261.71 / Avg: 262.07 / Max: 262.59Min: 291.23 / Avg: 298.64 / Max: 302.97Min: 180.19 / Avg: 180.37 / Max: 180.58Min: 235.83 / Avg: 236.55 / Max: 237.39Min: 265.49 / Avg: 266.1 / Max: 267.21Min: 318.3 / Avg: 318.65 / Max: 319.09Min: 343.15 / Avg: 343.36 / Max: 343.63Min: 291.69 / Avg: 292.4 / Max: 292.84

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX306090120150SE +/- 0.30, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.25, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.21, N = 3150.10145.23149.2891.1988.1283.4774.8178.4854.7548.1636.4330.4679.03
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX306090120150Min: 149.61 / Avg: 150.1 / Max: 150.66Min: 145.16 / Avg: 145.23 / Max: 145.32Min: 149.1 / Avg: 149.28 / Max: 149.38Min: 90.81 / Avg: 91.19 / Max: 91.65Min: 87.99 / Avg: 88.12 / Max: 88.25Min: 83.38 / Avg: 83.47 / Max: 83.61Min: 74.67 / Avg: 74.81 / Max: 74.89Min: 78.07 / Avg: 78.48 / Max: 78.91Min: 54.74 / Avg: 54.75 / Max: 54.76Min: 48.06 / Avg: 48.16 / Max: 48.24Min: 36.29 / Avg: 36.43 / Max: 36.54Min: 30.06 / Avg: 30.46 / Max: 30.67Min: 78.64 / Avg: 79.03 / Max: 79.35

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX306090120150SE +/- 0.02, N = 3SE +/- 0.23, N = 3SE +/- 0.22, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3140.64121.41122.9496.9997.2096.2072.4585.6461.9954.2641.8034.5973.36
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX306090120150Min: 140.6 / Avg: 140.64 / Max: 140.67Min: 121.18 / Avg: 121.41 / Max: 121.87Min: 122.62 / Avg: 122.94 / Max: 123.36Min: 96.85 / Avg: 96.99 / Max: 97.12Min: 97.11 / Avg: 97.2 / Max: 97.29Min: 96.16 / Avg: 96.2 / Max: 96.25Min: 72.37 / Avg: 72.45 / Max: 72.49Min: 85.61 / Avg: 85.64 / Max: 85.67Min: 61.95 / Avg: 61.99 / Max: 62.01Min: 54.24 / Avg: 54.26 / Max: 54.3Min: 41.77 / Avg: 41.8 / Max: 41.83Min: 34.57 / Avg: 34.59 / Max: 34.6Min: 73.31 / Avg: 73.36 / Max: 73.39

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 BenchmarkRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 12SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 32.783.603.563.593.553.614.654.515.916.497.879.164.69MIN: 0.23 / MAX: 3.19MIN: 0.23 / MAX: 4.14MIN: 0.23 / MAX: 4.1MIN: 0.11 / MAX: 4.24MIN: 0.23 / MAX: 4.09MIN: 0.23 / MAX: 4.14MIN: 0.27 / MAX: 5.37MIN: 0.23 / MAX: 5.21MIN: 0.27 / MAX: 6.84MIN: 0.27 / MAX: 7.45MIN: 0.27 / MAX: 9.03MIN: 0.23 / MAX: 10.53MIN: 0.27 / MAX: 5.45
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215Min: 2.75 / Avg: 2.78 / Max: 2.8Min: 3.59 / Avg: 3.6 / Max: 3.6Min: 3.55 / Avg: 3.56 / Max: 3.56Min: 2.93 / Avg: 3.59 / Max: 3.7Min: 3.53 / Avg: 3.55 / Max: 3.57Min: 3.59 / Avg: 3.61 / Max: 3.62Min: 4.63 / Avg: 4.65 / Max: 4.67Min: 4.45 / Avg: 4.51 / Max: 4.55Min: 5.88 / Avg: 5.91 / Max: 5.95Min: 6.48 / Avg: 6.49 / Max: 6.5Min: 7.8 / Avg: 7.87 / Max: 7.99Min: 9.11 / Avg: 9.16 / Max: 9.21Min: 4.64 / Avg: 4.69 / Max: 4.73

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 33.304.184.144.304.234.325.635.537.257.939.5911.155.67MIN: 3.15 / MAX: 3.39MIN: 4.1 / MAX: 4.29MIN: 3.8 / MAX: 4.28MIN: 1.32 / MAX: 4.51MIN: 4.14 / MAX: 4.29MIN: 4.15 / MAX: 4.43MIN: 5.21 / MAX: 5.75MIN: 5.23 / MAX: 5.69MIN: 6.94 / MAX: 7.39MIN: 7.82 / MAX: 8.13MIN: 9.28 / MAX: 9.71MIN: 9.79 / MAX: 11.28MIN: 4.85 / MAX: 5.74
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215Min: 3.3 / Avg: 3.3 / Max: 3.31Min: 4.18 / Avg: 4.18 / Max: 4.19Min: 4.13 / Avg: 4.14 / Max: 4.16Min: 3.39 / Avg: 4.3 / Max: 4.39Min: 4.23 / Avg: 4.23 / Max: 4.24Min: 4.32 / Avg: 4.32 / Max: 4.33Min: 5.63 / Avg: 5.63 / Max: 5.64Min: 5.51 / Avg: 5.53 / Max: 5.55Min: 7.25 / Avg: 7.25 / Max: 7.25Min: 7.92 / Avg: 7.93 / Max: 7.94Min: 9.57 / Avg: 9.59 / Max: 9.6Min: 11.14 / Avg: 11.15 / Max: 11.16Min: 5.66 / Avg: 5.67 / Max: 5.67

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPURTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX400800120016002000SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 1.33, N = 3SE +/- 0.58, N = 34744904787617437569287841185134116501964892
OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPURTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX30060090012001500Min: 760 / Avg: 760.67 / Max: 762Min: 755 / Avg: 755.67 / Max: 756Min: 784 / Avg: 784.33 / Max: 785Min: 1185 / Avg: 1185.33 / Max: 1186Min: 1339 / Avg: 1341.33 / Max: 1343Min: 1648 / Avg: 1649.67 / Max: 1652Min: 1963 / Avg: 1964.33 / Max: 1967Min: 891 / Avg: 892 / Max: 893

OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPURTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX6001200180024003000SE +/- 1.33, N = 3SE +/- 1.15, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.45, N = 3SE +/- 1.33, N = 3SE +/- 1.45, N = 3SE +/- 2.00, N = 3SE +/- 2.00, N = 3SE +/- 5.90, N = 3SE +/- 1.00, N = 36587347109629039261245105915481715215126201232
OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPURTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX5001000150020002500Min: 733 / Avg: 734.33 / Max: 737Min: 708 / Avg: 710 / Max: 712Min: 961 / Avg: 961.67 / Max: 963Min: 902 / Avg: 902.67 / Max: 904Min: 923 / Avg: 925.67 / Max: 928Min: 1056 / Avg: 1058.67 / Max: 1060Min: 1545 / Avg: 1547.67 / Max: 1550Min: 1711 / Avg: 1715 / Max: 1717Min: 2147 / Avg: 2151 / Max: 2153Min: 2608 / Avg: 2619.67 / Max: 2627Min: 1231 / Avg: 1232 / Max: 1234

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX20406080100SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 2.53, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 375.0565.2264.4456.9750.6747.4236.0758.2241.9835.7124.6220.3736.63
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1428425670Min: 74.81 / Avg: 75.05 / Max: 75.23Min: 65.03 / Avg: 65.22 / Max: 65.33Min: 64.36 / Avg: 64.44 / Max: 64.49Min: 54.25 / Avg: 56.97 / Max: 92.35Min: 50.65 / Avg: 50.67 / Max: 50.68Min: 47.4 / Avg: 47.42 / Max: 47.44Min: 36.06 / Avg: 36.07 / Max: 36.09Min: 58.13 / Avg: 58.22 / Max: 58.36Min: 41.94 / Avg: 41.98 / Max: 42.03Min: 35.7 / Avg: 35.71 / Max: 35.72Min: 24.6 / Avg: 24.62 / Max: 24.64Min: 20.36 / Avg: 20.37 / Max: 20.39Min: 36.56 / Avg: 36.63 / Max: 36.73

