NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2012250-HA-NVIDIAGPU61&grr&sro.

NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060 TIRTX 3080AMD 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 2060 6GB (1365/7000MHz)NVIDIA 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 9.3.0ext43840x2160NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (435/405MHz)NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz)NVIDIA TU104 HD AudioZotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TU102 HD AudioNVIDIA TITAN RTX 24GB (1350/7000MHz)NVIDIA GeForce RTX 3060 Ti 8GB (1665/7000MHz)NVIDIA Device 228bNVIDIA GeForce RTX 3080 10GB (1710/9501MHz)NVIDIA Device 1aefOpenBenchmarking.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 ondemand (Boost: Enabled) - CPU Microcode: 0xa201009OpenCL Details- RTX 2060: GPU Compute Cores: 1920- RTX 2060 SUPER: GPU Compute Cores: 2176- RTX 2070: GPU Compute Cores: 2304- RTX 2070 SUPER: GPU Compute Cores: 2560- RTX 2080: GPU Compute Cores: 2944- RTX 2080 SUPER: GPU Compute Cores: 3072- RTX 2080 Ti: GPU Compute Cores: 4352- TITAN RTX: GPU Compute Cores: 4608- RTX 3060 TI: GPU Compute Cores: 4864- RTX 3080: GPU Compute Cores: 8704Python 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 Linux GPU Performance Comptue RTX 30 RTX 20blender: Barbershop - NVIDIA OptiXvkfft: lczero: OpenCLredshift: luxcorerender-cl: Foodluxcorerender-cl: LuxCore Benchmarkoctanebench: Total Scoreluxcorerender-cl: DLSCblender: Pabellon Barcelona - NVIDIA OptiXplaidml: No - Training - VGG19 - OpenCLplaidml: No - Training - VGG16 - OpenCLblender: Classroom - NVIDIA OptiXfahbench: ncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetplaidml: No - Inference - NASNer Large - OpenCLrealsr-ncnn: 4x - Yesblender: Fishy Cat - NVIDIA OptiXblender: BMW27 - NVIDIA OptiXvkresample: 2x - Doubleplaidml: No - Inference - DenseNet 201 - OpenCLclpeak: Double-Precision Doubleluxcorerender-cl: Rainbow Colors and Prismbetsy: ETC2 RGB - Highestplaidml: No - Inference - Inception V3 - OpenCLbetsy: ETC1 - Highestplaidml: No - Inference - VGG19 - OpenCLplaidml: No - Inference - VGG16 - OpenCLvkresample: 2x - Singleplaidml: No - Inference - ResNet 50 - OpenCLrealsr-ncnn: 4x - Noplaidml: No - Inference - IMDB LSTM - OpenCLrodinia: OpenCL Particle Filterhashcat: TrueCrypt RIPEMD160 + XTShashcat: SHA-512hashcat: SHA1hashcat: MD5plaidml: No - Inference - Mobilenet - OpenCLplaidml: Yes - Inference - Mobilenet - OpenCLclpeak: Integer Compute INTwaifu2x-ncnn: 2x - 3 - Yescl-mem: Copycl-mem: Writecl-mem: Readclpeak: Single-Precision Floatmandelgpu: GPUarrayfire: Conjugate Gradient OpenCLhashcat: 7-Zipviennacl: OpenCL LU Factorizationclpeak: Global Memory Bandwidthfinancebench: Black-Scholes OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiTITAN RTXRTX 3060 TIRTX 30801779.462290397524691.212.80195.0098063.30206.8622.0427.12147.65183.291318.2914.3221.4124.5811.6114.4756.9813.431.85.484.014.424.154.4412.4231.8185.94867.1336.27350.961125.45231.277.988.748171.786.18988.38110.9627.195320.9512.707392.028.96031180010493666678248933333259306333331282.271720.245224.685.779239.5251.6297.55369.81253858256.72.65043900074.5062277.4012.5651758.1729585113993781.323.63244.2245534.19194.4124.5830.00144.40207.077018.4914.6322.8025.7111.5314.7757.2214.181.935.704.334.474.344.6713.0438.4275.89258.9430.90309.619147.13261.5311.417.733203.785.451100.61126.7622.282376.5911.540440.367.98134960011834333339314900000292720000001581.852011.996956.555.313288.3340.1397.16985.02278640038.12.07349053374.0853369.4210.4541826.3029546114953751.303.56243.2612184.14198.6330.27148.17205.232218.6814.5121.4125.0511.7414.5557.1313.601.875.594.154.454.194.6012.6639.0774.65458.3431.34302.845148.04268.1810.947.646202.055.309103.03129.6522.269379.7011.187447.477.85835670012132666679535466667299555666671566.362004.517094.245.314285.7323.9397.17190.53283803060.12.08650023374.1817369.1410.225996.8229427128413511.863.67264.5349434.32132.7327.7833.7589.12229.760018.5814.5521.7925.2511.3614.5357.1313.481.885.604.224.464.304.6412.7742.3263.17848.0325.44261.969149.68309.2710.046.653220.434.824121.35152.5819.523422.869.972499.436.900423733142673333311183366667354660333331701.992300.018551.574.761292.3320.6397.18591.77321637774.32.06059370075.7984370.178.224971.6228745135763411.883.55261.3295044.23132.9028.3234.1386.13244.417118.7714.4521.8124.6211.3714.5857.2513.561.865.564.104.484.254.5012.6945.3959.40345.5126.24235.512152.28344.689.276.153242.544.375128.62161.8819.024442.789.473545.486.288461367155950000012203533333384932333331726.882333.799330.834.605290.5331.9397.18860.55343080891.12.07263736777.1727369.657.620911.3230475146343251.973.60268.1143684.32126.9332.2938.781.14260.895718.6514.4722.1324.7311.2214.3657.0813.121.885.684.214.504.304.6512.7249.1654.03742.6025.22216.539160.48373.969.195.507266.394.004143.39180.2317.507468.608.842588.045.809527287173410000013653000000431369666671816.872489.1110244.084.358302.0350.8437.810347.92368037096.61.89371196776.6869405.686.749899.1434110169522462.184.58354.8567695.53103.9736.944.0273.99304.036218.3214.3621.4524.6911.4414.6556.6913.961.956.024.564.484.434.7412.6463.5344.18632.8021.67152.853213.54519.0312.14351.183.177185.09231.7314.767636.847.605754.694.507657967224170000017751300000554883333332414.963316.3113432.893.856324.0446.6545.612677.18447272306.01.67088530078.3244508.006.014905.2236216170092352.235.03383.4637395.95102.5137.5644.5173.40307.034818.2114.3521.8824.9511.2514.3656.5213.321.836.034.024.434.204.4912.7766.5041.73131.7218.64149.204228.78545.2213.564.116359.133.043194.50244.0013.561654.767.360782.294.296688167235036666718576400000581043000002551.383392.9613791.913.827320.8495.4568.214109.68460475602.61.63793723381.3167530.485.691565.9932556167992392.975.91383.4165837.1384.9529.3834.9856.33235.716718.5715.1121.3524.6911.4114.5157.1813.411.865.554.114.474.254.5412.5448.0454.14436.7420.15264.871177.41306.1217.116.040236.404.358133.11167.7317.676454.668.784689.617.040427100140690000011103733333329276000001875.372428.748365.854.371294.1384.3392.816033.64280941400.22.09258130075.7896389.188.328421.5140997186681654.007.84565.0995129.6055.6340.8847.5038.85320.657118.4514.5022.1525.3411.7114.7456.9613.951.915.614.204.524.344.5612.7879.2334.20621.4811.48148.284261.32545.9121.913.664398.642.701223.64280.3111.220730.766.3451019.794.290723200242603333319151100000564291333333062.003623.8215586.033.512354.7645.3674.229490.81421918457.51.55798130079.3217662.244.869OpenBenchmarking.org

