NVIDIA GPU Compute Benchmarks

Benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2106089-IB-NVIDIACOM84
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 5 Tests
Game Development 2 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 3 Tests
Multi-Core 5 Tests
NVIDIA GPU Compute 22 Tests
OpenCL 4 Tests
Renderers 4 Tests
Vulkan Compute 5 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 SUPER
June 03 2021
  7 Hours, 7 Minutes
RTX 2070
June 06 2021
  7 Hours, 8 Minutes
RTX 2070 SUPER
June 05 2021
  6 Hours, 3 Minutes
RTX 2080
June 03 2021
  6 Hours, 9 Minutes
RTX 2080 SUPER
June 05 2021
  5 Hours, 28 Minutes
RTX 2080 Ti
June 06 2021
  4 Hours, 47 Minutes
TITAN RTX
June 04 2021
  4 Hours, 45 Minutes
RTX 3060
June 04 2021
  5 Hours, 58 Minutes
RTX 3060 Ti
June 05 2021
  5 Hours, 10 Minutes
RTX 3070
June 04 2021
  4 Hours, 37 Minutes
RTX 3070 Ti
June 02 2021
  4 Hours, 49 Minutes
RTX 3080
June 03 2021
  4 Hours, 1 Minute
RTX 3080 Ti
June 03 2021
  4 Hours, 36 Minutes
RTX 3090
June 02 2021
  4 Hours, 22 Minutes
Invert Hiding All Results Option
  5 Hours, 21 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


NVIDIA GPU 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 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 3070 Ti 8GBNVIDIA GeForce RTX 3080 10GBNVIDIA GeForce RTX 3080 Ti 12GBNVIDIA GeForce RTX 3090 24GBNVIDIA TU106 HD AudioNVIDIA TU104 HD AudioNVIDIA TU102 HD AudioNVIDIA GeForce RTX 3060NVIDIA GA104 HD AudioNVIDIA GA102 HD AudioASUS VP28URealtek RTL8125 2.5GbE + Intel I211Ubuntu 21.045.11.0-17-generic (x86_64)GNOME Shell 3.38.4X Server 1.20.11NVIDIA 465.314.6.0OpenCL 3.0 CUDA 11.3.1161.2.168GCC 10.3.0 + CUDA 11.3ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA GPU Compute Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/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-build-config=bootstrap-lto-lean --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 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 3070 Ti: GPU Compute Cores: 6144- RTX 3080: GPU Compute Cores: 8704- RTX 3080 Ti: GPU Compute Cores: 10240- RTX 3090: GPU Compute Cores: 10496- Python 3.9.5- 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 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 3080 TiRTX 3090Result OverviewPhoronix Test Suite100%176%252%328%404%BlenderChaos Group V-RAYLuxCoreRendervkpeakclpeakHashcatOctaneBenchMixbenchLeelaChessZeroRedShift DemoPlaidMLIndigoBenchSHOC Scalable HeterOgeneous ComputingVkResampleRealSR-NCNNArrayFireViennaCLcl-memFAHBenchWaifu2x-NCNN VulkanNAMD CUDA

RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 3080 TiRTX 3090Per Watt Result OverviewPhoronix Test Suite100%121%141%162%Chaos Group V-RAYArrayFireMixbenchclpeakLuxCoreRenderLeelaChessZeroOctaneBenchIndigoBenchPlaidMLFAHBenchHashcatSHOC Scalable HeterOgeneous Computingcl-memP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

