NVIDIA Compute Tests

Benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2011301-HA-NC792657606&rdt.

NVIDIA Compute TestsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 TiAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (2311 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600 + 2000GBNVIDIA GeForce RTX 3080 10GB (1710/9501MHz)NVIDIA Device 1aefASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.4.0-54-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 455.45.014.6.0OpenCL 1.2 CUDA 11.1.1141.2.142GCC 9.3.0ext43840x2160Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA TU104 HD AudioNVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz)NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)NVIDIA TU106 HD AudioNVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TU102 HD AudioNVIDIA GeForce RTX 2060 6GB (1365/7000MHz)NVIDIA TU106 HD AudioeVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz)NVIDIA TU116 HD AudioNVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)NVIDIA TU106 HD AudioNVIDIA TITAN RTX 24GB (555/810MHz)NVIDIA TU102 HD AudioNVIDIA GeForce GTX 1060 6GB (1506/4006MHz)NVIDIA GP106 HD AudioeVGA NVIDIA GeForce GTX 1660 SUPER 6GB (1530/7000MHz)NVIDIA TU116 HD AudioNVIDIA GeForce RTX 3060 Ti 8GB (1665/7000MHz)NVIDIA Device 228bOpenBenchmarking.orgCompiler Details- --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 Processor Details- Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0xa201009OpenCL Details- RTX 3080: GPU Compute Cores: 8704- RTX 2080: GPU Compute Cores: 2944- RTX 2080 SUPER: GPU Compute Cores: 3072- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2070: GPU Compute Cores: 2304- RTX 2080 Ti: GPU Compute Cores: 4352- RTX 2060: GPU Compute Cores: 1920- GTX 1660 Ti: GPU Compute Cores: 1536- RTX 2060 SUPER: GPU Compute Cores: 2176- TITAN RTX: GPU Compute Cores: 4608- GTX 1060: GPU Compute Cores: 1280- GTX 1660 SUPER: GPU Compute Cores: 1408- RTX 3060 Ti: GPU Compute Cores: 4864Python Details- Python 2.7.18 + Python 3.8.5Security Details- 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

NVIDIA Compute Testshashcat: MD5hashcat: SHA1hashcat: SHA-512hashcat: 7-Ziphashcat: TrueCrypt RIPEMD160 + XTSwaifu2x-ncnn: 2x - 3 - Yesfahbench: octanebench: Total Scoreluxcorerender-cl: LuxCore Benchmarkluxcorerender-cl: DLSCluxcorerender-cl: Rainbow Colors and Prismluxcorerender-cl: Foodrodinia: OpenCL Particle Filterarrayfire: Conjugate Gradient OpenCLclpeak: Global Memory Bandwidthclpeak: Single-Precision Floatclpeak: Double-Precision Doubleclpeak: Integer Compute INTfinancebench: Black-Scholes OpenCLplaidml: Yes - Inference - Mobilenet - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - DenseNet 201 - OpenCLplaidml: No - Inference - IMDB LSTM - OpenCLlczero: OpenCLcl-mem: Readcl-mem: Writecl-mem: Copymandelgpu: GPUviennacl: OpenCL LU Factorizationredshift: blender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXvkfft: ncnn: Vulkan GPU - squeezenetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: 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-tinyrealsr-ncnn: 4x - Yesrealsr-ncnn: 4x - Noindigobench: OpenCL GPU - Supercarindigobench: OpenCL GPU - Bedroomgeekbench: GPU OpenCLgeekbench: GPU NVIDIA CUDAgeekbench: GPU VulkanRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti540303142861834552857123067000009392906923883.519306.7671537.2420477.269.2920.823.544.8551.627633.3428088.78514.4014574.474.9213725.402995.56243.50975.5628389634.1615.3339.9401282795.277.953617214.9641.2922.7359.14458.51496314.074.451.731.981.541.803.130.643.884.711.311.823.516.5035.7206.57643.58916.595197267208331158724385817285711219500000015354142866399154589714.582242.5543259.1629933.484.208.951.796.3552.094368.919117.91343.499509.307.7152340.011714.00150.94544.7215758394.1334.2288.5341286781.776.133534229.5387.2645.98135.02974.80285644.294.161.461.751.371.502.660.613.297.691.552.213.727.0260.0959.61124.8257.71111477312185698487425657000001346771428617053000007041805240334.368257.4767265.1499653.614.349.031.885.9041.917405.7710190.43373.0410455.186.9122480.881831.76159.34587.7217915434.4344.1298.9363715438.977.107732526.3982.6043.57130.28917.27307204.204.061.371.761.321.522.610.633.127.441.521.963.527.0754.7839.03125.4787.884124272128277108359350269714291098440000013992428575779474235934.769227.7661258.4720713.574.299.861.786.9802.076367.048537.01306.518494.998.3182297.001707.65148.55498.2414332394.2313.9288.2316276201.075.743335226.4190.5148.84135.341002.41276824.184.091.381.711.361.662.760.633.238.201.662.003.847.1963.75410.20624.4907.6771058991104509608229996671429955891428612127857145041003599335.211205.4939242.7253563.514.1910.981.277.8042.094368.847203.49267.767134.1610.2632008.991580.07148.07447.0612723396.7328.4284.5280144899.175.094037331.96147.1658.17198.241803.97266004.584.231.541.641.261.562.790.583.438.961.742.143.937.2774.80611.53723.4307.394938059966485125557407285711784038571422231285718825606502293.835300.8935349.4127084.605.6512.082.114.4911.678502.7313338.39516.5313253.586.1583227.212405.89211.01747.5023269540.7445.4320.8446864473.478.612024719.8373.9133.09104.80902.94373843.874.021.511.641.341.492.730.683.105.681.301.723.306.5344.7257.74333.19010.91315258316785813248925730414286815828571410350285714333423068255.792180.9695192.5980862.763.317.831.179.0042.671275.125480.01229.295248.4312.5871696.451282.52124.27389.4510249297.3251.2239.0247283060.772.833847937.35149.3168.22210.221783.16208834.754.431.561.811.371.632.920.673.5710.321.982.564.437.8486.60212.93618.2525.5348071283535726891835481428662199600007947428573357002369887.243129.4973124.7371611.962.374.76416670.9911.7463.228222.014448.17173.674443.7215.5250671351.92985.9793.61299.077051235.4207.4197.2197542242.768.608783383.09281.98168.18489.372732.32170976.055.301.842.101.561.813.630.724.3315.092.383.556.039.30123.84817.73314.3044.36064871670035906327434614286874707142911048428574599733242405.553189.0783225.4088223.263.9610.451.178.6562.198348.066758.49245.516753.7911.4921952.071509.02137.81416.1511284372.2311.8270.4262260550.672.334340233.87154.2563.22209.051877.55249755.414.951.721.891.631.723.350.724.169.851.912.804.658.5480.58712.37721.6666.865870769057275750530863142861693583333321188166678374206255504.124270.6805350.6624994.425.4612.131.994.8051.756484.4013604.68498.1413266.226.3723284.452394.82208.22718.5121084514.5456.0291.8443646920.976.274025621.2682.3135.12114.001002.97369335.054.661.752.111.621.893.330.813.736.281.731.963.887.4745.5538.00931.75710.5881511481558671280031289740000044024428574652714291982421422649.251101.290280.907511.451.735.340.6312.1055.023147.514095.43150.151226.2813.468982.70778.9978.97226.155925152.8147.4137.8128084240.361.72941064170.15548.35344.25973.87127887.705.762.112.471.782.293.760.805.3118.543.265.457.629.87144.62820.12810.2823.5473679833671378441799770000061783142867845142863338472379007.060136.0813131.8566782.202.605.541.0511.6172.670273.924543.04170.634308.2315.3611371.101075.0799.49296.827324293.5230.0239.0198638055.868.705376478.26270.19165.55476.552593.95184505.354.671.531.821.331.662.880.643.9313.972.323.045.258.58120.90717.21415.2414.662646806638760351329920000001109117142914069285715869184340674.236234.5598378.7130335.797.1316.842.806.9882.094389.0216012.88302.828290.918.3742439.191875.83177.04686.6622842393.5383.6298.2278997773.175.825624018.0655.9537.2486.20581.54320653.964.271.741.761.361.773.030.633.446.021.701.653.726.5652.4688.63333.52011.394132421136797112321OpenBenchmarking.org

