NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20

Benchmarks by Michael Larabel 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 2012250-HA-NVIDIAGPU61
Jump To Table - Results

View

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

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 2 Tests
Game Development 2 Tests
HPC - High Performance Computing 5 Tests
Machine Learning 3 Tests
Multi-Core 3 Tests
NVIDIA GPU Compute 20 Tests
OpenCL 5 Tests
Server CPU Tests 2 Tests
Vulkan Compute 6 Tests
Common Workstation Benchmarks 2 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests 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
December 25 2020
  4 Hours, 39 Minutes
RTX 2060 SUPER
December 24 2020
  4 Hours, 40 Minutes
RTX 2070
December 25 2020
  4 Hours, 25 Minutes
RTX 2070 SUPER
December 23 2020
  6 Hours, 52 Minutes
RTX 2080
December 24 2020
  4 Hours, 2 Minutes
RTX 2080 SUPER
December 23 2020
  3 Hours, 29 Minutes
RTX 2080 Ti
December 23 2020
  3 Hours, 53 Minutes
TITAN RTX
December 24 2020
  3 Hours, 18 Minutes
RTX 3060 TI
December 22 2020
  3 Hours, 51 Minutes
RTX 3080
December 22 2020
  3 Hours, 11 Minutes
Invert Hiding All Results Option
  4 Hours, 14 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 Linux GPU Performance Comptue RTX 30 RTX 20OpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600NVIDIA GeForce RTX 3060 Ti 8GB (1665/7000MHz)NVIDIA GeForce RTX 3080 10GB (1710/9501MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz)NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz)NVIDIA TITAN RTX 24GB (1350/7000MHz)Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (435/405MHz)NVIDIA GeForce RTX 2060 6GB (1365/7000MHz)NVIDIA Device 228bNVIDIA Device 1aefNVIDIA TU102 HD AudioNVIDIA TU104 HD AudioNVIDIA TU106 HD AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.4.0-58-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 460.27.044.6.0OpenCL 1.2 CUDA 11.2.661.2.155GCC 9.3.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA Linux GPU Performance Comptue RTX 30 RTX 20 BenchmarksSystem Logs- --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 ondemand (Boost: Enabled) - CPU Microcode: 0xa201009- RTX 3060 TI: GPU Compute Cores: 4864- RTX 3080: GPU Compute Cores: 8704- RTX 2080 Ti: GPU Compute Cores: 4352- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2080 SUPER: GPU Compute Cores: 3072- TITAN RTX: GPU Compute Cores: 4608- RTX 2080: GPU Compute Cores: 2944- RTX 2060 SUPER: GPU Compute Cores: 2176- RTX 2070: GPU Compute Cores: 2304- RTX 2060: GPU Compute Cores: 1920- Python 2.7.18 + Python 3.8.5- 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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060Result OverviewPhoronix Test Suite100%165%229%294%358%BlenderclpeakLuxCoreRender OpenCLOctaneBenchRedShift DemoFinanceBenchVkResamplePlaidMLBetsy GPU CompressorHashcatRealSR-NCNNRodiniacl-memLeelaChessZeroMandelGPUVkFFTFAHBenchArrayFireWaifu2x-NCNN VulkanViennaCLNCNN

NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20betsy: ETC1 - Highestbetsy: ETC2 RGB - Highestplaidml: No - Training - VGG16 - OpenCLluxcorerender-cl: DLSCplaidml: No - Training - VGG19 - OpenCLplaidml: No - Inference - VGG16 - OpenCLluxcorerender-cl: Foodluxcorerender-cl: Rainbow Colors and Prismplaidml: No - Inference - VGG19 - OpenCLplaidml: No - Inference - IMDB LSTM - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - ResNet 50 - OpenCLplaidml: Yes - Inference - Mobilenet - OpenCLplaidml: No - Inference - DenseNet 201 - OpenCLplaidml: No - Inference - Inception V3 - OpenCLplaidml: No - Inference - NASNer Large - OpenCLlczero: OpenCLncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2luxcorerender-cl: LuxCore Benchmarkncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mrodinia: OpenCL Particle Filterarrayfire: Conjugate Gradient OpenCLblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA OptiXfahbench: hashcat: MD5hashcat: SHA1hashcat: 7-Ziphashcat: SHA-512hashcat: TrueCrypt RIPEMD160 + XTSoctanebench: Total Scoreredshift: financebench: Black-Scholes OpenCLcl-mem: Copycl-mem: Readcl-mem: Writeclpeak: Integer Compute INTclpeak: Single-Precision Floatclpeak: Double-Precision Doubleclpeak: Global Memory Bandwidthmandelgpu: GPUviennacl: OpenCL LU Factorizationrealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yesvkfft: vkresample: 2x - Doublevkresample: 2x - Singlewaifu2x-ncnn: 2x - 3 - YesRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20604.3586.04034.987.1329.38167.732.9717.11133.11689.611875.37454.662428.74177.41236.4048.041679912.544.544.254.475.914.115.551.8613.4157.1814.5111.4124.6921.3515.1118.577.0402.09220.1556.3336.74565.9984.95235.716732927600000111037333335813001406900000427100383.4165832398.328294.1392.8384.38365.8516033.64306.12389.18280941400.275.78968.78454.14432556264.87117.6764.3712.7013.66447.509.6040.88280.314.0021.91223.641019.793062.00730.763623.82261.32398.6479.231866812.784.564.344.527.844.205.611.9113.9556.9614.7411.7125.3422.1514.5018.454.2901.55711.4838.8521.48421.5155.63320.657156429133333191511000009813002426033333723200565.0995121654.869354.7674.2645.315586.0329490.81545.91662.24421918457.579.32176.34534.20640997148.28411.2203.5123.17744.025.5336.9231.732.1812.14185.09754.692414.96636.843316.31213.54351.1863.531695212.644.744.434.484.584.566.021.9513.9656.6914.6511.4424.6921.4514.3618.324.5071.67021.6773.9932.80899.14103.97304.036255488333333177513000008853002241700000657967354.8567692466.014324.0545.6446.613432.8912677.18519.03508.00447272306.078.32447.60544.18634110152.85314.7673.8564.8246.65333.754.3227.78152.581.8610.04121.35499.431701.99422.862300.01149.68220.4342.321284112.774.644.304.463.674.225.601.8813.4857.1314.5311.3625.2521.7914.5518.586.9002.06025.4489.1248.03996.82132.73229.760035466033333111833666675937001426733333423733264.5349433518.224292.3397.1320.68551.578591.77309.27370.17321637774.375.79849.97263.17829427261.96919.5234.7614.0045.50738.74.3232.29180.231.979.19143.39588.041816.87468.602489.11160.48266.3949.161463412.724.654.304.503.604.215.681.8813.1257.0814.3611.2224.7322.1314.4718.655.8091.89325.2281.1442.60911.32126.93260.895743136966667136530000007119671734100000527287268.1143683256.749302.0437.8350.810244.0810347.92373.96405.68368037096.676.68698.84254.03730475216.53917.5074.3583.0434.11644.515.9537.56244.002.2313.56194.50782.292551.38654.763392.96228.78359.1366.501700912.774.494.204.435.034.026.031.8313.3256.5214.3611.2524.9521.8814.3518.214.2961.63718.6473.4031.72905.22102.51307.034858104300000185764000009372332350366667688167383.4637392355.691320.8568.2495.413791.9114109.68545.22530.48460475602.681.31677.36041.73136216149.20413.5613.8274.3756.15334.134.2328.32161.881.889.27128.62545.481726.88442.782333.79152.28242.5445.391357612.694.504.254.483.554.105.561.8613.5657.2514.5811.3724.6221.8114.4518.776.2882.07226.2486.1345.51971.62132.90244.417138493233333122035333336373671559500000461367261.3295043417.620290.5397.1331.99330.838860.55344.68369.65343080891.177.17279.47359.40328745235.51219.0244.6055.4517.73330.004.1924.58126.761.3211.41100.61440.361581.85376.592011.99147.13203.7838.421139913.044.674.344.473.634.335.701.9314.1857.2214.7711.5325.7122.8014.6318.497.9812.07330.90144.4058.941758.17194.41207.07702927200000093149000004905331183433333349600244.22455337810.454288.3397.1340.16956.556985.02261.53369.42278640038.174.085311.54075.89229585309.61922.2825.3135.3097.64630.274.14129.651.3010.94103.03447.471566.36379.702004.51148.04202.0539.071149512.664.604.194.453.564.155.591.8713.6057.1314.5511.7425.0521.4114.5118.687.8582.08631.34148.1758.341826.30198.63205.23222995556666795354666675002331213266667356700243.26121837510.225285.7397.1323.97094.247190.53268.18369.14283803060.174.181711.18774.65429546302.84522.2695.3146.1898.74827.123.3022.04110.961.217.9888.38392.021282.27320.951720.24125.45171.7831.81975212.424.444.154.422.804.015.481.813.4356.9814.4711.6124.5821.4114.3218.298.9602.65036.27147.6567.131779.46206.86183.29132593063333382489333334390001049366667311800195.00980646912.565239.5297.5251.65224.685369.81231.27277.40253858256.774.506212.70785.94822903350.96127.1955.779OpenBenchmarking.org

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060246810SE +/- 0.051, N = 14SE +/- 0.052, N = 14SE +/- 0.049, N = 14SE +/- 0.054, N = 13SE +/- 0.060, N = 14SE +/- 0.051, N = 14SE +/- 0.048, N = 14SE +/- 0.052, N = 13SE +/- 0.052, N = 13SE +/- 0.054, N = 134.3582.7013.1774.8244.0043.0434.3755.4515.3096.1891. (CXX) g++ options: -O3 -O2 -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: HighestRTX 3060 TIRTX 3080RTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060246810SE +/- 0.066, N = 13SE +/- 0.063, N = 13SE +/- 0.053, N = 15SE +/- 0.057, N = 14SE +/- 0.058, N = 13SE +/- 0.064, N = 12SE +/- 0.060, N = 13SE +/- 0.064, N = 12SE +/- 0.084, N = 96.0403.6646.6535.5074.1166.1537.7337.6468.7481. (CXX) g++ options: -O3 -O2 -lpthread -ldl