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX510152025SE +/- 0.000, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.010, N = 3SE +/- 0.006, N = 3SE +/- 0.004, N = 3SE +/- 0.011, N = 3SE +/- 0.031, N = 3SE +/- 0.031, N = 3SE +/- 0.017, N = 35.5827.3477.3797.7207.7437.98211.0338.42011.45912.89017.39320.77811.163
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX510152025Min: 5.58 / Avg: 5.58 / Max: 5.58Min: 7.34 / Avg: 7.35 / Max: 7.35Min: 7.38 / Avg: 7.38 / Max: 7.38Min: 7.71 / Avg: 7.72 / Max: 7.73Min: 7.74 / Avg: 7.74 / Max: 7.75Min: 7.98 / Avg: 7.98 / Max: 7.99Min: 11.02 / Avg: 11.03 / Max: 11.05Min: 8.41 / Avg: 8.42 / Max: 8.43Min: 11.45 / Avg: 11.46 / Max: 11.47Min: 12.88 / Avg: 12.89 / Max: 12.91Min: 17.35 / Avg: 17.39 / Max: 17.45Min: 20.74 / Avg: 20.78 / Max: 20.84Min: 11.14 / Avg: 11.16 / Max: 11.2

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1224364860SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.38, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 318.3823.2323.4624.5224.9025.6933.3725.6634.0137.2345.9952.8633.67
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1122334455Min: 18.37 / Avg: 18.38 / Max: 18.39Min: 23.22 / Avg: 23.23 / Max: 23.23Min: 23.46 / Avg: 23.46 / Max: 23.47Min: 24.5 / Avg: 24.52 / Max: 24.55Min: 24.89 / Avg: 24.9 / Max: 24.91Min: 25.68 / Avg: 25.69 / Max: 25.7Min: 33.35 / Avg: 33.37 / Max: 33.4Min: 25.44 / Avg: 25.66 / Max: 25.77Min: 33.98 / Avg: 34.01 / Max: 34.04Min: 37.22 / Avg: 37.23 / Max: 37.25Min: 45.24 / Avg: 45.99 / Max: 46.4Min: 52.75 / Avg: 52.86 / Max: 52.93Min: 33.64 / Avg: 33.67 / Max: 33.7

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX20406080100SE +/- 0.27, N = 3SE +/- 0.35, N = 3SE +/- 0.39, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.19, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.26, N = 385.6575.8475.1163.6359.5454.2044.5372.2053.9950.0334.4029.6743.33
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1632486480Min: 85.11 / Avg: 85.64 / Max: 85.98Min: 75.16 / Avg: 75.84 / Max: 76.3Min: 74.36 / Avg: 75.11 / Max: 75.69Min: 63.23 / Avg: 63.63 / Max: 63.84Min: 58.9 / Avg: 59.53 / Max: 59.95Min: 53.85 / Avg: 54.2 / Max: 54.47Min: 44.25 / Avg: 44.53 / Max: 44.7Min: 72.11 / Avg: 72.2 / Max: 72.25Min: 53.72 / Avg: 53.99 / Max: 54.23Min: 49.89 / Avg: 50.03 / Max: 50.11Min: 34.24 / Avg: 34.4 / Max: 34.54Min: 29.57 / Avg: 29.67 / Max: 29.73Min: 42.85 / Avg: 43.33 / Max: 43.75

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX20406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 374.5063.9264.9551.2751.6850.6638.4944.3531.9228.9922.1818.4738.74
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CUDARTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1428425670Min: 74.45 / Avg: 74.5 / Max: 74.53Min: 63.86 / Avg: 63.92 / Max: 63.96Min: 64.92 / Avg: 64.95 / Max: 64.97Min: 51.25 / Avg: 51.27 / Max: 51.3Min: 51.59 / Avg: 51.68 / Max: 51.73Min: 50.59 / Avg: 50.66 / Max: 50.7Min: 38.46 / Avg: 38.49 / Max: 38.51Min: 44.27 / Avg: 44.35 / Max: 44.4Min: 31.89 / Avg: 31.92 / Max: 31.94Min: 28.9 / Avg: 28.99 / Max: 29.08Min: 22.11 / Avg: 22.18 / Max: 22.24Min: 18.4 / Avg: 18.47 / Max: 18.54Min: 38.69 / Avg: 38.74 / Max: 38.78

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX80160240320400SE +/- 0.53, N = 3SE +/- 0.33, N = 3SE +/- 1.78, N = 3SE +/- 0.02, N = 3SE +/- 0.24, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 3SE +/- 0.83, N = 3SE +/- 0.28, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 3SE +/- 1.08, N = 3349.26309.02303.67263.37234.44215.02155.57377.59263.99223.67149.53122.90152.761. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX70140210280350Min: 348.39 / Avg: 349.26 / Max: 350.22Min: 308.5 / Avg: 309.02 / Max: 309.63Min: 301.89 / Avg: 303.67 / Max: 307.23Min: 263.33 / Avg: 263.37 / Max: 263.41Min: 234.07 / Avg: 234.44 / Max: 234.89Min: 214.86 / Avg: 215.02 / Max: 215.26Min: 155.24 / Avg: 155.57 / Max: 155.9Min: 377.03 / Avg: 377.59 / Max: 377.95Min: 262.57 / Avg: 263.99 / Max: 265.44Min: 223.11 / Avg: 223.67 / Max: 223.96Min: 149.06 / Avg: 149.53 / Max: 149.85Min: 122.76 / Avg: 122.9 / Max: 123.05Min: 150.89 / Avg: 152.75 / Max: 154.631. (CXX) g++ options: -O3 -pthread

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX140280420560700SE +/- 0.03, N = 3SE +/- 0.48, N = 3SE +/- 0.70, N = 3SE +/- 0.01, N = 3SE +/- 0.92, N = 3SE +/- 0.03, N = 3SE +/- 1.36, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.68, N = 3SE +/- 0.77, N = 3SE +/- 4.52, N = 3231.53263.47267.84308.54345.97376.32522.28209.56303.90360.44537.24656.28515.021. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX120240360480600Min: 231.47 / Avg: 231.53 / Max: 231.59Min: 262.62 / Avg: 263.47 / Max: 264.28Min: 267.13 / Avg: 267.84 / Max: 269.24Min: 308.53 / Avg: 308.54 / Max: 308.55Min: 344.14 / Avg: 345.97 / Max: 346.92Min: 376.27 / Avg: 376.32 / Max: 376.38Min: 520.91 / Avg: 522.28 / Max: 524.99Min: 209.48 / Avg: 209.56 / Max: 209.63Min: 303.89 / Avg: 303.9 / Max: 303.91Min: 360.31 / Avg: 360.44 / Max: 360.67Min: 535.88 / Avg: 537.24 / Max: 537.92Min: 654.74 / Avg: 656.28 / Max: 657.15Min: 506.35 / Avg: 515.02 / Max: 521.561. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 2.61, N = 15SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 336.9230.9731.2528.5226.5825.7419.5224.3817.8216.1011.649.7219.94
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX816243240Min: 36.91 / Avg: 36.92 / Max: 36.93Min: 30.95 / Avg: 30.97 / Max: 30.99Min: 31.21 / Avg: 31.25 / Max: 31.28Min: 25.85 / Avg: 28.52 / Max: 65.07Min: 26.55 / Avg: 26.58 / Max: 26.62Min: 25.72 / Avg: 25.74 / Max: 25.78Min: 19.46 / Avg: 19.52 / Max: 19.62Min: 24.35 / Avg: 24.38 / Max: 24.44Min: 17.79 / Avg: 17.82 / Max: 17.84Min: 16.08 / Avg: 16.1 / Max: 16.13Min: 11.62 / Avg: 11.64 / Max: 11.69Min: 9.69 / Avg: 9.72 / Max: 9.77Min: 19.93 / Avg: 19.94 / Max: 19.96

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 2080RTX 2080 SUPERRTX 3060RTX 3080RTX 3090TITAN RTX130260390520650SE +/- 8.15, N = 4SE +/- 4.50, N = 23243541944926004721. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 2080RTX 2080 SUPERRTX 3060RTX 3080RTX 3090TITAN RTX110220330440550Min: 475 / Avg: 491.5 / Max: 506Min: 467 / Avg: 471.5 / Max: 4761. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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 AtomsRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX0.04030.08060.12090.16120.2015SE +/- 0.00117, N = 4SE +/- 0.00089, N = 5SE +/- 0.00168, N = 5SE +/- 0.00086, N = 5SE +/- 0.00043, N = 5SE +/- 0.00158, N = 5SE +/- 0.00059, N = 5SE +/- 0.00096, N = 4SE +/- 0.00032, N = 5SE +/- 0.00122, N = 8SE +/- 0.00167, N = 15SE +/- 0.00109, N = 15SE +/- 0.00052, N = 50.179140.166660.161450.151400.148330.146140.144080.162810.139040.141510.131380.135500.16623
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 AtomsRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX12345Min: 0.18 / Avg: 0.18 / Max: 0.18Min: 0.16 / Avg: 0.17 / Max: 0.17Min: 0.16 / Avg: 0.16 / Max: 0.17Min: 0.15 / Avg: 0.15 / Max: 0.15Min: 0.15 / Avg: 0.15 / Max: 0.15Min: 0.14 / Avg: 0.15 / Max: 0.15Min: 0.14 / Avg: 0.14 / Max: 0.15Min: 0.16 / Avg: 0.16 / Max: 0.17Min: 0.14 / Avg: 0.14 / Max: 0.14Min: 0.14 / Avg: 0.14 / Max: 0.14Min: 0.13 / Avg: 0.13 / Max: 0.14Min: 0.13 / Avg: 0.14 / Max: 0.14Min: 0.17 / Avg: 0.17 / Max: 0.17