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti12000M24000M36000M48000M60000MSE +/- 102079526.49, N = 7SE +/- 109307854.28, N = 7SE +/- 63553325.94, N = 7SE +/- 41495700.95, N = 7SE +/- 181560574.59, N = 7SE +/- 98630343.33, N = 7SE +/- 34176226.97, N = 7SE +/- 40766579.62, N = 7SE +/- 41830567.71, N = 7SE +/- 147390714.04, N = 7SE +/- 29398291.17, N = 7SE +/- 46882020.11, N = 7SE +/- 53297878.10, N = 754030314286385817285714256570000035026971429299966714295574072857125730414286183548142862743461428653086314286128974000001799770000032992000000

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti80M160M240M320M400M311017484.35322401428.48311117905.89288952169.21313223916.56396354718.56278488631.45286208945.71275454497.06341784951.41184587919.24244831690.71311715797.43

Hashcat

Benchmark: SHA1

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti4000M8000M12000M16000M20000MSE +/- 36837886.26, N = 7SE +/- 10928839.09, N = 7SE +/- 40239943.60, N = 7SE +/- 7407910.83, N = 7SE +/- 9114520.82, N = 7SE +/- 26687552.20, N = 7SE +/- 12096446.32, N = 7SE +/- 43107894.32, N = 15SE +/- 13942803.47, N = 7SE +/- 31084579.96, N = 6SE +/- 6046717.22, N = 7SE +/- 10473604.66, N = 7SE +/- 8294912.79, N = 718345528571121950000001346771428610984400000955891428617840385714815828571462199600008747071429169358333334402442857617831428611091171429

Hashcat

Benchmark: SHA1

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti30M60M90M120M150M100535705.7696128268.62102514995.6494385776.1097164967.49121618842.5889207530.6294836299.4284129215.91104602759.1060925712.5785534112.72103115175.84

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti500M1000M1500M2000M2500MSE +/- 3329521.63, N = 7SE +/- 2244509.55, N = 7SE +/- 900264.51, N = 7SE +/- 953653.91, N = 7SE +/- 1566073.13, N = 7SE +/- 1585907.32, N = 7SE +/- 1478370.13, N = 7SE +/- 824002.18, N = 7SE +/- 1642277.33, N = 7SE +/- 4053921.28, N = 6SE +/- 1680378.97, N = 7SE +/- 537821.25, N = 7SE +/- 849289.42, N = 72306700000153541428617053000001399242857121278571422231285711035028571794742857110484285721188166674652714297845142861406928571

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti3M6M9M12M15M12429064.1912234041.6912407758.8411496268.3312061400.8014695988.6411143378.5311525083.3710630748.2712848448.806439856.1510393151.8112797897.19

Hashcat

Benchmark: 7-Zip

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti200K400K600K800K1000KSE +/- 2622.40, N = 10SE +/- 4180.88, N = 13SE +/- 6880.46, N = 15SE +/- 6166.48, N = 15SE +/- 249.73, N = 11SE +/- 6317.53, N = 10SE +/- 4365.82, N = 12SE +/- 2005.81, N = 11SE +/- 2513.28, N = 11SE +/- 6837.61, N = 10SE +/- 915.40, N = 12SE +/- 2811.01, N = 15SE +/- 558.54, N = 11939290639915704180577947504100882560433342335700459973837420198242333847586918

Hashcat

Benchmark: 7-Zip

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti2K4K6K8K10K8221.938699.019972.838523.908840.4611015.308031.648357.977181.638110.583824.577098.629708.43

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti150K300K450K600K750KSE +/- 2510.22, N = 8SE +/- 1086.65, N = 7SE +/- 4540.66, N = 15SE +/- 3357.49, N = 15SE +/- 366.29, N = 9SE +/- 1367.60, N = 7SE +/- 1010.44, N = 8SE +/- 494.41, N = 8SE +/- 2317.91, N = 10SE +/- 3170.74, N = 8SE +/- 1264.28, N = 11SE +/- 2205.50, N = 10SE +/- 3786.64, N = 9692388458971524033423593359933650229306825236988324240625550142264237900434067

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti120024003600480060005092.004417.863899.844726.824924.794940.533869.993963.534691.055053.522915.073798.775389.75

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti3691215SE +/- 0.028, N = 9SE +/- 0.020, N = 8SE +/- 0.020, N = 8SE +/- 0.028, N = 8SE +/- 0.022, N = 7SE +/- 0.021, N = 8SE +/- 0.029, N = 7SE +/- 0.030, N = 6SE +/- 0.030, N = 7SE +/- 0.023, N = 8SE +/- 0.036, N = 5SE +/- 0.026, N = 6SE +/- 0.032, N = 83.5194.5824.3684.7695.2113.8355.7927.2435.5534.1249.2517.0604.236