NVIDIA GPU Compute Benchmarksplaidml: No - Inference - ResNet 50 - OpenCLplaidml: No - Inference - VGG16 - OpenCLplaidml: No - Inference - VGG19 - OpenCLviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - dGEMV-Nviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dGEMV-Tcl-mem: Readcl-mem: Writecl-mem: Copyviennacl: OpenCL BLAS - sCOPYviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - dDOTshoc: OpenCL - Texture Read Bandwidthclpeak: Global Memory Bandwidthmixbench: NVIDIA CUDA - Single Precisionmixbench: NVIDIA CUDA - Double Precisionmixbench: NVIDIA CUDA - Half Precisionarrayfire: BLAS OpenCLclpeak: Single-Precision Floatclpeak: Double-Precision Doublevkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4shoc: OpenCL - FFT SPshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - S3Dviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-TTshoc: OpenCL - MD5 Hashmixbench: NVIDIA CUDA - Integerclpeak: Integer Compute INTvkpeak: int32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: int16-vec4hashcat: MD5hashcat: SHA1hashcat: SHA-512hashcat: 7-Ziphashcat: TrueCrypt RIPEMD160 + XTSindigobench: OpenCL GPU - Supercarindigobench: OpenCL GPU - Bedroomluxcorerender: Rainbow Colors and Prism - GPUluxcorerender: DLSC - GPUluxcorerender: LuxCore Benchmark - GPUluxcorerender: Orange Juice - GPUluxcorerender: Danish Mood - GPUlczero: OpenCLfahbench: octanebench: Total Scorev-ray: NVIDIA CUDA GPUv-ray: NVIDIA RTX GPUnamd-cuda: ATPase Simulation - 327,506 Atomsarrayfire: Conjugate Gradient OpenCLvkresample: 2x - Singleblender: BMW27 - CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - CUDAblender: Classroom - NVIDIA OptiXblender: Fishy Cat - CUDAblender: Fishy Cat - NVIDIA OptiXblender: Pabellon Barcelona - CUDAblender: Pabellon Barcelona - NVIDIA OptiXblender: Barbershop - CUDAblender: Barbershop - NVIDIA OptiXrealsr-ncnn: 4x - Yesrealsr-ncnn: 4x - Nowaifu2x-ncnn: 2x - 3 - Yesbetsy: ETC1 - Highestbetsy: ETC2 RGB - Highestredshift: RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 3080 TiRTX 3090378.75128.87101.87255372388325396.8333.0288.22803273684011110.73368.688225.59221.6514480.232611.247122.60263.138314.108311.488298.4616219.42258.32258.51949.9603023.53188.78324424424318.30107811.277090.648246.828206.715437.697201.01286431428579398457143129148571449322734990023.2997.34714.133.933.914.512.8814680207.9955242.6832285308030.155022.07622.32763.8530.15299.30143.45121.5061.15545.19183.311083.281767.4276.12311.6425.3226.1398.489376380.72131.82104.17258369388319396.8324.0284.62703223674001081.44369.268377.73226.3214636.772680.127244.69267.898449.258451.078439.9516496.22262.90262.86954.2513112.87192.70625125024818.67027995.967155.078365.018319.685530.457362.19294051714299571242857131465714350067335553823.4407.40913.263.893.914.482.8114730205.3082242.9420455197850.152472.09122.29764.8330.39308.70146.54122.6560.40556.43186.121113.491819.2574.97511.4935.305374418.68152.36120.83258370382325392.0314.9289.02783213633971144.90363.959668.05256.3319471.033017.868456.17305.279780.529791.339764.6719106.95305.23307.311088.043269.42199.71727827828321.38799219.348446.249756.509705.636445.648534.723395590000011049914286153571428658056741238824.4517.64813.104.974.535.443.5817353227.9419258.36370879310080.143232.08919.88151.8525.90174.2990.5697.7551.39361.62130.76595.811011.9564.22010.1654.853351442.29164.37129.95251371388334396.8330.7290.22783233704041119.86369.3010803.63288.6621586.183346.889258.58345.8110901.1710886.6510871.1821212.96338.65341.361099.393350.00197.20632332032632424.010010234.259079.5410862.1210806.247123.959468.383799864285712300142857169673333364276045288324.8817.74212.165.154.695.583.7118660244.5184260.4580527809590.138012.07419.05351.5229.08169.3486.7496.8650.15354.5129.02585.52975.2259.5569.4934.6485.0176.873338472.09183.11145.29251389427356437.5347.0301.72883304054411168.27405.7611622.18314.8523388.223667.1710434.55378.2511920.7611917.0311924.6723328.09371.68370.771203.713719.30212.73835334935435026.457111161.7010392.3311820.6711765.097814.8310383.044174605714313596771429189361666771265050621725.7047.96812.155.374.845.773.8520576261.5680270.3021477999810.135221.89717.51650.7425.68160.4281.8895.6844.55344.55123.53555.03913.2654.0688.8804.395322638.39235.75187.25319460518375545.6447.0322.83044044775171180.65507.0814851.91409.0528438.064821.3813781.33522.3116498.5116487.6116457.9132202.58513.77513.101483.304835.13271.24746946647546834.965214731.9713127.4616358.3516279.2710811.5714076.575407435714317815328571246056666789241064481333.35211.03115.286.836.517.105.0127734305.3103359.84390499013240.133241.67714.78138.4919.24152.3973.3072.4233.92283.9698.64548.91899.5944.2257.6293.872245652.41248.34197.09316462542372567.8494.7319.33054034955311168.30530.2915431.56425.4528374.424994.9314490.00548.4817206.4817203.1517183.0433598.08535.94536.021578.375057.65288.60049649348649536.751915399.9513853.3917030.3916941.2811258.4414765.385668448571418687942857258308333394440067887535.31411.59216.837.046.927.215.2129168307.5860382.421153100613860.133041.64013.56036.7918.72152.7073.4369.4632.74281.0897.57551.44907.4641.9137.3373.855233340.13122.2597.37289221327303318.0302.2270.02753063153291255.28315.4412815.83178.2013379.483490.1612561.56214.356818.809039.776836.8313718.14213.55213.53934.1702770.78172.08320420415.15915883.156338.906809.186780.544488.855969.65240050142867762328571111970000042760929991325.8608.50415.365.364.566.063.6118675182.0035293.77972585211680.154712.49423.13543.8523.56127.1577.8784.5553.92316.30115.21962.31876.6867.13410.3624.850300456.40168.99133.75328224399333393.1383.8293.22893593713982120.83388.8718247.61255.2219243.595040.8716021.63303.929684.3912854.499720.6719484.46304.87305.191153.043432.76211.71729129329221.61308458.848378.399700.509646.856403.148477.233415844285711068742857158990000058714542798934.00611.45120.997.196.047.614.9126639236.5058384.178014125616580.129282.08317.67331.8217.4285.3753.6661.6739.24218.4582.07596.57552.1150.6358.3174.180237495.68194.52154.05326221397333393.2380.4294.92813583703982131.07389.2621395.37302.0222837.375790.3420072.72362.3011498.1015292.8511572.6023200.57361.24362.431135.093795.35218.30633833933725.552110033.7810264.4711545.0811492.637629.6710070.324028150000013145171429188668571468759150318837.36612.89223.458.256.988.435.8129253267.0698413.181789141718280.126112.08717.54928.9515.7376.0546.9954.1333.50189.9172.98507.79466.4246.6337.8154.035227513.37202.76160.06528539.1516.1337.63314354785212072.97528.7321337.83305.0423025.875805.7521524.49368.7111707.8715511.7511727.9223509.08366.91367.881536.784710.76286.10734534734326.272510120.8010957.1011695.9611649.907730.7510205.764147745714313375128571191694285772006451271338.94713.73323.778.717.418.676.0331739267.2819454.496616148619820.124851.66813.55727.8017.0973.4144.1852.6034.17184.7667.18501.65459.7840.5647.0443.7304.2495.736201730.16281.36223.94367241629377672.8646.2354.73564805556012210.17662.3929218.85421.8831733.307417.8929577.13545.9617183.8522809.1117097.7834278.04534.50536.451918.516305.82339.02349950149850137.518113956.2115474.8917087.3317024.2711290.9814570.685896241428619257628571273858571499197071997546.49617.54128.2011.679.9910.798.0037477321.3305568.257212178523730.120991.55511.26821.9411.2860.8736.0941.4122.79146.2952.80442.84407.3332.3706.0363.3663.3174.387164789.35311.73248.34363230705367804.8733.2355.03584895926442167.41794.5532644.68469.1635590.078125.7133723.34623.3319639.6625895.8319465.2739163.48604.88611.032289.548100.68419.32855956155756041.830815545.6317317.3119501.4719408.5612829.1616203.0165846485714216602428573070157143109712080760051.44120.03733.2513.5111.5411.969.2839409335.0981666.478575204927820.120661.5139.56118.859.7152.6431.6835.4619.92124.4345.88386.72358.7829.2865.6353.2833.0844.082143816.85323.31257.64723825.7745.5363.03654986076572219.90813.5734169.74494.2437668.368463.7635210.03652.3420790.4927527.9420789.4841672.10651.06651.892346.138327.84429.59960060259844.110216502.9018051.5920714.1620597.7013650.6616881.7669978700000228282500003242516667115300084788653.01120.76534.2714.0611.9912.359.7240348344.9875679.584181209928570.119881.4759.30218.369.4851.2829.9234.4019.11120.3844.12373.69345.1928.1805.5173.2353.0123.939139OpenBenchmarking.org

PlaidML

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1.20132.40263.60394.80526.00655.1275.1264.9085.1644.2605.3235.0694.3135.3394.5724.3174.0174.1614.087

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.40030.80061.20091.60122.00151.7791.7601.6441.6171.3301.6811.4831.2181.7741.3691.3071.1831.2021.157

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.31320.62640.93961.25281.5661.2931.3921.3001.2560.9591.2271.0840.9181.2860.9870.9670.8840.8920.856

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2004006008001000SE +/- 0.45, N = 6SE +/- 1.07, N = 6SE +/- 0.74, N = 6SE +/- 0.79, N = 6SE +/- 0.66, N = 5SE +/- 0.46, N = 6SE +/- 0.18, N = 5SE +/- 0.20, N = 5SE +/- 0.24, N = 6SE +/- 0.45, N = 5SE +/- 0.92, N = 5SE +/- 0.41, N = 5SE +/- 0.55, N = 5SE +/- 0.43, N = 5652.41816.85789.35730.16513.37495.68456.40340.13638.39472.09442.29418.68380.72378.75

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER70140210280350SE +/- 0.54, N = 3SE +/- 0.49, N = 4SE +/- 0.58, N = 4SE +/- 0.47, N = 4SE +/- 0.72, N = 3SE +/- 0.45, N = 3SE +/- 0.35, N = 3SE +/- 0.09, N = 3SE +/- 0.63, N = 3SE +/- 0.45, N = 3SE +/- 0.75, N = 3SE +/- 0.34, N = 3SE +/- 0.54, N = 3SE +/- 0.41, N = 3248.34323.31311.73281.36202.76194.52168.99122.25235.75183.11164.37152.36131.82128.87