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX160320480640800SE +/- 0.33, N = 3SE +/- 2.50, N = 42913883883863884275183253993966307225201. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650Min: 385 / Avg: 385.67 / Max: 386Min: 317 / Avg: 324.5 / Max: 3271. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX140280420560700SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 1.53, N = 3SE +/- 0.33, N = 3SE +/- 6.17, N = 6SE +/- 1.00, N = 33084034014024044405213283983975926505161. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550Min: 401 / Avg: 401.33 / Max: 402Min: 400 / Avg: 401.67 / Max: 403Min: 439 / Avg: 440.33 / Max: 441Min: 520 / Avg: 520.67 / Max: 521Min: 325 / Avg: 328 / Max: 330Min: 397 / Avg: 397.33 / Max: 398Min: 572 / Avg: 592 / Max: 602Min: 649 / Avg: 650 / Max: 6521. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650SE +/- 0.33, N = 3SE +/- 3.75, N = 4SE +/- 5.54, N = 6SE +/- 0.58, N = 32793683673663704044783113613655476074771. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550Min: 365 / Avg: 365.67 / Max: 366Min: 300 / Avg: 311.25 / Max: 315Min: 528 / Avg: 546.5 / Max: 556Min: 606 / Avg: 607 / Max: 6081. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 4.00, N = 4SE +/- 3.40, N = 6SE +/- 0.33, N = 3SE +/- 1.15, N = 32523283213253163284053023573574685043891. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX90180270360450Min: 328 / Avg: 328.33 / Max: 329Min: 321 / Avg: 321.33 / Max: 322Min: 324 / Avg: 324.67 / Max: 325Min: 316 / Avg: 316.33 / Max: 317Min: 405 / Avg: 405.33 / Max: 406Min: 290 / Avg: 302 / Max: 306Min: 456 / Avg: 467.67 / Max: 474Min: 503 / Avg: 503.67 / Max: 504Min: 387 / Avg: 389 / Max: 3911. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX80160240320400SE +/- 0.33, N = 3SE +/- 1.00, N = 3SE +/- 3.42, N = 4SE +/- 0.89, N = 6SE +/- 0.33, N = 32122622602602502503222893243253733753051. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX70140210280350Min: 262 / Avg: 262.33 / Max: 263Min: 258 / Avg: 260 / Max: 261Min: 279 / Avg: 289.25 / Max: 293Min: 369 / Avg: 372.5 / Max: 375Min: 374 / Avg: 374.67 / Max: 3751. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650SE +/- 1.15, N = 3SE +/- 1.00, N = 3SE +/- 1.00, N = 3SE +/- 1.20, N = 3SE +/- 3.67, N = 3SE +/- 1.00, N = 3SE +/- 3.40, N = 6SE +/- 1.33, N = 3SE +/- 8.00, N = 22472502933293574811992923404975994561. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550Min: 248 / Avg: 250 / Max: 252Min: 327 / Avg: 329 / Max: 330Min: 355 / Avg: 357 / Max: 358Min: 479 / Avg: 481.33 / Max: 483Min: 192 / Avg: 199.33 / Max: 203Min: 290 / Avg: 292 / Max: 293Min: 486 / Avg: 496.67 / Max: 503Min: 598 / Avg: 599.33 / Max: 602Min: 448 / Avg: 456 / Max: 4641. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX80160240320400SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 3.18, N = 3SE +/- 3.34, N = 4SE +/- 3.42, N = 6SE +/- 1.20, N = 3SE +/- 1.86, N = 32182762712812792883082712902933503662961. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX70140210280350Min: 275 / Avg: 276.33 / Max: 277Min: 270 / Avg: 270.67 / Max: 272Min: 280 / Avg: 281 / Max: 282Min: 302 / Avg: 308.33 / Max: 312Min: 261 / Avg: 271 / Max: 275Min: 338 / Avg: 349.67 / Max: 357Min: 364 / Avg: 365.67 / Max: 368Min: 292 / Avg: 295.67 / Max: 2981. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650SE +/- 1.00, N = 2SE +/- 1.15, N = 3SE +/- 1.67, N = 3SE +/- 0.67, N = 3SE +/- 2.00, N = 2SE +/- 1.33, N = 3SE +/- 5.50, N = 2SE +/- 3.18, N = 6SE +/- 1.33, N = 3SE +/- 2.65, N = 32172462522893243524721992923415016034681. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550Min: 245 / Avg: 246 / Max: 247Min: 250 / Avg: 252 / Max: 254Min: 287 / Avg: 288.67 / Max: 292Min: 323 / Avg: 324.33 / Max: 325Min: 350 / Avg: 352 / Max: 354Min: 469 / Avg: 471.67 / Max: 473Min: 193 / Avg: 198.5 / Max: 204Min: 490 / Avg: 500.83 / Max: 507Min: 602 / Avg: 603.33 / Max: 606Min: 463 / Avg: 468 / Max: 4721. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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 PrismRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX612182430SE +/- 0.03, N = 3SE +/- 0.09, N = 4SE +/- 0.01, N = 4SE +/- 0.29, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 4SE +/- 0.04, N = 4SE +/- 0.04, N = 5SE +/- 0.11, N = 5SE +/- 0.10, N = 3SE +/- 0.04, N = 6SE +/- 0.05, N = 47.9111.2310.979.869.299.2412.3413.2617.7218.9222.3126.3312.92MIN: 6.97 / MAX: 8.2MIN: 5.85 / MAX: 11.69MIN: 10.17 / MAX: 11.29MIN: 3.83 / MAX: 10.57MIN: 8.89 / MAX: 9.66MIN: 8.32 / MAX: 9.68MIN: 10.56 / MAX: 12.86MIN: 12.32 / MAX: 13.86MIN: 16.31 / MAX: 18.32MIN: 17.65 / MAX: 20.07MIN: 20.53 / MAX: 23.39MIN: 23.57 / MAX: 27.71MIN: 11.38 / MAX: 13.49
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX612182430Min: 7.85 / Avg: 7.91 / Max: 7.95Min: 10.95 / Avg: 11.23 / Max: 11.34Min: 10.94 / Avg: 10.97 / Max: 10.99Min: 6.69 / Avg: 9.86 / Max: 10.2Min: 9.29 / Avg: 9.29 / Max: 9.3Min: 9.23 / Avg: 9.24 / Max: 9.25Min: 12.25 / Avg: 12.34 / Max: 12.42Min: 13.19 / Avg: 13.26 / Max: 13.35Min: 17.63 / Avg: 17.72 / Max: 17.79Min: 18.55 / Avg: 18.92 / Max: 19.24Min: 22.13 / Avg: 22.31 / Max: 22.49Min: 26.25 / Avg: 26.33 / Max: 26.46Min: 12.77 / Avg: 12.92 / Max: 12.98

