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
Show Result Confidence Charts

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 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 Benchmarksviennacl: OpenCL BLAS - sAXPYcl-mem: Readshoc: OpenCL - Triadshoc: OpenCL - Reductionshoc: OpenCL - Texture Read Bandwidthcl-mem: Copycl-mem: Writeviennacl: OpenCL BLAS - sCOPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dDOTclpeak: Global Memory Bandwidthmixbench: OpenCL - Double Precisionmixbench: OpenCL - Single Precisionshoc: OpenCL - S3Dshoc: OpenCL - FFT SPclpeak: Single-Precision Floatclpeak: Double-Precision Doubleshoc: OpenCL - GEMM SGEMM_Nviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-TTshoc: OpenCL - MD5 Hashmixbench: OpenCL - Integerclpeak: Integer Compute INThashcat: MD5hashcat: SHA1hashcat: 7-Ziphashcat: SHA-512hashcat: TrueCrypt RIPEMD160 + XTSindigobench: OpenCL GPU - Bedroomindigobench: OpenCL GPU - Supercarluxcorerender-cl: DLSCluxcorerender-cl: Foodluxcorerender-cl: LuxCore Benchmarkluxcorerender-cl: Rainbow Colors and Prismlczero: OpenCLgromacs-gpu: Water Benchmarkfahbench: octanebench: Total Scorev-ray: NVIDIA CUDA GPUv-ray: NVIDIA RTX GPUnamd-cuda: ATPase Simulation - 327,506 Atomsvkresample: 2x - Doublevkresample: 2x - Singlearrayfire: Conjugate Gradient OpenCLfinancebench: Black-Scholes OpenCLrealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Yesbetsy: ETC1 - Highestbetsy: ETC2 RGB - Highestredshift: rodinia: OpenCL Particle Filterblender: BMW27 - CUDAblender: Classroom - CUDAblender: Fishy Cat - CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXblender: Pabellon Barcelona - CUDAblender: Pabellon Barcelona - NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090253297.412.6239263.2811035.42239.3251.7218212280291308275.99195.677223.66147.563801.4985390.85231.532451.9922021716.31167256.565393.4925867371429823335714344228210511714293103885.58218.3793.301.202.787.91122485.789183.8393193.726074746580.17914349.25727.2222.65919.77633312.76585.6455.8526.7839.4014778.98974.50304.55140.6436.92150.1075.051812.31583.12208.09329396.912.7589317.7281106.30286.9335.1276263368388403368.53221.548240.30188.877963.1256982.39263.473046.3624924824918.36628197.386949.7929173328571930708571449398211863857143498787.34723.2294.181.323.6011.23145376.271207.6500243.2716284907340.16666309.01822.2472.08216.41420011.51375.8415.3826.0818.4423807.99163.92301.61121.4130.97145.2365.221790.07544.98194.57321396.812.7737317.4601064.28283.4321.8271260367388401368.47226.008392.72193.427967.6167259.99267.843114.4725525425218.71948354.507048.6529906328571951190000050295512170428573575137.37923.4594.141.293.5610.97148296.358205.5287243.2805034787100.16145303.67122.2842.09515.99111.37375.1115.3735.9398.3603787.89064.95308.95122.9431.25149.2864.441844.76556.87198.29325396.812.7814323.2711133.93290.8318.7281260366386402369.45260.389773.71199.2811087.478583.14308.543319.2729028929321.81519693.078612.75350967285711110704285759039014209714294263577.72024.5184.301.793.599.86174096.753229.3150264.4860187619620.15140263.37319.5012.07012.80710.41963.6324.8905.6367.5233507.01851.27172.2596.9928.5291.1956.971015.84357.54134.86317396.812.7697317.8481114.90290.1331.2279250370388404369.16290.2910940.42196.9271098.168890.45345.973349.3632932733232424.323510825.099246.85385484714291221944285763576015621857144622137.74324.8954.231.863.559.29187817.111246.1809262.529077439030.14833234.43718.9942.07411.8319.44259.5354.6724.9716.8283426.25751.68169.0097.2026.5888.1250.67987.73354.15134.57328437.512.8073328.7711165.16300.6348.6288250404427440405.56314.0911866.92213.0581203.3410284.15376.323725.0235735235735426.624311714.4310291.50428575428571355440000071872717356857145359277.98225.6904.321.903.619.24210507.391262.0703266.6842297569260.14614215.02417.4361.90010.5258.92654.1994.4374.6116.2273235.78450.66160.6596.2025.7483.4747.42925.55345.65128.99405545.612.8851370.5011187.96321.6449.5308322478518521507.06432.1716375.16271.7001487.9513380.02522.284831.9447647348335.345916219.0813256.895518631428617685385714892680224774285765667511.03333.3715.632.194.6512.34276398.178298.6427352.02728992812450.14408155.56914.7581.6909.3117.86044.5293.9653.8515.1382474.46438.49152.8672.4519.5274.8136.07916.09285.52104.11389545.312.8550350.9711169.72306.3476.8296305477520516504.51439.2917145.67289.5961574.8513624.14515.024975.6247446845647236.289216892.9113017.215555460000017755985714894887224934285765433811.16333.6665.672.084.6912.92272997.018292.3992363.87204789212320.16623152.75514.1821.6889.1357.55743.3294.0136.8752464.70238.74161.8073.3619.9479.0336.63969.58297.11109.02302315.824.3577306.3171256.43266.7296.4271289311325328314.23177.7213135.07171.800934.05912487.45209.562772.3020119919919415.22506602.455737.442282927142977133428574302559789714293001888.42025.6565.532.064.5113.26184566.086180.3698288.47316578410590.16281377.58923.3522.51816.66200011.18272.1985.2596.4499.7343059.76344.35128.5085.6424.3878.4858.22863.87319.41122.25357393.124.7052324.7092119.25297.0383.3292324362399398389.00255.1418832.99211.8821152.9116008.65303.903438.4929329229221.69319593.818364.543291898571411092171429588691141212857142839011.45934.0117.252.995.9117.72259207.505236.5535382.77131118515480.13904263.98717.6692.09112.9768.84653.9904.5414.9746.7902406.96831.9285.4861.9917.8254.7541.98549.79217.7886.04357393.124.6655325.8452121.56296.9379.8294325365396397389.08300.7222115.69218.5011135.1420059.00360.443775.8734234134125.528511288.3710229.183864135714313107471429686000166518571450340012.89037.2307.933.366.4918.92292087.657266.1016410.558253134117150.14151223.66917.5162.09010.4648.40050.0314.3074.2936.0302285.97928.9976.2654.2616.1048.1635.71462.60190.0576.96468666.025.2918387.7292204.20354.5641.3350373547630592662.16385.8330534.44339.9071915.3829322.87537.246181.2349450149749237.400217004.8315094.025545870000018934633333984625239856666771056717.39345.9929.593.967.8722.31367339.127318.6499560.121285165021510.13138149.53111.4041.5617.6166.42834.3963.6203.3454.5231664.38622.1861.6341.8011.6436.4324.62400.08147.5456.72504825.625.4663391.9582237.77363.4741.1366375607722650811.92500.4735766.27429.3332348.6735070.69656.288144.8160160359960044.437018323.7118024.3466668842857226796714291144540286544285785027520.77852.86111.154.669.1626.33386239.200343.3605678.2442196426200.13550122.8979.2751.4856.3055.85629.6713.4513.0164.0001413.76718.4751.4334.599.7230.4620.37336.99120.3546.75OpenBenchmarking.org

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRTX 3090TITAN RTXRTX 2080 TiRTX 3070RTX 2080RTX 3060 TiRTX 2080 SUPERRTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 3060RTX 206060120180240300Min: 8.12 / Avg: 235.82 / Max: 349.45Min: 14.4 / Avg: 186.22 / Max: 286.17Min: 5.32 / Avg: 165.77 / Max: 309.64Min: 8.76 / Avg: 139.42 / Max: 219.83Min: 13.81 / Avg: 131.99 / Max: 221.75Min: 10.54 / Avg: 125.39 / Max: 199.26Min: 9.41 / Avg: 124.5 / Max: 256.58Min: 14.19 / Avg: 123.82 / Max: 220.83Min: 10.2 / Avg: 109.24 / Max: 183.51Min: 7.66 / Avg: 107.12 / Max: 181.1Min: 13.25 / Avg: 102.37 / Max: 169.54Min: 10.05 / Avg: 99.86 / Max: 165.39

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadTITAN RTXRTX 2080RTX 2070 SUPERRTX 2080 TiRTX 3090RTX 2080 SUPERRTX 2060 SUPERRTX 2060RTX 2070RTX 3070RTX 3060 TiRTX 30600.1850.370.5550.740.9250.3020.3760.3800.3800.3930.4100.4900.5280.5410.8110.8200.822