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER60120180240300SE +/- 0.48, N = 3SE +/- 0.33, N = 3SE +/- 0.52, N = 3SE +/- 0.38, N = 3SE +/- 0.28, N = 3SE +/- 0.31, N = 3SE +/- 0.33, N = 3SE +/- 0.06, N = 3SE +/- 0.55, N = 3SE +/- 0.32, N = 3SE +/- 0.58, N = 3SE +/- 0.17, N = 3SE +/- 0.39, N = 3SE +/- 0.28, N = 3197.09257.64248.34223.94160.06154.05133.7597.37187.25145.29129.95120.83104.17101.87

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 - sDOTTITAN RTXRTX 3080 TiRTX 3080RTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER80160240320400SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 33163633673273282893192512512672582551. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

cl-mem

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: ReadTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1.22112.44223.66334.88446.10555.0645.2925.1054.9114.7675.0195.0054.9644.9825.4274.5464.4665.1134.961

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: WriteTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1.11332.22663.33994.45325.56654.5644.8884.7684.7884.5244.9484.9364.6474.3754.4883.9053.7434.3314.199

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.9411.8822.8233.7644.7053.0712.3912.2922.6602.9423.8003.8014.1823.1283.8063.4323.4063.9533.695

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 - dGEMV-NTITAN RTXRTX 3080 TiRTX 3080RTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER100200300400500SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 34622312412222242224603893713723693741. (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: Texture Read BandwidthTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER5101520257.6299.5389.53111.59213.82318.62720.11715.5698.01411.11410.49511.45112.23711.915

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 - dAXPYTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER160320480640800SE +/- 0.33, N = 35427237056295283974003275184273883833883881. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TTITAN RTXRTX 3080 TiRTX 3080RTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER80160240320400SE +/- 0.33, N = 3SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 33723683773343343033763563343263203261. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTRTX 2080 Ti0.68991.37982.06972.75963.44953.066

cl-mem

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

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2004006008001000SE +/- 0.09, N = 9SE +/- 0.18, N = 10SE +/- 0.37, N = 9SE +/- 0.18, N = 9SE +/- 0.11, N = 9SE +/- 0.19, N = 8SE +/- 0.18, N = 8SE +/- 0.11, N = 7SE +/- 0.15, N = 8SE +/- 0.11, N = 8SE +/- 0.08, N = 8SE +/- 0.06, N = 8SE +/- 0.10, N = 8SE +/- 0.10, N = 8567.8825.7804.8672.8539.1393.2393.1318.0545.6437.5396.8392.0396.8396.81. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER160320480640800SE +/- 0.75, N = 9SE +/- 0.18, N = 10SE +/- 0.48, N = 9SE +/- 0.35, N = 9SE +/- 0.26, N = 9SE +/- 0.10, N = 8SE +/- 0.07, N = 8SE +/- 0.12, N = 7SE +/- 0.38, N = 8SE +/- 0.31, N = 8SE +/- 0.55, N = 8SE +/- 0.15, N = 8SE +/- 0.35, N = 8SE +/- 0.37, N = 8494.7745.5733.2646.2516.1380.4383.8302.2447.0347.0330.7314.9324.0333.01. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER80160240320400SE +/- 0.08, N = 9SE +/- 0.07, N = 10SE +/- 0.11, N = 9SE +/- 0.20, N = 9SE +/- 0.13, N = 9SE +/- 0.14, N = 8SE +/- 0.17, N = 8SE +/- 0.11, N = 7SE +/- 0.09, N = 8SE +/- 0.09, N = 8SE +/- 0.08, N = 8SE +/- 0.04, N = 8SE +/- 0.07, N = 8SE +/- 0.08, N = 8319.3363.0355.0354.7337.6294.9293.2270.0322.8301.7290.2289.0284.6288.21. (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 - sCOPYTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER80160240320400SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 33053653583563312812892753062882782782702801. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER110220330440550SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 34034984904804353583593064053303233223223271. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER130260390520650SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 34956075925554783713713154774053703633673691. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER140280420560700SE +/- 0.33, N = 3SE +/- 0.67, N = 35316576456015213993983295194414043984004011. (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 BandwidthTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER5001000150020002500SE +/- 3.30, N = 3SE +/- 4.61, N = 3SE +/- 6.37, N = 3SE +/- 0.73, N = 3SE +/- 1.31, N = 4SE +/- 1.91, N = 4SE +/- 2.95, N = 4SE +/- 3.60, N = 4SE +/- 1.11, N = 3SE +/- 2.81, N = 3SE +/- 1.56, N = 3SE +/- 0.65, N = 3SE +/- 3.17, N = 3SE +/- 2.79, N = 41168.302219.902167.412210.172072.972131.072120.831255.281180.651168.271119.861144.901081.441110.731. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Global Memory BandwidthTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2468107.5627.8286.7756.3976.8787.8747.2815.9906.2687.2575.8226.3667.8036.662

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2004006008001000SE +/- 0.03, N = 13SE +/- 0.01, N = 14SE +/- 0.03, N = 13SE +/- 0.07, N = 12SE +/- 0.40, N = 13SE +/- 0.25, N = 13SE +/- 0.22, N = 13SE +/- 0.01, N = 11SE +/- 0.45, N = 12SE +/- 0.21, N = 13SE +/- 0.14, N = 15SE +/- 0.07, N = 13SE +/- 0.05, N = 15SE +/- 0.08, N = 13530.29813.57794.55662.39528.73389.26388.87315.44507.08405.76369.30363.95369.26368.681. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Mixbench

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Single PrecisionTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER130260390520650291.75451.72398.39419.95361.63602.37481.61390.76301.00316.62243.67217.99259.33230.25

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Double PrecisionTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2468108.2556.7125.7956.2355.3078.5436.7685.4768.8287.9886.7445.9626.7536.360

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Single PrecisionTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER7K14K21K28K35KSE +/- 520.86, N = 15SE +/- 561.56, N = 15SE +/- 563.16, N = 15SE +/- 546.33, N = 15SE +/- 213.66, N = 15SE +/- 177.14, N = 15SE +/- 9.34, N = 14SE +/- 1.31, N = 14SE +/- 497.84, N = 15SE +/- 124.12, N = 15SE +/- 12.22, N = 15SE +/- 5.79, N = 14SE +/- 6.70, N = 14SE +/- 12.37, N = 1415431.5634169.7432644.6829218.8521337.8321395.3718247.6112815.8314851.9111622.1810803.639668.058377.738225.591. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Double PrecisionTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER110220330440550SE +/- 13.41, N = 15SE +/- 10.54, N = 15SE +/- 8.40, N = 15SE +/- 8.42, N = 15SE +/- 1.51, N = 14SE +/- 0.66, N = 14SE +/- 0.53, N = 14SE +/- 0.07, N = 14SE +/- 11.13, N = 15SE +/- 1.19, N = 15SE +/- 0.41, N = 14SE +/- 0.29, N = 14SE +/- 0.26, N = 14SE +/- 0.24, N = 14425.45494.24469.16421.88305.04302.02255.22178.20409.05314.85288.66256.33226.32221.651. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: Half PrecisionTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER8K16K24K32K40KSE +/- 394.62, N = 15SE +/- 800.73, N = 15SE +/- 685.00, N = 15SE +/- 632.41, N = 15SE +/- 4.24, N = 14SE +/- 2.92, N = 14SE +/- 1.61, N = 14SE +/- 0.78, N = 14SE +/- 105.21, N = 14SE +/- 70.30, N = 14SE +/- 33.25, N = 15SE +/- 45.34, N = 14SE +/- 42.04, N = 14SE +/- 52.79, N = 1428374.4237668.3635590.0731733.3023025.8722837.3719243.5913379.4828438.0623388.2221586.1819471.0314636.7714480.231. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