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 1.15, N = 3SE +/- 2.00, N = 3SE +/- 0.67, N = 3SE +/- 2.00, N = 2SE +/- 1.33, N = 3SE +/- 3.09, N = 4SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 5.20, N = 6SE +/- 1.86, N = 3SE +/- 2.73, N = 32182482532903263574752012923414946014741. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550Min: 218 / Avg: 218.33 / Max: 219Min: 246 / Avg: 247.67 / Max: 249Min: 251 / Avg: 253 / Max: 255Min: 288 / Avg: 290 / Max: 294Min: 325 / Avg: 326.33 / Max: 327Min: 355 / Avg: 357 / Max: 359Min: 472 / Avg: 474.67 / Max: 476Min: 192 / Avg: 201.25 / Max: 205Min: 291 / Avg: 291.67 / Max: 293Min: 340 / Avg: 341.33 / Max: 343Min: 477 / Avg: 494.33 / Max: 505Min: 599 / Avg: 601.33 / Max: 605Min: 469 / Avg: 474.33 / Max: 4781. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX5001000150020002500SE +/- 1.41, N = 3SE +/- 0.63, N = 4SE +/- 3.12, N = 3SE +/- 1.35, N = 3SE +/- 3.05, N = 3SE +/- 1.33, N = 3SE +/- 3.03, N = 3SE +/- 0.91, N = 4SE +/- 3.31, N = 4SE +/- 6.27, N = 4SE +/- 6.23, N = 3SE +/- 5.35, N = 3SE +/- 4.50, N = 31035.421106.301064.281133.931114.901165.161187.961256.432119.252121.562204.202237.771169.721. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX400800120016002000Min: 1032.61 / Avg: 1035.42 / Max: 1036.96Min: 1105 / Avg: 1106.3 / Max: 1108.02Min: 1059.64 / Avg: 1064.28 / Max: 1070.22Min: 1131.64 / Avg: 1133.93 / Max: 1136.3Min: 1110.98 / Avg: 1114.9 / Max: 1120.9Min: 1162.5 / Avg: 1165.16 / Max: 1166.6Min: 1182.04 / Avg: 1187.96 / Max: 1192Min: 1255.14 / Avg: 1256.43 / Max: 1259.01Min: 2114.06 / Avg: 2119.25 / Max: 2128.52Min: 2110.36 / Avg: 2121.56 / Max: 2133.51Min: 2196.92 / Avg: 2204.2 / Max: 2216.59Min: 2227.08 / Avg: 2237.77 / Max: 2243.35Min: 1162.04 / Avg: 1169.72 / Max: 1177.621. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215SE +/- 0.046, N = 4SE +/- 0.050, N = 4SE +/- 0.034, N = 5SE +/- 0.084, N = 15SE +/- 0.021, N = 5SE +/- 0.040, N = 5SE +/- 0.085, N = 15SE +/- 0.070, N = 5SE +/- 0.053, N = 5SE +/- 0.051, N = 5SE +/- 0.071, N = 3SE +/- 0.034, N = 7SE +/- 0.044, N = 612.76511.51311.37310.4199.4428.9267.86011.1828.8468.4006.4285.8567.557
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX48121620Min: 12.7 / Avg: 12.76 / Max: 12.9Min: 11.43 / Avg: 11.51 / Max: 11.65Min: 11.27 / Avg: 11.37 / Max: 11.48Min: 10.11 / Avg: 10.42 / Max: 10.98Min: 9.4 / Avg: 9.44 / Max: 9.51Min: 8.86 / Avg: 8.93 / Max: 9.06Min: 7.62 / Avg: 7.86 / Max: 8.7Min: 11.06 / Avg: 11.18 / Max: 11.44Min: 8.76 / Avg: 8.85 / Max: 9.05Min: 8.34 / Avg: 8.4 / Max: 8.6Min: 6.35 / Avg: 6.43 / Max: 6.57Min: 5.78 / Avg: 5.86 / Max: 6.04Min: 7.47 / Avg: 7.56 / Max: 7.73

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX612182430SE +/- 0.040, N = 4SE +/- 0.031, N = 5SE +/- 0.025, N = 5SE +/- 0.016, N = 5SE +/- 0.017, N = 5SE +/- 0.013, N = 5SE +/- 0.021, N = 5SE +/- 0.096, N = 5SE +/- 0.010, N = 5SE +/- 0.004, N = 5SE +/- 0.136, N = 3SE +/- 0.010, N = 5SE +/- 0.022, N = 527.22222.24722.28419.50118.99417.43614.75823.35217.66917.51611.4049.27514.1821. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX612182430Min: 27.13 / Avg: 27.22 / Max: 27.3Min: 22.16 / Avg: 22.25 / Max: 22.35Min: 22.2 / Avg: 22.28 / Max: 22.34Min: 19.45 / Avg: 19.5 / Max: 19.55Min: 18.96 / Avg: 18.99 / Max: 19.04Min: 17.4 / Avg: 17.44 / Max: 17.47Min: 14.68 / Avg: 14.76 / Max: 14.81Min: 23.16 / Avg: 23.35 / Max: 23.64Min: 17.64 / Avg: 17.67 / Max: 17.7Min: 17.51 / Avg: 17.52 / Max: 17.53Min: 11.27 / Avg: 11.4 / Max: 11.68Min: 9.25 / Avg: 9.28 / Max: 9.3Min: 14.12 / Avg: 14.18 / Max: 14.261. (CXX) g++ options: -O3 -pthread

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: HighestRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 30903691215SE +/- 0.009, N = 5SE +/- 0.007, N = 5SE +/- 0.021, N = 6SE +/- 0.074, N = 15SE +/- 0.011, N = 6SE +/- 0.011, N = 7SE +/- 0.064, N = 15SE +/- 0.085, N = 8SE +/- 0.014, N = 6SE +/- 0.012, N = 7SE +/- 0.026, N = 3SE +/- 0.010, N = 89.4018.4428.3607.5236.8286.2275.1389.7346.7906.0304.5234.0001. (CXX) g++ options: -O3 -O2 -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: HighestRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 30903691215Min: 9.38 / Avg: 9.4 / Max: 9.43Min: 8.43 / Avg: 8.44 / Max: 8.47Min: 8.27 / Avg: 8.36 / Max: 8.4Min: 7.33 / Avg: 7.52 / Max: 8.09Min: 6.8 / Avg: 6.83 / Max: 6.87Min: 6.2 / Avg: 6.23 / Max: 6.29Min: 5 / Avg: 5.14 / Max: 5.77Min: 9.57 / Avg: 9.73 / Max: 10.2Min: 6.73 / Avg: 6.79 / Max: 6.83Min: 6 / Avg: 6.03 / Max: 6.07Min: 4.47 / Avg: 4.52 / Max: 4.57Min: 3.97 / Avg: 4 / Max: 4.071. (CXX) g++ options: -O3 -O2 -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: HighestRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX246810SE +/- 0.007, N = 6SE +/- 0.007, N = 7SE +/- 0.010, N = 7SE +/- 0.070, N = 15SE +/- 0.013, N = 7SE +/- 0.008, N = 8SE +/- 0.042, N = 15SE +/- 0.011, N = 6SE +/- 0.010, N = 7SE +/- 0.009, N = 8SE +/- 0.018, N = 3SE +/- 0.008, N = 9SE +/- 1.561, N = 156.7836.0815.9395.6364.9714.6113.8516.4494.9744.2933.3453.0166.8751. (CXX) g++ options: -O3 -O2 -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: HighestRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215Min: 6.77 / Avg: 6.78 / Max: 6.8Min: 6.07 / Avg: 6.08 / Max: 6.11Min: 5.9 / Avg: 5.94 / Max: 5.97Min: 5.43 / Avg: 5.64 / Max: 6.1Min: 4.93 / Avg: 4.97 / Max: 5.03Min: 4.57 / Avg: 4.61 / Max: 4.64Min: 3.77 / Avg: 3.85 / Max: 4.43Min: 6.42 / Avg: 6.45 / Max: 6.5Min: 4.94 / Avg: 4.97 / Max: 5Min: 4.26 / Avg: 4.29 / Max: 4.33Min: 3.31 / Avg: 3.35 / Max: 3.37Min: 3 / Avg: 3.02 / Max: 3.07Min: 3.7 / Avg: 6.88 / Max: 25.171. (CXX) g++ options: -O3 -O2 -lpthread -ldl