FAHBench

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti70140210280350SE +/- 0.28, N = 3SE +/- 0.19, N = 3SE +/- 0.32, N = 3SE +/- 0.17, N = 3SE +/- 0.40, N = 3SE +/- 0.36, N = 3SE +/- 0.21, N = 3SE +/- 0.21, N = 3SE +/- 0.37, N = 3SE +/- 1.07, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 3306.77242.55257.48227.77205.49300.89180.97129.50189.08270.68101.29136.08234.56

FAHBench

OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterFAHBench 2.3.2RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.47250.9451.41751.892.36251.681.801.981.891.881.841.771.831.731.661.511.632.10

OctaneBench

Total Score

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti120240360480600537.24259.16265.15258.47242.73349.41192.60124.74225.41350.6680.91131.86378.71

OctaneBench

Total Score

OpenBenchmarking.orgScore Per Watt, More Is BetterOctaneBench 2020.1Total ScoreRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.5131.0261.5392.0522.5651.871.591.731.681.721.551.631.281.571.501.061.212.28

LuxCoreRender OpenCL

Scene: LuxCore Benchmark

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti246810SE +/- 0.07, N = 14SE +/- 0.04, N = 12SE +/- 0.01, N = 3SE +/- 0.06, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 12SE +/- 0.01, N = 3SE +/- 0.11, N = 127.263.483.613.573.514.602.761.963.264.421.452.205.79MIN: 0.15 / MAX: 8.46MIN: 0.14 / MAX: 4.06MIN: 0.23 / MAX: 4.14MIN: 0.12 / MAX: 4.19MIN: 0.23 / MAX: 4.01MIN: 0.27 / MAX: 5.34MIN: 0.24 / MAX: 3.15MIN: 0.23 / MAX: 2.27MIN: 0.23 / MAX: 3.79MIN: 0.27 / MAX: 5.17MIN: 0.12 / MAX: 1.67MIN: 0.2 / MAX: 2.52MIN: 0.12 / MAX: 6.75

LuxCoreRender OpenCL

Scene: LuxCore Benchmark

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.0090.0180.0270.0360.0450.030.020.030.030.030.020.030.030.030.020.020.020.04

LuxCoreRender OpenCL

Scene: DLSC

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti3691215SE +/- 0.15, N = 12SE +/- 0.06, N = 12SE +/- 0.02, N = 3SE +/- 0.08, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 12SE +/- 0.00, N = 3SE +/- 0.14, N = 129.294.204.344.294.195.653.312.373.965.461.732.607.13MIN: 3.1 / MAX: 9.73MIN: 1.51 / MAX: 4.4MIN: 3.08 / MAX: 4.47MIN: 1.19 / MAX: 4.5MIN: 4.09 / MAX: 4.28MIN: 5.25 / MAX: 5.77MIN: 1.83 / MAX: 3.4MIN: 2.26 / MAX: 2.42MIN: 3.76 / MAX: 4.1MIN: 3.9 / MAX: 5.67MIN: 0.43 / MAX: 1.81MIN: 2.33 / MAX: 2.67MIN: 1.94 / MAX: 7.5

LuxCoreRender OpenCL

Scene: DLSC

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.0090.0180.0270.0360.0450.040.030.030.030.030.030.030.030.030.030.020.030.04

LuxCoreRender OpenCL

Scene: Rainbow Colors and Prism

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti510152025SE +/- 0.4586334, N = 15SE +/- 0.1793871, N = 12SE +/- 0.0522772, N = 3SE +/- 0.2639327, N = 12SE +/- 0.0543537, N = 4SE +/- 0.0331742, N = 4SE +/- 0.0353073, N = 3SE +/- 0.0048958, N = 3SE +/- 0.0319774, N = 4SE +/- 0.0783102, N = 4SE +/- 0.1074070, N = 12SE +/- 0.0320724, N = 3SE +/- 0.5108456, N = 1520.82000008.95000009.03000009.860000010.980000012.08000007.83000004.764166710.450000012.13000005.34000005.540000016.8400000MIN: 11.17 / MAX: 22.47MIN: 4.35 / MAX: 9.64MIN: 6.18 / MAX: 9.55MIN: 3.83 / MAX: 10.58MIN: 9.77 / MAX: 11.57MIN: 9.2 / MAX: 12.83MIN: 6.32 / MAX: 8.15MIN: 3.69 / MAX: 4.95MIN: 9.04 / MAX: 11.03MIN: 11.08 / MAX: 12.83MIN: 1.87 / MAX: 5.68MIN: 4.4 / MAX: 5.82MIN: 6.81 / MAX: 18.28

LuxCoreRender OpenCL

Scene: Rainbow Colors and Prism

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.03380.06760.10140.13520.1690.110.080.080.090.100.080.080.070.090.070.080.070.15

LuxCoreRender OpenCL

Scene: Food

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.79651.5932.38953.1863.9825SE +/- 0.06, N = 12SE +/- 0.03, N = 12SE +/- 0.01, N = 3SE +/- 0.04, N = 12SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 12SE +/- 0.01, N = 3SE +/- 0.06, N = 123.541.791.881.781.272.111.170.991.171.990.631.052.80MIN: 0.17 / MAX: 4.48MIN: 0.17 / MAX: 2.23MIN: 0.21 / MAX: 2.32MIN: 0.13 / MAX: 2.23MIN: 0.23 / MAX: 1.52MIN: 0.24 / MAX: 2.63MIN: 0.22 / MAX: 1.39MIN: 0.22 / MAX: 1.17MIN: 0.21 / MAX: 1.44MIN: 0.21 / MAX: 2.46MIN: 0.14 / MAX: 0.76MIN: 0.21 / MAX: 1.25MIN: 0.19 / MAX: 3.53

LuxCoreRender OpenCL

Scene: Food

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.00450.0090.01350.0180.02250.020.010.010.010.010.010.010.010.010.010.010.010.02

Rodinia

Test: OpenCL Particle Filter

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti3691215SE +/- 0.035, N = 15SE +/- 0.045, N = 6SE +/- 0.014, N = 7SE +/- 0.018, N = 6SE +/- 0.006, N = 6SE +/- 0.007, N = 8SE +/- 0.020, N = 5SE +/- 0.022, N = 4SE +/- 0.021, N = 5SE +/- 0.008, N = 8SE +/- 0.068, N = 4SE +/- 0.014, N = 4SE +/- 0.008, N = 64.8556.3555.9046.9807.8044.4919.00411.7468.6564.80512.10511.6176.9881. (CXX) g++ options: -O2 -lOpenCL