Blender

Blend File: Barbershop - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX400800120016002000SE +/- 2.01, N = 3SE +/- 0.52, N = 3SE +/- 2.84, N = 3SE +/- 1.90, N = 3SE +/- 0.81, N = 3SE +/- 0.14, N = 3SE +/- 1.58, N = 3SE +/- 0.84, N = 3SE +/- 1.49, N = 3SE +/- 1.56, N = 31779.461758.171826.30996.82971.62911.32899.14565.99421.51905.22

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.1RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX9K18K27K36K45KSE +/- 44.06, N = 3SE +/- 257.75, N = 3SE +/- 149.21, N = 3SE +/- 213.44, N = 3SE +/- 95.96, N = 3SE +/- 51.40, N = 3SE +/- 78.30, N = 3SE +/- 86.88, N = 3SE +/- 284.10, N = 3SE +/- 413.34, N = 3229032958529546294272874530475341103255640997362161. (CXX) g++ options: -O3 -pthread

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX4K8K12K16K20KSE +/- 66.84, N = 3SE +/- 69.95, N = 3SE +/- 54.87, N = 3SE +/- 49.97, N = 3SE +/- 51.64, N = 3SE +/- 48.26, N = 3SE +/- 54.85, N = 3SE +/- 26.30, N = 3SE +/- 122.65, N = 3SE +/- 110.73, N = 397521139911495128411357614634169521679918668170091. (CXX) g++ options: -flto -pthread

RedShift Demo

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX100200300400500SE +/- 0.88, N = 3SE +/- 1.00, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3469378375351341325246239165235