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 FilterRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215SE +/- 0.011, N = 5SE +/- 0.008, N = 6SE +/- 0.024, N = 6SE +/- 0.045, N = 6SE +/- 0.011, N = 7SE +/- 0.010, N = 7SE +/- 0.010, N = 8SE +/- 0.024, N = 5SE +/- 0.022, N = 6SE +/- 0.011, N = 7SE +/- 0.026, N = 3SE +/- 0.007, N = 8SE +/- 0.021, N = 88.9897.9917.8907.0186.2575.7844.4649.7636.9685.9794.3863.7674.7021. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3691215Min: 8.96 / Avg: 8.99 / Max: 9.02Min: 7.96 / Avg: 7.99 / Max: 8.01Min: 7.83 / Avg: 7.89 / Max: 7.99Min: 6.94 / Avg: 7.02 / Max: 7.24Min: 6.21 / Avg: 6.26 / Max: 6.29Min: 5.75 / Avg: 5.78 / Max: 5.83Min: 4.42 / Avg: 4.46 / Max: 4.5Min: 9.69 / Avg: 9.76 / Max: 9.82Min: 6.91 / Avg: 6.97 / Max: 7.05Min: 5.94 / Avg: 5.98 / Max: 6.03Min: 4.34 / Avg: 4.39 / Max: 4.42Min: 3.74 / Avg: 3.77 / Max: 3.79Min: 4.63 / Avg: 4.7 / Max: 4.771. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX600M1200M1800M2400M3000MSE +/- 850690.00, N = 7SE +/- 1191123.63, N = 7SE +/- 2076381.60, N = 7SE +/- 2098266.21, N = 7SE +/- 3482228.94, N = 7SE +/- 1721354.47, N = 7SE +/- 1806187.40, N = 7SE +/- 1072539.11, N = 7SE +/- 1114987.57, N = 7SE +/- 1513813.94, N = 7SE +/- 2292257.50, N = 3SE +/- 3339151.39, N = 7SE +/- 2223773.83, N = 7105117142911863857141217042857142097142915621857141735685714224774285797897142914121285711665185714239856666728654428572249342857
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX500M1000M1500M2000M2500MMin: 1048300000 / Avg: 1051171428.57 / Max: 1053800000Min: 1182600000 / Avg: 1186385714.29 / Max: 1191700000Min: 1211400000 / Avg: 1217042857.14 / Max: 1225400000Min: 1414400000 / Avg: 1420971428.57 / Max: 1428500000Min: 1553100000 / Avg: 1562185714.29 / Max: 1577500000Min: 1730100000 / Avg: 1735685714.29 / Max: 1742900000Min: 2241800000 / Avg: 2247742857.14 / Max: 2254700000Min: 975600000 / Avg: 978971428.57 / Max: 983500000Min: 1407800000 / Avg: 1412128571.43 / Max: 1416500000Min: 1659200000 / Avg: 1665185714.29 / Max: 1670100000Min: 2394000000 / Avg: 2398566666.67 / Max: 2401200000Min: 2855000000 / Avg: 2865442857.14 / Max: 2880800000Min: 2238800000 / Avg: 2249342857.14 / Max: 2258000000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX5000M10000M15000M20000M25000MSE +/- 2725528.10, N = 7SE +/- 7264539.72, N = 7SE +/- 4823948.20, N = 7SE +/- 3493521.70, N = 7SE +/- 13573045.02, N = 7SE +/- 14364688.85, N = 7SE +/- 13351911.38, N = 7SE +/- 4409613.80, N = 7SE +/- 8126637.98, N = 7SE +/- 6748005.50, N = 7SE +/- 6568950.53, N = 3SE +/- 10394772.36, N = 7SE +/- 10849872.25, N = 78233357143930708571495119000001110704285712219442857135544000001768538571477133428571109217142913107471429189346333332267967142917755985714
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX4000M8000M12000M16000M20000MMin: 8222000000 / Avg: 8233357142.86 / Max: 8243500000Min: 9286200000 / Avg: 9307085714.29 / Max: 9332400000Min: 9496200000 / Avg: 9511900000 / Max: 9527500000Min: 11097600000 / Avg: 11107042857.14 / Max: 11117900000Min: 12179200000 / Avg: 12219442857.14 / Max: 12280700000Min: 13516300000 / Avg: 13554400000 / Max: 13612300000Min: 17651600000 / Avg: 17685385714.29 / Max: 17736700000Min: 7696800000 / Avg: 7713342857.14 / Max: 7733000000Min: 11065400000 / Avg: 11092171428.57 / Max: 11127800000Min: 13073500000 / Avg: 13107471428.57 / Max: 13124700000Min: 18925900000 / Avg: 18934633333.33 / Max: 18947500000Min: 22643000000 / Avg: 22679671428.57 / Max: 22721600000Min: 17717100000 / Avg: 17755985714.29 / Max: 17793800000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX14000M28000M42000M56000M70000MSE +/- 15994429.30, N = 7SE +/- 20426310.23, N = 7SE +/- 31650906.21, N = 7SE +/- 10209186.21, N = 7SE +/- 63739890.76, N = 7SE +/- 16181895.49, N = 7SE +/- 56534306.60, N = 7SE +/- 16702105.86, N = 7SE +/- 11341315.72, N = 7SE +/- 30034122.32, N = 7SE +/- 55820277.08, N = 3SE +/- 37493084.17, N = 7SE +/- 49932907.37, N = 725867371429291733285712990632857135096728571385484714294285754285755186314286228292714293291898571438641357143554587000006666884285755554600000
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX12000M24000M36000M48000M60000MMin: 25817200000 / Avg: 25867371428.57 / Max: 25947300000Min: 29087700000 / Avg: 29173328571.43 / Max: 29231700000Min: 29770800000 / Avg: 29906328571.43 / Max: 29975300000Min: 35064800000 / Avg: 35096728571.43 / Max: 35140900000Min: 38346000000 / Avg: 38548471428.57 / Max: 38768100000Min: 42792100000 / Avg: 42857542857.14 / Max: 42926000000Min: 54982100000 / Avg: 55186314285.71 / Max: 55371500000Min: 22766800000 / Avg: 22829271428.57 / Max: 22880400000Min: 32873800000 / Avg: 32918985714.29 / Max: 32962500000Min: 38526700000 / Avg: 38641357142.86 / Max: 38749100000Min: 55347200000 / Avg: 55458700000 / Max: 55519300000Min: 66547500000 / Avg: 66668842857.14 / Max: 66850000000Min: 55389500000 / Avg: 55554600000 / Max: 55720300000

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1.31672.63343.95015.26686.5835SE +/- 0.007, N = 7SE +/- 0.005, N = 7SE +/- 0.012, N = 7SE +/- 0.034, N = 7SE +/- 0.006, N = 8SE +/- 0.005, N = 8SE +/- 0.030, N = 8SE +/- 0.006, N = 7SE +/- 0.056, N = 15SE +/- 0.003, N = 8SE +/- 0.006, N = 3SE +/- 0.006, N = 9SE +/- 0.011, N = 85.8525.3825.3734.8904.6724.4373.9655.2594.5414.3073.6203.4514.013
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX246810Min: 5.83 / Avg: 5.85 / Max: 5.87Min: 5.37 / Avg: 5.38 / Max: 5.41Min: 5.34 / Avg: 5.37 / Max: 5.43Min: 4.83 / Avg: 4.89 / Max: 5.07Min: 4.65 / Avg: 4.67 / Max: 4.7Min: 4.42 / Avg: 4.44 / Max: 4.46Min: 3.88 / Avg: 3.97 / Max: 4.11Min: 5.24 / Avg: 5.26 / Max: 5.28Min: 4.46 / Avg: 4.54 / Max: 5.32Min: 4.29 / Avg: 4.31 / Max: 4.32Min: 3.61 / Avg: 3.62 / Max: 3.63Min: 3.41 / Avg: 3.45 / Max: 3.47Min: 3.98 / Avg: 4.01 / Max: 4.07

cl-mem

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

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX2004006008001000SE +/- 0.09, N = 7SE +/- 0.10, N = 8SE +/- 0.09, N = 8SE +/- 0.08, N = 8SE +/- 0.10, N = 8SE +/- 0.10, N = 8SE +/- 0.11, N = 8SE +/- 1.48, N = 7SE +/- 0.17, N = 8SE +/- 0.18, N = 8SE +/- 5.79, N = 8SE +/- 0.17, N = 9SE +/- 0.45, N = 8297.4396.9396.8396.8396.8437.5545.6315.8393.1393.1666.0825.6545.31. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX150300450600750Min: 297.1 / Avg: 297.36 / Max: 297.6Min: 396.6 / Avg: 396.86 / Max: 397.2Min: 396.5 / Avg: 396.76 / Max: 397.1Min: 396.5 / Avg: 396.75 / Max: 397Min: 396.5 / Avg: 396.83 / Max: 397.1Min: 437.2 / Avg: 437.45 / Max: 437.8Min: 545.1 / Avg: 545.64 / Max: 546Min: 308 / Avg: 315.83 / Max: 318.3Min: 392.6 / Avg: 393.06 / Max: 393.6Min: 392.5 / Avg: 393.13 / Max: 393.7Min: 625.5 / Avg: 665.96 / Max: 672.8Min: 824.9 / Avg: 825.63 / Max: 826.6Min: 542.6 / Avg: 545.31 / Max: 5471. (CC) gcc options: -O2 -flto -lOpenCL

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX200K400K600K800K1000KSE +/- 318.72, N = 8SE +/- 666.62, N = 9SE +/- 498.01, N = 8SE +/- 4003.26, N = 7SE +/- 526.25, N = 8SE +/- 3956.17, N = 15SE +/- 586.68, N = 8SE +/- 912.89, N = 8SE +/- 67.41, N = 10SE +/- 360.86, N = 10SE +/- 7188.96, N = 3SE +/- 976.83, N = 8SE +/- 1486.48, N = 8310388349878357513426357462213535927656675300188428390503400710567850275654338
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX150K300K450K600K750KMin: 309500 / Avg: 310387.5 / Max: 311800Min: 346900 / Avg: 349877.78 / Max: 354000Min: 355400 / Avg: 357512.5 / Max: 359200Min: 420900 / Avg: 426357.14 / Max: 450300Min: 460200 / Avg: 462212.5 / Max: 463700Min: 510300 / Avg: 535926.67 / Max: 547000Min: 654900 / Avg: 656675 / Max: 659200Min: 296100 / Avg: 300187.5 / Max: 302600Min: 428100 / Avg: 428390 / Max: 428900Min: 501000 / Avg: 503400 / Max: 505000Min: 698000 / Avg: 710566.67 / Max: 722900Min: 847500 / Avg: 850275 / Max: 854700Min: 647300 / Avg: 654337.5 / Max: 659300