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Training - Network: VGG16 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601122334455SE +/- 0.18, N = 2SE +/- 0.36, N = 2SE +/- 0.33, N = 2SE +/- 0.20, N = 234.9847.5044.0233.7538.7044.5134.1330.0030.2727.12

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.10, N = 12SE +/- 0.14, N = 12SE +/- 0.08, N = 12SE +/- 0.06, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 37.139.605.534.324.325.954.234.194.143.30MIN: 2.58 / MAX: 7.38MIN: 3.45 / MAX: 9.87MIN: 2.02 / MAX: 5.76MIN: 1.6 / MAX: 4.51MIN: 4.13 / MAX: 4.4MIN: 5.62 / MAX: 6.04MIN: 4.15 / MAX: 4.3MIN: 4.11 / MAX: 4.29MIN: 3.79 / MAX: 4.28MIN: 3.16 / MAX: 3.4

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Training - Network: VGG19 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2060918273645SE +/- 0.08, N = 2SE +/- 0.15, N = 2SE +/- 0.05, N = 2SE +/- 0.04, N = 229.3840.8836.9027.7832.2937.5628.3224.5822.04

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206060120180240300SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3167.73280.31231.73152.58180.23244.00161.88126.76129.65110.96

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20600.91.82.73.64.5SE +/- 0.05, N = 12SE +/- 0.07, N = 14SE +/- 0.04, N = 12SE +/- 0.04, N = 12SE +/- 0.01, N = 3SE +/- 0.03, N = 5SE +/- 0.03, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 32.974.002.181.861.972.231.881.321.301.21MIN: 0.19 / MAX: 3.74MIN: 0.17 / MAX: 5.07MIN: 0.15 / MAX: 2.71MIN: 0.18 / MAX: 2.3MIN: 0.27 / MAX: 2.37MIN: 0.23 / MAX: 2.76MIN: 0.23 / MAX: 2.29MIN: 0.23 / MAX: 1.59MIN: 0.23 / MAX: 1.55MIN: 0.24 / MAX: 1.44

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060510152025SE +/- 0.48, N = 12SE +/- 0.65, N = 12SE +/- 0.27, N = 12SE +/- 0.20, N = 12SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 317.1121.9112.1410.049.1913.569.2711.4110.947.98MIN: 8.56 / MAX: 18.35MIN: 12.02 / MAX: 23.73MIN: 6.39 / MAX: 12.87MIN: 5.24 / MAX: 10.68MIN: 7.68 / MAX: 9.63MIN: 12.87 / MAX: 14.06MIN: 8.34 / MAX: 9.64MIN: 9.87 / MAX: 11.85MIN: 9.85 / MAX: 11.46MIN: 7.02 / MAX: 8.25

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206050100150200250SE +/- 0.08, N = 3SE +/- 0.28, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.14, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3133.11223.64185.09121.35143.39194.50128.62100.61103.0388.38

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20602004006008001000SE +/- 0.42, N = 3SE +/- 1.56, N = 3SE +/- 1.36, N = 3SE +/- 0.23, N = 3SE +/- 0.10, N = 3SE +/- 1.34, N = 3SE +/- 1.14, N = 3SE +/- 0.53, N = 3SE +/- 1.13, N = 3SE +/- 0.58, N = 3689.611019.79754.69499.43588.04782.29545.48440.36447.47392.02

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20607001400210028003500SE +/- 4.77, N = 3SE +/- 8.25, N = 3SE +/- 4.12, N = 3SE +/- 3.23, N = 3SE +/- 1.68, N = 3SE +/- 2.13, N = 3SE +/- 0.70, N = 3SE +/- 2.50, N = 3SE +/- 3.57, N = 3SE +/- 1.88, N = 31875.373062.002414.961701.991816.872551.381726.881581.851566.361282.27

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060160320480640800SE +/- 0.51, N = 3SE +/- 1.40, N = 3SE +/- 0.39, N = 3SE +/- 0.62, N = 3SE +/- 0.40, N = 3SE +/- 2.07, N = 3SE +/- 0.34, N = 3SE +/- 0.68, N = 3SE +/- 0.70, N = 3SE +/- 0.61, N = 3454.66730.76636.84422.86468.60654.76442.78376.59379.70320.95

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20608001600240032004000SE +/- 1.99, N = 3SE +/- 12.23, N = 3SE +/- 16.01, N = 3SE +/- 0.32, N = 3SE +/- 1.35, N = 3SE +/- 16.11, N = 3SE +/- 3.97, N = 3SE +/- 2.83, N = 3SE +/- 1.56, N = 3SE +/- 1.92, N = 32428.743623.823316.312300.012489.113392.962333.792011.992004.511720.24

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206060120180240300SE +/- 0.26, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3177.41261.32213.54149.68160.48228.78152.28147.13148.04125.45