ArrayFire

Test: Conjugate Gradient OpenCL

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1.13022.26043.39064.52085.651SE +/- 0.009, N = 9SE +/- 0.009, N = 9SE +/- 0.011, N = 10SE +/- 0.008, N = 10SE +/- 0.002, N = 10SE +/- 0.003, N = 10SE +/- 0.009, N = 10SE +/- 0.003, N = 10SE +/- 0.004, N = 10SE +/- 0.006, N = 10SE +/- 0.015, N = 9SE +/- 0.014, N = 10SE +/- 0.003, N = 101.6272.0941.9172.0762.0941.6782.6713.2282.1981.7565.0232.6702.0941. (CXX) g++ options: -rdynamic

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti140280420560700SE +/- 4.38, N = 12SE +/- 0.09, N = 13SE +/- 0.07, N = 15SE +/- 2.10, N = 14SE +/- 0.21, N = 15SE +/- 3.38, N = 12SE +/- 1.44, N = 15SE +/- 0.45, N = 12SE +/- 0.50, N = 13SE +/- 2.39, N = 13SE +/- 0.06, N = 10SE +/- 1.52, N = 12SE +/- 0.15, N = 15633.34368.91405.77367.04368.84502.73275.12222.01348.06484.40147.51273.92389.021. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti2468106.216.327.196.508.095.985.515.876.626.133.396.377.45

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti6K12K18K24K30KSE +/- 211.97, N = 13SE +/- 74.65, N = 12SE +/- 94.85, N = 15SE +/- 86.35, N = 15SE +/- 93.84, N = 15SE +/- 160.87, N = 15SE +/- 104.44, N = 15SE +/- 45.28, N = 15SE +/- 72.24, N = 15SE +/- 131.35, N = 15SE +/- 65.66, N = 15SE +/- 29.82, N = 12SE +/- 24.65, N = 1328088.789117.9110190.438537.017203.4913338.395480.014448.176758.4913604.684095.434543.0416012.881. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti70140210280350309.31152.55179.85144.93157.05158.64131.53142.17124.64132.66101.60117.45327.99

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti110220330440550SE +/- 1.61, N = 3SE +/- 1.04, N = 3SE +/- 0.26, N = 3SE +/- 0.34, N = 3SE +/- 0.79, N = 3SE +/- 2.16, N = 3SE +/- 0.32, N = 3SE +/- 0.50, N = 3SE +/- 0.38, N = 3SE +/- 2.49, N = 3SE +/- 0.30, N = 3SE +/- 0.26, N = 3SE +/- 0.58, N = 3514.40343.49373.04306.51267.76516.53229.29173.67245.51498.14150.15170.63302.821. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.96531.93062.89593.86124.82653.523.574.293.583.794.143.443.673.073.563.072.994.04

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti3K6K9K12K15KSE +/- 137.97, N = 15SE +/- 74.73, N = 12SE +/- 96.25, N = 15SE +/- 96.07, N = 15SE +/- 81.80, N = 15SE +/- 136.49, N = 15SE +/- 46.67, N = 15SE +/- 53.45, N = 15SE +/- 70.14, N = 15SE +/- 161.08, N = 15SE +/- 14.65, N = 15SE +/- 31.94, N = 12SE +/- 65.69, N = 1414574.479509.3010455.188494.997134.1613253.585248.434443.726753.7913266.221226.284308.238290.911. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS Per Watt, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti306090120150116.90127.83152.30119.43120.15147.86103.54112.2799.10118.2719.3996.51128.32

FinanceBench

Benchmark: Black-Scholes OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti48121620SE +/- 0.043122, N = 15SE +/- 0.040260, N = 14SE +/- 0.083219, N = 15SE +/- 0.048730, N = 14SE +/- 0.009511, N = 14SE +/- 0.094451, N = 15SE +/- 0.035770, N = 15SE +/- 0.162363, N = 15SE +/- 0.162802, N = 15SE +/- 0.224039, N = 15SE +/- 0.326577, N = 15SE +/- 0.069806, N = 15SE +/- 0.027743, N = 154.9210007.7150006.9120008.31800010.2630006.15800012.58700015.52506711.4920006.37200013.46800015.3610008.3740001. (CXX) g++ options: -O3 -lOpenCL

PlaidML

FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti8001600240032004000SE +/- 17.78, N = 8SE +/- 7.50, N = 8SE +/- 7.43, N = 8SE +/- 11.50, N = 8SE +/- 3.85, N = 8SE +/- 9.32, N = 8SE +/- 20.43, N = 15SE +/- 1.98, N = 8SE +/- 9.97, N = 8SE +/- 19.10, N = 8SE +/- 1.08, N = 7SE +/- 4.66, N = 7SE +/- 1.48, N = 83725.402340.012480.882297.002008.993227.211696.451351.921952.073284.45982.701371.102439.19

PlaidML

FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti112233445543.2236.2443.2736.7841.2249.6733.1433.0334.9541.5319.8528.5345.66

PlaidML

FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti6001200180024003000SE +/- 9.67, N = 9SE +/- 3.83, N = 8SE +/- 3.49, N = 8SE +/- 6.37, N = 9SE +/- 2.41, N = 9SE +/- 8.40, N = 9SE +/- 3.21, N = 8SE +/- 1.27, N = 8SE +/- 3.27, N = 8SE +/- 5.99, N = 9SE +/- 1.55, N = 7SE +/- 3.18, N = 7SE +/- 2.49, N = 82995.561714.001831.761707.651580.072405.891282.52985.971509.022394.82778.991075.071875.83

PlaidML

FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti71421283529.9024.6928.1125.0925.2429.9021.4920.9123.5126.4014.0919.7031.55

PlaidML

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti50100150200250SE +/- 0.38, N = 3SE +/- 0.24, N = 3SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.20, N = 3SE +/- 0.27, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.22, N = 3243.50150.94159.34148.55148.07211.01124.2793.61137.81208.2278.9799.49177.04

PlaidML

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.59851.1971.79552.3942.99251.941.642.091.461.551.651.491.321.371.531.491.742.66