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: WriteRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX160320480640800SE +/- 0.30, N = 7SE +/- 0.22, N = 8SE +/- 0.21, N = 8SE +/- 0.22, N = 8SE +/- 0.51, N = 8SE +/- 0.52, N = 8SE +/- 0.46, N = 8SE +/- 1.71, N = 7SE +/- 0.10, N = 8SE +/- 0.10, N = 8SE +/- 0.36, N = 3SE +/- 0.42, N = 9SE +/- 0.86, N = 8251.7335.1321.8318.7331.2348.6449.5296.4383.3379.8641.3741.1476.81. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX130260390520650Min: 250.9 / Avg: 251.7 / Max: 252.9Min: 334.2 / Avg: 335.08 / Max: 335.9Min: 321.1 / Avg: 321.83 / Max: 322.7Min: 317.8 / Avg: 318.69 / Max: 319.4Min: 328.9 / Avg: 331.23 / Max: 333.3Min: 346.7 / Avg: 348.56 / Max: 350.7Min: 448 / Avg: 449.45 / Max: 451.1Min: 291.2 / Avg: 296.39 / Max: 300.6Min: 383.1 / Avg: 383.33 / Max: 383.9Min: 379.5 / Avg: 379.78 / Max: 380.4Min: 640.8 / Avg: 641.3 / Max: 642Min: 739.5 / Avg: 741.14 / Max: 743.3Min: 472.8 / Avg: 476.83 / Max: 480.31. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX80160240320400SE +/- 0.05, N = 7SE +/- 0.15, N = 8SE +/- 0.15, N = 8SE +/- 0.19, N = 7SE +/- 0.14, N = 8SE +/- 0.14, N = 8SE +/- 0.08, N = 8SE +/- 1.32, N = 7SE +/- 0.22, N = 8SE +/- 0.16, N = 8SE +/- 0.20, N = 3SE +/- 0.06, N = 9SE +/- 0.12, N = 8239.3286.9283.4290.8290.1300.6321.6266.7297.0296.9354.5363.4306.31. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX60120180240300Min: 239.1 / Avg: 239.26 / Max: 239.4Min: 286.5 / Avg: 286.94 / Max: 287.5Min: 282.5 / Avg: 283.43 / Max: 283.9Min: 290.3 / Avg: 290.83 / Max: 291.6Min: 289.3 / Avg: 290.11 / Max: 290.4Min: 299.8 / Avg: 300.64 / Max: 301Min: 321.3 / Avg: 321.56 / Max: 321.8Min: 262.7 / Avg: 266.7 / Max: 270.6Min: 296.2 / Avg: 297.01 / Max: 297.9Min: 296.2 / Avg: 296.93 / Max: 297.6Min: 354.1 / Avg: 354.5 / Max: 354.7Min: 363.2 / Avg: 363.43 / Max: 363.7Min: 305.9 / Avg: 306.34 / Max: 3071. (CC) gcc options: -O2 -flto -lOpenCL

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX2K4K6K8K10KSE +/- 0.34, N = 8SE +/- 7.32, N = 9SE +/- 7.35, N = 9SE +/- 1.92, N = 9SE +/- 1.77, N = 9SE +/- 1.79, N = 10SE +/- 12.95, N = 10SE +/- 3.66, N = 9SE +/- 2.73, N = 10SE +/- 20.37, N = 10SE +/- 62.64, N = 6SE +/- 29.12, N = 11SE +/- 38.91, N = 102451.993046.363114.473319.273349.363725.024831.942772.303438.493775.876181.238144.814975.621. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX14002800420056007000Min: 2450.14 / Avg: 2451.99 / Max: 2453.13Min: 3015.78 / Avg: 3046.36 / Max: 3088.87Min: 3093.5 / Avg: 3114.47 / Max: 3156.56Min: 3306.91 / Avg: 3319.27 / Max: 3324.97Min: 3339.77 / Avg: 3349.36 / Max: 3358.99Min: 3714.66 / Avg: 3725.02 / Max: 3734.66Min: 4796.21 / Avg: 4831.94 / Max: 4917.63Min: 2752.92 / Avg: 2772.3 / Max: 2795.21Min: 3424.77 / Avg: 3438.49 / Max: 3451.1Min: 3681.41 / Avg: 3775.87 / Max: 3908.73Min: 5892.13 / Avg: 6181.23 / Max: 6319.14Min: 7996.28 / Avg: 8144.81 / Max: 8324.39Min: 4829.13 / Avg: 4975.62 / Max: 5262.491. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX200K400K600K800K1000KSE +/- 407.84, N = 11SE +/- 442.89, N = 11SE +/- 444.64, N = 11SE +/- 1953.37, N = 10SE +/- 13230.07, N = 15SE +/- 627.85, N = 11SE +/- 1256.70, N = 10SE +/- 572.45, N = 11SE +/- 370.86, N = 11SE +/- 425.97, N = 11SE +/- 8325.39, N = 8SE +/- 2731.76, N = 10SE +/- 5022.05, N = 154422824939825029555903906357607187278926804302555886916860009846251144540894887
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX200K400K600K800K1000KMin: 439600 / Avg: 442281.82 / Max: 444200Min: 491800 / Avg: 493981.82 / Max: 496100Min: 500100 / Avg: 502954.55 / Max: 505400Min: 573700 / Avg: 590390 / Max: 595200Min: 450800 / Avg: 635760 / Max: 650800Min: 715300 / Avg: 718727.27 / Max: 721600Min: 882400 / Avg: 892680 / Max: 896900Min: 425600 / Avg: 430254.55 / Max: 432700Min: 586000 / Avg: 588690.91 / Max: 590400Min: 683700 / Avg: 686000 / Max: 687600Min: 926400 / Avg: 984625 / Max: 994200Min: 1132400 / Avg: 1144540 / Max: 1153100Min: 827900 / Avg: 894886.67 / Max: 908000

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 OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX0.59831.19661.79492.39322.9915SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 9SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.016, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.004, N = 3SE +/- 0.002, N = 10SE +/- 0.004, N = 102.6592.0822.0952.0702.0741.9001.6902.5182.0912.0901.5611.4851.6881. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX246810Min: 2.65 / Avg: 2.66 / Max: 2.67Min: 2.07 / Avg: 2.08 / Max: 2.09Min: 2.09 / Avg: 2.09 / Max: 2.11Min: 2.07 / Avg: 2.07 / Max: 2.08Min: 2.07 / Avg: 2.07 / Max: 2.08Min: 1.9 / Avg: 1.9 / Max: 1.9Min: 1.68 / Avg: 1.69 / Max: 1.69Min: 2.49 / Avg: 2.52 / Max: 2.62Min: 2.09 / Avg: 2.09 / Max: 2.1Min: 2.09 / Avg: 2.09 / Max: 2.1Min: 1.55 / Avg: 1.56 / Max: 1.57Min: 1.47 / Avg: 1.49 / Max: 1.5Min: 1.67 / Avg: 1.69 / Max: 1.711. (CXX) g++ options: -rdynamic