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 - sAXPYRTX 2060RTX 3060RTX 2080RTX 2070RTX 2070 SUPERRTX 2060 SUPERRTX 2080 SUPERRTX 3060 TiRTX 3070TITAN RTXRTX 2080 TiRTX 3080RTX 3090110220330440550SE +/- 4.00, N = 4SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.15, N = 3SE +/- 0.33, N = 3SE +/- 3.40, N = 6SE +/- 0.33, N = 32523023163213253283283573573894054685041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRTX 3090TITAN RTXRTX 2070 SUPERRTX 2060 SUPERRTX 2080 TiRTX 2080RTX 2060RTX 3060 TiRTX 3070RTX 2080 SUPERRTX 3060RTX 20702468103.7064.7325.6005.7205.7205.7365.8446.3606.4216.4506.5246.716

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthTITAN RTXRTX 2080 TiRTX 3090RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060RTX 3060RTX 3070RTX 3060 Ti5101520257.6218.1909.93210.75211.17011.60011.96012.25913.09415.20318.91220.820

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 3060RTX 3060 TiRTX 3070RTX 2070RTX 2070 SUPERRTX 2080RTX 2060 SUPERRTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 30902004006008001000SE +/- 0.09, N = 7SE +/- 1.48, N = 7SE +/- 0.17, N = 8SE +/- 0.18, N = 8SE +/- 0.09, N = 8SE +/- 0.08, N = 8SE +/- 0.10, N = 8SE +/- 0.10, N = 8SE +/- 0.10, N = 8SE +/- 0.45, N = 8SE +/- 0.11, N = 8SE +/- 5.79, N = 8SE +/- 0.17, N = 9297.4315.8393.1393.1396.8396.8396.8396.9437.5545.3545.6666.0825.61. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 3090TITAN RTXRTX 2080 TiRTX 2080RTX 2070 SUPERRTX 2060RTX 2060 SUPERRTX 3060 TiRTX 3070RTX 2070RTX 2080 SUPERRTX 30600.90971.81942.72913.63884.54852.3432.8272.9703.3833.5003.5313.5903.7703.7813.7863.8104.043

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 2080RTX 2070RTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3060RTX 3070RTX 3060 TiRTX 3080RTX 3090612182430SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.01, 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 = 1112.6212.7612.7712.7712.7812.8112.8612.8924.3624.6724.7125.2925.471. (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 3060RTX 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 3060 TiRTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 309090180270360450SE +/- 0.03, N = 11SE +/- 0.17, N = 15SE +/- 0.05, N = 12SE +/- 0.09, N = 12SE +/- 0.07, N = 12SE +/- 0.09, N = 12SE +/- 0.43, N = 12SE +/- 0.35, N = 12SE +/- 0.08, N = 12SE +/- 1.26, N = 12SE +/- 0.03, N = 12SE +/- 0.25, N = 3SE +/- 0.04, N = 12263.28306.32317.46317.73317.85323.27324.71325.85328.77350.97370.50387.73391.961. (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 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 30905001000150020002500SE +/- 1.41, N = 3SE +/- 3.12, N = 3SE +/- 0.63, N = 4SE +/- 3.05, N = 3SE +/- 1.35, N = 3SE +/- 1.33, N = 3SE +/- 4.50, 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 = 31035.421064.281106.301114.901133.931165.161169.721187.961256.432119.252121.562204.202237.771. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

cl-mem

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

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2060RTX 3060RTX 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 3070RTX 3060 TiRTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 309080160240320400SE +/- 0.05, N = 7SE +/- 1.32, N = 7SE +/- 0.15, N = 8SE +/- 0.15, N = 8SE +/- 0.14, N = 8SE +/- 0.19, N = 7SE +/- 0.16, N = 8SE +/- 0.22, N = 8SE +/- 0.14, N = 8SE +/- 0.12, N = 8SE +/- 0.08, N = 8SE +/- 0.20, N = 3SE +/- 0.06, N = 9239.3266.7283.4286.9290.1290.8296.9297.0300.6306.3321.6354.5363.41. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 2060RTX 3060RTX 2070 SUPERRTX 2070RTX 2080RTX 2060 SUPERRTX 2080 SUPERRTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3080RTX 3090160320480640800SE +/- 0.30, N = 7SE +/- 1.71, N = 7SE +/- 0.22, N = 8SE +/- 0.21, N = 8SE +/- 0.51, N = 8SE +/- 0.22, N = 8SE +/- 0.52, N = 8SE +/- 0.10, N = 8SE +/- 0.10, N = 8SE +/- 0.46, N = 8SE +/- 0.86, N = 8SE +/- 0.36, N = 3SE +/- 0.42, N = 9251.7296.4318.7321.8331.2335.1348.6379.8383.3449.5476.8641.3741.11. (CC) gcc options: -O2 -flto -lOpenCL

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 - sCOPYRTX 2060RTX 2070RTX 3060RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 2080 SUPERRTX 3060 TiRTX 3070TITAN RTXRTX 2080 TiRTX 3080RTX 309080160240320400SE +/- 0.67, N = 3SE +/- 3.34, N = 4SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 1.86, N = 3SE +/- 3.18, N = 3SE +/- 3.42, N = 6SE +/- 1.20, N = 32182712712762792812882902932963083503661. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTRTX 2060RTX 2080RTX 2080 SUPERRTX 2070RTX 2070 SUPERRTX 2060 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 309080160240320400SE +/- 1.00, N = 3SE +/- 0.33, N = 3SE +/- 3.42, N = 4SE +/- 0.89, N = 6SE +/- 0.33, N = 32122502502602602622893053223243253733751. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYRTX 2060RTX 3060RTX 3060 TiRTX 3070RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 2080RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090130260390520650SE +/- 3.75, N = 4SE +/- 0.33, N = 3SE +/- 5.54, N = 6SE +/- 0.58, N = 32793113613653663673683704044774785476071. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYRTX 2060RTX 3060RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2080RTX 3070RTX 3060 TiRTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 3090160320480640800SE +/- 2.50, N = 4SE +/- 0.33, N = 32913253863883883883963994275185206307221. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 2060RTX 3060RTX 3070RTX 3060 TiRTX 2070RTX 2070 SUPERRTX 2060 SUPERRTX 2080RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090140280420560700SE +/- 1.53, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 6.17, N = 6SE +/- 1.00, N = 33083283973984014024034044405165215926501. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

clpeak

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 3060RTX 2080RTX 2080 TiRTX 2060RTX 2070 SUPERTITAN RTXRTX 2060 SUPERRTX 3060 TiRTX 3090RTX 3070RTX 2080 SUPERRTX 20702468105.7726.1176.1206.1366.5806.9777.1607.5007.5637.6827.7808.246

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2060RTX 3060RTX 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 3060 TiRTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 30902004006008001000SE +/- 0.29, N = 15SE +/- 0.69, N = 10SE +/- 0.30, N = 13SE +/- 0.17, N = 13SE +/- 0.13, N = 13SE +/- 0.27, N = 15SE +/- 0.17, N = 15SE +/- 0.38, N = 15SE +/- 0.12, N = 15SE +/- 1.69, N = 13SE +/- 0.56, N = 12SE +/- 0.02, N = 3SE +/- 1.06, N = 14275.99314.23368.47368.53369.16369.45389.00389.08405.56504.51507.06662.16811.921. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Mixbench

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionRTX 3060RTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 3090RTX 3060 TiRTX 2070RTX 2080RTX 3070TITAN RTXRTX 2080 SUPERRTX 2080 Ti36912155.1755.8426.3106.3806.4876.6807.0637.1008.0798.1798.3909.450

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Single PrecisionRTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3060RTX 3090RTX 3060 TiRTX 3070130260390520650220.08223.96244.11259.05278.61311.78311.78348.97381.98472.79494.93599.86

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 2060RTX 2080RTX 2070 SUPERRTX 3060RTX 2060 SUPERTITAN RTXRTX 2080 SUPERRTX 3060 TiRTX 2070RTX 2080 TiRTX 3070RTX 30902468104.2124.3894.7304.8485.0205.2025.3805.5306.0666.0906.1046.337

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 3060TITAN RTXRTX 2070RTX 3070RTX 2080 SUPERRTX 3090RTX 2080 TiRTX 3060 Ti61218243019.6519.7322.7222.9023.7024.9325.6526.2526.3126.3726.5226.93

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 2060RTX 2080RTX 2060 SUPERRTX 2070 SUPERRTX 3060RTX 2070RTX 3060 TiRTX 2080 SUPERTITAN RTXRTX 3070RTX 2080 TiRTX 3090153045607537.9243.9844.1744.3044.7448.0450.6450.9054.8356.3757.2168.83