PlaidML

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti2004006008001000SE +/- 2.17, N = 6SE +/- 0.60, N = 5SE +/- 0.40, N = 6SE +/- 0.88, N = 6SE +/- 0.20, N = 5SE +/- 0.56, N = 6SE +/- 0.32, N = 5SE +/- 0.27, N = 5SE +/- 0.34, N = 5SE +/- 1.90, N = 6SE +/- 0.32, N = 4SE +/- 0.24, N = 4SE +/- 0.90, N = 6975.56544.72587.72498.24447.06747.50389.45299.07416.15718.51226.15296.82686.66

PlaidML

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti36912158.306.187.046.036.127.715.105.144.996.563.484.789.36

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti6K12K18K24K30KSE +/- 105.50, N = 3SE +/- 43.62, N = 3SE +/- 84.56, N = 3SE +/- 59.70, N = 3SE +/- 60.47, N = 3SE +/- 133.47, N = 3SE +/- 85.05, N = 3SE +/- 72.01, N = 3SE +/- 33.40, N = 3SE +/- 141.13, N = 3SE +/- 48.50, N = 3SE +/- 20.08, N = 3SE +/- 47.37, N = 3283891575817915143321272323269102497051112842108459257324228421. (CXX) g++ options: -flto -pthread

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.26Backend: OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti306090120150103.8582.8791.4477.6276.5094.3067.8760.9368.8182.3755.1161.33120.64

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti140280420560700SE +/- 5.82, N = 9SE +/- 1.61, N = 8SE +/- 2.29, N = 8SE +/- 1.82, N = 7SE +/- 0.10, N = 8SE +/- 3.54, N = 8SE +/- 0.07, N = 7SE +/- 0.50, N = 6SE +/- 0.23, N = 7SE +/- 2.07, N = 8SE +/- 0.02, N = 5SE +/- 1.52, N = 7SE +/- 0.06, N = 8634.1394.1434.4394.2396.7540.7297.3235.4372.2514.5152.8293.5393.51. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1.19482.38963.58444.77925.9744.624.555.314.505.225.014.154.094.414.272.824.275.02

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti130260390520650SE +/- 2.78, N = 9SE +/- 1.71, N = 8SE +/- 2.08, N = 8SE +/- 1.89, N = 7SE +/- 0.27, N = 8SE +/- 1.82, N = 8SE +/- 0.38, N = 7SE +/- 0.26, N = 6SE +/- 0.28, N = 7SE +/- 1.51, N = 8SE +/- 0.36, N = 5SE +/- 1.33, N = 7SE +/- 0.03, N = 8615.3334.2344.1313.9328.4445.4251.2207.4311.8456.0147.4230.0383.61. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1.0892.1783.2674.3565.4454.533.964.313.664.433.913.633.583.803.902.743.374.84

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti70140210280350SE +/- 1.91, N = 9SE +/- 0.81, N = 8SE +/- 1.13, N = 8SE +/- 1.07, N = 7SE +/- 0.06, N = 8SE +/- 0.85, N = 8SE +/- 0.08, N = 7SE +/- 0.27, N = 6SE +/- 0.37, N = 7SE +/- 0.44, N = 8SE +/- 0.28, N = 5SE +/- 0.69, N = 7SE +/- 0.09, N = 8339.9288.5298.9288.2284.5320.8239.0197.2270.4291.8137.8239.0298.21. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.86631.73262.59893.46524.33152.523.423.773.383.823.053.493.493.392.582.593.483.85

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPURTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti100M200M300M400M500MSE +/- 1875555.71, N = 9SE +/- 2274447.08, N = 9SE +/- 1757515.78, N = 9SE +/- 1273824.38, N = 9SE +/- 1098102.02, N = 8SE +/- 2727377.34, N = 10SE +/- 387178.22, N = 8SE +/- 615153.65, N = 7SE +/- 2576635.94, N = 9SE +/- 2676982.40, N = 9SE +/- 458649.89, N = 5SE +/- 545279.65, N = 7SE +/- 552442.28, N = 8401282795.2341286781.7363715438.9316276201.0280144899.1446864473.4247283060.7197542242.7262260550.6443646920.9128084240.3198638055.8278997773.11. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec Per Watt, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPURTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti900K1800K2700K3600K4500K3127589.373349006.113682880.253284888.703316968.864140168.012826824.403061658.832790140.783502262.871890713.652676263.233434300.75

ViennaCL

OpenCL LU Factorization

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti20406080100SE +/- 0.35, N = 15SE +/- 0.44, N = 11SE +/- 0.39, N = 12SE +/- 0.35, N = 11SE +/- 0.23, N = 11SE +/- 0.46, N = 12SE +/- 0.34, N = 11SE +/- 0.22, N = 11SE +/- 0.29, N = 11SE +/- 0.60, N = 11SE +/- 0.50, N = 11SE +/- 0.28, N = 11SE +/- 0.23, N = 1277.9576.1377.1175.7475.0978.6172.8368.6172.3376.2761.7368.7175.831. (CXX) g++ options: -rdynamic -lOpenCL

ViennaCL

OpenCL LU Factorization

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.52651.0531.57952.1062.63251.201.711.741.772.311.852.032.341.781.131.582.141.94

RedShift Demo

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti2004006008001000SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 1.86, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 31723423253523732474798334022561064764240

Blender

Blend File: BMW27 - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti4080120160200SE +/- 2.61, N = 15SE +/- 2.52, N = 15SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 2.63, N = 15SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 3.22, N = 12SE +/- 0.04, N = 3SE +/- 0.02, N = 314.9629.5326.3926.4131.9619.8337.3583.0933.8721.26170.1578.2618.06

Blender

Blend File: Classroom - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: NVIDIA OptiXRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti120240360480600SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.33, N = 3SE +/- 1.47, N = 3SE +/- 0.30, N = 3SE +/- 0.34, N = 3SE +/- 0.04, N = 3SE +/- 1.38, N = 3SE +/- 0.76, N = 341.2987.2682.6090.51147.1673.91149.31281.98154.2582.31548.35270.1955.95

Blender

Blend File: Fishy Cat - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti70140210280350SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 322.7345.9843.5748.8458.1733.0968.22168.1863.2235.12344.25165.5537.24

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti2004006008001000SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.19, N = 3SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.68, N = 3SE +/- 0.11, N = 3SE +/- 0.67, N = 3SE +/- 0.06, N = 359.14135.02130.28135.34198.24104.80210.22489.37209.05114.00973.87476.5586.20

