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
Allow Limiting Results To Certain Suite(s)

Statistics

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

Graph Settings

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
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 Behavior (Only Show Selected Data)
  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 Benchmarksclpeak: Single-Precision Floatblender: Classroom - CUDAblender: Barbershop - NVIDIA OptiXmixbench: OpenCL - Single Precisionblender: Classroom - NVIDIA OptiXblender: Pabellon Barcelona - CUDAblender: Pabellon Barcelona - NVIDIA OptiXv-ray: NVIDIA CUDA GPUblender: Fishy Cat - CUDAblender: BMW27 - CUDAv-ray: NVIDIA RTX GPUluxcorerender-cl: Foodblender: BMW27 - NVIDIA OptiXindigobench: OpenCL GPU - Bedroomblender: Fishy Cat - NVIDIA OptiXoctanebench: Total Scoreredshift: luxcorerender-cl: DLSCclpeak: Integer Compute INTluxcorerender-cl: Rainbow Colors and Prismshoc: OpenCL - GEMM SGEMM_Nluxcorerender-cl: LuxCore Benchmarklczero: OpenCLfinancebench: Black-Scholes OpenCLclpeak: Double-Precision Doubleviennacl: OpenCL BLAS - dGEMM-TTvkresample: 2x - Doubleviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-NNcl-mem: Writeclpeak: Global Memory Bandwidthhashcat: SHA1vkresample: 2x - Singleshoc: OpenCL - FFT SPhashcat: SHA-512hashcat: MD5shoc: OpenCL - MD5 Hashshoc: OpenCL - S3Drealsr-ncnn: 4x - Yesindigobench: OpenCL GPU - Supercarhashcat: TrueCrypt RIPEMD160 + XTSmixbench: OpenCL - Double Precisioncl-mem: Readmixbench: OpenCL - Integerhashcat: 7-Ziprodinia: OpenCL Particle Filterviennacl: OpenCL BLAS - dAXPYbetsy: ETC2 RGB - Highestbetsy: ETC1 - Highestrealsr-ncnn: 4x - Noviennacl: OpenCL BLAS - dCOPYshoc: OpenCL - Texture Read Bandwidthviennacl: OpenCL BLAS - dDOTshoc: OpenCL - Triadviennacl: OpenCL BLAS - sAXPYfahbench: arrayfire: Conjugate Gradient OpenCLviennacl: OpenCL BLAS - sDOTwaifu2x-ncnn: 2x - 3 - Yesviennacl: OpenCL BLAS - sCOPYgromacs-gpu: Water Benchmarkcl-mem: Copyshoc: OpenCL - Reductionnamd-cuda: ATPase Simulation - 327,506 AtomsRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060RTX 3060 TiRTX 3070RTX 3080RTX 30905390.85304.551812.317223.66150.10583.12208.09474140.6474.506581.2036.925.58275.05193.726074773.305393.497.912451.992.781224819.776333231.53349.257217220251.7275.99823335714327.222801.49810511714292586737142916.3116147.56385.64518.379310388195.67297.47256.564422828.9892919.4016.78312.7652801035.4230812.6239253183.83932.6592125.8522185.789239.3263.2810.179146982.39301.611790.078240.30145.23544.98194.57490121.4163.927341.3230.977.34765.22243.2716283804.186949.7911.233046.363.601453716.414200263.47309.018248249249335.1368.53930708571422.247963.12511863857142917332857118.3662188.87775.84123.229349878221.54396.98197.384939827.9913888.4426.08111.5133681106.3040312.7589329207.65002.0822635.3822766.271286.9317.7280.166667259.99308.951844.768392.72149.28556.87198.29478122.9464.957101.2931.257.37964.44243.2805033784.147048.6510.973114.473.561482915.991267.84303.671254252255321.8368.47951190000022.284967.61612170428572990632857118.7194193.42775.11123.459357513226.00396.88354.505029557.8903888.3605.93911.3733671064.2840112.7737321205.52872.0952605.3732716.358283.4317.4600.161458583.14172.251015.849773.7191.19357.54134.8676196.9951.279621.7928.527.72056.97264.4860183504.308612.759.863319.273.591740912.807308.54263.373289293290318.7369.451110704285719.5011087.4714209714293509672