ArrayFire

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

OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2K4K6K8K10KSE +/- 12.10, N = 4SE +/- 3.92, N = 4SE +/- 1.74, N = 4SE +/- 5.63, N = 4SE +/- 17.44, N = 4SE +/- 0.72, N = 4SE +/- 0.26, N = 4SE +/- 6.19, N = 4SE +/- 8.53, N = 4SE +/- 0.34, N = 4SE +/- 7.17, N = 4SE +/- 0.43, N = 4SE +/- 6.61, N = 4SE +/- 0.91, N = 44994.938463.768125.717417.895805.755790.345040.873490.164821.383667.173346.883017.862680.122611.241. (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.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER8K16K24K32K40KSE +/- 183.70, N = 15SE +/- 28.06, N = 14SE +/- 21.75, N = 15SE +/- 69.64, N = 13SE +/- 2.30, N = 14SE +/- 12.54, N = 14SE +/- 7.12, N = 15SE +/- 16.58, N = 14SE +/- 222.21, N = 15SE +/- 83.80, N = 15SE +/- 89.35, N = 15SE +/- 77.61, N = 15SE +/- 99.77, N = 15SE +/- 77.28, N = 1514490.0035210.0333723.3429577.1321524.4920072.7216021.6312561.5613781.3310434.559258.588456.177244.697122.601. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER140280420560700SE +/- 1.27, N = 3SE +/- 0.05, N = 3SE +/- 1.38, N = 3SE +/- 1.37, N = 3SE +/- 0.84, N = 3SE +/- 0.02, N = 3SE +/- 0.38, N = 3SE +/- 0.01, N = 3SE +/- 1.40, N = 3SE +/- 0.96, N = 3SE +/- 0.84, N = 3SE +/- 0.80, N = 3SE +/- 0.74, N = 3SE +/- 0.74, N = 3548.48652.34623.33545.96368.71362.30303.92214.35522.31378.25345.81305.27267.89263.131. (CXX) g++ options: -O3 -rdynamic -lOpenCL

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 155.55, N = 3SE +/- 65.40, N = 3SE +/- 104.27, N = 3SE +/- 74.66, N = 3SE +/- 49.99, N = 3SE +/- 7.52, N = 3SE +/- 13.93, N = 3SE +/- 0.24, N = 3SE +/- 114.67, N = 3SE +/- 53.05, N = 3SE +/- 88.42, N = 3SE +/- 43.99, N = 3SE +/- 56.83, N = 3SE +/- 61.71, N = 317206.4820790.4919639.6617183.8511707.8711498.109684.396818.8016498.5111920.7610901.179780.528449.258314.10

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER6K12K18K24K30KSE +/- 134.86, N = 3SE +/- 137.76, N = 3SE +/- 108.44, N = 3SE +/- 75.50, N = 3SE +/- 78.89, N = 3SE +/- 58.84, N = 3SE +/- 31.64, N = 3SE +/- 12.40, N = 3SE +/- 79.54, N = 3SE +/- 60.73, N = 3SE +/- 59.30, N = 3SE +/- 43.80, N = 3SE +/- 46.44, N = 3SE +/- 42.90, N = 317203.1527527.9425895.8322809.1115511.7515292.8512854.499039.7716487.6111917.0310886.659791.338451.078311.48

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalarTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 92.50, N = 3SE +/- 80.41, N = 3SE +/- 30.73, N = 3SE +/- 43.04, N = 3SE +/- 57.85, N = 3SE +/- 43.84, N = 3SE +/- 25.27, N = 3SE +/- 9.15, N = 3SE +/- 43.12, N = 3SE +/- 60.69, N = 3SE +/- 29.14, N = 3SE +/- 32.23, N = 3SE +/- 22.92, N = 3SE +/- 21.01, N = 317183.0420789.4819465.2717097.7811727.9211572.609720.676836.8316457.9111924.6710871.189764.678439.958298.46

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER9K18K27K36K45KSE +/- 148.11, N = 3SE +/- 91.14, N = 3SE +/- 51.02, N = 3SE +/- 88.40, N = 3SE +/- 114.74, N = 3SE +/- 88.97, N = 3SE +/- 49.62, N = 3SE +/- 0.44, N = 3SE +/- 86.26, N = 3SE +/- 118.62, N = 3SE +/- 0.93, N = 3SE +/- 64.46, N = 3SE +/- 45.05, N = 3SE +/- 40.81, N = 333598.0841672.1039163.4834278.0423509.0823200.5719484.4613718.1432202.5823328.0921212.9619106.9516496.2216219.42

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER61218243024.3324.3323.3522.8021.2225.7225.0324.3524.3525.7621.1021.6324.3222.57

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER153045607555.5966.8562.7657.4247.2656.0349.4746.0857.9450.2743.1944.1246.6643.35

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER140280420560700SE +/- 1.43, N = 3SE +/- 1.37, N = 3SE +/- 0.01, N = 3SE +/- 1.32, N = 3SE +/- 0.95, N = 3SE +/- 0.34, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 1.54, N = 3SE +/- 0.95, N = 3SE +/- 0.02, N = 3SE +/- 0.79, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3535.94651.06604.88534.50366.91361.24304.87213.55513.77371.68338.65305.23262.90258.32

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER140280420560700SE +/- 1.43, N = 3SE +/- 0.79, N = 3SE +/- 0.61, N = 3SE +/- 0.35, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.31, N = 3SE +/- 0.03, N = 3SE +/- 1.31, N = 3SE +/- 0.00, N = 2SE +/- 0.01, N = 3SE +/- 0.50, N = 3SE +/- 0.06, N = 2SE +/- 0.65, N = 3536.02651.89611.03536.45367.88362.43305.19213.53513.10370.77341.36307.31262.86258.51