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 3080RTX 2080 TiTITAN RTXRTX 3090110220330440550SE +/- 0.36, N = 13SE +/- 0.33, N = 13SE +/- 0.42, N = 13SE +/- 0.43, N = 13SE +/- 0.54, N = 14SE +/- 0.39, N = 14SE +/- 0.65, N = 14SE +/- 1.06, N = 14SE +/- 0.73, N = 14SE +/- 4.62, N = 3SE +/- 4.13, N = 15SE +/- 2.90, N = 15SE +/- 9.22, N = 15177.72195.67221.54226.00255.14260.38290.29300.72314.09385.83432.17439.29500.471. (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 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 30908K16K24K32K40KSE +/- 75.94, N = 15SE +/- 6.28, N = 13SE +/- 2.54, N = 13SE +/- 6.29, N = 14SE +/- 1.55, N = 14SE +/- 1.97, N = 14SE +/- 1.98, N = 13SE +/- 14.06, N = 15SE +/- 3.96, N = 14SE +/- 4.81, N = 14SE +/- 86.13, N = 15SE +/- 541.23, N = 15SE +/- 645.17, N = 157223.668240.308392.729773.7110940.4211866.9213135.0716375.1617145.6718832.9922115.6930534.4435766.271. (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 3060RTX 2060 SUPERRTX 2070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2080 SUPERRTX 3070RTX 2080 TiTITAN RTXRTX 3080RTX 309090180270360450SE +/- 0.05, N = 14SE +/- 0.04, N = 14SE +/- 0.07, N = 15SE +/- 0.04, N = 14SE +/- 0.05, N = 14SE +/- 0.04, N = 13SE +/- 0.05, N = 14SE +/- 0.06, N = 14SE +/- 0.08, N = 14SE +/- 0.06, N = 14SE +/- 0.07, N = 14SE +/- 0.09, N = 3SE +/- 0.20, N = 14147.56171.80188.88193.43196.93199.28211.88213.06218.50271.70289.60339.91429.331. (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 3060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 3070RTX 3060 TiRTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 30905001000150020002500SE +/- 0.68, N = 15SE +/- 0.12, N = 12SE +/- 0.09, N = 12SE +/- 0.17, N = 12SE +/- 0.48, N = 12SE +/- 0.38, N = 12SE +/- 0.41, N = 12SE +/- 0.17, N = 12SE +/- 0.35, N = 12SE +/- 1.05, N = 12SE +/- 0.50, N = 12SE +/- 2.13, N = 3SE +/- 0.98, N = 13801.50934.06963.13967.621087.471098.161135.141152.911203.341487.951574.851915.382348.671. (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 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 30908K16K24K32K40KSE +/- 55.97, N = 15SE +/- 83.80, N = 15SE +/- 80.51, N = 15SE +/- 80.96, N = 15SE +/- 15.95, N = 12SE +/- 54.52, N = 13SE +/- 88.44, N = 15SE +/- 198.54, N = 15SE +/- 162.29, N = 15SE +/- 16.76, N = 13SE +/- 12.28, N = 14SE +/- 109.43, N = 3SE +/- 56.57, N = 135390.856982.397259.998583.148890.4510284.1512487.4513380.0213624.1416008.6520059.0029322.8735070.691. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090140280420560700SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.48, N = 3SE +/- 0.70, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.92, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 4.52, N = 3SE +/- 1.36, N = 3SE +/- 0.68, N = 3SE +/- 0.77, N = 3209.56231.53263.47267.84303.90308.54345.97360.44376.32515.02522.28537.24656.281. (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.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRTX 2060RTX 3060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 3060 TiRTX 2080 SUPERRTX 3070RTX 2080 TiTITAN RTXRTX 3080RTX 30902K4K6K8K10KSE +/- 0.34, N = 8SE +/- 3.66, N = 9SE +/- 7.32, N = 9SE +/- 7.35, N = 9SE +/- 1.92, N = 9SE +/- 1.77, N = 9SE +/- 2.73, N = 10SE +/- 1.79, N = 10SE +/- 20.37, N = 10SE +/- 12.95, N = 10SE +/- 38.91, N = 10SE +/- 62.64, N = 6SE +/- 29.12, N = 112451.992772.303046.363114.473319.273349.363438.493725.023775.874831.944975.626181.238144.811. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

ViennaCL

OpenBenchmarking.orgGFLOPs/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 3060 TiRTX 3070RTX 2080RTX 2080 Ti0.7021.4042.1062.8083.512.2102.3272.4902.6202.8342.8423.060

OpenBenchmarking.orgGFLOPs/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 2060RTX 3060 TiRTX 30700.64891.29781.94672.59563.24452.2942.6002.884

OpenBenchmarking.orgGFLOPs/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 3060RTX 3090RTX 2080TITAN RTXRTX 2080 SUPER0.69751.3952.09252.793.48752.1392.6862.7722.9083.100

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 3060 TiRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090130260390520650SE +/- 3.09, N = 4SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 1.15, N = 3SE +/- 2.00, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 2.00, N = 2SE +/- 2.73, N = 3SE +/- 1.33, N = 3SE +/- 5.20, N = 6SE +/- 1.86, N = 32012182482532902923263413574744754946011. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 3060 TiRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090130260390520650SE +/- 5.50, N = 2SE +/- 1.00, N = 2SE +/- 1.15, N = 3SE +/- 1.67, N = 3SE +/- 0.67, N = 3SE +/- 2.00, N = 2SE +/- 2.65, N = 3SE +/- 1.33, N = 3SE +/- 3.18, N = 6SE +/- 1.33, N = 31992172462522892923243413524684725016031. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 3060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090130260390520650SE +/- 3.67, N = 3SE +/- 1.15, N = 3SE +/- 1.00, N = 3SE +/- 1.00, N = 3SE +/- 1.00, N = 3SE +/- 8.00, N = 2SE +/- 1.20, N = 3SE +/- 3.40, N = 6SE +/- 1.33, N = 31992472502922933293403574564814975991. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 3060RTX 2080RTX 2080 SUPERTITAN RTXRTX 3080RTX 3090130260390520650SE +/- 4.50, N = 2SE +/- 8.15, N = 41943243544724926001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGHash/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3060RTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 2070RTX 3060 TiRTX 2080RTX 3070RTX 2080 SUPERRTX 3090TITAN RTXRTX 2080 Ti0.13730.27460.41190.54920.68650.2990.3350.3600.3700.3870.3900.4150.4750.4800.5050.5490.610

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 30901020304050SE +/- 0.01, N = 12SE +/- 0.01, N = 12SE +/- 0.01, N = 12SE +/- 0.02, N = 12SE +/- 0.01, N = 13SE +/- 0.01, N = 13SE +/- 0.02, N = 13SE +/- 0.02, N = 13SE +/- 0.02, N = 13SE +/- 0.02, N = 13SE +/- 0.12, N = 13SE +/- 0.08, N = 3SE +/- 0.09, N = 1415.2316.3118.3718.7221.6921.8224.3225.5326.6235.3536.2937.4044.441. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Mixbench

OpenBenchmarking.orgGIOPS Per Watt, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerRTX 3060RTX 2060RTX 3090RTX 2060 SUPERRTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2080RTX 2080 SUPERTITAN RTXRTX 3070RTX 2080 Ti70140210280350190.95216.66230.61230.71237.56244.15254.32255.63294.97297.27305.19344.32

clpeak

OpenBenchmarking.orgGIOPS Per Watt, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2060 SUPERRTX 2060RTX 2070TITAN RTXRTX 2070 SUPERRTX 3060RTX 2080RTX 3060 TiRTX 2080 TiRTX 3090RTX 2080 SUPERRTX 30704080120160200113.37115.13119.26123.61123.90126.68127.83128.13136.43137.69148.77159.35

Mixbench

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

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 30904K8K12K16K20KSE +/- 166.10, N = 15SE +/- 11.60, N = 13SE +/- 8.41, N = 13SE +/- 8.25, N = 13SE +/- 8.76, N = 14SE +/- 0.73, N = 12SE +/- 9.69, N = 14SE +/- 1.03, N = 14SE +/- 6.58, N = 15SE +/- 16.25, N = 14SE +/- 122.22, N = 15SE +/- 5.02, N = 3SE +/- 363.85, N = 156602.457256.568197.388354.509593.819693.0710825.0911288.3711714.4316219.0816892.9117004.8318323.711. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

clpeak

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

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2060RTX 3060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 30904K8K12K16K20KSE +/- 47.74, N = 15SE +/- 20.50, N = 13SE +/- 83.52, N = 15SE +/- 78.69, N = 15SE +/- 89.81, N = 15SE +/- 71.02, N = 15SE +/- 85.43, N = 15SE +/- 50.89, N = 13SE +/- 65.60, N = 13SE +/- 473.13, N = 15SE +/- 128.94, N = 15SE +/- 160.26, N = 15SE +/- 116.54, N = 125393.495737.446949.797048.658364.548612.759246.8510229.1810291.5013017.2113256.8915094.0218024.341. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Hashcat

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 2060RTX 3060RTX 2060 SUPERRTX 3060 TiRTX 2070 SUPERRTX 2070RTX 2080RTX 2080 SUPERRTX 3070RTX 3090TITAN RTXRTX 2080 Ti80M160M240M320M400M281385844.25282461402.46295180004.23298932052.77301310795.77306967445.83318066692.34318467603.88332753520.51342710719.35359788914.02389692802.51