857121.8151199.28163.63224.518426357260.38396.89693.075903907.0183867.5235.63610.4193661133.9340212.7814325229.31502.0702604.8902816.753290.8323.2710.151408890.45169.00987.7310940.4288.12354.15134.5774397.2051.689031.8626.587.74350.67262.529073424.239246.859.293349.363.551878111.831345.97324234.437327332329331.2369.161221944285718.9941098.1615621857143854847142924.3235196.92759.53524.895462213290.29396.810825.096357606.2573886.8284.9719.4423701114.9040412.7697317246.18092.0742504.6722797.111290.1317.8480.1483310284.15160.65925.5511866.9283.47345.65128.9975696.2050.669261.9025.747.98247.42266.6842293234.3210291.509.243725.023.612105010.525376.32354215.024352357357348.6405.561355440000017.4361203.3417356857144285754285726.6243213.05854.19925.690535927314.09437.511714.437187275.7844276.2274.6118.9264041165.1644012.8073328262.07031.9002504.4372887.391300.6328.7710.1461413380.02152.86916.0916375.1674.81285.52104.1192872.4538.4912452.1919.5211.03336.07352.0272892475.6313256.8912.344831.944.65276399.311522.28155.569473483476449.5507.061768538571414.7581487.9522477428575518631428635.3459271.70044.52933.371656675432.17545.616219.088926804.4645185.1383.8517.8604781187.9652112.8851405298.64271.6903223.9653088.178321.6370.5010.1440813624.14161.80969.5817145.6779.03297.11109.0289273.3638.7412322.0819.9411.16336.63363.8720472465.6713017.2112.924975.624.69272999.135515.02472152.755468456474476.8504.511775598571414.1821574.8522493428575555460000036.2892289.59643.32933.666654338439.29545.316892.918948874.7025206.8757.5574771169.7251612.8550389292.39921.6883054.0132967.018306.3350.9710.1662312487.45128.50863.8713135.0778.48319.41122.2578485.6444.3510592.0624.388.42058.22288.4731653055.535737.4413.262772.304.511845616.662000209.56194377.589199199201296.4314.23771334285723.352934.0599789714292282927142915.2250171.80072.19825.656300188177.72315.86602.454302559.7633259.7346.44911.1823111256.4332824.3577302180.36982.5182895.2592716.086266.7306.3170.1628116008.6585.48549.7918832.9954.75217.7886.04118561.9931.9215482.9917.8211.45941.98382.771312407.258364.5417.723438.495.912592012.976303.90263.987292292293383.3389.001109217142917.6691152.9114121285713291898571421.6931211.88253.99034.011428390255.14393.19593.815886916.9683996.7904.9748.8463622119.2539824.7052357236.55352.0913244.5412927.505297.0324.7090.1390420059.0076.26462.6022115.6948.16190.0576.96134154.2628.9917153.3616.1012.89035.71410.5582532287.9310229.1818.923775.876.492920810.464360.44223.669341341342379.8389.081310747142917.5161135.1416651857143864135714325.5285218.50150.03137.230503400300.72393.111288.376860005.9793966.0304.2938.4003652121.5639724.6655357266.10162.0903254.3072947.657296.9325.8450.1415129322.8761.63400.0830534.4436.43147.5456.72165041.8022.1821513.9611.6417.39324.62560.1212851669.5915094.0222.316181.237.87367337.616537.24492149.531501497494641.3662.161893463333311.4041915.3823985666675545870000037.4002339.90734.39645.992710567385.83666.017004.839846254.3866304.5233.3456.4285472204.2059225.2918468318.64991.5613733.6203509.127354.5387.7290.1313835070.6951.43336.9935766.2730.46120.3546.75196434.5918.4726204.669.7220.77820.37678.244214111.1518024.3426.338144.819.16386236.305656.28600122.897603599601741.1811.92226796714299.2752348.6728654428576666884285744.4370429.33329.67152.861850275500.47825.618323.7111445403.7677224.0003.0165.8566072237.7765025.4663504343.36051.4853753.4513669.200363.4391.9580.13550OpenBenchmarking.org