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: FFT SPTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER5001000150020002500SE +/- 0.84, N = 12SE +/- 1.60, N = 13SE +/- 1.82, N = 13SE +/- 0.32, N = 13SE +/- 0.35, N = 12SE +/- 0.32, N = 12SE +/- 0.15, N = 12SE +/- 0.06, N = 12SE +/- 1.41, N = 12SE +/- 0.30, N = 12SE +/- 0.39, N = 12SE +/- 0.30, N = 12SE +/- 0.42, N = 12SE +/- 0.12, N = 121578.372346.132289.541918.511536.781135.091153.04934.171483.301203.711099.391088.04954.25949.961. (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_NTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2K4K6K8K10KSE +/- 26.53, N = 10SE +/- 31.35, N = 12SE +/- 30.90, N = 12SE +/- 18.49, N = 11SE +/- 5.86, N = 10SE +/- 20.27, N = 10SE +/- 2.76, N = 10SE +/- 5.34, N = 9SE +/- 27.28, N = 10SE +/- 1.82, N = 10SE +/- 1.20, N = 9SE +/- 0.86, N = 9SE +/- 9.39, N = 9SE +/- 7.64, N = 95057.658327.848100.686305.824710.763795.353432.762770.784835.133719.303350.003269.423112.873023.531. (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: S3DTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER90180270360450SE +/- 0.08, N = 13SE +/- 0.12, N = 13SE +/- 0.22, N = 13SE +/- 0.19, N = 13SE +/- 0.05, N = 12SE +/- 0.16, N = 13SE +/- 0.10, N = 13SE +/- 0.07, N = 13SE +/- 0.13, N = 13SE +/- 0.07, N = 13SE +/- 0.09, N = 12SE +/- 0.09, N = 13SE +/- 0.07, N = 13SE +/- 0.04, N = 13288.60429.60419.33339.02286.11218.31211.72172.08271.25212.74197.21199.72192.71188.781. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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-NNTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER130260390520650SE +/- 1.20, N = 3SE +/- 1.33, N = 3SE +/- 1.20, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 3SE +/- 1.67, N = 3SE +/- 0.67, N = 34966005594993453412922054703533232852522471. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER130260390520650SE +/- 1.33, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 1.67, N = 3SE +/- 1.53, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 24936025615013473392934673493202842512461. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER130260390520650SE +/- 1.20, N = 3SE +/- 1.33, N = 3SE +/- 1.33, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 3.00, N = 2SE +/- 0.67, N = 34865985574983433402922044763543262832492471. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s Per Watt, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTTITAN RTXRTX 3080 TiRTX 3080RTX 2080 SUPER0.66041.32081.98122.64163.3022.9352.4622.5972.923

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTTITAN RTXRTX 3080 TiRTX 3080RTX 2080 TiRTX 2080 SUPERRTX 2080120240360480600SE +/- 2.00, N = 24955605014683503241. (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.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1020304050SE +/- 0.04, N = 14SE +/- 0.04, N = 14SE +/- 0.06, N = 14SE +/- 0.00, N = 14SE +/- 0.01, N = 13SE +/- 0.05, N = 13SE +/- 0.03, N = 13SE +/- 0.01, N = 12SE +/- 0.04, N = 14SE +/- 0.00, N = 13SE +/- 0.01, N = 15SE +/- 0.01, N = 13SE +/- 0.01, N = 13SE +/- 0.01, N = 1536.7544.1141.8337.5226.2725.5521.6115.1634.9726.4624.0121.3918.6718.301. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Mixbench

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

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: NVIDIA CUDA - Benchmark: IntegerTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 379.98, N = 15SE +/- 363.78, N = 15SE +/- 306.59, N = 15SE +/- 265.32, N = 15SE +/- 10.76, N = 15SE +/- 0.87, N = 14SE +/- 0.45, N = 14SE +/- 0.32, N = 14SE +/- 340.68, N = 15SE +/- 1.25, N = 14SE +/- 5.84, N = 14SE +/- 0.86, N = 14SE +/- 44.96, N = 15SE +/- 74.45, N = 1515399.9516502.9015545.6313956.2110120.8010033.788458.845883.1514731.9711161.7010234.259219.347995.967811.271. (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 INTTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 163.86, N = 15SE +/- 105.32, N = 12SE +/- 114.00, N = 12SE +/- 110.02, N = 15SE +/- 52.74, N = 13SE +/- 62.48, N = 13SE +/- 76.78, N = 15SE +/- 3.88, N = 15SE +/- 52.71, N = 12SE +/- 83.89, N = 15SE +/- 73.78, N = 15SE +/- 83.15, N = 15SE +/- 84.44, N = 15SE +/- 85.91, N = 1513853.3918051.5917317.3115474.8910957.1010264.478378.396338.9013127.4610392.339079.548446.247155.077090.641. (CXX) g++ options: -O3 -rdynamic -lOpenCL

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 44.08, N = 3SE +/- 26.66, N = 3SE +/- 0.24, N = 3SE +/- 1.14, N = 3SE +/- 0.71, N = 3SE +/- 0.75, N = 3SE +/- 8.15, N = 3SE +/- 0.77, N = 3SE +/- 43.31, N = 3SE +/- 30.36, N = 3SE +/- 1.08, N = 3SE +/- 8.24, N = 3SE +/- 0.21, N = 3SE +/- 21.65, N = 317030.3920714.1619501.4717087.3311695.9611545.089700.506809.1816358.3511820.6710862.129756.508365.018246.82

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 46.17, N = 3SE +/- 2.62, N = 3SE +/- 0.25, N = 3SE +/- 0.02, N = 3SE +/- 1.12, N = 3SE +/- 1.00, N = 3SE +/- 4.72, N = 3SE +/- 0.54, N = 3SE +/- 45.18, N = 3SE +/- 30.69, N = 3SE +/- 0.27, N = 3SE +/- 8.84, N = 3SE +/- 0.63, N = 3SE +/- 20.82, N = 316941.2820597.7019408.5617024.2711649.9011492.639646.856780.5416279.2711765.0910806.249705.638319.688206.71

OpenBenchmarking.orgGIOPS Per Watt, More Is Bettervkpeak 20210424int16-vec4TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080RTX 2070 SUPERRTX 2060 SUPER2040608010069.4263.6860.2466.9763.6782.3776.9469.9170.5264.3367.6757.23

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalarTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER3K6K9K12K15KSE +/- 27.84, N = 3SE +/- 1.11, N = 3SE +/- 20.56, N = 3SE +/- 1.14, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 3.46, N = 3SE +/- 5.77, N = 3SE +/- 27.43, N = 3SE +/- 20.31, N = 3SE +/- 0.36, N = 3SE +/- 0.30, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 311258.4413650.6612829.1611290.987730.757629.676403.144488.8510811.577814.837123.956445.645530.455437.69

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4K8K12K16K20KSE +/- 5.90, N = 3SE +/- 4.03, N = 3SE +/- 4.40, N = 3SE +/- 0.42, N = 3SE +/- 0.81, N = 3SE +/- 0.82, N = 3SE +/- 11.39, N = 3SE +/- 7.82, N = 3SE +/- 14.70, N = 3SE +/- 0.06, N = 3SE +/- 1.82, N = 3SE +/- 21.85, N = 3SE +/- 0.29, N = 3SE +/- 14.82, N = 314765.3816881.7616203.0114570.6810205.7610070.328477.235969.6514076.5710383.049468.388534.727362.197201.01

Hashcat

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: SHA1TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER30M60M90M120M150M121687941.74118925208.32107541023.93107438579.0491799645.83114015304.24109455812.73102307536.60127340705.79105384516.64104350302.6894933726.5197668381.5494045209.54