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 3060RTX 2070RTX 2080RTX 3060 TiRTX 2080 SUPERRTX 3070TITAN RTXRTX 3090RTX 2080 Ti30M60M90M120M150M90798237.0892186785.8695456867.0296531515.7997616405.52100791249.30101504398.17101709880.24110690821.06111981983.06115091186.65122493551.98

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3060RTX 2060 SUPERRTX 2060RTX 2070 SUPERRTX 2070RTX 3090RTX 2080RTX 2080 SUPERTITAN RTXRTX 3060 TiRTX 2080 TiRTX 30702K4K6K8K10K8428.738544.438683.238881.509214.479377.959423.509524.619652.8310113.7611111.7511442.68

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 2060RTX 3060RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2080 SUPERRTX 3060 TiRTX 2080RTX 3070TITAN RTXRTX 3090RTX 2080 Ti3M6M9M12M15M11595577.6411892942.8711943947.4612097027.3412377776.2912688099.6812747527.2012836884.8013926432.2414038746.8414246382.5015312675.54

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiRTX 3080TITAN RTXRTX 309014000M28000M42000M56000M70000MSE +/- 16702105.86, N = 7SE +/- 15994429.30, N = 7SE +/- 20426310.23, N = 7SE +/- 31650906.21, N = 7SE +/- 11341315.72, N = 7SE +/- 10209186.21, N = 7SE +/- 63739890.76, N = 7SE +/- 30034122.32, N = 7SE +/- 16181895.49, N = 7SE +/- 56534306.60, N = 7SE +/- 55820277.08, N = 3SE +/- 49932907.37, N = 7SE +/- 37493084.17, N = 722829271429258673714292917332857129906328571329189857143509672857138548471429386413571434285754285755186314286554587000005555460000066668842857

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 30905000M10000M15000M20000M25000MSE +/- 4409613.80, N = 7SE +/- 2725528.10, N = 7SE +/- 7264539.72, N = 7SE +/- 4823948.20, N = 7SE +/- 8126637.98, N = 7SE +/- 3493521.70, N = 7SE +/- 13573045.02, N = 7SE +/- 6748005.50, N = 7SE +/- 14364688.85, N = 7SE +/- 13351911.38, N = 7SE +/- 10849872.25, N = 7SE +/- 6568950.53, N = 3SE +/- 10394772.36, N = 77713342857823335714393070857149511900000110921714291110704285712219442857131074714291355440000017685385714177559857141893463333322679671429

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 3090200K400K600K800K1000KSE +/- 572.45, N = 11SE +/- 407.84, N = 11SE +/- 442.89, N = 11SE +/- 444.64, N = 11SE +/- 370.86, N = 11SE +/- 1953.37, N = 10SE +/- 13230.07, N = 15SE +/- 425.97, N = 11SE +/- 627.85, N = 11SE +/- 1256.70, N = 10SE +/- 5022.05, N = 15SE +/- 8325.39, N = 8SE +/- 2731.76, N = 104302554422824939825029555886915903906357606860007187278926808948879846251144540

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 3090600M1200M1800M2400M3000MSE +/- 1072539.11, N = 7SE +/- 850690.00, N = 7SE +/- 1191123.63, N = 7SE +/- 2076381.60, N = 7SE +/- 1114987.57, N = 7SE +/- 2098266.21, N = 7SE +/- 3482228.94, N = 7SE +/- 1513813.94, N = 7SE +/- 1721354.47, N = 7SE +/- 1806187.40, N = 7SE +/- 2223773.83, N = 7SE +/- 2292257.50, N = 3SE +/- 3339151.39, N = 7978971429105117142911863857141217042857141212857114209714291562185714166518571417356857142247742857224934285723985666672865442857

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 3060 TiRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 3090200K400K600K800K1000KSE +/- 912.89, N = 8SE +/- 318.72, N = 8SE +/- 666.62, N = 9SE +/- 498.01, N = 8SE +/- 4003.26, N = 7SE +/- 67.41, N = 10SE +/- 526.25, N = 8SE +/- 360.86, N = 10SE +/- 3956.17, N = 15SE +/- 1486.48, N = 8SE +/- 586.68, N = 8SE +/- 7188.96, N = 3SE +/- 976.83, N = 8300188310388349878357513426357428390462213503400535927654338656675710567850275

IndigoBench

OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 2060 SUPERRTX 2060RTX 2080TITAN RTXRTX 2070RTX 2070 SUPERRTX 2080 SUPERRTX 2080 TiRTX 3090RTX 3060 TiRTX 3060RTX 30700.01760.03520.05280.07040.0880.0500.0510.0530.0530.0560.0600.0600.0600.0680.0700.0740.078

OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarTITAN RTXRTX 2060RTX 2080 TiRTX 2080RTX 2060 SUPERRTX 2070RTX 3090RTX 2070 SUPERRTX 2080 SUPERRTX 3060RTX 3060 TiRTX 30700.0540.1080.1620.2160.270.1630.1690.1700.1720.1800.1810.1870.1900.1900.2390.2400.240

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 3090510152025SE +/- 0.000, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.006, N = 3SE +/- 0.010, N = 3SE +/- 0.017, N = 3SE +/- 0.004, N = 3SE +/- 0.011, N = 3SE +/- 0.031, N = 3SE +/- 0.031, N = 35.5827.3477.3797.7207.7437.9828.42011.03311.16311.45912.89017.39320.778

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 3060RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 30901224364860SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.38, N = 3SE +/- 0.05, N = 318.3823.2323.4624.5224.9025.6625.6933.3733.6734.0137.2345.9952.86

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: DLSCRTX 2060RTX 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 2080 SUPERRTX 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 30903691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.304.144.184.234.304.325.535.635.677.257.939.5911.15MIN: 3.15 / MAX: 3.39MIN: 3.8 / MAX: 4.28MIN: 4.1 / MAX: 4.29MIN: 4.14 / MAX: 4.29MIN: 1.32 / MAX: 4.51MIN: 4.15 / MAX: 4.43MIN: 5.23 / MAX: 5.69MIN: 5.21 / MAX: 5.75MIN: 4.85 / MAX: 5.74MIN: 6.94 / MAX: 7.39MIN: 7.82 / MAX: 8.13MIN: 9.28 / MAX: 9.71MIN: 9.79 / MAX: 11.28

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 2060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 30901.04852.0973.14554.1945.2425SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 4SE +/- 0.03, N = 7SE +/- 0.03, N = 3SE +/- 0.03, N = 31.201.291.321.791.861.902.062.082.192.993.363.964.66MIN: 0.21 / MAX: 1.43MIN: 0.21 / MAX: 1.55MIN: 0.23 / MAX: 1.59MIN: 0.09 / MAX: 2.3MIN: 0.21 / MAX: 2.29MIN: 0.21 / MAX: 2.38MIN: 0.22 / MAX: 2.57MIN: 0.22 / MAX: 2.61MIN: 0.23 / MAX: 2.7MIN: 0.2 / MAX: 3.75MIN: 0.2 / MAX: 4.25MIN: 0.26 / MAX: 4.99MIN: 0.29 / MAX: 5.93

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 2060RTX 2080RTX 2070RTX 2070 SUPERRTX 2060 SUPERRTX 2080 SUPERRTX 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 30903691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, 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 = 32.783.553.563.593.603.614.514.654.695.916.497.879.16MIN: 0.23 / MAX: 3.19MIN: 0.23 / MAX: 4.09MIN: 0.23 / MAX: 4.1MIN: 0.11 / MAX: 4.24MIN: 0.23 / MAX: 4.14MIN: 0.23 / MAX: 4.14MIN: 0.23 / MAX: 5.21MIN: 0.27 / MAX: 5.37MIN: 0.27 / MAX: 5.45MIN: 0.27 / MAX: 6.84MIN: 0.27 / MAX: 7.45MIN: 0.27 / MAX: 9.03MIN: 0.23 / MAX: 10.53

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismTITAN RTXRTX 2080RTX 2080 TiRTX 2060RTX 2070 SUPERRTX 2080 SUPERRTX 2060 SUPERRTX 2070RTX 3090RTX 3060RTX 3060 TiRTX 30700.03650.0730.10950.1460.18250.0790.0800.0800.0870.0900.0900.1000.1030.1260.1420.1600.162

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 2060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.29, N = 12SE +/- 0.01, N = 4SE +/- 0.09, N = 4SE +/- 0.03, N = 4SE +/- 0.05, N = 4SE +/- 0.04, N = 4SE +/- 0.04, N = 5SE +/- 0.11, N = 5SE +/- 0.10, N = 3SE +/- 0.04, N = 67.919.249.299.8610.9711.2312.3412.9213.2617.7218.9222.3126.33MIN: 6.97 / MAX: 8.2MIN: 8.32 / MAX: 9.68MIN: 8.89 / MAX: 9.66MIN: 3.83 / MAX: 10.57MIN: 10.17 / MAX: 11.29MIN: 5.85 / MAX: 11.69MIN: 10.56 / MAX: 12.86MIN: 11.38 / MAX: 13.49MIN: 12.32 / MAX: 13.86MIN: 16.31 / MAX: 18.32MIN: 17.65 / MAX: 20.07MIN: 20.53 / MAX: 23.39MIN: 23.57 / MAX: 27.71