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 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 20608K16K24K32K40KSE +/- 56.57, N = 13SE +/- 109.43, N = 3SE +/- 12.28, N = 14SE +/- 16.76, N = 13SE +/- 162.29, N = 15SE +/- 198.54, N = 15SE +/- 88.44, N = 15SE +/- 54.52, N = 13SE +/- 15.95, N = 12SE +/- 80.96, N = 15SE +/- 80.51, N = 15SE +/- 83.80, N = 15SE +/- 55.97, N = 1535070.6929322.8720059.0016008.6513624.1413380.0212487.4510284.158890.458583.147259.996982.395390.851. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CUDARTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERTITAN RTXRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2060RTX 207070140210280350SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.53, N = 3SE +/- 0.02, N = 351.4361.6376.2685.48128.50152.86160.65161.80169.00172.25301.61304.55308.95

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: NVIDIA OptiXRTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 3060RTX 2080 TiRTX 2080 SUPERTITAN RTXRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2060RTX 2070400800120016002000SE +/- 2.26, N = 3SE +/- 0.48, N = 3SE +/- 0.73, N = 3SE +/- 2.14, N = 3SE +/- 0.15, N = 3SE +/- 0.51, N = 3SE +/- 0.76, N = 3SE +/- 0.70, N = 3SE +/- 0.79, N = 3SE +/- 0.36, N = 3SE +/- 0.39, N = 3SE +/- 0.62, N = 3SE +/- 3.33, N = 3336.99400.08462.60549.79863.87916.09925.55969.58987.731015.841790.071812.311844.76

Mixbench

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

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Single PrecisionRTX 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 20608K16K24K32K40KSE +/- 645.17, N = 15SE +/- 541.23, N = 15SE +/- 86.13, N = 15SE +/- 4.81, N = 14SE +/- 3.96, N = 14SE +/- 14.06, N = 15SE +/- 1.98, N = 13SE +/- 1.97, N = 14SE +/- 1.55, N = 14SE +/- 6.29, N = 14SE +/- 2.54, N = 13SE +/- 6.28, N = 13SE +/- 75.94, N = 1535766.2730534.4422115.6918832.9917145.6716375.1613135.0711866.9210940.429773.718392.728240.307223.661. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiRTX 3060TITAN RTXRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060306090120150SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.25, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.30, N = 330.4636.4348.1654.7574.8178.4879.0383.4788.1291.19145.23149.28150.10

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CUDARTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060130260390520650SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.48, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.40, N = 3SE +/- 0.14, N = 3SE +/- 1.13, N = 3120.35147.54190.05217.78285.52297.11319.41345.65354.15357.54544.98556.87583.12

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 206050100150200250SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 3SE +/- 0.02, N = 346.7556.7276.9686.04104.11109.02122.25128.99134.57134.86194.57198.29208.09

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 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2070 SUPERRTX 2080 SUPERRTX 2080RTX 2060 SUPERRTX 2070RTX 2060400800120016002000SE +/- 1.33, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 31964165013411185928892784761756743490478474

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CUDARTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2060 SUPERRTX 2070RTX 2060306090120150SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.23, N = 3SE +/- 0.22, N = 3SE +/- 0.02, N = 334.5941.8054.2661.9972.4573.3685.6496.2096.9997.20121.41122.94140.64

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CUDARTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2060 SUPERRTX 2070RTX 206020406080100SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 318.4722.1828.9931.9238.4938.7444.3550.6651.2751.6863.9264.9574.50