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206090180270360450SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.39, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.19, N = 3SE +/- 0.46, N = 3SE +/- 0.18, N = 3SE +/- 0.28, N = 3SE +/- 0.18, N = 3236.40398.64351.18220.43266.39359.13242.54203.78202.05171.78

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206020406080100SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 348.0479.2363.5342.3249.1666.5045.3938.4239.0731.81

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20604K8K12K16K20KSE +/- 26.30, N = 3SE +/- 122.65, N = 3SE +/- 54.85, N = 3SE +/- 49.97, N = 3SE +/- 48.26, N = 3SE +/- 110.73, N = 3SE +/- 51.64, N = 3SE +/- 69.95, N = 3SE +/- 54.87, N = 3SE +/- 66.84, N = 316799186681695212841146341700913576113991149597521. (CXX) g++ options: -flto -pthread

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenetRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.17, N = 4SE +/- 0.12, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 15SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.16, N = 5SE +/- 0.17, N = 4SE +/- 0.17, N = 3SE +/- 0.14, N = 312.5412.7812.6412.7712.7212.7712.6913.0412.6612.42MIN: 11.94 / MAX: 15.69MIN: 12.35 / MAX: 20.47MIN: 12.22 / MAX: 14.36MIN: 11.98 / MAX: 34.45MIN: 12.26 / MAX: 13.5MIN: 12.01 / MAX: 24.52MIN: 11.97 / MAX: 24.76MIN: 12.34 / MAX: 24MIN: 12.23 / MAX: 24.28MIN: 11.98 / MAX: 24.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601.06652.1333.19954.2665.3325SE +/- 0.05, N = 4SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 15SE +/- 0.23, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 5SE +/- 0.07, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 34.544.564.744.644.654.494.504.674.604.44MIN: 4.25 / MAX: 5.73MIN: 4.3 / MAX: 4.85MIN: 4.31 / MAX: 5.6MIN: 4.23 / MAX: 5.42MIN: 4.19 / MAX: 5.42MIN: 4.26 / MAX: 4.85MIN: 4.19 / MAX: 13.41MIN: 4.31 / MAX: 5.1MIN: 4.35 / MAX: 13.48MIN: 4.21 / MAX: 4.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20600.99681.99362.99043.98724.984SE +/- 0.06, N = 4SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 15SE +/- 0.10, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 5SE +/- 0.08, N = 4SE +/- 0.01, N = 3SE +/- 0.03, N = 34.254.344.434.304.304.204.254.344.194.15MIN: 4.02 / MAX: 5.79MIN: 4.17 / MAX: 4.73MIN: 4.13 / MAX: 11.06MIN: 4.06 / MAX: 19.54MIN: 4.12 / MAX: 4.69MIN: 4.14 / MAX: 4.93MIN: 4.07 / MAX: 4.62MIN: 4.12 / MAX: 4.79MIN: 4.14 / MAX: 4.4MIN: 4.06 / MAX: 4.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v2RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601.0172.0343.0514.0685.085SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 13SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 4SE +/- 0.03, N = 3SE +/- 0.02, N = 34.474.524.484.464.504.434.484.474.454.42MIN: 4.34 / MAX: 5.99MIN: 4.42 / MAX: 13.63MIN: 4.38 / MAX: 4.9MIN: 4.31 / MAX: 4.82MIN: 4.35 / MAX: 5.04MIN: 4.32 / MAX: 5.06MIN: 4.36 / MAX: 14.35MIN: 4.37 / MAX: 4.78MIN: 4.34 / MAX: 4.91MIN: 4.31 / MAX: 4.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060246810SE +/- 0.07, N = 12SE +/- 0.10, N = 12SE +/- 0.04, N = 13SE +/- 0.05, N = 12SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.917.844.583.673.605.033.553.633.562.80MIN: 0.25 / MAX: 6.86MIN: 0.15 / MAX: 9.17MIN: 0.19 / MAX: 5.4MIN: 0.2 / MAX: 4.25MIN: 0.27 / MAX: 4.14MIN: 0.32 / MAX: 5.72MIN: 0.23 / MAX: 4.07MIN: 0.23 / MAX: 4.15MIN: 0.23 / MAX: 4.1MIN: 0.23 / MAX: 3.2