clpeak

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

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX4K8K12K16K20KSE +/- 47.74, N = 15SE +/- 83.52, N = 15SE +/- 78.69, N = 15SE +/- 71.02, N = 15SE +/- 85.43, N = 15SE +/- 65.60, N = 13SE +/- 128.94, N = 15SE +/- 20.50, N = 13SE +/- 89.81, N = 15SE +/- 50.89, N = 13SE +/- 160.26, N = 15SE +/- 116.54, N = 12SE +/- 473.13, N = 155393.496949.797048.658612.759246.8510291.5013256.895737.448364.5410229.1815094.0218024.3413017.211. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3K6K9K12K15KMin: 5156.46 / Avg: 5393.49 / Max: 5782.65Min: 6523.26 / Avg: 6949.79 / Max: 7428.09Min: 6633.73 / Avg: 7048.65 / Max: 7552.75Min: 8212.86 / Avg: 8612.75 / Max: 8995.91Min: 8811.58 / Avg: 9246.85 / Max: 9749.47Min: 10034.43 / Avg: 10291.5 / Max: 10717.16Min: 12419.93 / Avg: 13256.89 / Max: 13965.39Min: 5643.29 / Avg: 5737.44 / Max: 5888.02Min: 8008.02 / Avg: 8364.54 / Max: 8872.18Min: 9989.84 / Avg: 10229.18 / Max: 10490.99Min: 13847.57 / Avg: 15094.02 / Max: 15933.97Min: 17594.89 / Avg: 18024.34 / Max: 18637.14Min: 6591.24 / Avg: 13017.21 / Max: 14306.921. (CXX) g++ options: -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX612182430SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 11SE +/- 0.01, N = 1112.6212.7612.7712.7812.7712.8112.8924.3624.7124.6725.2925.4712.861. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX612182430Min: 12.62 / Avg: 12.62 / Max: 12.63Min: 12.75 / Avg: 12.76 / Max: 12.77Min: 12.77 / Avg: 12.77 / Max: 12.78Min: 12.78 / Avg: 12.78 / Max: 12.78Min: 12.76 / Avg: 12.77 / Max: 12.78Min: 12.8 / Avg: 12.81 / Max: 12.81Min: 12.88 / Avg: 12.89 / Max: 12.89Min: 24.34 / Avg: 24.36 / Max: 24.39Min: 24.67 / Avg: 24.71 / Max: 24.75Min: 24.65 / Avg: 24.67 / Max: 24.69Min: 25.29 / Avg: 25.29 / Max: 25.3Min: 25.45 / Avg: 25.47 / Max: 25.49Min: 12.83 / Avg: 12.85 / Max: 12.881. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX90180270360450SE +/- 0.03, N = 11SE +/- 0.09, N = 12SE +/- 0.05, N = 12SE +/- 0.09, N = 12SE +/- 0.07, N = 12SE +/- 0.08, N = 12SE +/- 0.03, N = 12SE +/- 0.17, N = 15SE +/- 0.43, N = 12SE +/- 0.35, N = 12SE +/- 0.25, N = 3SE +/- 0.04, N = 12SE +/- 1.26, N = 12263.28317.73317.46323.27317.85328.77370.50306.32324.71325.85387.73391.96350.971. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX70140210280350Min: 263.12 / Avg: 263.28 / Max: 263.39Min: 317.29 / Avg: 317.73 / Max: 318.2Min: 317.25 / Avg: 317.46 / Max: 317.72Min: 322.64 / Avg: 323.27 / Max: 323.72Min: 317.42 / Avg: 317.85 / Max: 318.29Min: 328.42 / Avg: 328.77 / Max: 329.38Min: 370.32 / Avg: 370.5 / Max: 370.68Min: 303.99 / Avg: 306.32 / Max: 306.78Min: 323.12 / Avg: 324.71 / Max: 327.49Min: 324.59 / Avg: 325.84 / Max: 328.25Min: 387.25 / Avg: 387.73 / Max: 388.09Min: 391.67 / Avg: 391.96 / Max: 392.23Min: 342.07 / Avg: 350.97 / Max: 357.521. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX5001000150020002500SE +/- 0.68, N = 15SE +/- 0.09, N = 12SE +/- 0.17, N = 12SE +/- 0.48, N = 12SE +/- 0.38, N = 12SE +/- 0.35, N = 12SE +/- 1.05, N = 12SE +/- 0.12, N = 12SE +/- 0.17, N = 12SE +/- 0.41, N = 12SE +/- 2.13, N = 3SE +/- 0.98, N = 13SE +/- 0.50, N = 12801.50963.13967.621087.471098.161203.341487.95934.061152.911135.141915.382348.671574.851. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX400800120016002000Min: 799.98 / Avg: 801.5 / Max: 810.8Min: 962.74 / Avg: 963.13 / Max: 963.63Min: 966.37 / Avg: 967.62 / Max: 968.65Min: 1085.21 / Avg: 1087.47 / Max: 1090.1Min: 1095.69 / Avg: 1098.16 / Max: 1100.8Min: 1201.03 / Avg: 1203.34 / Max: 1205.2Min: 1483.23 / Avg: 1487.95 / Max: 1494.98Min: 933.27 / Avg: 934.06 / Max: 934.62Min: 1151.78 / Avg: 1152.91 / Max: 1153.66Min: 1132.43 / Avg: 1135.14 / Max: 1137.67Min: 1911.13 / Avg: 1915.38 / Max: 1917.74Min: 2343.94 / Avg: 2348.67 / Max: 2355.29Min: 1572.6 / Avg: 1574.85 / Max: 1578.121. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX8K16K24K32K40KSE +/- 55.97, N = 15SE +/- 83.80, N = 15SE +/- 80.51, N = 15SE +/- 80.96, N = 15SE +/- 15.95, N = 12SE +/- 54.52, N = 13SE +/- 198.54, N = 15SE +/- 88.44, N = 15SE +/- 16.76, N = 13SE +/- 12.28, N = 14SE +/- 109.43, N = 3SE +/- 56.57, N = 13SE +/- 162.29, N = 155390.856982.397259.998583.148890.4510284.1513380.0212487.4516008.6520059.0029322.8735070.6913624.141. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX6K12K18K24K30KMin: 5189.06 / Avg: 5390.85 / Max: 5832.91Min: 6633.6 / Avg: 6982.39 / Max: 7496.64Min: 6861.93 / Avg: 7259.99 / Max: 7683.59Min: 8178 / Avg: 8583.14 / Max: 9014.48Min: 8803.19 / Avg: 8890.45 / Max: 8982.74Min: 10011.14 / Avg: 10284.15 / Max: 10661.4Min: 12414.1 / Avg: 13380.02 / Max: 14513.65Min: 11255.16 / Avg: 12487.45 / Max: 12599.99Min: 15836.29 / Avg: 16008.65 / Max: 16038.59Min: 19989.76 / Avg: 20059 / Max: 20103.21Min: 29116.57 / Avg: 29322.87 / Max: 29489.33Min: 34622.87 / Avg: 35070.69 / Max: 35225.1Min: 12715.59 / Avg: 13624.14 / Max: 14639.231. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX2004006008001000SE +/- 0.29, N = 15SE +/- 0.17, N = 13SE +/- 0.30, N = 13SE +/- 0.27, N = 15SE +/- 0.13, N = 13SE +/- 0.12, N = 15SE +/- 0.56, N = 12SE +/- 0.69, N = 10SE +/- 0.17, N = 15SE +/- 0.38, N = 15SE +/- 0.02, N = 3SE +/- 1.06, N = 14SE +/- 1.69, N = 13275.99368.53368.47369.45369.16405.56507.06314.23389.00389.08662.16811.92504.511. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX140280420560700Min: 272.28 / Avg: 275.99 / Max: 276.54Min: 366.81 / Avg: 368.53 / Max: 368.87Min: 366 / Avg: 368.47 / Max: 369.3Min: 365.87 / Avg: 369.45 / Max: 369.99Min: 368.03 / Avg: 369.16 / Max: 369.66Min: 403.94 / Avg: 405.56 / Max: 405.8Min: 502.56 / Avg: 507.06 / Max: 509.09Min: 308.48 / Avg: 314.23 / Max: 315.45Min: 386.62 / Avg: 389 / Max: 389.38Min: 384.25 / Avg: 389.08 / Max: 389.74Min: 662.11 / Avg: 662.16 / Max: 662.18Min: 802.28 / Avg: 811.92 / Max: 813.54Min: 497.1 / Avg: 504.51 / Max: 513.751. (CXX) g++ options: -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX1020304050SE +/- 0.01, N = 12SE +/- 0.01, N = 12SE +/- 0.02, N = 12SE +/- 0.01, N = 13SE +/- 0.02, N = 13SE +/- 0.02, N = 13SE +/- 0.02, N = 13SE +/- 0.01, N = 12SE +/- 0.01, N = 13SE +/- 0.02, N = 13SE +/- 0.08, N = 3SE +/- 0.09, N = 14SE +/- 0.12, N = 1316.3118.3718.7221.8224.3226.6235.3515.2321.6925.5337.4044.4436.291. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX918273645Min: 16.25 / Avg: 16.31 / Max: 16.41Min: 18.26 / Avg: 18.37 / Max: 18.42Min: 18.62 / Avg: 18.72 / Max: 18.82Min: 21.76 / Avg: 21.82 / Max: 21.86Min: 24.23 / Avg: 24.32 / Max: 24.41Min: 26.47 / Avg: 26.62 / Max: 26.72Min: 35.19 / Avg: 35.35 / Max: 35.45Min: 15.21 / Avg: 15.23 / Max: 15.26Min: 21.63 / Avg: 21.69 / Max: 21.79Min: 25.44 / Avg: 25.53 / Max: 25.65Min: 37.32 / Avg: 37.4 / Max: 37.56Min: 43.96 / Avg: 44.44 / Max: 45.1Min: 35.66 / Avg: 36.29 / Max: 37.051. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX510152025SE +/- 0.060602, N = 15SE +/- 0.043753, N = 15SE +/- 0.009545, N = 14SE +/- 0.012692, N = 13SE +/- 0.009750, N = 14SE +/- 0.038362, N = 15SE +/- 0.054471, N = 15SE +/- 0.251378, N = 15SE +/- 0.020839, N = 15SE +/- 0.002752, N = 14SE +/- 0.146254, N = 15SE +/- 0.039276, N = 15SE +/- 0.101653, N = 1519.77633316.41420015.99100012.80700011.83100010.5250009.31100016.66200012.97600010.4640007.6160006.3050009.1350001. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX510152025Min: 19.69 / Avg: 19.78 / Max: 20.62Min: 16.35 / Avg: 16.41 / Max: 17.03Min: 15.92 / Avg: 15.99 / Max: 16.08Min: 12.69 / Avg: 12.81 / Max: 12.88Min: 11.77 / Avg: 11.83 / Max: 11.9Min: 10.42 / Avg: 10.53 / Max: 11.05Min: 9.24 / Avg: 9.31 / Max: 10.07Min: 16.22 / Avg: 16.66 / Max: 19.14Min: 12.94 / Avg: 12.98 / Max: 13.26Min: 10.45 / Avg: 10.46 / Max: 10.49Min: 7.34 / Avg: 7.62 / Max: 9.4Min: 6.26 / Avg: 6.31 / Max: 6.85Min: 8.81 / Avg: 9.14 / Max: 9.921. (CXX) g++ options: -O3 -march=native -fopenmp