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.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPURTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2070 SUPERRTX 2080 SUPERRTX 2080RTX 2060 SUPERRTX 2070RTX 20606001200180024003000SE +/- 5.90, N = 3SE +/- 2.00, N = 3SE +/- 2.00, N = 3SE +/- 1.45, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 1.33, N = 3SE +/- 1.15, N = 32620215117151548124512321059962926903734710658

LuxCoreRender OpenCL

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 20601.04852.0973.14554.1945.2425SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 7SE +/- 0.03, N = 4SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 12SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.663.963.362.992.192.082.061.901.861.791.321.291.20MIN: 0.29 / MAX: 5.93MIN: 0.26 / MAX: 4.99MIN: 0.2 / MAX: 4.25MIN: 0.2 / MAX: 3.75MIN: 0.23 / MAX: 2.7MIN: 0.22 / MAX: 2.61MIN: 0.22 / MAX: 2.57MIN: 0.21 / MAX: 2.38MIN: 0.21 / MAX: 2.29MIN: 0.09 / MAX: 2.3MIN: 0.23 / MAX: 1.59MIN: 0.21 / MAX: 1.55MIN: 0.21 / MAX: 1.43

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 2080 TiTITAN RTXRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060816243240SE +/- 0.01, N = 5SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 2.61, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 39.7211.6416.1017.8219.5219.9424.3825.7426.5828.5230.9731.2536.92

IndigoBench

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

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 2060510152025SE +/- 0.031, N = 3SE +/- 0.031, N = 3SE +/- 0.011, N = 3SE +/- 0.004, N = 3SE +/- 0.017, N = 3SE +/- 0.010, N = 3SE +/- 0.006, N = 3SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.000, N = 320.77817.39312.89011.45911.16311.0338.4207.9827.7437.7207.3797.3475.582

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3090RTX 3080RTX 3070RTX 2080 TiTITAN RTXRTX 3060 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 3060RTX 2070RTX 2060 SUPERRTX 206020406080100SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 2.53, N = 15SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 320.3724.6235.7136.0736.6341.9847.4250.6756.9758.2264.4465.2275.05

OctaneBench

OctaneBench is a test of the OctaneRender on the GPU and requires the use of NVIDIA CUDA. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreRTX 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2070RTX 2060 SUPERRTX 2060150300450600750678.24560.12410.56382.77363.87352.03288.47266.68264.49262.53243.28243.27193.73

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 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 2060100200300400500SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 1.20, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 1.76, N = 3SE +/- 1.67, N = 3SE +/- 1.86, N = 3141166228240246247305323342350378380477

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 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2070 SUPERRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.01, 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 +/- 0.08, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 311.159.597.937.255.675.635.534.324.304.234.184.143.30MIN: 9.79 / MAX: 11.28MIN: 9.28 / MAX: 9.71MIN: 7.82 / MAX: 8.13MIN: 6.94 / MAX: 7.39MIN: 4.85 / MAX: 5.74MIN: 5.21 / MAX: 5.75MIN: 5.23 / MAX: 5.69MIN: 4.15 / MAX: 4.43MIN: 1.32 / MAX: 4.51MIN: 4.14 / MAX: 4.29MIN: 4.1 / MAX: 4.29MIN: 3.8 / MAX: 4.28MIN: 3.15 / MAX: 3.39

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 3090RTX 3080RTX 2080 TiTITAN RTXRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 3060RTX 20604K8K12K16K20KSE +/- 116.54, N = 12SE +/- 160.26, N = 15SE +/- 128.94, N = 15SE +/- 473.13, N = 15SE +/- 65.60, N = 13SE +/- 50.89, N = 13SE +/- 85.43, N = 15SE +/- 71.02, N = 15SE +/- 89.81, N = 15SE +/- 78.69, N = 15SE +/- 83.52, N = 15SE +/- 20.50, N = 13SE +/- 47.74, N = 1518024.3415094.0213256.8913017.2110291.5010229.189246.858612.758364.547048.656949.795737.445393.491. (CXX) g++ options: -O3 -rdynamic -lOpenCL