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 3060RTX 2080RTX 2080 SUPERRTX 3060 TiTITAN RTXRTX 2080 TiRTX 3070RTX 3080RTX 30908K16K24K32K40KSE +/- 40.29, N = 3SE +/- 59.97, N = 3SE +/- 73.63, N = 3SE +/- 31.66, N = 3SE +/- 95.55, N = 3SE +/- 72.61, N = 3SE +/- 98.63, N = 3SE +/- 104.85, N = 3SE +/- 211.49, N = 3SE +/- 120.07, N = 3SE +/- 49.53, N = 3SE +/- 210.78, N = 3SE +/- 98.56, N = 3122481453714829174091845618781210502592027299276392920836733386231. (CXX) g++ options: -flto -pthread

GROMACS

OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2020.3Water BenchmarkTITAN RTXRTX 2070 SUPERRTX 2080 TiRTX 2080RTX 3090RTX 2070RTX 2060RTX 2060 SUPERRTX 2080 SUPERRTX 3060 TiRTX 3070RTX 30600.01190.02380.03570.04760.05950.0380.0400.0400.0430.0430.0450.0460.0500.0500.0500.0520.053

FAHBench

OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterFAHBench 2.3.2RTX 3090TITAN RTXRTX 2060RTX 2080RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080 SUPERRTX 3060RTX 2080 TiRTX 3060 TiRTX 30700.49640.99281.48921.98562.4821.6081.7591.7881.8151.8301.8871.9202.0002.0682.0802.1102.206

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 3060RTX 2060 SUPERRTX 2070RTX 2070 SUPERTITAN RTXRTX 2080RTX 2080 SUPERRTX 3060 TiRTX 3070RTX 2080 TiRTX 3080RTX 30903691215SE +/- 0.004, N = 3SE +/- 0.017, N = 3SE +/- 0.015, N = 3SE +/- 0.024, N = 3SE +/- 0.036, N = 3SE +/- 0.011, N = 3SE +/- 0.031, N = 3SE +/- 0.023, N = 3SE +/- 0.047, N = 3SE +/- 0.052, N = 3SE +/- 0.015, N = 3SE +/- 0.125, N = 3SE +/- 0.011, N = 25.7896.0866.2716.3586.7537.0187.1117.3917.5057.6578.1789.1279.2001. (CXX) g++ options: -O3 -lpthread -ldl -lrt -lm

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 3060RTX 2060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 3060 TiRTX 2080RTX 2080 SUPERRTX 3070TITAN RTXRTX 2080 TiRTX 3080RTX 309070140210280350SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.51, N = 3SE +/- 0.19, N = 3SE +/- 0.45, N = 3SE +/- 0.36, N = 3SE +/- 0.26, N = 3SE +/- 0.55, N = 3SE +/- 0.36, N = 3SE +/- 3.72, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 3180.37183.84205.53207.65229.32236.55246.18262.07266.10292.40298.64318.65343.36

OctaneBench

OpenBenchmarking.orgScore Per Watt, More Is BetterOctaneBench 2020.1Total ScoreRTX 2080 TiRTX 2080TITAN RTXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080 SUPERRTX 3090RTX 3060 TiRTX 3070RTX 30600.52291.04581.56872.09162.61451.5801.5861.5911.6351.6701.6951.7001.7402.0112.3102.3172.324

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreRTX 2060RTX 2060 SUPERRTX 2070RTX 2080RTX 2070 SUPERRTX 2080 SUPERRTX 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 3090150300450600750193.73243.27243.28262.53264.49266.68288.47352.03363.87382.77410.56560.12678.24

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 2070RTX 2060 SUPERRTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 3090400800120016002000SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 1.33, N = 34744784907437567617848929281185134116501964

OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPURTX 2060RTX 2070RTX 2060 SUPERRTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 30906001200180024003000SE +/- 1.15, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 1.45, N = 3SE +/- 2.00, N = 3SE +/- 2.00, N = 3SE +/- 5.90, N = 36587107349039269621059123212451548171521512620

RealSR-NCNN

OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818GPU Temperature MonitorRTX 2080 TiRTX 3060RTX 2070 SUPERRTX 2060RTX 2070RTX 2080RTX 3060 TiRTX 2060 SUPERTITAN RTXRTX 3070RTX 2080 SUPERRTX 30901224364860Min: 39 / Avg: 52.01 / Max: 60Min: 38 / Avg: 51.42 / Max: 58Min: 32 / Avg: 49.79 / Max: 59Min: 33 / Avg: 46.85 / Max: 56Min: 32 / Avg: 46.6 / Max: 57Min: 29 / Avg: 44.71 / Max: 58Min: 32 / Avg: 44.68 / Max: 55Min: 30 / Avg: 43.67 / Max: 53Min: 32 / Avg: 43.08 / Max: 52Min: 30 / Avg: 42.51 / Max: 53Min: 30 / Avg: 42.32 / Max: 51Min: 26 / Avg: 34.79 / Max: 43

OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818GPU Temperature MonitorRTX 2080RTX 2070RTX 2080 TiRTX 2070 SUPERRTX 2060RTX 2060 SUPERRTX 3070TITAN RTXRTX 2080 SUPERRTX 3060 TiRTX 3060RTX 30901530456075Min: 47 / Avg: 73.37 / Max: 81Min: 46 / Avg: 68.58 / Max: 75Min: 50 / Avg: 66.57 / Max: 73Min: 47 / Avg: 65.58 / Max: 72Min: 42 / Avg: 65.25 / Max: 70Min: 40 / Avg: 64.41 / Max: 71Min: 39 / Avg: 63.65 / Max: 71Min: 42 / Avg: 63.57 / Max: 73Min: 40 / Avg: 63.51 / Max: 73Min: 39 / Avg: 63.14 / Max: 69Min: 43 / Avg: 61.29 / Max: 64Min: 33 / Avg: 50.01 / Max: 59

Waifu2x-NCNN Vulkan

OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818GPU Temperature MonitorRTX 2080RTX 2080 TiRTX 2070TITAN RTXRTX 2070 SUPERRTX 2060 SUPERRTX 2080 SUPERRTX 2060RTX 3070RTX 3060 TiRTX 3090RTX 30601326395265Min: 60 / Avg: 64.61 / Max: 69Min: 57 / Avg: 61.18 / Max: 66Min: 56 / Avg: 60.92 / Max: 66Min: 56 / Avg: 60.39 / Max: 65Min: 55 / Avg: 59.27 / Max: 64Min: 53 / Avg: 58.62 / Max: 63Min: 54 / Avg: 58.44 / Max: 64Min: 53 / Avg: 57.76 / Max: 63Min: 52 / Avg: 55.98 / Max: 61Min: 51 / Avg: 55.58 / Max: 61Min: 48 / Avg: 51.28 / Max: 55Min: 45 / Avg: 50.14 / Max: 57

NAMD CUDA

OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD CUDA 2.14GPU Temperature MonitorRTX 2080TITAN RTXRTX 3090RTX 2070RTX 2080 TiRTX 2060 SUPERRTX 3070RTX 3060RTX 2060RTX 3060 TiRTX 2070 SUPERRTX 2080 SUPER1326395265Min: 52 / Avg: 58.92 / Max: 66Min: 49 / Avg: 53.65 / Max: 57Min: 49 / Avg: 53.08 / Max: 57Min: 46 / Avg: 52.62 / Max: 59Min: 48 / Avg: 52.47 / Max: 57Min: 45 / Avg: 51.98 / Max: 58Min: 45 / Avg: 51.2 / Max: 59Min: 46 / Avg: 51.06 / Max: 59Min: 43 / Avg: 50.68 / Max: 58Min: 43 / Avg: 50.03 / Max: 58Min: 44 / Avg: 49.14 / Max: 54Min: 42 / Avg: 47.54 / Max: 53

Betsy GPU Compressor

OpenBenchmarking.orgCelsius, Fewer Is BetterBetsy GPU Compressor 1.1 BetaGPU Temperature MonitorRTX 2080RTX 2070RTX 2080 TiRTX 3090RTX 2060 SUPERRTX 3070TITAN RTXRTX 2060RTX 2070 SUPERRTX 3060RTX 3060 TiRTX 2080 SUPER1326395265Min: 55 / Avg: 59.89 / Max: 65Min: 48 / Avg: 53.08 / Max: 58Min: 48 / Avg: 51.78 / Max: 55Min: 48 / Avg: 51.07 / Max: 55Min: 46 / Avg: 50.74 / Max: 57Min: 46 / Avg: 50.46 / Max: 57Min: 46 / Avg: 50.45 / Max: 55Min: 45 / Avg: 50.41 / Max: 61Min: 45 / Avg: 49.08 / Max: 53Min: 43 / Avg: 48.93 / Max: 55Min: 44 / Avg: 48.92 / Max: 56Min: 44 / Avg: 47.46 / Max: 52

