NCNN Vulkan - AMD vs. NVIDIA

NCNN Vulkan benchmarks by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2009260-PTS-NCNNVULK08
Jump To Table - Results

View

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

Limit displaying results to tests within:

NVIDIA GPU Compute 2 Tests
Vulkan Compute 2 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GTX 1060
September 25 2020
  34 Minutes
GTX 1070
September 26 2020
  1 Hour, 20 Minutes
GTX 1080
September 25 2020
  23 Minutes
GTX 1650
September 25 2020
  38 Minutes
GTX 1650 SUPER
September 26 2020
  29 Minutes
GTX 1660
September 26 2020
  41 Minutes
GTX 1660 SUPER
September 26 2020
  23 Minutes
GTX 1660 Ti
September 26 2020
  1 Hour, 15 Minutes
RTX 2060
September 25 2020
  1 Hour, 7 Minutes
RTX 2060 SUPER
September 25 2020
  19 Minutes
RTX 2070
September 26 2020
  19 Minutes
RTX 2070 SUPER
September 25 2020
  1 Hour, 1 Minute
RTX 2080
September 26 2020
  1 Hour
RTX 2080 SUPER
September 26 2020
  58 Minutes
RTX 2080 Ti
September 26 2020
  55 Minutes
RX Vega 56
September 25 2020
  20 Minutes
RX 5600 XT
September 25 2020
  19 Minutes
RX 5700
September 25 2020
  18 Minutes
RX 5700 XT
September 25 2020
  1 Hour, 5 Minutes
Radeon VII
September 25 2020
  25 Minutes
Invert Hiding All Results Option
  42 Minutes

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


NCNN Vulkan - AMD vs. NVIDIAProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGTX 1060GTX 1070GTX 1080GTX 1650GTX 1650 SUPERGTX 1660GTX 1660 SUPERGTX 1660 TiRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRX Vega 56RX 5600 XTRX 5700RX 5700 XTRadeon VIIAMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600 + 2000GBNVIDIA GeForce GTX 1060 6GB (1506/4006MHz)NVIDIA GP106 HD AudioDELL P2415QRealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.4.0-48-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 450.664.6.0OpenCL 2.0 AMD-APP (3182.0) + OpenCL 1.2 CUDA 11.0.2281.2.133GCC 9.3.0 + CUDA 11.0ext43840x2160NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)NVIDIA GP104 HD AudioNVIDIA GeForce GTX 1080 8GB (1607/5005MHz)ASUS NVIDIA GeForce GTX 1650 4GB (1485/4001MHz)NVIDIA Device 10faASUS NVIDIA GeForce GTX 1650 SUPER 4GB (375/810MHz)NVIDIA TU116 HD AudioASUS NVIDIA GeForce GTX 1660 6GB (1530/4001MHz)eVGA NVIDIA GeForce GTX 1660 SUPER 6GB (1530/7000MHz)eVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz)NVIDIA GeForce RTX 2060 6GB (1365/7000MHz)NVIDIA TU106 HD AudioNVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (420/405MHz)NVIDIA GeForce RTX 2070 SUPER 8GB (375/405MHz)NVIDIA TU104 HD AudioZotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA GeForce RTX 2080 SUPER 8GB (405/405MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TU102 HD AudioAMD Radeon RX 56/64 8GB (1590/800MHz)AMD Vega 10 HDMI Audio5.9.0-050900rc6daily20200925-generic (x86_64) 202009244.6 Mesa 20.3.0-devel (git-3173367 2020-09-25 focal-oibaf-ppa) (LLVM 10.0.1)OpenCL 2.0 AMD-APP (3182.0)1.2.145Sapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1780/875MHz)AMD Navi 10 HDMI AudioAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz)AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz)AMD Radeon VII 16GB (1801/1000MHz)AMD Vega 20 HDMI AudioOpenBenchmarking.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,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 -vProcessor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013Security 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 STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

GTX 1060GTX 1070GTX 1080GTX 1650GTX 1650 SUPERGTX 1660GTX 1660 SUPERGTX 1660 TiRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRX Vega 56RX 5600 XTRX 5700RX 5700 XTRadeon VIIResult OverviewPhoronix Test Suite100%206%311%417%522%RealSR-NCNNNCNNNCNNRealSR-NCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNN4x - YesVulkan GPU - vgg16Vulkan GPU - efficientnet-b04x - NoVulkan GPU - alexnetVulkan GPU-v3-v3 - mobilenet-v3Vulkan GPU - resnet50Vulkan GPU - resnet18Vulkan GPU - googlenetVulkan GPU - squeezenetVulkan GPU - mnasnetVulkan GPU-v2-v2 - mobilenet-v2Vulkan GPU - mobilenetVulkan GPU - shufflenet-v2Vulkan GPU - yolov4-tinyVulkan GPU - blazeface