LuxCoreRender OpenCL

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 3090RTX 3080RTX 3070RTX 3060 TiRTX 3060TITAN RTXRTX 2080 TiRTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2060612182430SE +/- 0.04, N = 6SE +/- 0.10, N = 3SE +/- 0.11, N = 5SE +/- 0.04, N = 5SE +/- 0.04, N = 4SE +/- 0.05, N = 4SE +/- 0.03, N = 4SE +/- 0.09, N = 4SE +/- 0.01, N = 4SE +/- 0.29, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 326.3322.3118.9217.7213.2612.9212.3411.2310.979.869.299.247.91MIN: 23.57 / MAX: 27.71MIN: 20.53 / MAX: 23.39MIN: 17.65 / MAX: 20.07MIN: 16.31 / MAX: 18.32MIN: 12.32 / MAX: 13.86MIN: 11.38 / MAX: 13.49MIN: 10.56 / MAX: 12.86MIN: 5.85 / MAX: 11.69MIN: 10.17 / MAX: 11.29MIN: 3.83 / MAX: 10.57MIN: 8.89 / MAX: 9.66MIN: 8.32 / MAX: 9.68MIN: 6.97 / MAX: 8.2

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 3090RTX 3080TITAN RTXRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 3060 TiRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 3060RTX 20602K4K6K8K10KSE +/- 29.12, N = 11SE +/- 62.64, N = 6SE +/- 38.91, N = 10SE +/- 12.95, N = 10SE +/- 20.37, N = 10SE +/- 1.79, N = 10SE +/- 2.73, N = 10SE +/- 1.77, N = 9SE +/- 1.92, N = 9SE +/- 7.35, N = 9SE +/- 7.32, N = 9SE +/- 3.66, N = 9SE +/- 0.34, N = 88144.816181.234975.624831.943775.873725.023438.493349.363319.273114.473046.362772.302451.991. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

LuxCoreRender OpenCL

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 3090RTX 3080RTX 3070RTX 3060 TiTITAN RTXRTX 2080 TiRTX 3060RTX 2080 SUPERRTX 2060 SUPERRTX 2070 SUPERRTX 2070RTX 2080RTX 20603691215SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 39.167.876.495.914.694.654.513.613.603.593.563.552.78MIN: 0.23 / MAX: 10.53MIN: 0.27 / MAX: 9.03MIN: 0.27 / MAX: 7.45MIN: 0.27 / MAX: 6.84MIN: 0.27 / MAX: 5.45MIN: 0.27 / MAX: 5.37MIN: 0.23 / MAX: 5.21MIN: 0.23 / MAX: 4.14MIN: 0.23 / MAX: 4.14MIN: 0.11 / MAX: 4.24MIN: 0.23 / MAX: 4.1MIN: 0.23 / MAX: 4.09MIN: 0.23 / MAX: 3.19

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 3090RTX 3080RTX 3070RTX 2080 TiTITAN RTXRTX 3060 TiRTX 2080 SUPERRTX 2080RTX 3060RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 20608K16K24K32K40KSE +/- 98.56, N = 3SE +/- 210.78, N = 3SE +/- 49.53, N = 3SE +/- 120.07, N = 3SE +/- 211.49, N = 3SE +/- 104.85, N = 3SE +/- 98.63, N = 3SE +/- 72.61, N = 3SE +/- 95.55, N = 3SE +/- 31.66, N = 3SE +/- 73.63, N = 3SE +/- 59.97, N = 3SE +/- 40.29, N = 3386233673329208276392729925920210501878118456174091482914537122481. (CXX) g++ options: -flto -pthread