OpenBenchmarking.orgCelsius, Fewer Is BetterBetsy GPU Compressor 1.1 BetaGPU Temperature MonitorRTX 2080RTX 2070RTX 2060RTX 2080 TiRTX 2060 SUPERRTX 2070 SUPERRTX 3070RTX 3090RTX 3060RTX 3060 TiRTX 2080 SUPER1326395265Min: 56 / Avg: 60.79 / Max: 66Min: 49 / Avg: 55.15 / Max: 63Min: 46 / Avg: 53.57 / Max: 63Min: 48 / Avg: 53.32 / Max: 58Min: 46 / Avg: 52.82 / Max: 62Min: 46 / Avg: 51.22 / Max: 60Min: 46 / Avg: 51.14 / Max: 58Min: 47 / Avg: 51.07 / Max: 55Min: 44 / Avg: 49.88 / Max: 57Min: 44 / Avg: 49.56 / Max: 58Min: 45 / Avg: 48.64 / Max: 53

VkResample

OpenBenchmarking.orgCelsius, Fewer Is BetterVkResample 1.0GPU Temperature MonitorRTX 2080RTX 2080 TiRTX 2070RTX 3060RTX 2060 SUPERRTX 2060RTX 3090RTX 3070RTX 3060 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTX1224364860Min: 54 / Avg: 58.93 / Max: 63Min: 49 / Avg: 52.8 / Max: 57Min: 47 / Avg: 52.33 / Max: 56Min: 44 / Avg: 51.84 / Max: 57Min: 45 / Avg: 50.68 / Max: 55Min: 45 / Avg: 50.62 / Max: 54Min: 46 / Avg: 50.45 / Max: 55Min: 45 / Avg: 50.39 / Max: 55Min: 43 / Avg: 49.21 / Max: 53Min: 44 / Avg: 48.98 / Max: 53Min: 43 / Avg: 47.68 / Max: 51Min: 32 / Avg: 40.41 / Max: 47

OpenBenchmarking.orgCelsius, Fewer Is BetterVkResample 1.0GPU Temperature MonitorRTX 2080RTX 3060RTX 2080 TiRTX 3090RTX 2070RTX 2060RTX 2060 SUPERRTX 3070RTX 2070 SUPERRTX 3060 TiRTX 2080 SUPERTITAN RTX1122334455Min: 48 / Avg: 50.76 / Max: 57Min: 48 / Avg: 50.2 / Max: 58Min: 43 / Avg: 45.78 / Max: 53Min: 42 / Avg: 44.81 / Max: 51Min: 42 / Avg: 44.69 / Max: 52Min: 41 / Avg: 43.61 / Max: 52Min: 41 / Avg: 43.48 / Max: 53Min: 41 / Avg: 43.46 / Max: 53Min: 40 / Avg: 42.69 / Max: 50Min: 39 / Avg: 41.85 / Max: 52Min: 39 / Avg: 41.7 / Max: 49Min: 39 / Avg: 40.53 / Max: 48

RedShift Demo

OpenBenchmarking.orgCelsius, Fewer Is BetterRedShift Demo 3.0GPU Temperature MonitorRTX 2080RTX 2080 TiTITAN RTXRTX 3090RTX 2070RTX 2060 SUPERRTX 3070RTX 3060 TiRTX 2070 SUPERRTX 2080 SUPERRTX 2060RTX 30601530456075Min: 62 / Avg: 74.31 / Max: 77Min: 61 / Avg: 72.42 / Max: 75Min: 60 / Avg: 71.93 / Max: 74Min: 58 / Avg: 68.17 / Max: 70Min: 57 / Avg: 68.13 / Max: 70Min: 54 / Avg: 67.74 / Max: 69Min: 53 / Avg: 66.54 / Max: 68Min: 53 / Avg: 65.62 / Max: 67Min: 55 / Avg: 64.56 / Max: 66Min: 53 / Avg: 62.87 / Max: 65Min: 51 / Avg: 62.3 / Max: 63Min: 43 / Avg: 56.83 / Max: 59

Rodinia

OpenBenchmarking.orgCelsius, Fewer Is BetterRodinia 3.1GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 2070RTX 2060 SUPERRTX 3090RTX 2070 SUPERRTX 2080 SUPERRTX 2060RTX 3060 TiRTX 3070RTX 30601428425670Min: 60 / Avg: 65.24 / Max: 70Min: 58 / Avg: 63.9 / Max: 69Min: 58 / Avg: 63.77 / Max: 69Min: 54 / Avg: 59.79 / Max: 65Min: 53 / Avg: 58.82 / Max: 62Min: 55 / Avg: 58.58 / Max: 62Min: 53 / Avg: 58.3 / Max: 62Min: 53 / Avg: 58 / Max: 62Min: 52 / Avg: 56.79 / Max: 60Min: 51 / Avg: 55.7 / Max: 59Min: 51 / Avg: 55.6 / Max: 60Min: 44 / Avg: 48.45 / Max: 52

ArrayFire

OpenBenchmarking.orgCelsius, Fewer Is BetterArrayFire 3.7GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 3090RTX 2060 SUPERRTX 3060RTX 2070RTX 2080 SUPERRTX 2070 SUPERRTX 2060RTX 3070RTX 3060 Ti1224364860Min: 55 / Avg: 57.49 / Max: 60Min: 54 / Avg: 56.74 / Max: 60Min: 53 / Avg: 56.11 / Max: 59Min: 52 / Avg: 54.8 / Max: 57Min: 49 / Avg: 51.74 / Max: 56Min: 47 / Avg: 51.34 / Max: 57Min: 48 / Avg: 51.14 / Max: 55Min: 48 / Avg: 50.81 / Max: 54Min: 48 / Avg: 50.8 / Max: 54Min: 47 / Avg: 50.47 / Max: 54Min: 47 / Avg: 50.42 / Max: 54Min: 47 / Avg: 50.19 / Max: 54

FinanceBench

OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25GPU Temperature MonitorRTX 2080RTX 3090TITAN RTXRTX 3060RTX 2080 TiRTX 2070 SUPERRTX 2060 SUPERRTX 2080 SUPERRTX 3070RTX 2070RTX 2060RTX 3060 Ti1122334455Min: 47 / Avg: 49.79 / Max: 53Min: 47 / Avg: 49.59 / Max: 53Min: 46 / Avg: 48.87 / Max: 52Min: 46 / Avg: 48.17 / Max: 51Min: 45 / Avg: 47.98 / Max: 52Min: 42 / Avg: 44 / Max: 47Min: 41 / Avg: 43.36 / Max: 47Min: 40 / Avg: 43.27 / Max: 47Min: 41 / Avg: 43.23 / Max: 46Min: 40 / Avg: 42.98 / Max: 46Min: 40 / Avg: 42.75 / Max: 46Min: 39 / Avg: 42.12 / Max: 46

Blender

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 2070RTX 3060 TiRTX 3070RTX 2060 SUPERRTX 3090RTX 2060RTX 2070 SUPERRTX 2080 SUPERRTX 30601530456075Min: 61 / Avg: 71.75 / Max: 76Min: 59 / Avg: 69.63 / Max: 73Min: 60 / Avg: 69.21 / Max: 73Min: 56 / Avg: 65.62 / Max: 69Min: 53 / Avg: 65.52 / Max: 70Min: 53 / Avg: 65.46 / Max: 70Min: 53 / Avg: 65.32 / Max: 69Min: 57 / Avg: 63.9 / Max: 67Min: 51 / Avg: 62.55 / Max: 65Min: 51 / Avg: 61.02 / Max: 64Min: 51 / Avg: 59.69 / Max: 63Min: 43 / Avg: 56.25 / Max: 59

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080RTX 2080 TiTITAN RTXRTX 3070RTX 3060 TiRTX 3090RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2080 SUPERRTX 2060RTX 30601530456075Min: 62 / Avg: 75.95 / Max: 78Min: 60 / Avg: 72.01 / Max: 74Min: 60 / Avg: 71.77 / Max: 73Min: 53 / Avg: 70.17 / Max: 73Min: 53 / Avg: 69.67 / Max: 72Min: 56 / Avg: 67.45 / Max: 70Min: 53 / Avg: 65.15 / Max: 67Min: 54 / Avg: 64.67 / Max: 66Min: 56 / Avg: 64.51 / Max: 66Min: 52 / Avg: 64.26 / Max: 66Min: 51 / Avg: 62.96 / Max: 64Min: 44 / Avg: 58.48 / Max: 60

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 2070RTX 3070RTX 2060 SUPERRTX 3060 TiRTX 2070 SUPERRTX 3090RTX 2060RTX 2080 SUPERRTX 30601530456075Min: 63 / Avg: 76.3 / Max: 80Min: 60 / Avg: 72.55 / Max: 76Min: 61 / Avg: 72 / Max: 75Min: 54 / Avg: 68.54 / Max: 72Min: 54 / Avg: 67.84 / Max: 72Min: 52 / Avg: 67.83 / Max: 71Min: 53 / Avg: 67.43 / Max: 71Min: 55 / Avg: 65.63 / Max: 69Min: 58 / Avg: 65.07 / Max: 68Min: 51 / Avg: 64.68 / Max: 68Min: 55 / Avg: 64.27 / Max: 67Min: 44 / Avg: 57.8 / Max: 61