LuxCoreRender OpenCL

Scene: Food

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX0.91.82.73.64.5SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 12SE +/- 0.03, N = 4SE +/- 0.01, N = 3SE +/- 0.04, N = 12SE +/- 0.05, N = 12SE +/- 0.07, N = 14SE +/- 0.03, N = 51.211.321.301.861.881.972.182.974.002.23MIN: 0.24 / MAX: 1.44MIN: 0.23 / MAX: 1.59MIN: 0.23 / MAX: 1.55MIN: 0.18 / MAX: 2.3MIN: 0.23 / MAX: 2.29MIN: 0.27 / MAX: 2.37MIN: 0.15 / MAX: 2.71MIN: 0.19 / MAX: 3.74MIN: 0.17 / MAX: 5.07MIN: 0.23 / MAX: 2.76

LuxCoreRender OpenCL

Scene: LuxCore Benchmark

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 12SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 13SE +/- 0.07, N = 12SE +/- 0.10, N = 12SE +/- 0.02, N = 32.803.633.563.673.553.604.585.917.845.03MIN: 0.23 / MAX: 3.2MIN: 0.23 / MAX: 4.15MIN: 0.23 / MAX: 4.1MIN: 0.2 / MAX: 4.25MIN: 0.23 / MAX: 4.07MIN: 0.27 / MAX: 4.14MIN: 0.19 / MAX: 5.4MIN: 0.25 / MAX: 6.86MIN: 0.15 / MAX: 9.17MIN: 0.32 / MAX: 5.72

OctaneBench

Total Score

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX120240360480600195.01244.22243.26264.53261.33268.11354.86383.42565.10383.46

LuxCoreRender OpenCL

Scene: DLSC

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 12SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 12SE +/- 0.10, N = 12SE +/- 0.14, N = 12SE +/- 0.01, N = 33.304.194.144.324.234.325.537.139.605.95MIN: 3.16 / MAX: 3.4MIN: 4.11 / MAX: 4.29MIN: 3.79 / MAX: 4.28MIN: 1.6 / MAX: 4.51MIN: 4.15 / MAX: 4.3MIN: 4.13 / MAX: 4.4MIN: 2.02 / MAX: 5.76MIN: 2.58 / MAX: 7.38MIN: 3.45 / MAX: 9.87MIN: 5.62 / MAX: 6.04

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX50100150200250SE +/- 0.04, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3206.86194.41198.63132.73132.90126.93103.9784.9555.63102.51

PlaidML

FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Training - Network: VGG19 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX918273645SE +/- 0.04, N = 2SE +/- 0.05, N = 2SE +/- 0.15, N = 2SE +/- 0.08, N = 222.0424.5827.7828.3232.2936.9029.3840.8837.56

PlaidML

FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Training - Network: VGG16 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1122334455SE +/- 0.20, N = 2SE +/- 0.33, N = 2SE +/- 0.18, N = 2SE +/- 0.36, N = 227.1230.0030.2733.7534.1338.7044.0234.9847.5044.51

Blender

Blend File: Classroom - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX306090120150SE +/- 0.39, N = 3SE +/- 0.38, N = 3SE +/- 0.95, N = 3SE +/- 0.32, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.50, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3SE +/- 0.17, N = 3147.65144.40148.1789.1286.1381.1473.9956.3338.8573.40

FAHBench

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX70140210280350SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.30, N = 3SE +/- 0.07, N = 3183.29207.08205.23229.76244.42260.90304.04235.72320.66307.03