NCNN Vulkan - AMD vs. NVIDIAncnn: 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 - NoGTX 1060GTX 1070GTX 1080GTX 1650GTX 1650 SUPERGTX 1660GTX 1660 SUPERGTX 1660 TiRTX 2060RTX 2060 SUPERRTX 2070RTX 2070 SUPERRTX 2080RTX 2080 SUPERRTX 2080 TiRX Vega 56RX 5600 XTRX 5700RX 5700 XTRadeon VII7.775.991.972.421.602.073.650.705.4520.203.135.408.0010.52143.94920.5436.525.471.852.321.551.963.490.714.5814.982.393.845.919.15102.78715.3745.835.262.232.251.471.933.400.714.1315.042.013.784.918.84116.45217.2146.836.291.942.291.572.173.500.705.3124.153.373.748.4211.95215.51829.3725.805.421.601.881.401.633.210.644.0921.552.612.955.8310.67186.17925.6585.525.571.772.141.512.003.190.674.3316.982.373.055.759.92138.72119.8935.205.091.481.981.331.792.870.633.9415.42.382.755.029.41120.14817.5385.245.131.611.831.461.632.840.663.7815.332.262.745.049.45117.67417.1504.724.901.541.791.421.642.840.693.5611.082.002.434.268.7486.37213.4004.604.621.451.931.321.682.610.623.3610.311.722.223.848.5476.37312.1294.674.831.451.701.321.772.890.623.719.641.732.243.888.4275.43712.0074.334.651.441.751.361.542.690.663.238.471.682.063.758.3063.86310.6154.284.651.491.761.441.512.760.713.338.051.631.983.578.2260.36010.0614.304.451.481.621.391.512.710.633.237.631.511.933.538.1254.8409.4634.014.531.441.731.361.482.730.673.055.601.421.613.147.7744.9868.2604.896.312.954.652.343.0910.540.875.7411.562.204.386.547.6766.10810.2543.586.542.153.111.842.337.250.764.2415.241.735.245.028.5380.26012.0793.586.602.183.131.862.257.850.774.2714.911.715.385.248.4958.9299.3583.366.582.052.961.732.086.630.733.8713.701.574.814.468.3255.6788.9825.039.022.844.132.603.1511.070.927.2210.422.043.786.6210.0041.2887.177OpenBenchmarking.org

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringGTX 1650GTX 1650 SUPERGTX 1660GTX 1660 TiGTX 1060RX 5700 XTRX 5700GTX 1660 SUPERRTX 2060GTX 1070RX Vega 56RX 5600 XTRadeon VIIRTX 2070RTX 2070 SUPERRTX 2060 SUPERRTX 2080RTX 2080 SUPERGTX 1080RTX 2080 Ti50100150200250Min: 5.43 / Avg: 53.96 / Max: 68.86Min: 6.51 / Avg: 71.29 / Max: 96.43Min: 6.69 / Avg: 72.09 / Max: 109.23Min: 7.41 / Avg: 78.56 / Max: 133.19Min: 5.95 / Avg: 86 / Max: 131.08Min: 29 / Avg: 88.95 / Max: 225Min: 31 / Avg: 89.52 / Max: 165Min: 10.75 / Avg: 90.37 / Max: 129.22Min: 9.49 / Avg: 91.04 / Max: 164.41Min: 6.75 / Avg: 92.52 / Max: 162.74Min: 11 / Avg: 96.87 / Max: 167Min: 22 / Avg: 98.3 / Max: 171Min: 21 / Avg: 104.49 / Max: 267Min: 7.53 / Avg: 105.98 / Max: 181.01Min: 14.42 / Avg: 107.67 / Max: 220.78Min: 10.34 / Avg: 108.02 / Max: 179.76Min: 13.31 / Avg: 108.43 / Max: 221.85Min: 8.89 / Avg: 110.83 / Max: 255.3Min: 6.57 / Avg: 115.01 / Max: 188.22Min: 7.79 / Avg: 115.51 / Max: 274.43