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnetRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601.0262.0523.0784.1045.13SE +/- 0.06, N = 4SE +/- 0.13, N = 3SE +/- 0.26, N = 3SE +/- 0.07, N = 15SE +/- 0.21, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 5SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 34.114.204.564.224.214.024.104.334.154.01MIN: 3.87 / MAX: 5.49MIN: 3.91 / MAX: 10.98MIN: 3.93 / MAX: 5.1MIN: 3.86 / MAX: 5.14MIN: 3.86 / MAX: 4.92MIN: 3.88 / MAX: 4.28MIN: 3.82 / MAX: 4.59MIN: 4.04 / MAX: 4.77MIN: 4 / MAX: 16.56MIN: 3.83 / MAX: 4.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060246810SE +/- 0.05, N = 4SE +/- 0.06, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 15SE +/- 0.21, N = 3SE +/- 0.57, N = 3SE +/- 0.04, N = 5SE +/- 0.06, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 35.555.616.025.605.686.035.565.705.595.48MIN: 5.34 / MAX: 7.32MIN: 5.45 / MAX: 5.87MIN: 5.37 / MAX: 11.96MIN: 5.28 / MAX: 16.37MIN: 5.29 / MAX: 17.94MIN: 5.28 / MAX: 339.41MIN: 5.37 / MAX: 6.08MIN: 5.43 / MAX: 17.45MIN: 5.42 / MAX: 5.85MIN: 5.32 / MAX: 5.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazefaceRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20600.43880.87761.31641.75522.194SE +/- 0.02, N = 4SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 15SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 5SE +/- 0.03, N = 4SE +/- 0.05, N = 3SE +/- 0.03, N = 31.861.911.951.881.881.831.861.931.871.80MIN: 1.78 / MAX: 2.03MIN: 1.82 / MAX: 2.14MIN: 1.85 / MAX: 2.39MIN: 1.78 / MAX: 2.2MIN: 1.77 / MAX: 2.21MIN: 1.78 / MAX: 2.03MIN: 1.81 / MAX: 2.28MIN: 1.85 / MAX: 2.11MIN: 1.8 / MAX: 2.15MIN: 1.79 / MAX: 1.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenetRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206048121620SE +/- 0.33, N = 4SE +/- 0.37, N = 3SE +/- 0.49, N = 3SE +/- 0.21, N = 14SE +/- 0.39, N = 3SE +/- 0.68, N = 2SE +/- 0.35, N = 5SE +/- 0.43, N = 4SE +/- 0.27, N = 3SE +/- 0.55, N = 313.4113.9513.9613.4813.1213.3213.5614.1813.6013.43MIN: 12.46 / MAX: 28.14MIN: 12.96 / MAX: 24.07MIN: 12.74 / MAX: 15.74MIN: 12.43 / MAX: 26.89MIN: 12.41 / MAX: 14.53MIN: 12.38 / MAX: 25.82MIN: 12.71 / MAX: 20.62MIN: 12.62 / MAX: 15.92MIN: 12.94 / MAX: 24.05MIN: 12.61 / MAX: 15.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601326395265SE +/- 0.43, N = 4SE +/- 0.09, N = 3SE +/- 0.27, N = 3SE +/- 0.13, N = 15SE +/- 0.37, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 5SE +/- 0.14, N = 4SE +/- 0.13, N = 3SE +/- 0.31, N = 357.1856.9656.6957.1357.0856.5257.2557.2257.1356.98MIN: 54.93 / MAX: 68.94MIN: 56.04 / MAX: 59.71MIN: 55.51 / MAX: 58.35MIN: 54.93 / MAX: 68.8MIN: 55.71 / MAX: 70.92MIN: 55.22 / MAX: 72.77MIN: 55.82 / MAX: 67.69MIN: 55.71 / MAX: 64.21MIN: 56.01 / MAX: 66.17MIN: 55.41 / MAX: 58.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206048121620SE +/- 0.21, N = 4SE +/- 0.25, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 15SE +/- 0.14, N = 3SE +/- 0.25, N = 3SE +/- 0.12, N = 5SE +/- 0.19, N = 4SE +/- 0.19, N = 3SE +/- 0.26, N = 314.5114.7414.6514.5314.3614.3614.5814.7714.5514.47MIN: 13.97 / MAX: 25.49MIN: 14.13 / MAX: 15.8MIN: 14.13 / MAX: 15.56MIN: 14.06 / MAX: 27.16MIN: 14.01 / MAX: 15.12MIN: 13.96 / MAX: 17.74MIN: 14.21 / MAX: 16.27MIN: 14.08 / MAX: 16.79MIN: 14.18 / MAX: 15.25MIN: 14.01 / MAX: 23.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnetRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.15, N = 4SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 15SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 5SE +/- 0.04, N = 4SE +/- 0.08, N = 3SE +/- 0.22, N = 311.4111.7111.4411.3611.2211.2511.3711.5311.7411.61MIN: 10.77 / MAX: 22.45MIN: 11.28 / MAX: 12.12MIN: 11.09 / MAX: 11.74MIN: 10.75 / MAX: 15.63MIN: 10.85 / MAX: 11.85MIN: 11 / MAX: 11.61MIN: 11.04 / MAX: 17.87MIN: 11.27 / MAX: 18.29MIN: 11.39 / MAX: 12.18MIN: 11.08 / MAX: 18.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060612182430SE +/- 0.35, N = 4SE +/- 0.56, N = 3SE +/- 0.33, N = 3SE +/- 0.18, N = 15SE +/- 0.40, N = 3SE +/- 0.37, N = 3SE +/- 0.23, N = 5SE +/- 0.09, N = 4SE +/- 0.54, N = 3SE +/- 0.15, N = 324.6925.3424.6925.2524.7324.9524.6225.7125.0524.58MIN: 23.66 / MAX: 26.48MIN: 24.02 / MAX: 26.96MIN: 23.98 / MAX: 37.45MIN: 23.93 / MAX: 36.67MIN: 23.79 / MAX: 35.29MIN: 23.91 / MAX: 36.02MIN: 23.99 / MAX: 26.48MIN: 24.88 / MAX: 31.53MIN: 24.29 / MAX: 41.55MIN: 23.83 / MAX: 37.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tinyRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060510152025SE +/- 0.64, N = 4SE +/- 0.70, N = 3SE +/- 0.60, N = 3SE +/- 0.24, N = 15SE +/- 0.60, N = 3SE +/- 0.66, N = 3SE +/- 0.41, N = 5SE +/- 0.07, N = 4SE +/- 0.58, N = 3SE +/- 0.56, N = 321.3522.1521.4521.7922.1321.8821.8122.8021.4121.41MIN: 20.24 / MAX: 29.48MIN: 20.53 / MAX: 30.78MIN: 20.52 / MAX: 33.08MIN: 20.42 / MAX: 29.15MIN: 20.69 / MAX: 28.53MIN: 20.33 / MAX: 23.41MIN: 20.55 / MAX: 24.56MIN: 22.31 / MAX: 25.04MIN: 20.58 / MAX: 23.53MIN: 20.54 / MAX: 32.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssdRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206048121620SE +/- 0.73, N = 4SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 15SE +/- 0.02, N = 3SE +/- 0.19, N = 3SE +/- 0.24, N = 4SE +/- 0.12, N = 4SE +/- 0.14, N = 2SE +/- 0.05, N = 315.1114.5014.3614.5514.4714.3514.4514.6314.5114.32MIN: 13.72 / MAX: 369.11MIN: 14.11 / MAX: 14.97MIN: 13.91 / MAX: 27.4MIN: 13.96 / MAX: 25.49MIN: 14.11 / MAX: 24.43MIN: 13.84 / MAX: 22.5MIN: 13.6 / MAX: 27.41MIN: 14.15 / MAX: 16.53MIN: 14.12 / MAX: 15.9MIN: 14.04 / MAX: 14.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400mRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060510152025SE +/- 0.28, N = 4SE +/- 0.35, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 15SE +/- 0.19, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 5SE +/- 0.15, N = 4SE +/- 0.06, N = 3SE +/- 0.08, N = 318.5718.4518.3218.5818.6518.2118.7718.4918.6818.29MIN: 17.78 / MAX: 20.78MIN: 17.4 / MAX: 28.56MIN: 17.72 / MAX: 19.14MIN: 17.91 / MAX: 28.99MIN: 18.24 / MAX: 19.54MIN: 17.88 / MAX: 20.03MIN: 18.01 / MAX: 30.34MIN: 18.01 / MAX: 28.46MIN: 18.38 / MAX: 19.17MIN: 17.99 / MAX: 28.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.067, N = 3SE +/- 0.018, N = 3SE +/- 0.076, N = 3SE +/- 0.014, N = 3SE +/- 0.010, N = 3SE +/- 0.016, N = 3SE +/- 0.006, N = 3SE +/- 0.027, N = 3SE +/- 0.017, N = 3SE +/- 0.009, N = 37.0404.2904.5076.9005.8094.2966.2887.9817.8588.9601. (CXX) g++ options: -O2 -lOpenCL