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 3090RTX 3080TITAN RTXRTX 2080 TiRTX 3070RTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 3060RTX 2060510152025SE +/- 0.039276, N = 15SE +/- 0.146254, N = 15SE +/- 0.101653, N = 15SE +/- 0.054471, N = 15SE +/- 0.002752, N = 14SE +/- 0.038362, N = 15SE +/- 0.009750, N = 14SE +/- 0.012692, N = 13SE +/- 0.020839, N = 15SE +/- 0.009545, N = 14SE +/- 0.043753, N = 15SE +/- 0.251378, N = 15SE +/- 0.060602, N = 156.3050007.6160009.1350009.31100010.46400010.52500011.83100012.80700012.97600015.99100016.41420016.66200019.7763331. (CXX) g++ options: -O3 -march=native -fopenmp

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3090RTX 3080RTX 2080 TiTITAN RTXRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 2060RTX 3060140280420560700SE +/- 0.77, N = 3SE +/- 0.68, N = 3SE +/- 1.36, N = 3SE +/- 4.52, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.92, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.70, N = 3SE +/- 0.48, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3656.28537.24522.28515.02376.32360.44345.97308.54303.90267.84263.47231.53209.561. (CXX) g++ options: -O3 -rdynamic -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.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTRTX 3090RTX 3080TITAN RTXRTX 2080 SUPERRTX 2080RTX 3060130260390520650SE +/- 8.15, N = 4SE +/- 4.50, N = 26004924723543241941. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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 3090RTX 3080TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 2060RTX 306080160240320400SE +/- 0.08, N = 3SE +/- 0.24, N = 3SE +/- 1.08, N = 3SE +/- 0.19, N = 3SE +/- 0.12, N = 3SE +/- 0.28, N = 3SE +/- 0.24, N = 3SE +/- 0.02, N = 3SE +/- 0.83, N = 3SE +/- 1.78, N = 3SE +/- 0.33, N = 3SE +/- 0.53, N = 3SE +/- 0.28, N = 3122.90149.53152.76155.57215.02223.67234.44263.37263.99303.67309.02349.26377.591. (CXX) g++ options: -O3 -pthread

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-NTRTX 3090RTX 3080RTX 2080 TiTITAN RTXRTX 2080 SUPERRTX 3070RTX 2080RTX 3060 TiRTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 2060RTX 3060130260390520650SE +/- 1.33, N = 3SE +/- 3.18, N = 6SE +/- 2.65, N = 3SE +/- 2.00, N = 2SE +/- 1.67, N = 3SE +/- 1.86, N = 3SE +/- 0.88, N = 3SE +/- 5.50, N = 26035014734683523413272922902542482171991. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNRTX 3090RTX 3080RTX 2080 TiTITAN RTXRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 3060130260390520650SE +/- 1.33, N = 3SE +/- 3.40, N = 6SE +/- 8.00, N = 2SE +/- 1.00, N = 3SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 1.00, N = 3SE +/- 1.15, N = 3SE +/- 3.67, N = 35994974834563573413322932922522491991. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNRTX 3090RTX 3080RTX 2080 TiTITAN RTXRTX 2080 SUPERRTX 3070RTX 2080RTX 3060 TiRTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 2060RTX 3060130260390520650SE +/- 1.86, N = 3SE +/- 5.20, N = 6SE +/- 2.73, N = 3SE +/- 2.00, N = 2SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 1.00, N = 3SE +/- 2.19, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 2SE +/- 3.09, N = 46014944764743573423292932912552492202011. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

cl-mem

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

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3090RTX 3080TITAN RTXRTX 2080 TiRTX 3060 TiRTX 3070RTX 2080 SUPERRTX 2060 SUPERRTX 2080RTX 2070RTX 2070 SUPERRTX 3060RTX 2060160320480640800SE +/- 0.42, N = 9SE +/- 0.36, N = 3SE +/- 0.86, N = 8SE +/- 0.46, N = 8SE +/- 0.10, N = 8SE +/- 0.10, N = 8SE +/- 0.52, N = 8SE +/- 0.22, N = 8SE +/- 0.51, N = 8SE +/- 0.21, N = 8SE +/- 0.22, N = 8SE +/- 1.71, N = 7SE +/- 0.30, N = 7741.1641.3476.8449.5383.3379.8348.6335.1331.2321.8318.7296.4251.71. (CC) gcc options: -O2 -flto -lOpenCL