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: SHA-512TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4M8M12M16M20M16905956.9416765237.4115008611.1315209447.8312784504.7716411609.9615163734.6814388149.7617555452.6314124956.0413960472.6813001337.1913497084.8613006126.22

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: 7-ZipTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER3K6K9K12K15K11386.079312.468341.168989.327635.7212048.4310048.598644.7311209.3112169.8811541.888779.928752.068622.05

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER160032004800640080005920.115731.544963.495136.914896.677275.866770.975661.316142.104604.784386.734973.294944.904926.05

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER15000M30000M45000M60000M75000MSE +/- 90062008.87, N = 7SE +/- 104099604.32, N = 7SE +/- 114085221.76, N = 7SE +/- 119086542.02, N = 7SE +/- 82415641.88, N = 7SE +/- 64426488.19, N = 7SE +/- 50524660.91, N = 7SE +/- 33928239.60, N = 7SE +/- 73945478.17, N = 7SE +/- 48387138.48, N = 7SE +/- 104693541.11, N = 7SE +/- 40022380.64, N = 7SE +/- 62259505.74, N = 7SE +/- 49115005.26, N = 75668448571469978700000658464857145896241428641477457143402815000003415844285724005014286540743571434174605714337998642857339559000002940517142928643142857

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER5000M10000M15000M20000M25000MSE +/- 22120437.19, N = 7SE +/- 26924236.29, N = 6SE +/- 27258234.73, N = 7SE +/- 23290062.40, N = 7SE +/- 6164287.09, N = 7SE +/- 23586201.72, N = 7SE +/- 5748658.52, N = 7SE +/- 7946598.98, N = 7SE +/- 22447650.36, N = 7SE +/- 15457664.37, N = 7SE +/- 25963370.33, N = 7SE +/- 5146308.37, N = 7SE +/- 13731990.06, N = 7SE +/- 9752578.59, N = 71868794285722828250000216602428571925762857113375128571131451714291106874285777623285711781532857113596771429123001428571104991428695712428579398457143

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER700M1400M2100M2800M3500MSE +/- 3167166.63, N = 6SE +/- 2166012.72, N = 6SE +/- 2909578.36, N = 7SE +/- 3881545.38, N = 7SE +/- 2485372.17, N = 7SE +/- 2159742.99, N = 7SE +/- 2343684.52, N = 7SE +/- 1910248.05, N = 7SE +/- 2857349.20, N = 6SE +/- 1633078.21, N = 6SE +/- 2564067.95, N = 6SE +/- 430076.72, N = 7SE +/- 1259413.53, N = 7SE +/- 880321.52, N = 725830833333242516667307015714327385857141916942857188668571415899000001119700000246056666718936166671696733333153571428613146571431291485714

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER200K400K600K800K1000KSE +/- 555.18, N = 10SE +/- 879.27, N = 10SE +/- 815.38, N = 10SE +/- 415.55, N = 10SE +/- 340.13, N = 11SE +/- 535.21, N = 11SE +/- 305.81, N = 11SE +/- 258.83, N = 11SE +/- 337.46, N = 10SE +/- 498.27, N = 10SE +/- 447.26, N = 10SE +/- 1961.31, N = 15SE +/- 338.47, N = 11SE +/- 469.64, N = 1194440011530001097120991970720064687591587145427609892410712650642760580567500673493227

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER200K400K600K800K1000KSE +/- 340.04, N = 8SE +/- 405.57, N = 7SE +/- 528.10, N = 9SE +/- 816.73, N = 8SE +/- 463.85, N = 8SE +/- 863.64, N = 8SE +/- 78.96, N = 9SE +/- 121.65, N = 8SE +/- 2086.05, N = 8SE +/- 4311.72, N = 6SE +/- 841.20, N = 6SE +/- 432.37, N = 8SE +/- 350.48, N = 8SE +/- 208.74, N = 8678875847886807600719975512713503188427989299913644813506217452883412388355538349900

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: SupercarTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1224364860SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 335.3153.0151.4446.5038.9537.3734.0125.8633.3525.7024.8824.4523.4423.30

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER510152025SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.006, N = 3SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.005, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.016, N = 311.59220.76520.03717.54113.73312.89211.4518.50411.0317.9687.7427.6487.4097.347

LuxCoreRender

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.04880.09760.14640.19520.2440.1070.1660.1600.1510.1640.2170.1860.1730.1010.1110.1060.1150.1260.131

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER816243240SE +/- 0.01, N = 5SE +/- 0.00, N = 6SE +/- 0.24, N = 6SE +/- 0.08, N = 6SE +/- 0.06, N = 6SE +/- 0.05, N = 6SE +/- 0.05, N = 5SE +/- 0.00, N = 4SE +/- 0.02, N = 4SE +/- 0.01, N = 4SE +/- 0.00, N = 4SE +/- 0.03, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 416.8334.2733.2528.2023.7723.4520.9915.3615.2812.1512.1613.1013.2614.13MIN: 15.76 / MAX: 18.22MIN: 30.52 / MAX: 36.32MIN: 30.01 / MAX: 35.85MIN: 26.09 / MAX: 31.07MIN: 21.81 / MAX: 25.33MIN: 20.97 / MAX: 24.32MIN: 19.21 / MAX: 22.15MIN: 13.94 / MAX: 16.32MIN: 13.65 / MAX: 16.66MIN: 11.25 / MAX: 12.81MIN: 11.24 / MAX: 12.82MIN: 12.42 / MAX: 13.77MIN: 12.41 / MAX: 14.02MIN: 13.33 / MAX: 14.65

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.01420.02840.04260.05680.0710.0330.0460.0430.0450.0630.0540.0510.0520.0340.0380.0460.0370.0330.032

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.01350.0270.04050.0540.06750.0360.0450.0430.0440.0600.0520.0490.0490.0360.0390.0470.0370.0360.035

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER48121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.0414.0613.5111.678.718.257.195.366.835.375.154.973.893.93MIN: 6.59 / MAX: 7.3MIN: 13.57 / MAX: 14.34MIN: 12.39 / MAX: 13.74MIN: 11.22 / MAX: 11.86MIN: 8.19 / MAX: 8.87MIN: 8.13 / MAX: 8.41MIN: 6.89 / MAX: 7.44MIN: 5.23 / MAX: 5.58MIN: 6.56 / MAX: 6.93MIN: 5.07 / MAX: 5.51MIN: 5.03 / MAX: 5.33MIN: 4.86 / MAX: 5.09MIN: 3.78 / MAX: 4.04MIN: 3.81 / MAX: 4.12

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.9211.9911.549.997.416.986.044.566.514.844.694.533.913.91MIN: 2.23 / MAX: 8.19MIN: 3.93 / MAX: 14.25MIN: 3.63 / MAX: 13.73MIN: 3.32 / MAX: 11.84MIN: 2.28 / MAX: 8.81MIN: 2.27 / MAX: 8.27MIN: 1.87 / MAX: 7.15MIN: 1.64 / MAX: 5.37MIN: 1.93 / MAX: 7.74MIN: 1.66 / MAX: 5.75MIN: 1.66 / MAX: 5.58MIN: 1.3 / MAX: 5.39MIN: 1.41 / MAX: 4.63MIN: 1.4 / MAX: 4.62