ArrayFire

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

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20600.59631.19261.78892.38522.9815SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.010, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.010, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 32.0921.5571.6702.0601.8931.6372.0722.0732.0862.6501. (CXX) g++ options: -rdynamic

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060816243240SE +/- 2.49, N = 15SE +/- 0.01, N = 3SE +/- 2.49, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 320.1511.4821.6725.4425.2218.6426.2430.9031.3436.27

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: NVIDIA OptiXRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060306090120150SE +/- 0.23, N = 3SE +/- 0.16, N = 3SE +/- 0.50, N = 3SE +/- 0.32, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.38, N = 3SE +/- 0.95, N = 3SE +/- 0.39, N = 356.3338.8573.9989.1281.1473.4086.13144.40148.17147.65

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601530456075SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 336.7421.4832.8048.0342.6031.7245.5158.9458.3467.13

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: NVIDIA OptiXRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060400800120016002000SE +/- 0.84, N = 3SE +/- 1.49, N = 3SE +/- 1.58, N = 3SE +/- 1.90, N = 3SE +/- 0.14, N = 3SE +/- 1.56, N = 3SE +/- 0.81, N = 3SE +/- 0.52, N = 3SE +/- 2.84, N = 3SE +/- 2.01, N = 3565.99421.51899.14996.82911.32905.22971.621758.171826.301779.46

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206050100150200250SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 384.9555.63103.97132.73126.93102.51132.90194.41198.63206.86

FAHBench

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

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206070140210280350SE +/- 0.14, N = 3SE +/- 0.30, N = 3SE +/- 0.05, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.10, N = 3SE +/- 0.18, N = 3235.72320.66304.04229.76260.90307.03244.42207.08205.23183.29