Blender

Blend File: Barbershop - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: NVIDIA OptiXRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1660 SUPERRTX 3060 Ti6001200180024003000SE +/- 0.76, N = 3SE +/- 0.64, N = 3SE +/- 0.11, N = 3SE +/- 0.49, N = 3SE +/- 1.58, N = 3SE +/- 1.60, N = 3SE +/- 4.43, N = 3SE +/- 8.92, N = 3SE +/- 3.65, N = 3SE +/- 1.43, N = 3SE +/- 0.53, N = 3SE +/- 1.52, N = 3458.51974.80917.271002.411803.97902.941783.162732.321877.551002.972593.95581.54

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-29RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti11K22K33K44K55KSE +/- 166.79, N = 3SE +/- 62.43, N = 3SE +/- 53.90, N = 3SE +/- 58.08, N = 3SE +/- 10.04, N = 3SE +/- 82.79, N = 3SE +/- 27.14, N = 3SE +/- 14.84, N = 3SE +/- 51.26, N = 3SE +/- 118.84, N = 3SE +/- 4.67, N = 3SE +/- 34.18, N = 3SE +/- 25.15, N = 349631285643072027682266003738420883170972497536933127881845032065

VkFFT

OpenBenchmarking.orgBenchmark Score Per Watt, More Is BetterVkFFT 2020-09-29RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti70140210280350329.04253.77281.33264.03286.99287.99235.12241.67250.53261.32188.54227.18328.58