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER3691215SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.2112.3511.9610.798.678.437.616.067.105.775.585.444.484.51MIN: 5.68 / MAX: 9.07MIN: 10.23 / MAX: 17.13MIN: 9.91 / MAX: 16.43MIN: 8.72 / MAX: 14.46MIN: 6.96 / MAX: 10.98MIN: 6.69 / MAX: 10.55MIN: 6.03 / MAX: 9.24MIN: 4.73 / MAX: 7.39MIN: 5.6 / MAX: 8.83MIN: 4.67 / MAX: 6.58MIN: 4.54 / MAX: 6.31MIN: 4.44 / MAX: 6.12MIN: 3.75 / MAX: 4.81MIN: 3.75 / MAX: 4.99

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER3691215SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 6SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 45.219.729.288.006.035.814.913.615.013.853.713.582.812.88MIN: 1.69 / MAX: 6.28MIN: 3.01 / MAX: 11.82MIN: 2.69 / MAX: 11.32MIN: 2.38 / MAX: 9.7MIN: 2.03 / MAX: 7.29MIN: 1.82 / MAX: 7.01MIN: 1.66 / MAX: 5.96MIN: 1.15 / MAX: 4.3MIN: 1.68 / MAX: 6.06MIN: 1.19 / MAX: 4.64MIN: 1.18 / MAX: 4.47MIN: 1.17 / MAX: 4.31MIN: 0.88 / MAX: 3.32MIN: 0.92 / MAX: 3.41

LeelaChessZero

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

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER9K18K27K36K45KSE +/- 46.38, N = 3SE +/- 52.75, N = 3SE +/- 106.84, N = 3SE +/- 186.45, N = 3SE +/- 101.51, N = 3SE +/- 168.57, N = 3SE +/- 77.49, N = 3SE +/- 110.08, N = 3SE +/- 103.74, N = 3SE +/- 110.32, N = 3SE +/- 29.46, N = 3SE +/- 217.96, N = 3SE +/- 32.62, N = 3SE +/- 72.46, N = 329168403483940937477317392925326639186752773420576186601735314730146801. (CXX) g++ options: -flto -pthread

FAHBench

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

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER70140210280350SE +/- 0.59, N = 3SE +/- 0.19, N = 3SE +/- 0.79, N = 3SE +/- 0.26, N = 3SE +/- 0.12, N = 3SE +/- 0.47, N = 3SE +/- 0.27, N = 3SE +/- 0.16, N = 3SE +/- 0.75, N = 3SE +/- 0.45, N = 3SE +/- 0.35, N = 3SE +/- 0.18, N = 3SE +/- 0.59, N = 3SE +/- 0.40, N = 3307.59344.99335.10321.33267.28267.07236.51182.00305.31261.57244.52227.94205.31208.00

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 ScoreTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER150300450600750382.42679.58666.48568.26454.50413.18384.18293.78359.84270.30260.46258.36242.94242.68

Chaos Group V-RAY

OpenBenchmarking.orgvpaths Per Watt, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER36912155.5737.6117.4197.3867.9659.5329.1508.5705.8146.5766.0976.2455.1325.066

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER5001000150020002500SE +/- 0.88, N = 3SE +/- 1.33, N = 3SE +/- 2.03, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 1.15, N = 3SE +/- 0.33, N = 31006209920491785148614171256852990799780793519530

OpenBenchmarking.orgvrays Per Watt, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER481216208.01810.42810.39310.53812.42013.68213.13612.4978.1448.8349.0028.4937.9477.727

OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPUTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER6001200180024003000SE +/- 1.76, N = 3SE +/- 9.02, N = 3SE +/- 3.48, N = 3SE +/- 3.00, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.76, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 31386285727822373198218281658116813249819591008785803

NAMD CUDA

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

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 AtomsTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.03490.06980.10470.13960.1745SE +/- 0.00130, N = 5SE +/- 0.00010, N = 5SE +/- 0.00031, N = 5SE +/- 0.00023, N = 5SE +/- 0.00014, N = 3SE +/- 0.00049, N = 5SE +/- 0.00020, N = 5SE +/- 0.00054, N = 5SE +/- 0.00078, N = 5SE +/- 0.00058, N = 5SE +/- 0.00019, N = 5SE +/- 0.00016, N = 5SE +/- 0.00031, N = 5SE +/- 0.00029, N = 50.133040.119880.120660.120990.124850.126110.129280.154710.133240.135220.138010.143230.152470.15502

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 OpenCLTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER0.56121.12241.68362.24482.806SE +/- 0.005, N = 11SE +/- 0.000, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.001, N = 10SE +/- 0.004, N = 11SE +/- 0.001, N = 10SE +/- 0.001, N = 9SE +/- 0.001, N = 10SE +/- 0.002, N = 10SE +/- 0.002, N = 101.6401.4751.5131.5551.6682.0872.0832.4941.6771.8972.0742.0892.0912.0761. (CXX) g++ options: -rdynamic

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: SingleTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER612182430SE +/- 0.032, N = 5SE +/- 0.010, N = 5SE +/- 0.007, N = 5SE +/- 0.006, N = 5SE +/- 0.003, N = 5SE +/- 0.004, N = 5SE +/- 0.006, N = 5SE +/- 0.001, N = 5SE +/- 0.020, N = 5SE +/- 0.012, N = 5SE +/- 0.023, N = 5SE +/- 0.018, N = 5SE +/- 0.033, N = 5SE +/- 0.032, N = 513.5609.3029.56111.26813.55717.54917.67323.13514.78117.51619.05319.88122.29722.3271. (CXX) g++ options: -O3 -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: BMW27 - Compute: CUDATITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1428425670SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 336.7918.3618.8521.9427.8028.9531.8243.8538.4950.7451.5251.8564.8363.85

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER714212835SE +/- 0.01, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 4SE +/- 2.65, N = 15SE +/- 0.01, N = 4SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 2.65, N = 15SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 318.729.489.7111.2817.0915.7317.4223.5619.2425.6829.0825.9030.3930.15

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDATITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER70140210280350SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.20, N = 3SE +/- 0.41, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3152.7051.2852.6460.8773.4176.0585.37127.15152.39160.42169.34174.29308.70299.30

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER306090120150SE +/- 0.16, N = 3SE +/- 0.31, N = 3SE +/- 0.06, N = 3SE +/- 0.23, N = 3SE +/- 0.22, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.63, N = 3SE +/- 0.27, N = 373.4329.9231.6836.0944.1846.9953.6677.8773.3081.8886.7490.56146.54143.45

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDATITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER306090120150SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 369.4634.4035.4641.4152.6054.1361.6784.5572.4295.6896.8697.75122.65121.50

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1428425670SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 2.61, N = 15SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 2.59, N = 15SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 332.7419.1119.9222.7934.1733.5039.2453.9233.9244.5550.1551.3960.4061.15

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDATITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER120240360480600SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.34, N = 3SE +/- 0.25, N = 3SE +/- 0.11, N = 3281.08120.38124.43146.29184.76189.91218.45316.30283.96344.55354.50361.62556.43545.19