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 PrecisionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX8K16K24K32K40KSE +/- 75.94, N = 15SE +/- 6.28, N = 13SE +/- 2.54, N = 13SE +/- 6.29, N = 14SE +/- 1.55, N = 14SE +/- 1.97, N = 14SE +/- 14.06, N = 15SE +/- 1.98, N = 13SE +/- 4.81, N = 14SE +/- 86.13, N = 15SE +/- 541.23, N = 15SE +/- 645.17, N = 15SE +/- 3.96, N = 147223.668240.308392.729773.7110940.4211866.9216375.1613135.0718832.9922115.6930534.4435766.2717145.671. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Single PrecisionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX6K12K18K24K30KMin: 6450.49 / Avg: 7223.66 / Max: 7341.11Min: 8216.78 / Avg: 8240.3 / Max: 8295.08Min: 8373.46 / Avg: 8392.72 / Max: 8405.78Min: 9728.18 / Avg: 9773.71 / Max: 9788.01Min: 10930.21 / Avg: 10940.42 / Max: 10946Min: 11855.24 / Avg: 11866.92 / Max: 11881.95Min: 16205.32 / Avg: 16375.16 / Max: 16437.57Min: 13123.51 / Avg: 13135.07 / Max: 13143.07Min: 18782.11 / Avg: 18832.99 / Max: 18852.54Min: 21091.57 / Avg: 22115.69 / Max: 22269.49Min: 28252.07 / Avg: 30534.44 / Max: 32457.58Min: 33972.43 / Avg: 35766.27 / Max: 39252.74Min: 17118.11 / Avg: 17145.67 / Max: 17172.211. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX4K8K12K16K20KSE +/- 11.60, N = 13SE +/- 8.41, N = 13SE +/- 8.25, N = 13SE +/- 0.73, N = 12SE +/- 9.69, N = 14SE +/- 6.58, N = 15SE +/- 16.25, N = 14SE +/- 166.10, N = 15SE +/- 8.76, N = 14SE +/- 1.03, N = 14SE +/- 5.02, N = 3SE +/- 363.85, N = 15SE +/- 122.22, N = 157256.568197.388354.509693.0710825.0911714.4316219.086602.459593.8111288.3717004.8318323.7116892.911. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX3K6K9K12K15KMin: 7216.91 / Avg: 7256.56 / Max: 7326.11Min: 8158.7 / Avg: 8197.38 / Max: 8256.38Min: 8281.55 / Avg: 8354.5 / Max: 8372.29Min: 9687.7 / Avg: 9693.07 / Max: 9695.04Min: 10761.83 / Avg: 10825.09 / Max: 10853.69Min: 11626.92 / Avg: 11714.43 / Max: 11738.82Min: 16098.14 / Avg: 16219.08 / Max: 16301.58Min: 4277.01 / Avg: 6602.45 / Max: 6772.76Min: 9554.52 / Avg: 9593.81 / Max: 9627.71Min: 11281.87 / Avg: 11288.37 / Max: 11296.32Min: 16996.95 / Avg: 17004.83 / Max: 17014.15Min: 17401.64 / Avg: 18323.71 / Max: 20705.14Min: 15622.66 / Avg: 16892.91 / Max: 17137.21. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX110220330440550SE +/- 0.33, N = 13SE +/- 0.42, N = 13SE +/- 0.43, N = 13SE +/- 0.39, N = 14SE +/- 0.65, N = 14SE +/- 0.73, N = 14SE +/- 4.13, N = 15SE +/- 0.36, N = 13SE +/- 0.54, N = 14SE +/- 1.06, N = 14SE +/- 4.62, N = 3SE +/- 9.22, N = 15SE +/- 2.90, N = 15195.67221.54226.00260.38290.29314.09432.17177.72255.14300.72385.83500.47439.291. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX90180270360450Min: 193.15 / Avg: 195.67 / Max: 196.32Min: 217.68 / Avg: 221.54 / Max: 222.28Min: 221.81 / Avg: 226 / Max: 226.77Min: 256.63 / Avg: 260.38 / Max: 261.12Min: 284.79 / Avg: 290.29 / Max: 291.94Min: 306.56 / Avg: 314.09 / Max: 317.54Min: 376.99 / Avg: 432.17 / Max: 440.82Min: 174.48 / Avg: 177.72 / Max: 178.41Min: 251.24 / Avg: 255.14 / Max: 256.69Min: 293.8 / Avg: 300.72 / Max: 303.43Min: 377.46 / Avg: 385.83 / Max: 393.41Min: 460.82 / Avg: 500.47 / Max: 551.87Min: 421.89 / Avg: 439.29 / Max: 456.861. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX90180270360450SE +/- 0.05, N = 14SE +/- 0.07, N = 15SE +/- 0.04, N = 14SE +/- 0.04, N = 13SE +/- 0.05, N = 14SE +/- 0.06, N = 14SE +/- 0.06, N = 14SE +/- 0.04, N = 14SE +/- 0.05, N = 14SE +/- 0.08, N = 14SE +/- 0.09, N = 3SE +/- 0.20, N = 14SE +/- 0.07, N = 14147.56188.88193.43199.28196.93213.06271.70171.80211.88218.50339.91429.33289.601. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090TITAN RTX80160240320400Min: 147.24 / Avg: 147.56 / Max: 148.01Min: 188.69 / Avg: 188.88 / Max: 189.73Min: 193.23 / Avg: 193.43 / Max: 193.75Min: 199.01 / Avg: 199.28 / Max: 199.57Min: 196.65 / Avg: 196.93 / Max: 197.25Min: 212.82 / Avg: 213.06 / Max: 213.61Min: 271.43 / Avg: 271.7 / Max: 272.11Min: 171.48 / Avg: 171.8 / Max: 172.18Min: 211.56 / Avg: 211.88 / Max: 212.27Min: 217.85 / Avg: 218.5 / Max: 218.93Min: 339.73 / Avg: 339.91 / Max: 340.05Min: 428.27 / Avg: 429.33 / Max: 430.79Min: 289.23 / Avg: 289.6 / Max: 290.221. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3090TITAN RTX60120180240300Min: 10.05 / Avg: 99.86 / Max: 165.39Min: 10.2 / Avg: 109.24 / Max: 183.51Min: 7.66 / Avg: 107.12 / Max: 181.1Min: 14.19 / Avg: 123.82 / Max: 220.83Min: 13.81 / Avg: 131.99 / Max: 221.75Min: 9.41 / Avg: 124.5 / Max: 256.58Min: 5.32 / Avg: 165.77 / Max: 309.64Min: 13.25 / Avg: 102.37 / Max: 169.54Min: 10.54 / Avg: 125.39 / Max: 199.26Min: 8.76 / Avg: 139.42 / Max: 219.83Min: 8.12 / Avg: 235.82 / Max: 349.45Min: 14.4 / Avg: 186.22 / Max: 286.17