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 2060 SUPERRTX 2070RTX 3090RTX 3060 TiRTX 3070RTX 2060RTX 2080 SUPERRTX 2070 SUPERRTX 30601428425670Min: 64 / Avg: 69.1 / Max: 71Min: 62 / Avg: 68.23 / Max: 70Min: 62 / Avg: 67.39 / Max: 69Min: 54 / Avg: 63.41 / Max: 66Min: 57 / Avg: 63.2 / Max: 65Min: 57 / Avg: 62.82 / Max: 66Min: 53 / Avg: 61.9 / Max: 65Min: 54 / Avg: 61.61 / Max: 65Min: 52 / Avg: 60.2 / Max: 62Min: 55 / Avg: 59.88 / Max: 61Min: 49 / Avg: 58.83 / Max: 62Min: 45 / Avg: 53.68 / Max: 57

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 3070RTX 3060 TiRTX 3090RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2060RTX 2080 SUPERRTX 30601530456075Min: 59 / Avg: 74.5 / Max: 78Min: 58 / Avg: 71.19 / Max: 74Min: 57 / Avg: 70.87 / Max: 74Min: 52 / Avg: 67.27 / Max: 71Min: 52 / Avg: 67.22 / Max: 70Min: 55 / Avg: 65.52 / Max: 69Min: 52 / Avg: 65.16 / Max: 67Min: 54 / Avg: 65.1 / Max: 67Min: 51 / Avg: 63.18 / Max: 66Min: 50 / Avg: 62.53 / Max: 64Min: 51 / Avg: 62.07 / Max: 65Min: 43 / Avg: 56.6 / Max: 58

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 2070RTX 2060 SUPERRTX 3070RTX 3090RTX 3060 TiRTX 2060RTX 2070 SUPERRTX 2080 SUPERRTX 30601530456075Min: 63 / Avg: 72.56 / Max: 77Min: 60 / Avg: 70.44 / Max: 74Min: 61 / Avg: 69.76 / Max: 73Min: 54 / Avg: 65.75 / Max: 69Min: 53 / Avg: 65.58 / Max: 68Min: 54 / Avg: 64.35 / Max: 67Min: 57 / Avg: 64.26 / Max: 68Min: 53 / Avg: 64.2 / Max: 67Min: 51 / Avg: 62.5 / Max: 65Min: 48 / Avg: 61.83 / Max: 64Min: 54 / Avg: 61.23 / Max: 63Min: 43 / Avg: 53.87 / Max: 58

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080TITAN RTXRTX 2080 TiRTX 3090RTX 3070RTX 3060 TiRTX 2070RTX 2070 SUPERRTX 2080 SUPERRTX 2060RTX 2060 SUPERRTX 30601428425670Min: 61 / Avg: 72.28 / Max: 74Min: 59 / Avg: 69.6 / Max: 71Min: 58 / Avg: 68.5 / Max: 70Min: 55 / Avg: 67.64 / Max: 69Min: 52 / Avg: 67.08 / Max: 69Min: 52 / Avg: 66.2 / Max: 68Min: 54 / Avg: 61.99 / Max: 63Min: 52 / Avg: 61.22 / Max: 62Min: 52 / Avg: 60.27 / Max: 61Min: 50 / Avg: 59.91 / Max: 61Min: 50 / Avg: 59.53 / Max: 61Min: 43 / Avg: 54.18 / Max: 58

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080RTX 2080 TiTITAN RTXRTX 3070RTX 3060 TiRTX 3090RTX 2070RTX 2070 SUPERRTX 2060 SUPERRTX 2080 SUPERRTX 2060RTX 30601530456075Min: 60 / Avg: 77.37 / Max: 79Min: 58 / Avg: 73.92 / Max: 76Min: 58 / Avg: 73.47 / Max: 76Min: 53 / Avg: 70.99 / Max: 73Min: 52 / Avg: 70.08 / Max: 72Min: 57 / Avg: 69.31 / Max: 71Min: 52 / Avg: 66.81 / Max: 70Min: 51 / Avg: 65.84 / Max: 67Min: 48 / Avg: 65.19 / Max: 69Min: 51 / Avg: 64.46 / Max: 66Min: 50 / Avg: 63.76 / Max: 66Min: 44 / Avg: 57.97 / Max: 59

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.92GPU Temperature MonitorRTX 2080RTX 2080 TiTITAN RTXRTX 3090RTX 3070RTX 3060 TiRTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2060RTX 2080 SUPERRTX 30601530456075Min: 63 / Avg: 74.5 / Max: 76Min: 62 / Avg: 72.16 / Max: 74Min: 61 / Avg: 71.26 / Max: 73Min: 58 / Avg: 67.84 / Max: 70Min: 54 / Avg: 67.01 / Max: 69Min: 53 / Avg: 66.6 / Max: 69Min: 56 / Avg: 65.14 / Max: 67Min: 53 / Avg: 64.03 / Max: 66Min: 55 / Avg: 63.85 / Max: 65Min: 51 / Avg: 62.71 / Max: 64Min: 54 / Avg: 62.08 / Max: 63Min: 43 / Avg: 54.88 / Max: 58

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 SUPERTITAN RTXRTX 3060RTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3070RTX 3060 TiRTX 3090RTX 30800.04030.08060.12090.16120.2015SE +/- 0.00117, N = 4SE +/- 0.00089, N = 5SE +/- 0.00052, N = 5SE +/- 0.00096, N = 4SE +/- 0.00168, N = 5SE +/- 0.00086, N = 5SE +/- 0.00043, N = 5SE +/- 0.00158, N = 5SE +/- 0.00059, N = 5SE +/- 0.00122, N = 8SE +/- 0.00032, N = 5SE +/- 0.00109, N = 15SE +/- 0.00167, N = 150.179140.166660.166230.162810.161450.151400.148330.146140.144080.141510.139040.135500.13138

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 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 309080160240320400SE +/- 0.28, N = 3SE +/- 0.53, N = 3SE +/- 0.33, N = 3SE +/- 1.78, N = 3SE +/- 0.83, N = 3SE +/- 0.02, N = 3SE +/- 0.24, N = 3SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 1.08, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 3377.59349.26309.02303.67263.99263.37234.44223.67215.02155.57152.76149.53122.901. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 2060RTX 3060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 3060 TiRTX 3070RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 3090612182430SE +/- 0.040, N = 4SE +/- 0.096, N = 5SE +/- 0.025, N = 5SE +/- 0.031, N = 5SE +/- 0.016, N = 5SE +/- 0.017, N = 5SE +/- 0.010, N = 5SE +/- 0.004, N = 5SE +/- 0.013, N = 5SE +/- 0.021, N = 5SE +/- 0.022, N = 5SE +/- 0.136, N = 3SE +/- 0.010, N = 527.22223.35222.28422.24719.50118.99417.66917.51617.43614.75814.18211.4049.2751. (CXX) g++ options: -O3 -pthread

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 3060RTX 2070RTX 3060 TiRTX 3070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3080RTX 30900.59831.19661.79492.39322.9915SE +/- 0.001, N = 10SE +/- 0.016, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 9SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.004, N = 10SE +/- 0.004, N = 3SE +/- 0.002, N = 102.6592.5182.0952.0912.0902.0822.0742.0701.9001.6901.6881.5611.4851. (CXX) g++ options: -rdynamic

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 3060RTX 2060 SUPERRTX 2070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3070RTX 2080 TiTITAN RTXRTX 3080RTX 3090510152025SE +/- 0.060602, N = 15SE +/- 0.251378, N = 15SE +/- 0.043753, N = 15SE +/- 0.009545, N = 14SE +/- 0.020839, N = 15SE +/- 0.012692, N = 13SE +/- 0.009750, N = 14SE +/- 0.038362, N = 15SE +/- 0.002752, N = 14SE +/- 0.054471, N = 15SE +/- 0.101653, N = 15SE +/- 0.146254, N = 15SE +/- 0.039276, N = 1519.77633316.66200016.41420015.99100012.97600012.80700011.83100010.52500010.4640009.3110009.1350007.6160006.3050001. (CXX) g++ options: -O3 -march=native -fopenmp

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 3060RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060 TiRTX 3070RTX 2080 TiTITAN RTXRTX 3080RTX 30903691215SE +/- 0.046, N = 4SE +/- 0.050, N = 4SE +/- 0.034, N = 5SE +/- 0.070, N = 5SE +/- 0.084, N = 15SE +/- 0.021, N = 5SE +/- 0.040, N = 5SE +/- 0.053, N = 5SE +/- 0.051, N = 5SE +/- 0.085, N = 15SE +/- 0.044, N = 6SE +/- 0.071, N = 3SE +/- 0.034, N = 712.76511.51311.37311.18210.4199.4428.9268.8468.4007.8607.5576.4285.856