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER4080120160200SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.02, N = 3SE +/- 0.54, N = 3SE +/- 0.57, N = 397.5744.1245.8852.8067.1872.9882.07115.2198.64123.53129.02130.76186.12183.31

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CUDATITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER2004006008001000SE +/- 0.26, N = 3SE +/- 0.32, N = 3SE +/- 0.21, N = 3SE +/- 0.45, N = 3SE +/- 0.27, N = 3SE +/- 0.24, N = 3SE +/- 0.31, N = 3SE +/- 0.24, N = 3SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3551.44373.69386.72442.84501.65507.79596.57962.31548.91555.03585.52595.811113.491083.28

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiXTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER400800120016002000SE +/- 3.15, N = 3SE +/- 0.77, N = 3SE +/- 0.34, N = 3SE +/- 0.86, N = 3SE +/- 0.30, N = 3SE +/- 0.33, N = 3SE +/- 0.26, N = 3SE +/- 0.51, N = 3SE +/- 0.69, N = 3SE +/- 1.18, N = 3SE +/- 3.68, N = 3SE +/- 1.83, N = 3SE +/- 0.26, N = 3SE +/- 0.20, N = 3907.46345.19358.78407.33459.78466.42552.11876.68899.59913.26975.221011.951819.251767.42

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: YesTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER20406080100SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.30, N = 3SE +/- 0.22, N = 3SE +/- 0.43, N = 3SE +/- 0.31, N = 341.9128.1829.2932.3740.5646.6350.6467.1344.2354.0759.5664.2274.9876.12

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER3691215SE +/- 0.014, N = 6SE +/- 0.005, N = 7SE +/- 0.004, N = 7SE +/- 0.012, N = 7SE +/- 0.008, N = 6SE +/- 0.009, N = 6SE +/- 0.004, N = 6SE +/- 0.009, N = 5SE +/- 0.008, N = 6SE +/- 0.014, N = 5SE +/- 0.020, N = 5SE +/- 0.004, N = 5SE +/- 0.017, N = 5SE +/- 0.012, N = 47.3375.5175.6356.0367.0447.8158.31710.3627.6298.8809.49310.16511.49311.642

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: YesTITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER1.19752.3953.59254.795.9875SE +/- 0.008, N = 8SE +/- 0.003, N = 9SE +/- 0.001, N = 9SE +/- 0.004, N = 9SE +/- 0.006, N = 9SE +/- 0.003, N = 8SE +/- 0.003, N = 8SE +/- 0.003, N = 7SE +/- 0.006, N = 8SE +/- 0.006, N = 8SE +/- 0.005, N = 8SE +/- 0.004, N = 7SE +/- 0.008, N = 7SE +/- 0.007, N = 73.8553.2353.2833.3663.7304.0354.1804.8503.8724.3954.6484.8535.3055.322

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: HighestRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 2080RTX 2060 SUPER246810SE +/- 0.006, N = 9SE +/- 0.012, N = 9SE +/- 0.006, N = 9SE +/- 0.014, N = 8SE +/- 0.011, N = 7SE +/- 0.009, N = 73.0123.0843.3174.2495.0176.1391. (CXX) g++ options: -O3 -O2 -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: HighestRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 2080RTX 2060 SUPER246810SE +/- 0.012, N = 8SE +/- 0.009, N = 8SE +/- 0.008, N = 8SE +/- 0.011, N = 7SE +/- 0.012, N = 6SE +/- 0.018, N = 53.9394.0824.3875.7366.8738.4891. (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 3.0TITAN RTXRTX 3090RTX 3080 TiRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPER80160240320400SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 3SE +/- 0.88, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 1.67, N = 3SE +/- 1.33, N = 3SE +/- 0.88, N = 3233139143164201227237300245322338351374376

102 Results Shown

PlaidML:
  No - Inference - ResNet 50 - OpenCL
  No - Inference - VGG16 - OpenCL
  No - Inference - VGG19 - OpenCL
PlaidML:
  No - Inference - ResNet 50 - OpenCL
  No - Inference - VGG16 - OpenCL
  No - Inference - VGG19 - OpenCL
ViennaCL
cl-mem:
  Read
  Write
  Copy
ViennaCL
SHOC Scalable HeterOgeneous Computing
ViennaCL:
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dGEMV-T
ViennaCL
cl-mem:
  Read
  Write
  Copy
ViennaCL:
  OpenCL BLAS - sCOPY
  OpenCL BLAS - sAXPY
  OpenCL BLAS - dCOPY
  OpenCL BLAS - dDOT
SHOC Scalable HeterOgeneous Computing
clpeak
clpeak
Mixbench:
  NVIDIA CUDA - Single Precision
  NVIDIA CUDA - Double Precision
Mixbench:
  NVIDIA CUDA - Single Precision
  NVIDIA CUDA - Double Precision
  NVIDIA CUDA - Half Precision
ArrayFire
clpeak:
  Single-Precision Float
  Double-Precision Double
vkpeak:
  fp32-scalar
  fp32-vec4
  fp16-scalar
  fp16-vec4
SHOC Scalable HeterOgeneous Computing:
  OpenCL - FFT SP
  OpenCL - GEMM SGEMM_N
vkpeak:
  fp64-scalar
  fp64-vec4
SHOC Scalable HeterOgeneous Computing:
  OpenCL - FFT SP
  OpenCL - GEMM SGEMM_N
  OpenCL - S3D
ViennaCL:
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-TN
ViennaCL
ViennaCL
SHOC Scalable HeterOgeneous Computing
Mixbench
clpeak
vkpeak:
  int32-scalar
  int32-vec4
vkpeak
vkpeak:
  int16-scalar
  int16-vec4
Hashcat:
  SHA1
  SHA-512
  7-Zip
  TrueCrypt RIPEMD160 + XTS
Hashcat:
  MD5
  SHA1
  SHA-512
  7-Zip
  TrueCrypt RIPEMD160 + XTS
IndigoBench:
  OpenCL GPU - Supercar
  OpenCL GPU - Bedroom
LuxCoreRender
LuxCoreRender
LuxCoreRender:
  DLSC - GPU
  LuxCore Benchmark - GPU
LuxCoreRender:
  DLSC - GPU
  LuxCore Benchmark - GPU
  Orange Juice - GPU
  Danish Mood - GPU
LeelaChessZero
FAHBench
OctaneBench
Chaos Group V-RAY
Chaos Group V-RAY
Chaos Group V-RAY
Chaos Group V-RAY
NAMD CUDA
ArrayFire
VkResample
Blender:
  BMW27 - CUDA
  BMW27 - NVIDIA OptiX
  Classroom - CUDA
  Classroom - NVIDIA OptiX
  Fishy Cat - CUDA
  Fishy Cat - NVIDIA OptiX
  Pabellon Barcelona - CUDA
  Pabellon Barcelona - NVIDIA OptiX
  Barbershop - CUDA
  Barbershop - NVIDIA OptiX
RealSR-NCNN:
  4x - Yes
  4x - No
Waifu2x-NCNN Vulkan
Betsy GPU Compressor:
  ETC1 - Highest
  ETC2 RGB - Highest
RedShift Demo