NCNN

Target: Vulkan GPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti246810SE +/- 0.14, N = 12SE +/- 0.06, N = 15SE +/- 0.09, N = 15SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 15SE +/- 0.06, N = 15SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 15SE +/- 0.08, N = 3SE +/- 0.08, N = 15SE +/- 0.06, N = 34.074.294.204.184.583.874.756.055.415.057.705.353.96MIN: 3.22 / MAX: 44.48MIN: 3.78 / MAX: 44.36MIN: 3.67 / MAX: 44.19MIN: 3.93 / MAX: 24.5MIN: 4.01 / MAX: 44.45MIN: 3.51 / MAX: 45MIN: 4.19 / MAX: 44.66MIN: 4.56 / MAX: 53.55MIN: 4.02 / MAX: 50.12MIN: 3.57 / MAX: 45.5MIN: 6.82 / MAX: 48.71MIN: 4.46 / MAX: 45.32MIN: 3.54 / MAX: 39.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1.2962.5923.8885.1846.48SE +/- 0.07, N = 12SE +/- 0.06, N = 15SE +/- 0.08, N = 15SE +/- 0.25, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 15SE +/- 0.05, N = 15SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 15SE +/- 0.10, N = 3SE +/- 0.09, N = 14SE +/- 0.01, N = 34.454.164.064.094.234.024.435.304.954.665.764.674.27MIN: 3.5 / MAX: 45.01MIN: 3.6 / MAX: 40.3MIN: 3.52 / MAX: 43.97MIN: 3.61 / MAX: 44.2MIN: 3.74 / MAX: 37.61MIN: 3.43 / MAX: 41.82MIN: 3.89 / MAX: 42.29MIN: 4.07 / MAX: 36.52MIN: 3.79 / MAX: 37.73MIN: 3.42 / MAX: 47.76MIN: 5 / MAX: 36.46MIN: 4.11 / MAX: 40.05MIN: 3.75 / MAX: 35.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.47480.94961.42441.89922.374SE +/- 0.06, N = 12SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 15SE +/- 0.06, N = 15SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 15SE +/- 0.09, N = 3SE +/- 0.04, N = 15SE +/- 0.12, N = 31.731.461.371.381.541.511.561.841.721.752.111.531.74MIN: 1.4 / MAX: 22.34MIN: 1.33 / MAX: 17.85MIN: 1.28 / MAX: 18.03MIN: 1.31 / MAX: 5.51MIN: 1.38 / MAX: 17.92MIN: 1.29 / MAX: 18.36MIN: 1.39 / MAX: 19.37MIN: 1.44 / MAX: 19.14MIN: 1.36 / MAX: 15.12MIN: 1.3 / MAX: 20.67MIN: 1.91 / MAX: 19.43MIN: 1.42 / MAX: 21.24MIN: 1.5 / MAX: 17.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.55581.11161.66742.22322.779SE +/- 0.07, N = 12SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.06, N = 15SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 15SE +/- 0.13, N = 3SE +/- 0.05, N = 15SE +/- 0.01, N = 31.981.751.761.711.641.641.812.101.892.112.471.821.76MIN: 1.65 / MAX: 17.98MIN: 1.57 / MAX: 17.89MIN: 1.52 / MAX: 21.3MIN: 1.55 / MAX: 19.3MIN: 1.61 / MAX: 2.65MIN: 1.53 / MAX: 18.23MIN: 1.61 / MAX: 18.64MIN: 1.66 / MAX: 16.77MIN: 1.58 / MAX: 9.02MIN: 1.55 / MAX: 19.9MIN: 2.28 / MAX: 17.9MIN: 1.63 / MAX: 22.45MIN: 1.73 / MAX: 3.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.40050.8011.20151.6022.0025SE +/- 0.06, N = 12SE +/- 0.05, N = 15SE +/- 0.06, N = 15SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.07, N = 15SE +/- 0.10, N = 3SE +/- 0.03, N = 15SE +/- 0.04, N = 31.541.371.321.361.261.341.371.561.631.621.781.331.36MIN: 1.25 / MAX: 19.9MIN: 1.21 / MAX: 18.01MIN: 1.16 / MAX: 20.88MIN: 1.2 / MAX: 17.51MIN: 1.24 / MAX: 1.92MIN: 1.18 / MAX: 20.07MIN: 1.23 / MAX: 22.22MIN: 1.26 / MAX: 21.01MIN: 1.21 / MAX: 20.82MIN: 1.19 / MAX: 20.26MIN: 1.51 / MAX: 11.8MIN: 1.24 / MAX: 18.01MIN: 1.29 / MAX: 15.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.51531.03061.54592.06122.5765SE +/- 0.06, N = 12SE +/- 0.03, N = 15SE +/- 0.05, N = 15SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 15SE +/- 0.07, N = 15SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 14SE +/- 0.17, N = 2SE +/- 0.06, N = 15SE +/- 0.14, N = 21.801.501.521.661.561.491.631.811.721.892.291.661.77MIN: 1.49 / MAX: 19.5MIN: 1.4 / MAX: 17.79MIN: 1.34 / MAX: 19.22MIN: 1.37 / MAX: 17.88MIN: 1.44 / MAX: 20.92MIN: 1.35 / MAX: 19.31MIN: 1.45 / MAX: 19.28MIN: 1.49 / MAX: 18.94MIN: 1.42 / MAX: 8.94MIN: 1.37 / MAX: 19.83MIN: 2.01 / MAX: 18.01MIN: 1.46 / MAX: 19.39MIN: 1.6 / MAX: 22.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.8461.6922.5383.3844.23SE +/- 0.11, N = 12SE +/- 0.05, N = 15SE +/- 0.05, N = 15SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 15SE +/- 0.06, N = 15SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 15SE +/- 0.06, N = 3SE +/- 0.05, N = 15SE +/- 0.13, N = 33.132.662.612.762.792.732.923.633.353.333.762.883.03MIN: 2.61 / MAX: 20.61MIN: 2.53 / MAX: 22.5MIN: 2.42 / MAX: 20.41MIN: 2.48 / MAX: 17.56MIN: 2.6 / MAX: 19.01MIN: 2.45 / MAX: 21.05MIN: 2.59 / MAX: 22.74MIN: 2.65 / MAX: 22.19MIN: 2.54 / MAX: 22.25MIN: 2.48 / MAX: 22.5MIN: 3.48 / MAX: 21.65MIN: 2.62 / MAX: 21.44MIN: 2.72 / MAX: 20.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.18230.36460.54690.72920.9115SE +/- 0.02, N = 12SE +/- 0.01, N = 15SE +/- 0.03, N = 15SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 15SE +/- 0.13, N = 3SE +/- 0.04, N = 15SE +/- 0.02, N = 30.640.610.630.630.580.680.670.720.720.810.800.640.63MIN: 0.51 / MAX: 30.84MIN: 0.54 / MAX: 21.62MIN: 0.54 / MAX: 27.09MIN: 0.56 / MAX: 20.82MIN: 0.57 / MAX: 0.84MIN: 0.52 / MAX: 27.01MIN: 0.56 / MAX: 23.74MIN: 0.57 / MAX: 6.28MIN: 0.55 / MAX: 7.89MIN: 0.51 / MAX: 27.19MIN: 0.63 / MAX: 19.93MIN: 0.56 / MAX: 26.92MIN: 0.57 / MAX: 91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1.19482.38963.58444.77925.974SE +/- 0.09, N = 12SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 15SE +/- 0.06, N = 15SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 15SE +/- 0.10, N = 3SE +/- 0.07, N = 15SE +/- 0.01, N = 33.883.293.123.233.433.103.574.334.163.735.313.933.44MIN: 3.16 / MAX: 22.34MIN: 3.03 / MAX: 22.52MIN: 2.89 / MAX: 20.85MIN: 3.02 / MAX: 18.59MIN: 3.19 / MAX: 21.25MIN: 2.84 / MAX: 21.01MIN: 3.3 / MAX: 22.32MIN: 3.53 / MAX: 24.2MIN: 3.15 / MAX: 21.29MIN: 2.87 / MAX: 23.31MIN: 4.95 / MAX: 24.26MIN: 3.5 / MAX: 21.95MIN: 3.41 / MAX: 3.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti510152025SE +/- 0.07, N = 12SE +/- 0.05, N = 15SE +/- 0.06, N = 15SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 15SE +/- 0.04, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 34.717.697.448.208.965.6810.3215.099.856.2818.5413.976.02MIN: 4 / MAX: 20.55MIN: 6.57 / MAX: 26.43MIN: 6.29 / MAX: 26.19MIN: 6.99 / MAX: 25.35MIN: 7.8 / MAX: 24.64MIN: 5 / MAX: 27.84MIN: 9.24 / MAX: 31.92MIN: 12.16 / MAX: 32.96MIN: 8.27 / MAX: 27.4MIN: 4.88 / MAX: 25.09MIN: 17.62 / MAX: 31.07MIN: 11.92 / MAX: 39.63MIN: 5.48 / MAX: 23.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.73351.4672.20052.9343.6675SE +/- 0.01, N = 11SE +/- 0.03, N = 14SE +/- 0.04, N = 13SE +/- 0.06, N = 3SE +/- 0.02, N = 15SE +/- 0.04, N = 15SE +/- 0.02, N = 3SE +/- 0.02, N = 2SE +/- 0.08, N = 14SE +/- 0.19, N = 3SE +/- 0.04, N = 15SE +/- 0.16, N = 31.311.551.521.661.741.301.982.381.911.733.262.321.70MIN: 1.18 / MAX: 9.46MIN: 1.44 / MAX: 18.28MIN: 1.39 / MAX: 15.39MIN: 1.52 / MAX: 18.57MIN: 1.62 / MAX: 17.79MIN: 1.22 / MAX: 20.6MIN: 1.8 / MAX: 19.93MIN: 2.08 / MAX: 9.06MIN: 1.62 / MAX: 7.23MIN: 1.22 / MAX: 19.76MIN: 2.96 / MAX: 19.72MIN: 2.11 / MAX: 25.13MIN: 1.36 / MAX: 19.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1.22632.45263.67894.90526.1315SE +/- 0.11, N = 11SE +/- 0.08, N = 15SE +/- 0.03, N = 15SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 15SE +/- 0.07, N = 15SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 12SE +/- 0.08, N = 3SE +/- 0.06, N = 15SE +/- 0.03, N = 31.822.211.962.002.141.722.563.552.801.965.453.041.65MIN: 1.4 / MAX: 22.36MIN: 1.72 / MAX: 22.49MIN: 1.61 / MAX: 19.29MIN: 1.74 / MAX: 2.9MIN: 1.83 / MAX: 17.66MIN: 1.47 / MAX: 22.17MIN: 2.18 / MAX: 22.08MIN: 2.36 / MAX: 22.1MIN: 1.81 / MAX: 26MIN: 1.49 / MAX: 22.41MIN: 4.92 / MAX: 21.52MIN: 2.39 / MAX: 19.77MIN: 1.57 / MAX: 16.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50RTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti246810SE +/- 0.07, N = 12SE +/- 0.07, N = 15SE +/- 0.07, N = 14SE +/- 0.24, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 15SE +/- 0.06, N = 15SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 15SE +/- 0.15, N = 3SE +/- 0.04, N = 15SE +/- 0.09, N = 33.513.723.523.843.933.304.436.034.653.887.625.253.72MIN: 2.98 / MAX: 20.05MIN: 3.38 / MAX: 22.49MIN: 3.25 / MAX: 21.15MIN: 3.47 / MAX: 18.13MIN: 3.73 / MAX: 21.52MIN: 2.94 / MAX: 22.59MIN: 4.07 / MAX: 22.33MIN: 4.75 / MAX: 21.46MIN: 3.72 / MAX: 21.74MIN: 2.96 / MAX: 22.65MIN: 7.05 / MAX: 23.24MIN: 4.76 / MAX: 22.66MIN: 3.41 / MAX: 21.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti3691215SE +/- 0.05, N = 12SE +/- 0.05, N = 15SE +/- 0.07, N = 15SE +/- 0.16, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 15SE +/- 0.08, N = 15SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 15SE +/- 0.13, N = 3SE +/- 0.08, N = 15SE +/- 0.05, N = 36.507.027.077.197.276.537.849.308.547.479.878.586.56MIN: 5.43 / MAX: 43.21MIN: 6.22 / MAX: 40.65MIN: 6.15 / MAX: 40.21MIN: 6.45 / MAX: 39.21MIN: 6.66 / MAX: 39.39MIN: 5.8 / MAX: 39.76MIN: 6.94 / MAX: 43.56MIN: 7.65 / MAX: 39.63MIN: 6.69 / MAX: 41.56MIN: 5.76 / MAX: 49.68MIN: 8.6 / MAX: 40.07MIN: 7.66 / MAX: 46.65MIN: 5.89 / MAX: 39.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti306090120150SE +/- 0.17, N = 3SE +/- 0.31, N = 3SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.43, N = 3SE +/- 0.16, N = 3SE +/- 0.26, N = 3SE +/- 0.17, N = 3SE +/- 0.34, N = 3SE +/- 0.18, N = 3SE +/- 0.24, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 335.7260.1054.7863.7574.8144.7386.60123.8580.5945.55144.63120.9152.47