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 3060RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060 TiRTX 3070RTX 2080 TiTITAN RTXRTX 3080RTX 309020406080100SE +/- 0.27, N = 3SE +/- 0.35, N = 3SE +/- 0.39, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.26, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 385.6575.8475.1172.2063.6359.5454.2053.9950.0344.5343.3334.4029.67

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 3060RTX 2070 SUPERRTX 2080RTX 3060 TiRTX 2080 SUPERRTX 3070TITAN RTXRTX 2080 TiRTX 3080RTX 30901.31672.63343.95015.26686.5835SE +/- 0.007, N = 7SE +/- 0.005, N = 7SE +/- 0.012, N = 7SE +/- 0.006, N = 7SE +/- 0.034, N = 7SE +/- 0.006, N = 8SE +/- 0.056, N = 15SE +/- 0.005, N = 8SE +/- 0.003, N = 8SE +/- 0.011, N = 8SE +/- 0.030, N = 8SE +/- 0.006, N = 3SE +/- 0.006, N = 95.8525.3825.3735.2594.8904.6724.5414.4374.3074.0133.9653.6203.451

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: ETC1 - Quality: HighestTITAN RTXRTX 2060RTX 3060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 3060 TiRTX 2080RTX 2080 SUPERRTX 3070RTX 2080 TiRTX 3080RTX 3090246810SE +/- 1.561, N = 15SE +/- 0.007, N = 6SE +/- 0.011, N = 6SE +/- 0.007, N = 7SE +/- 0.010, N = 7SE +/- 0.070, N = 15SE +/- 0.010, N = 7SE +/- 0.013, N = 7SE +/- 0.008, N = 8SE +/- 0.009, N = 8SE +/- 0.042, N = 15SE +/- 0.018, N = 3SE +/- 0.008, N = 96.8756.7836.4496.0815.9395.6364.9744.9714.6114.2933.8513.3453.0161. (CXX) g++ options: -O3 -O2 -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: HighestRTX 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 3060 TiRTX 2080 SUPERRTX 3070RTX 2080 TiRTX 3080RTX 30903691215SE +/- 0.085, N = 8SE +/- 0.009, N = 5SE +/- 0.007, N = 5SE +/- 0.021, N = 6SE +/- 0.074, N = 15SE +/- 0.011, N = 6SE +/- 0.014, N = 6SE +/- 0.011, N = 7SE +/- 0.012, N = 7SE +/- 0.064, N = 15SE +/- 0.026, N = 3SE +/- 0.010, N = 89.7349.4018.4428.3607.5236.8286.7906.2276.0305.1384.5234.0001. (CXX) g++ options: -O3 -O2 -lpthread -ldl

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 3060RTX 2080 TiTITAN RTXRTX 3060 TiRTX 3070RTX 3080RTX 3090100200300400500SE +/- 1.86, N = 3SE +/- 1.67, N = 3SE +/- 1.76, N = 3SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 1.20, N = 3SE +/- 0.67, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3477380378350342323305247246240228166141

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 3060RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 3060 TiRTX 2080RTX 3070RTX 2080 SUPERTITAN RTXRTX 2080 TiRTX 3080RTX 30903691215SE +/- 0.024, N = 5SE +/- 0.011, N = 5SE +/- 0.008, N = 6SE +/- 0.024, N = 6SE +/- 0.045, N = 6SE +/- 0.022, N = 6SE +/- 0.011, N = 7SE +/- 0.011, N = 7SE +/- 0.010, N = 7SE +/- 0.021, N = 8SE +/- 0.010, N = 8SE +/- 0.026, N = 3SE +/- 0.007, N = 89.7638.9897.9917.8907.0186.9686.2575.9795.7844.7024.4644.3863.7671. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl

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 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 2080 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 309020406080100SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 374.5064.9563.9251.6851.2750.6644.3538.7438.4931.9228.9922.1818.47

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDARTX 2070RTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 2080TITAN RTXRTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 309070140210280350SE +/- 0.02, N = 3SE +/- 0.53, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.24, 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 = 3308.95304.55301.61172.25169.00161.80160.65152.86128.5085.4876.2661.6351.43

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDARTX 2060RTX 2070RTX 2060 SUPERRTX 2080RTX 2070 SUPERRTX 2080 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 3090306090120150SE +/- 0.02, N = 3SE +/- 0.22, N = 3SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3140.64122.94121.4197.2096.9996.2085.6473.3672.4561.9954.2641.8034.59

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 2060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 3090816243240SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 2.61, N = 15SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 536.9231.2530.9728.5226.5825.7424.3819.9419.5217.8216.1011.649.72

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 2060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2080 SUPERTITAN RTXRTX 3060RTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 3090306090120150SE +/- 0.30, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.25, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.21, N = 3SE +/- 0.24, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3150.10149.28145.2391.1988.1283.4779.0378.4874.8154.7548.1636.4330.46

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 3060RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060 TiTITAN RTXRTX 2080 TiRTX 3070RTX 3080RTX 309020406080100SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 2.53, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 375.0565.2264.4458.2256.9750.6747.4241.9836.6336.0735.7124.6220.37

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiXRTX 2070RTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 2080TITAN RTXRTX 2080 SUPERRTX 2080 TiRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 3090400800120016002000SE +/- 3.33, N = 3SE +/- 0.62, N = 3SE +/- 0.39, N = 3SE +/- 0.36, N = 3SE +/- 0.79, N = 3SE +/- 0.70, 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 = 31844.761812.311790.071015.84987.73969.58925.55916.09863.87549.79462.60400.08336.99

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDARTX 2060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 3090130260390520650SE +/- 1.13, N = 3SE +/- 0.14, N = 3SE +/- 0.40, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.48, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3583.12556.87544.98357.54354.15345.65319.41297.11285.52217.78190.05147.54120.35

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 2060RTX 2070RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 3080RTX 309050100150200250SE +/- 0.02, N = 3SE +/- 0.22, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3208.09198.29194.57134.86134.57128.99122.25109.02104.1186.0476.9656.7246.75

113 Results Shown

GPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  OpenCL - Triad
ViennaCL
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Reduction
  OpenCL - Texture Read Bandwidth
cl-mem
cl-mem
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Triad
  OpenCL - Reduction
  OpenCL - Texture Read Bandwidth
cl-mem:
  Copy
  Write
ViennaCL:
  OpenCL BLAS - sCOPY
  OpenCL BLAS - sDOT
  OpenCL BLAS - dCOPY
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dDOT
clpeak
clpeak
Mixbench:
  OpenCL - Double Precision
  OpenCL - Single Precision
  OpenCL - S3D
  OpenCL - FFT SP
  OpenCL - GEMM SGEMM_N
Mixbench:
  OpenCL - Double Precision
  OpenCL - Single Precision
SHOC Scalable HeterOgeneous Computing:
  OpenCL - S3D
  OpenCL - FFT SP
clpeak:
  Single-Precision Float
  Double-Precision Double
SHOC Scalable HeterOgeneous Computing
ViennaCL:
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-TT
ViennaCL:
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-TT
SHOC Scalable HeterOgeneous Computing
SHOC Scalable HeterOgeneous Computing
Mixbench:
  OpenCL - Integer
  Integer Compute INT
Mixbench
clpeak
Hashcat:
  MD5
  SHA1
  7-Zip
  SHA-512
Hashcat:
  MD5
  SHA1
  7-Zip
  SHA-512
  TrueCrypt RIPEMD160 + XTS
IndigoBench:
  OpenCL GPU - Bedroom
  OpenCL GPU - Supercar
IndigoBench:
  OpenCL GPU - Bedroom
  OpenCL GPU - Supercar
LuxCoreRender OpenCL:
  DLSC
  Food
  LuxCore Benchmark
LuxCoreRender OpenCL
LuxCoreRender OpenCL
LeelaChessZero
GROMACS:
  Water Benchmark
 
GROMACS
FAHBench
OctaneBench
OctaneBench
Chaos Group V-RAY:
  NVIDIA CUDA GPU
  NVIDIA RTX GPU
RealSR-NCNN:
  GPU Temp Monitor:
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
NAMD CUDA
VkResample:
  2x - Double
  2x - Single
ArrayFire
FinanceBench
RealSR-NCNN:
  4x - No
  4x - Yes
Waifu2x-NCNN Vulkan
Betsy GPU Compressor:
  ETC1 - Highest
  ETC2 RGB - Highest
RedShift Demo
Rodinia
Blender:
  BMW27 - CUDA
  Classroom - CUDA
  Fishy Cat - CUDA
  BMW27 - NVIDIA OptiX
  Classroom - NVIDIA OptiX
  Fishy Cat - NVIDIA OptiX
  Barbershop - NVIDIA OptiX
  Pabellon Barcelona - CUDA
  Pabellon Barcelona - NVIDIA OptiX