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400mRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX510152025SE +/- 0.08, N = 3SE +/- 0.15, N = 4SE +/- 0.06, N = 3SE +/- 0.07, N = 15SE +/- 0.09, N = 5SE +/- 0.19, N = 3SE +/- 0.20, N = 3SE +/- 0.28, N = 4SE +/- 0.35, N = 3SE +/- 0.09, N = 318.2918.4918.6818.5818.7718.6518.3218.5718.4518.21MIN: 17.99 / MAX: 28.28MIN: 18.01 / MAX: 28.46MIN: 18.38 / MAX: 19.17MIN: 17.91 / MAX: 28.99MIN: 18.01 / MAX: 30.34MIN: 18.24 / MAX: 19.54MIN: 17.72 / MAX: 19.14MIN: 17.78 / MAX: 20.78MIN: 17.4 / MAX: 28.56MIN: 17.88 / MAX: 20.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssdRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX48121620SE +/- 0.05, N = 3SE +/- 0.12, N = 4SE +/- 0.14, N = 2SE +/- 0.06, N = 15SE +/- 0.24, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.73, N = 4SE +/- 0.09, N = 3SE +/- 0.19, N = 314.3214.6314.5114.5514.4514.4714.3615.1114.5014.35MIN: 14.04 / MAX: 14.98MIN: 14.15 / MAX: 16.53MIN: 14.12 / MAX: 15.9MIN: 13.96 / MAX: 25.49MIN: 13.6 / MAX: 27.41MIN: 14.11 / MAX: 24.43MIN: 13.91 / MAX: 27.4MIN: 13.72 / MAX: 369.11MIN: 14.11 / MAX: 14.97MIN: 13.84 / MAX: 22.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tinyRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX510152025SE +/- 0.56, N = 3SE +/- 0.07, N = 4SE +/- 0.58, N = 3SE +/- 0.24, N = 15SE +/- 0.41, N = 5SE +/- 0.60, N = 3SE +/- 0.60, N = 3SE +/- 0.64, N = 4SE +/- 0.70, N = 3SE +/- 0.66, N = 321.4122.8021.4121.7921.8122.1321.4521.3522.1521.88MIN: 20.54 / MAX: 32.23MIN: 22.31 / MAX: 25.04MIN: 20.58 / MAX: 23.53MIN: 20.42 / MAX: 29.15MIN: 20.55 / MAX: 24.56MIN: 20.69 / MAX: 28.53MIN: 20.52 / MAX: 33.08MIN: 20.24 / MAX: 29.48MIN: 20.53 / MAX: 30.78MIN: 20.33 / MAX: 23.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX612182430SE +/- 0.15, N = 3SE +/- 0.09, N = 4SE +/- 0.54, N = 3SE +/- 0.18, N = 15SE +/- 0.23, N = 5SE +/- 0.40, N = 3SE +/- 0.33, N = 3SE +/- 0.35, N = 4SE +/- 0.56, N = 3SE +/- 0.37, N = 324.5825.7125.0525.2524.6224.7324.6924.6925.3424.95MIN: 23.83 / MAX: 37.73MIN: 24.88 / MAX: 31.53MIN: 24.29 / MAX: 41.55MIN: 23.93 / MAX: 36.67MIN: 23.99 / MAX: 26.48MIN: 23.79 / MAX: 35.29MIN: 23.98 / MAX: 37.45MIN: 23.66 / MAX: 26.48MIN: 24.02 / MAX: 26.96MIN: 23.91 / MAX: 36.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnetRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3691215SE +/- 0.22, N = 3SE +/- 0.04, N = 4SE +/- 0.08, N = 3SE +/- 0.06, N = 15SE +/- 0.06, N = 5SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 4SE +/- 0.12, N = 3SE +/- 0.05, N = 311.6111.5311.7411.3611.3711.2211.4411.4111.7111.25MIN: 11.08 / MAX: 18.93MIN: 11.27 / MAX: 18.29MIN: 11.39 / MAX: 12.18MIN: 10.75 / MAX: 15.63MIN: 11.04 / MAX: 17.87MIN: 10.85 / MAX: 11.85MIN: 11.09 / MAX: 11.74MIN: 10.77 / MAX: 22.45MIN: 11.28 / MAX: 12.12MIN: 11 / MAX: 11.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX48121620SE +/- 0.26, N = 3SE +/- 0.19, N = 4SE +/- 0.19, N = 3SE +/- 0.07, N = 15SE +/- 0.12, N = 5SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.21, N = 4SE +/- 0.25, N = 3SE +/- 0.25, N = 314.4714.7714.5514.5314.5814.3614.6514.5114.7414.36MIN: 14.01 / MAX: 23.82MIN: 14.08 / MAX: 16.79MIN: 14.18 / MAX: 15.25MIN: 14.06 / MAX: 27.16MIN: 14.21 / MAX: 16.27MIN: 14.01 / MAX: 15.12MIN: 14.13 / MAX: 15.56MIN: 13.97 / MAX: 25.49MIN: 14.13 / MAX: 15.8MIN: 13.96 / MAX: 17.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1326395265SE +/- 0.31, N = 3SE +/- 0.14, N = 4SE +/- 0.13, N = 3SE +/- 0.13, N = 15SE +/- 0.17, N = 5SE +/- 0.37, N = 3SE +/- 0.27, N = 3SE +/- 0.43, N = 4SE +/- 0.09, N = 3SE +/- 0.17, N = 356.9857.2257.1357.1357.2557.0856.6957.1856.9656.52MIN: 55.41 / MAX: 58.77MIN: 55.71 / MAX: 64.21MIN: 56.01 / MAX: 66.17MIN: 54.93 / MAX: 68.8MIN: 55.82 / MAX: 67.69MIN: 55.71 / MAX: 70.92MIN: 55.51 / MAX: 58.35MIN: 54.93 / MAX: 68.94MIN: 56.04 / MAX: 59.71MIN: 55.22 / MAX: 72.