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti510152025SE +/- 0.012, N = 6SE +/- 0.033, N = 5SE +/- 0.029, N = 5SE +/- 0.031, N = 5SE +/- 0.014, N = 4SE +/- 0.011, N = 6SE +/- 0.015, N = 4SE +/- 0.034, N = 3SE +/- 0.021, N = 4SE +/- 0.028, N = 6SE +/- 0.017, N = 3SE +/- 0.026, N = 3SE +/- 0.025, N = 56.5769.6119.03110.20611.5377.74312.93617.73312.3778.00920.12817.2148.633

IndigoBench

Acceleration: OpenCL GPU - Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti1020304050SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 343.5924.8325.4824.4923.4333.1918.2514.3021.6731.7610.2815.2433.52

IndigoBench

Acceleration: OpenCL GPU - Scene: Supercar

OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.05180.10360.15540.20720.2590.190.180.180.180.180.170.170.180.170.150.160.160.23

IndigoBench

Acceleration: OpenCL GPU - Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti48121620SE +/- 0.024, N = 3SE +/- 0.008, N = 3SE +/- 0.005, N = 3SE +/- 0.009, N = 3SE +/- 0.001, N = 3SE +/- 0.014, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.008, N = 3SE +/- 0.009, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 316.5957.7117.8847.6777.39410.9135.5344.3606.86510.5883.5474.66211.394

IndigoBench

Acceleration: OpenCL GPU - Scene: Bedroom

OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti0.01580.03160.04740.06320.0790.070.050.060.050.060.050.050.050.050.050.050.050.07

Geekbench

Test: GPU OpenCL

OpenBenchmarking.orgScore, More Is BetterGeekbench 5Test: GPU OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti40K80K120K160K200KSE +/- 733.75, N = 3SE +/- 200.07, N = 3SE +/- 1025.87, N = 3SE +/- 521.87, N = 3SE +/- 668.55, N = 3SE +/- 303.84, N = 3SE +/- 772.57, N = 3SE +/- 420.54, N = 3SE +/- 823.09, N = 3SE +/- 1711.48, N = 3SE +/- 218.79, N = 3SE +/- 558.50, N = 3SE +/- 1279.48, N = 3197267114773124272105899938051525838071264871870761511483679864680132421

Geekbench

Test: GPU OpenCL

OpenBenchmarking.orgScore Per Watt, More Is BetterGeekbench 5Test: GPU OpenCLRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti50010001500200025001936.501613.121855.401658.791631.211962.161473.911730.981457.661557.54766.731296.982278.18

Geekbench

Test: GPU NVIDIA CUDA

OpenBenchmarking.orgScore, More Is BetterGeekbench 5Test: GPU NVIDIA CUDARTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti40K80K120K160K200KSE +/- 2347.00, N = 14SE +/- 663.75, N = 3SE +/- 1753.98, N = 3SE +/- 539.60, N = 3SE +/- 667.51, N = 3SE +/- 1291.90, N = 3SE +/- 411.67, N = 3SE +/- 128.28, N = 3SE +/- 657.64, N = 3SE +/- 1675.18, N = 15SE +/- 96.77, N = 3SE +/- 387.46, N = 3SE +/- 835.34, N = 3208331121856128277110450996641678588353567003905721558673367166387136797

Geekbench

Test: GPU NVIDIA CUDA

OpenBenchmarking.orgScore Per Watt, More Is BetterGeekbench 5Test: GPU NVIDIA CUDARTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti50010001500200025001916.201751.841815.721590.391523.731927.381314.211499.741421.931602.54592.621207.712139.98

Geekbench

Test: GPU Vulkan

OpenBenchmarking.orgScore, More Is BetterGeekbench 5Test: GPU VulkanRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti30K60K90K120K150KSE +/- 1286.56, N = 15SE +/- 1128.61, N = 3SE +/- 1145.26, N = 8SE +/- 1315.57, N = 3SE +/- 421.33, N = 3SE +/- 1281.91, N = 15SE +/- 820.21, N = 3SE +/- 734.49, N = 3SE +/- 343.85, N = 3SE +/- 1193.73, N = 15SE +/- 331.69, N = 3SE +/- 423.81, N = 3SE +/- 923.31, N = 151587249848710835996082851251324897268959063757501280033784460351112321

Geekbench

Test: GPU Vulkan

OpenBenchmarking.orgScore Per Watt, More Is BetterGeekbench 5Test: GPU VulkanRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti4008001200160020001502.881362.741486.191469.221608.471592.921275.011281.071116.651301.46715.071126.661806.21

Meta Performance Per Watts

Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsRTX 3080RTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2070RTX 2080 TiRTX 2060GTX 1660 TiRTX 2060 SUPERTITAN RTXGTX 1060GTX 1660 SUPERRTX 3060 Ti2K4K6K8K10K10055.705999.926419.105749.585278.848097.454332.553346.524907.677834.122331.463523.296912.71

Phoronix Test Suite v10.8.4