clpeak

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

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 3090RTX 3080RTX 2080 TiTITAN RTXRTX 2080 SUPERRTX 3070RTX 3060 TiRTX 2070 SUPERRTX 2080RTX 2060 SUPERRTX 2070RTX 3060RTX 20602004006008001000SE +/- 1.06, N = 14SE +/- 0.02, N = 3SE +/- 0.56, N = 12SE +/- 1.69, N = 13SE +/- 0.12, N = 15SE +/- 0.38, N = 15SE +/- 0.17, N = 15SE +/- 0.27, N = 15SE +/- 0.13, N = 13SE +/- 0.17, N = 13SE +/- 0.30, N = 13SE +/- 0.69, N = 10SE +/- 0.29, N = 15811.92662.16507.06504.51405.56389.08389.00369.45369.16368.53368.47314.23275.991. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Hashcat

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

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3090RTX 3080TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 2060RTX 30605000M10000M15000M20000M25000MSE +/- 10394772.36, N = 7SE +/- 6568950.53, N = 3SE +/- 10849872.25, N = 7SE +/- 13351911.38, N = 7SE +/- 14364688.85, N = 7SE +/- 6748005.50, N = 7SE +/- 13573045.02, N = 7SE +/- 3493521.70, N = 7SE +/- 8126637.98, N = 7SE +/- 4823948.20, N = 7SE +/- 7264539.72, N = 7SE +/- 2725528.10, N = 7SE +/- 4409613.80, N = 72267967142918934633333177559857141768538571413554400000131074714291221944285711107042857110921714299511900000930708571482333571437713342857

VkResample

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

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3090RTX 3080TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070RTX 3060 TiRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 3060RTX 2060612182430SE +/- 0.010, N = 5SE +/- 0.136, N = 3SE +/- 0.022, N = 5SE +/- 0.021, N = 5SE +/- 0.013, N = 5SE +/- 0.004, N = 5SE +/- 0.010, N = 5SE +/- 0.017, N = 5SE +/- 0.016, N = 5SE +/- 0.031, N = 5SE +/- 0.025, N = 5SE +/- 0.096, N = 5SE +/- 0.040, N = 49.27511.40414.18214.75817.43617.51617.66918.99419.50122.24722.28423.35227.2221. (CXX) g++ options: -O3 -pthread

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 SPRTX 3090RTX 3080TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3060 TiRTX 3070RTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRTX 3060RTX 20605001000150020002500SE +/- 0.98, N = 13SE +/- 2.13, N = 3SE +/- 0.50, N = 12SE +/- 1.05, N = 12SE +/- 0.35, N = 12SE +/- 0.17, N = 12SE +/- 0.41, N = 12SE +/- 0.38, N = 12SE +/- 0.48, N = 12SE +/- 0.17, N = 12SE +/- 0.09, N = 12SE +/- 0.12, N = 12SE +/- 0.68, N = 152348.671915.381574.851487.951203.341152.911135.141098.161087.47967.62963.13934.06801.501. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Hashcat

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

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3090RTX 3080TITAN RTXRTX 2080 TiRTX 2080 SUPERRTX 3070RTX 2080RTX 2070 SUPERRTX 3060 TiRTX 2070RTX 2060 SUPERRTX 2060RTX 3060600M1200M1800M2400M3000MSE +/- 3339151.39, N = 7SE +/- 2292257.50, N = 3SE +/- 2223773.83, N = 7SE +/- 1806187.40, N = 7SE +/- 1721354.47, N = 7SE +/- 1513813.94, N = 7SE +/- 3482228.94, N = 7SE +/- 2098266.21, N = 7SE +/- 1114987.57, N = 7SE +/- 2076381.60, N = 7SE +/- 1191123.63, N = 7SE +/- 850690.00, N = 7SE +/- 1072539.11, N = 7286544285723985666672249342857224774285717356857141665185714156218571414209714291412128571121704285711863857141051171429978971429