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: MD5RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206012000M24000M36000M48000M60000MSE +/- 23055223.56, N = 3SE +/- 39942305.61, N = 3SE +/- 63030953.60, N = 3SE +/- 41910871.04, N = 3SE +/- 13808974.54, N = 3SE +/- 33241139.17, N = 3SE +/- 30944592.06, N = 3SE +/- 8911415.90, N = 3SE +/- 9342079.24, N = 3SE +/- 11770207.21, N = 332927600000564291333335548833333335466033333431369666675810430000038493233333292720000002995556666725930633333

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20604000M8000M12000M16000M20000MSE +/- 16045802.50, N = 3SE +/- 13325289.24, N = 3SE +/- 20384389.45, N = 3SE +/- 1017076.42, N = 3SE +/- 3601851.38, N = 3SE +/- 24080351.60, N = 3SE +/- 14178073.84, N = 3SE +/- 7522189.40, N = 3SE +/- 2514844.82, N = 3SE +/- 2302414.19, N = 311103733333191511000001775130000011183366667136530000001857640000012203533333931490000095354666678248933333

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060200K400K600K800K1000KSE +/- 3659.23, N = 3SE +/- 503.32, N = 3SE +/- 3113.41, N = 3SE +/- 435.89, N = 3SE +/- 1963.27, N = 3SE +/- 520.68, N = 3SE +/- 1713.99, N = 3SE +/- 1192.10, N = 3SE +/- 726.48, N = 3SE +/- 1101.51, N = 3581300981300885300593700711967937233637367490533500233439000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060500M1000M1500M2000M2500MSE +/- 750555.35, N = 3SE +/- 2669165.50, N = 3SE +/- 1258305.74, N = 3SE +/- 933333.33, N = 3SE +/- 2042873.79, N = 3SE +/- 3263093.28, N = 3SE +/- 814452.78, N = 3SE +/- 1281058.59, N = 3SE +/- 845248.16, N = 3SE +/- 635959.47, N = 31406900000242603333322417000001426733333173410000023503666671559500000118343333312132666671049366667

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060150K300K450K600K750KSE +/- 550.76, N = 3SE +/- 750.56, N = 3SE +/- 1591.99, N = 3SE +/- 66.67, N = 3SE +/- 4580.29, N = 15SE +/- 1120.02, N = 3SE +/- 133.33, N = 3SE +/- 57.74, N = 3SE +/- 556.78, N = 3SE +/- 57.74, N = 3427100723200657967423733527287688167461367349600356700311800

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060120240360480600383.42565.10354.86264.53268.11383.46261.33244.22243.26195.01

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060100200300400500SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 0.88, N = 3SE +/- 0.88, N = 3239165246351325235341378375469

FinanceBench

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

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.000, N = 3SE +/- 0.020, N = 3SE +/- 0.007, N = 3SE +/- 0.003, N = 3SE +/- 0.022, N = 3SE +/- 0.005, N = 3SE +/- 0.019, N = 3SE +/- 0.010, N = 3SE +/- 0.017, N = 3SE +/- 0.001, N = 38.3284.8696.0148.2246.7495.6917.62010.45410.22512.5651. (CXX) g++ options: -O3 -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: CopyRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206080160240320400SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3294.1354.7324.0292.3302.0320.8290.5288.3285.7239.51. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060150300450600750SE +/- 0.44, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3392.8674.2545.6397.1437.8568.2397.1397.1397.1297.51. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060140280420560700SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.38, N = 3SE +/- 0.23, N = 3SE +/- 0.17, N = 3SE +/- 1.30, N = 3SE +/- 0.79, N = 3SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3384.3645.3446.6320.6350.8495.4331.9340.1323.9251.61. (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.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603K6K9K12K15KSE +/- 74.13, N = 15SE +/- 232.90, N = 3SE +/- 138.31, N = 15SE +/- 72.96, N = 15SE +/- 165.30, N = 3SE +/- 135.03, N = 15SE +/- 43.62, N = 3SE +/- 78.58, N = 15SE +/- 85.50, N = 15SE +/- 4.93, N = 38365.8515586.0313432.898551.5710244.0813791.919330.836956.557094.245224.681. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20606K12K18K24K30KSE +/- 0.44, N = 3SE +/- 0.32, N = 3SE +/- 138.31, N = 3SE +/- 84.78, N = 15SE +/- 174.06, N = 3SE +/- 193.76, N = 15SE +/- 6.84, N = 3SE +/- 75.69, N = 15SE +/- 90.04, N = 15SE +/- 56.79, N = 1516033.6429490.8112677.188591.7710347.9214109.688860.556985.027190.535369.811. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060120240360480600SE +/- 0.89, N = 3SE +/- 0.00, N = 3SE +/- 1.36, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 1.44, N = 3SE +/- 0.00, N = 3SE +/- 0.69, N = 3SE +/- 0.77, N = 3SE +/- 0.61, N = 3306.12545.91519.03309.27373.96545.22344.68261.53268.18231.271. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060140280420560700SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.66, N = 3SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.41, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 3389.18662.24508.00370.17405.68530.48369.65369.42369.14277.401. (CXX) g++ options: -O3 -rdynamic -lOpenCL