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenetRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX48121620SE +/- 0.55, N = 3SE +/- 0.43, N = 4SE +/- 0.27, N = 3SE +/- 0.21, N = 14SE +/- 0.35, N = 5SE +/- 0.39, N = 3SE +/- 0.49, N = 3SE +/- 0.33, N = 4SE +/- 0.37, N = 3SE +/- 0.68, N = 213.4314.1813.6013.4813.5613.1213.9613.4113.9513.32MIN: 12.61 / MAX: 15.67MIN: 12.62 / MAX: 15.92MIN: 12.94 / MAX: 24.05MIN: 12.43 / MAX: 26.89MIN: 12.71 / MAX: 20.62MIN: 12.41 / MAX: 14.53MIN: 12.74 / MAX: 15.74MIN: 12.46 / MAX: 28.14MIN: 12.96 / MAX: 24.07MIN: 12.38 / MAX: 25.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazefaceRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX0.43880.87761.31641.75522.194SE +/- 0.03, N = 3SE +/- 0.03, N = 4SE +/- 0.05, N = 3SE +/- 0.02, N = 15SE +/- 0.02, N = 5SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 4SE +/- 0.04, N = 3SE +/- 0.02, N = 31.801.931.871.881.861.881.951.861.911.83MIN: 1.79 / MAX: 1.96MIN: 1.85 / MAX: 2.11MIN: 1.8 / MAX: 2.15MIN: 1.78 / MAX: 2.2MIN: 1.81 / MAX: 2.28MIN: 1.77 / MAX: 2.21MIN: 1.85 / MAX: 2.39MIN: 1.78 / MAX: 2.03MIN: 1.82 / MAX: 2.14MIN: 1.78 / MAX: 2.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX246810SE +/- 0.03, N = 3SE +/- 0.06, N = 4SE +/- 0.02, N = 3SE +/- 0.06, N = 15SE +/- 0.04, N = 5SE +/- 0.21, N = 3SE +/- 0.26, N = 3SE +/- 0.05, N = 4SE +/- 0.06, N = 3SE +/- 0.57, N = 35.485.705.595.605.565.686.025.555.616.03MIN: 5.32 / MAX: 5.98MIN: 5.43 / MAX: 17.45MIN: 5.42 / MAX: 5.85MIN: 5.28 / MAX: 16.37MIN: 5.37 / MAX: 6.08MIN: 5.29 / MAX: 17.94MIN: 5.37 / MAX: 11.96MIN: 5.34 / MAX: 7.32MIN: 5.45 / MAX: 5.87MIN: 5.28 / MAX: 339.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnetRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1.0262.0523.0784.1045.13SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 15SE +/- 0.06, N = 5SE +/- 0.21, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 4SE +/- 0.13, N = 3SE +/- 0.02, N = 34.014.334.154.224.104.214.564.114.204.02MIN: 3.83 / MAX: 4.42MIN: 4.04 / MAX: 4.77MIN: 4 / MAX: 16.56MIN: 3.86 / MAX: 5.14MIN: 3.82 / MAX: 4.59MIN: 3.86 / MAX: 4.92MIN: 3.93 / MAX: 5.1MIN: 3.87 / MAX: 5.49MIN: 3.91 / MAX: 10.98MIN: 3.88 / MAX: 4.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v2RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1.0172.0343.0514.0685.085SE +/- 0.02, N = 3SE +/- 0.01, N = 4SE +/- 0.03, N = 3SE +/- 0.01, N = 13SE +/- 0.01, N = 5SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 34.424.474.454.464.484.504.484.474.524.43MIN: 4.31 / MAX: 4.8MIN: 4.37 / MAX: 4.78MIN: 4.34 / MAX: 4.91MIN: 4.31 / MAX: 4.82MIN: 4.36 / MAX: 14.35MIN: 4.35 / MAX: 5.04MIN: 4.38 / MAX: 4.9MIN: 4.34 / MAX: 5.99MIN: 4.42 / MAX: 13.63MIN: 4.32 / MAX: 5.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX0.99681.99362.99043.98724.984SE +/- 0.03, N = 3SE +/- 0.08, N = 4SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.05, N = 5SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 4SE +/- 0.09, N = 3SE +/- 0.00, N = 34.154.344.194.304.254.304.434.254.344.20MIN: 4.06 / MAX: 4.44MIN: 4.12 / MAX: 4.79MIN: 4.14 / MAX: 4.4MIN: 4.06 / MAX: 19.54MIN: 4.07 / MAX: 4.62MIN: 4.12 / MAX: 4.69MIN: 4.13 / MAX: 11.06MIN: 4.02 / MAX: 5.79MIN: 4.17 / MAX: 4.73MIN: 4.14 / MAX: 4.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1.06652.1333.19954.2665.3325SE +/- 0.03, N = 3SE +/- 0.07, N = 4SE +/- 0.02, N = 3SE +/- 0.07, N = 15SE +/- 0.04, N = 5SE +/- 0.23, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 4SE +/- 0.05, N = 3SE +/- 0.02, N = 34.444.674.604.644.504.654.744.544.564.49MIN: 4.21 / MAX: 4.75MIN: 4.31 / MAX: 5.1MIN: 4.35 / MAX: 13.48MIN: 4.23 / MAX: 5.42MIN: 4.19 / MAX: 13.41MIN: 4.19 / MAX: 5.42MIN: 4.31 / MAX: 5.6MIN: 4.25 / MAX: 5.73MIN: 4.3 / MAX: 4.85MIN: 4.26 / MAX: 4.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenetRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3691215SE +/- 0.14, N = 3SE +/- 0.17, N = 4SE +/- 0.17, N = 3SE +/- 0.14, N = 15SE +/- 0.16, N = 5SE +/- 0.11, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 4SE +/- 0.12, N = 3SE +/- 0.16, N = 312.4213.0412.6612.7712.6912.7212.6412.5412.7812.77MIN: 11.98 / MAX: 24.63MIN: 12.34 / MAX: 24MIN: 12.23 / MAX: 24.28MIN: 11.98 / MAX: 34.45MIN: 11.97 / MAX: 24.76MIN: 12.26 / MAX: 13.5MIN: 12.22 / MAX: 14.36MIN: 11.94 / MAX: 15.69MIN: 12.35 / MAX: 20.47MIN: 12.01 / MAX: 24.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PlaidML

FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX20406080100SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 331.8138.4239.0742.3245.3949.1663.5348.0479.2366.50

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX20406080100SE +/- 0.35, N = 3SE +/- 0.37, N = 3SE +/- 0.45, N = 3SE +/- 0.29, N = 3SE +/- 0.38, N = 3SE +/- 0.27, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 385.9575.8974.6563.1859.4054.0444.1954.1434.2141.73

Blender

Blend File: Fishy Cat - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1530456075SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 367.1358.9458.3448.0345.5142.6032.8036.7421.4831.72

Blender

Blend File: BMW27 - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: NVIDIA OptiXRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX816243240SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 2.49, N = 15SE +/- 2.49, N = 15SE +/- 0.01, N = 3SE +/- 0.00, N = 336.2730.9031.3425.4426.2425.2221.6720.1511.4818.64

VkResample

Upscale: 2x - Precision: Double

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX80160240320400SE +/- 0.05, N = 3SE +/- 0.28, N = 3SE +/- 0.78, N = 3SE +/- 0.26, N = 3SE +/- 0.63, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.88, N = 3SE +/- 0.30, N = 3SE +/- 0.10, N = 3350.96309.62302.85261.97235.51216.54152.85264.87148.28149.201. (CXX) g++ options: -O3 -pthread

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX60120180240300SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3125.45147.13148.04149.68152.28160.48213.54177.41261.32228.78

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX120240360480600SE +/- 0.61, N = 3SE +/- 0.69, N = 3SE +/- 0.77, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 1.36, N = 3SE +/- 0.89, N = 3SE +/- 0.00, N = 3SE +/- 1.44, N = 3231.27261.53268.18309.27344.68373.96519.03306.12545.91545.221. (CXX) g++ options: -O3 -rdynamic -lOpenCL

LuxCoreRender OpenCL

Scene: Rainbow Colors and Prism

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX510152025SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.27, N = 12SE +/- 0.48, N = 12SE +/- 0.65, N = 12SE +/- 0.02, N = 37.9811.4110.9410.049.279.1912.1417.1121.9113.56MIN: 7.02 / MAX: 8.25MIN: 9.87 / MAX: 11.85MIN: 9.85 / MAX: 11.46MIN: 5.24 / MAX: 10.68MIN: 8.34 / MAX: 9.64MIN: 7.68 / MAX: 9.63MIN: 6.39 / MAX: 12.87MIN: 8.56 / MAX: 18.35MIN: 12.02 / MAX: 23.73MIN: 12.87 / MAX: 14.06

Betsy GPU Compressor

Codec: ETC2 RGB - Quality: Highest

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: HighestRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 3060 TIRTX 3080TITAN RTX246810SE +/- 0.084, N = 9SE +/- 0.060, N = 13SE +/- 0.064, N = 12SE +/- 0.053, N = 15SE +/- 0.064, N = 12SE +/- 0.057, N = 14SE +/- 0.066, N = 13SE +/- 0.063, N = 13SE +/- 0.058, N = 138.7487.7337.6466.6536.1535.5076.0403.6644.1161. (CXX) g++ options: -O3 -O2 -lpthread -ldl

PlaidML

FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX90180270360450SE +/- 0.18, N = 3SE +/- 0.18, N = 3SE +/- 0.28, N = 3SE +/- 0.01, N = 3SE +/- 0.46, N = 3SE +/- 0.03, N = 3SE +/- 0.39, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.19, N = 3171.78203.78202.05220.43242.54266.39351.18236.40398.64359.13

Betsy GPU Compressor

Codec: ETC1 - Quality: Highest

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: HighestRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX246810SE +/- 0.054, N = 13SE +/- 0.052, N = 13SE +/- 0.052, N = 13SE +/- 0.054, N = 13SE +/- 0.048, N = 14SE +/- 0.060, N = 14SE +/- 0.049, N = 14SE +/- 0.051, N = 14SE +/- 0.052, N = 14SE +/- 0.051, N = 146.1895.4515.3094.8244.3754.0043.1774.3582.7013.0431. (CXX) g++ options: -O3 -O2 -lpthread -ldl

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX50100150200250SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.27, N = 3SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.28, N = 3SE +/- 0.14, N = 388.38100.61103.03121.35128.62143.39185.09133.11223.64194.50

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX60120180240300SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3110.96126.76129.65152.58161.88180.23231.73167.73280.31244.00

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX612182430SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 327.2022.2822.2719.5219.0217.5114.7717.6811.2213.561. (CXX) g++ options: -O3 -pthread

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX160320480640800SE +/- 0.61, N = 3SE +/- 0.68, N = 3SE +/- 0.70, N = 3SE +/- 0.62, N = 3SE +/- 0.34, N = 3SE +/- 0.40, N = 3SE +/- 0.39, N = 3SE +/- 0.51, N = 3SE +/- 1.40, N = 3SE +/- 2.07, N = 3320.95376.59379.70422.86442.78468.60636.84454.66730.76654.76

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3691215SE +/- 0.091, N = 3SE +/- 0.111, N = 3SE +/- 0.096, N = 3SE +/- 0.110, N = 3SE +/- 0.131, N = 3SE +/- 0.101, N = 3SE +/- 0.108, N = 3SE +/- 0.056, N = 3SE +/- 0.093, N = 3SE +/- 0.105, N = 312.70711.54011.1879.9729.4738.8427.6058.7846.3457.360

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX2004006008001000SE +/- 0.58, N = 3SE +/- 0.53, N = 3SE +/- 1.13, N = 3SE +/- 0.23, N = 3SE +/- 1.14, N = 3SE +/- 0.10, N = 3SE +/- 1.36, N = 3SE +/- 0.42, N = 3SE +/- 1.56, N = 3SE +/- 1.34, N = 3392.02440.36447.47499.43545.48588.04754.69689.611019.79782.29

Rodinia

Test: OpenCL Particle Filter

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle FilterRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3691215SE +/- 0.009, N = 3SE +/- 0.027, N = 3SE +/- 0.017, N = 3SE +/- 0.014, N = 3SE +/- 0.006, N = 3SE +/- 0.010, N = 3SE +/- 0.076, N = 3SE +/- 0.067, N = 3SE +/- 0.018, N = 3SE +/- 0.016, N = 38.9607.9817.8586.9006.2885.8094.5077.0404.2904.2961. (CXX) g++ options: -O2 -lOpenCL

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX150K300K450K600K750KSE +/- 57.74, N = 3SE +/- 57.74, N = 3SE +/- 556.78, N = 3SE +/- 66.67, N = 3SE +/- 133.33, N = 3SE +/- 4580.29, N = 15SE +/- 1591.99, N = 3SE +/- 550.76, N = 3SE +/- 750.56, N = 3SE +/- 1120.02, N = 3311800349600356700423733461367527287657967427100723200688167

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX500M1000M1500M2000M2500MSE +/- 635959.47, N = 3SE +/- 1281058.59, N = 3SE +/- 845248.16, N = 3SE +/- 933333.33, N = 3SE +/- 814452.78, N = 3SE +/- 2042873.79, N = 3SE +/- 1258305.74, N = 3SE +/- 750555.35, N = 3SE +/- 2669165.50, N = 3SE +/- 3263093.28, N = 31049366667118343333312132666671426733333155950000017341000002241700000140690000024260333332350366667

Hashcat

Benchmark: SHA1

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX4000M8000M12000M16000M20000MSE +/- 2302414.19, N = 3SE +/- 7522189.40, N = 3SE +/- 2514844.82, N = 3SE +/- 1017076.42, N = 3SE +/- 14178073.84, N = 3SE +/- 3601851.38, N = 3SE +/- 20384389.45, N = 3SE +/- 16045802.50, N = 3SE +/- 13325289.24, N = 3SE +/- 24080351.60, N = 382489333339314900000953546666711183366667122035333331365300000017751300000111037333331915110000018576400000

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5RTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX12000M24000M36000M48000M60000MSE +/- 11770207.21, N = 3SE +/- 8911415.90, N = 3SE +/- 9342079.24, N = 3SE +/- 41910871.04, N = 3SE +/- 30944592.06, N = 3SE +/- 13808974.54, N = 3SE +/- 63030953.60, N = 3SE +/- 23055223.56, N = 3SE +/- 39942305.61, N = 3SE +/- 33241139.17, N = 325930633333292720000002995556666735466033333384932333334313696666755488333333329276000005642913333358104300000

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX7001400210028003500SE +/- 1.88, N = 3SE +/- 2.50, N = 3SE +/- 3.57, N = 3SE +/- 3.23, N = 3SE +/- 0.70, N = 3SE +/- 1.68, N = 3SE +/- 4.12, N = 3SE +/- 4.77, N = 3SE +/- 8.25, N = 3SE +/- 2.13, N = 31282.271581.851566.361701.991726.881816.872414.961875.373062.002551.38