MandelGPU

MandelGPU is an OpenCL benchmark and this test runs with the OpenCL rendering float4 kernel with a maximum of 4096 iterations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPURTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060100M200M300M400M500MSE +/- 805777.35, N = 3SE +/- 2886689.51, N = 3SE +/- 590928.34, N = 3SE +/- 516930.54, N = 3SE +/- 774665.97, N = 3SE +/- 2487384.16, N = 3SE +/- 1494897.42, N = 3SE +/- 1645708.79, N = 3SE +/- 776602.98, N = 3SE +/- 1171800.01, N = 3280941400.2421918457.5447272306.0321637774.3368037096.6460475602.6343080891.1278640038.1283803060.1253858256.71. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile uses ViennaCL OpenCL support and runs the included computational benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206020406080100SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.40, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.16, N = 3SE +/- 0.40, N = 3SE +/- 0.18, N = 3SE +/- 0.20, N = 375.7979.3278.3275.8076.6981.3277.1774.0974.1874.511. (CXX) g++ options: -rdynamic -lOpenCL

RealSR-NCNN

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20603691215SE +/- 0.056, N = 3SE +/- 0.093, N = 3SE +/- 0.108, N = 3SE +/- 0.110, N = 3SE +/- 0.101, N = 3SE +/- 0.105, N = 3SE +/- 0.131, N = 3SE +/- 0.111, N = 3SE +/- 0.096, N = 3SE +/- 0.091, N = 38.7846.3457.6059.9728.8427.3609.47311.54011.18712.707

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206020406080100SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.21, N = 3SE +/- 0.29, N = 3SE +/- 0.27, N = 3SE +/- 0.22, N = 3SE +/- 0.38, N = 3SE +/- 0.37, N = 3SE +/- 0.45, N = 3SE +/- 0.35, N = 354.1434.2144.1963.1854.0441.7359.4075.8974.6585.95

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.1RTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20609K18K27K36K45KSE +/- 86.88, N = 3SE +/- 284.10, N = 3SE +/- 78.30, N = 3SE +/- 213.44, N = 3SE +/- 51.40, N = 3SE +/- 413.34, N = 3SE +/- 95.96, N = 3SE +/- 257.75, N = 3SE +/- 149.21, N = 3SE +/- 44.06, N = 3325564099734110294273047536216287452958529546229031. (CXX) g++ options: -O3 -pthread

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 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 206080160240320400SE +/- 0.88, N = 3SE +/- 0.30, N = 3SE +/- 0.12, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.63, N = 3SE +/- 0.28, N = 3SE +/- 0.78, N = 3SE +/- 0.05, N = 3264.87148.28152.85261.97216.54149.20235.51309.62302.85350.961. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 2060612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 317.6811.2214.7719.5217.5113.5619.0222.2822.2727.201. (CXX) g++ options: -O3 -pthread

Waifu2x-NCNN Vulkan

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 3060 TIRTX 3080RTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERTITAN RTXRTX 2080RTX 2060 SUPERRTX 2070RTX 20601.30032.60063.90095.20126.5015SE +/- 0.008, N = 3SE +/- 0.047, N = 5SE +/- 0.057, N = 3SE +/- 0.067, N = 4SE +/- 0.060, N = 3SE +/- 0.056, N = 3SE +/- 0.053, N = 3SE +/- 0.055, N = 3SE +/- 0.049, N = 3SE +/- 0.064, N = 34.3713.5123.8564.7614.3583.8274.6055.3135.3145.779

64 Results Shown

Betsy GPU Compressor:
  ETC1 - Highest
  ETC2 RGB - Highest
PlaidML
LuxCoreRender OpenCL
PlaidML:
  No - Training - VGG19 - OpenCL
  No - Inference - VGG16 - OpenCL
LuxCoreRender OpenCL:
  Food
  Rainbow Colors and Prism
PlaidML:
  No - Inference - VGG19 - OpenCL
  No - Inference - IMDB LSTM - OpenCL
  No - Inference - Mobilenet - OpenCL
  No - Inference - ResNet 50 - OpenCL
  Yes - Inference - Mobilenet - OpenCL
  No - Inference - DenseNet 201 - OpenCL
  No - Inference - Inception V3 - OpenCL
  No - Inference - NASNer Large - OpenCL
LeelaChessZero
NCNN:
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
LuxCoreRender OpenCL
NCNN:
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - regnety_400m
Rodinia
ArrayFire
Blender:
  BMW27 - NVIDIA OptiX
  Classroom - NVIDIA OptiX
  Fishy Cat - NVIDIA OptiX
  Barbershop - NVIDIA OptiX
  Pabellon Barcelona - NVIDIA OptiX
FAHBench
Hashcat:
  MD5
  SHA1
  7-Zip
  SHA-512
  TrueCrypt RIPEMD160 + XTS
OctaneBench
RedShift Demo
FinanceBench
cl-mem:
  Copy
  Read
  Write
clpeak:
  Integer Compute INT
  Single-Precision Float
  Double-Precision Double
  Global Memory Bandwidth
MandelGPU
ViennaCL
RealSR-NCNN:
  4x - No
  4x - Yes
VkFFT
VkResample:
  2x - Double
  2x - Single
Waifu2x-NCNN Vulkan