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX8001600240032004000SE +/- 1.92, N = 3SE +/- 2.83, N = 3SE +/- 1.56, N = 3SE +/- 0.32, N = 3SE +/- 3.97, N = 3SE +/- 1.35, N = 3SE +/- 16.01, N = 3SE +/- 1.99, N = 3SE +/- 12.23, N = 3SE +/- 16.11, N = 31720.242011.992004.512300.012333.792489.113316.312428.743623.823392.96

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3K6K9K12K15KSE +/- 4.93, N = 3SE +/- 78.58, N = 15SE +/- 85.50, N = 15SE +/- 72.96, N = 15SE +/- 43.62, N = 3SE +/- 165.30, N = 3SE +/- 138.31, N = 15SE +/- 74.13, N = 15SE +/- 232.90, N = 3SE +/- 135.03, N = 155224.686956.557094.248551.579330.8310244.0813432.898365.8515586.0313791.911. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Waifu2x-NCNN Vulkan

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX1.30032.60063.90095.20126.5015SE +/- 0.064, N = 3SE +/- 0.055, N = 3SE +/- 0.049, N = 3SE +/- 0.067, N = 4SE +/- 0.053, N = 3SE +/- 0.060, N = 3SE +/- 0.057, N = 3SE +/- 0.008, N = 3SE +/- 0.047, N = 5SE +/- 0.056, N = 35.7795.3135.3144.7614.6054.3583.8564.3713.5123.827

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX80160240320400SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3239.5288.3285.7292.3290.5302.0324.0294.1354.7320.81. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX140280420560700SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.23, N = 3SE +/- 0.79, N = 3SE +/- 0.17, N = 3SE +/- 0.38, N = 3SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 1.30, N = 3251.6340.1323.9320.6331.9350.8446.6384.3645.3495.41. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX150300450600750SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.17, N = 3SE +/- 0.44, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3297.5397.1397.1397.1397.1437.8545.6392.8674.2568.21. (CC) gcc options: -O2 -flto -lOpenCL

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX6K12K18K24K30KSE +/- 56.79, N = 15SE +/- 75.69, N = 15SE +/- 90.04, N = 15SE +/- 84.78, N = 15SE +/- 6.84, N = 3SE +/- 174.06, N = 3SE +/- 138.31, N = 3SE +/- 0.44, N = 3SE +/- 0.32, N = 3SE +/- 193.76, N = 155369.816985.027190.538591.778860.5510347.9212677.1816033.6429490.8114109.681. (CXX) g++ options: -O3 -rdynamic -lOpenCL

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPURTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX100M200M300M400M500MSE +/- 1171800.01, N = 3SE +/- 1645708.79, N = 3SE +/- 776602.98, N = 3SE +/- 516930.54, N = 3SE +/- 1494897.42, N = 3SE +/- 774665.97, N = 3SE +/- 590928.34, N = 3SE +/- 805777.35, N = 3SE +/- 2886689.51, N = 3SE +/- 2487384.16, N = 3253858256.7278640038.1283803060.1321637774.3343080891.1368037096.6447272306.0280941400.2421918457.5460475602.61. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

ArrayFire

Test: Conjugate Gradient OpenCL

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX0.59631.19261.78892.38522.9815SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.010, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.010, N = 32.6502.0732.0862.0602.0721.8931.6702.0921.5571.6371. (CXX) g++ options: -rdynamic

Hashcat

Benchmark: 7-Zip

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-ZipRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX200K400K600K800K1000KSE +/- 1101.51, N = 3SE +/- 1192.10, N = 3SE +/- 726.48, N = 3SE +/- 435.89, N = 3SE +/- 1713.99, N = 3SE +/- 1963.27, N = 3SE +/- 3113.41, N = 3SE +/- 3659.23, N = 3SE +/- 503.32, N = 3SE +/- 520.68, N = 3439000490533500233593700637367711967885300581300981300937233

ViennaCL

OpenCL LU Factorization

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX20406080100SE +/- 0.20, N = 3SE +/- 0.40, N = 3SE +/- 0.18, N = 3SE +/- 0.40, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.19, N = 374.5174.0974.1875.8077.1776.6978.3275.7979.3281.321. (CXX) g++ options: -rdynamic -lOpenCL

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX140280420560700SE +/- 0.14, N = 3SE +/- 0.41, N = 3SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.66, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3277.40369.42369.14370.17369.65405.68508.00389.18662.24530.481. (CXX) g++ options: -O3 -rdynamic -lOpenCL

FinanceBench

Benchmark: Black-Scholes OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRTX 3060 TIRTX 3080TITAN RTX3691215SE +/- 0.001, N = 3SE +/- 0.010, N = 3SE +/- 0.017, N = 3SE +/- 0.003, N = 3SE +/- 0.019, N = 3SE +/- 0.022, N = 3SE +/- 0.007, N = 3SE +/- 0.000, N = 3SE +/- 0.020, N = 3SE +/- 0.005, N = 312.56510.45410.2258.2247.6206.7496.0148.3284.8695.6911. (CXX) g++ options: -O3 -lOpenCL


Phoronix Test Suite v10.8.5