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRadeon VIIRTX 2070 SUPERRTX 2080 SUPERRTX 2080 TiRTX 2060RX Vega 56RX 5700RX 5700 XTRTX 2060 SUPERGTX 1660 TiRTX 2070GTX 1650 SUPERGTX 1060GTX 1650RX 5600 XTRTX 2080GTX 1660 SUPERGTX 1070GTX 1660GTX 10801632486480Min: 29 / Avg: 44.95 / Max: 66Min: 26 / Avg: 46.54 / Max: 68Min: 28 / Avg: 48.45 / Max: 72Min: 32 / Avg: 49.95 / Max: 71Min: 28 / Avg: 50.87 / Max: 70Min: 29 / Avg: 51.18 / Max: 65Min: 38 / Avg: 52.05 / Max: 67Min: 35 / Avg: 52.14 / Max: 74Min: 29 / Avg: 52.23 / Max: 71Min: 29 / Avg: 52.99 / Max: 69Min: 29 / Avg: 54.07 / Max: 74Min: 30 / Avg: 55.56 / Max: 66Min: 27 / Avg: 55.8 / Max: 69Min: 31 / Avg: 56.9 / Max: 66Min: 44 / Avg: 57.67 / Max: 66Min: 29 / Avg: 58.81 / Max: 82Min: 33 / Avg: 59.37 / Max: 70Min: 29 / Avg: 60.05 / Max: 78Min: 29 / Avg: 60.56 / Max: 79Min: 29 / Avg: 62.17 / Max: 79

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetRX 5700 XTRX 5600 XTRX 5700RTX 2080 TiRTX 2080RTX 2080 SUPERRTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060RX Vega 56Radeon VIIGTX 1660 SUPERGTX 1660 TiGTX 1660GTX 1650 SUPERGTX 1080GTX 1070GTX 1650GTX 1060246810SE +/- 0.03, N = 14SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.05, N = 15SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 15SE +/- 0.00, N = 3SE +/- 0.07, N = 4SE +/- 0.03, N = 3SE +/- 0.17, N = 15SE +/- 0.06, N = 7SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 15SE +/- 0.09, N = 4SE +/- 0.11, N = 43.363.583.584.014.284.304.334.604.674.724.895.035.205.245.525.805.836.526.837.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetRTX 2080 SUPERRTX 2080 TiRTX 2060 SUPERRTX 2070 SUPERRTX 2080RTX 2070RTX 2060GTX 1660 SUPERGTX 1660 TiGTX 1080GTX 1650 SUPERGTX 1070GTX 1660GTX 1060GTX 1650RX Vega 56RX 5600 XTRX 5700 XTRX 5700Radeon VII3691215SE +/- 0.05, N = 15SE +/- 0.03, N = 14SE +/- 0.10, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.05, N = 15SE +/- 0.12, N = 3SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 15SE +/- 0.01, N = 7SE +/- 0.08, N = 4SE +/- 0.02, N = 4SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 14SE +/- 0.01, N = 3SE +/- 0.06, N = 44.454.534.624.654.654.834.905.095.135.265.425.475.575.996.296.316.546.586.609.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 2070 SUPERRTX 2080 TiRTX 2060 SUPERRTX 2070GTX 1660 SUPERRTX 2080 SUPERRTX 2080RTX 2060GTX 1650 SUPERGTX 1660 TiGTX 1660GTX 1070GTX 1650GTX 1060RX 5700 XTRX 5600 XTRX 5700GTX 1080Radeon VIIRX Vega 560.66381.32761.99142.65523.319SE +/- 0.03, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 15SE +/- 0.06, N = 15SE +/- 0.04, N = 15SE +/- 0.02, N = 3SE +/- 0.04, N = 15SE +/- 0.06, N = 7SE +/- 0.02, N = 15SE +/- 0.00, N = 4SE +/- 0.02, N = 4SE +/- 0.07, N = 14SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.01, N = 4SE +/- 0.36, N = 31.441.441.451.451.481.481.491.541.601.611.771.851.941.972.052.152.182.232.842.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 2080 SUPERRTX 2070RTX 2080 TiRTX 2070 SUPERRTX 2080RTX 2060GTX 1660 TiGTX 1650 SUPERRTX 2060 SUPERGTX 1660 SUPERGTX 1660GTX 1080GTX 1650GTX 1070GTX 1060RX 5700 XTRX 5600 XTRX 5700Radeon VIIRX Vega 561.04632.09263.13894.18525.2315SE +/- 0.03, N = 15SE +/- 0.02, N = 3SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.06, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 7SE +/- 0.11, N = 3SE +/- 0.12, N = 4SE +/- 0.05, N = 15SE +/- 0.09, N = 4SE +/- 0.12, N = 14SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 4SE +/- 0.93, N = 31.621.701.731.751.761.791.831.881.931.982.142.252.292.322.422.963.113.134.134.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2RTX 2060 SUPERRTX 2070GTX 1660 SUPERRTX 2070 SUPERRTX 2080 TiRTX 2080 SUPERGTX 1650 SUPERRTX 2060RTX 2080GTX 1660 TiGTX 1080GTX 1660GTX 1070GTX 1650GTX 1060RX 5700 XTRX 5600 XTRX 5700RX Vega 56Radeon VII0.5851.171.7552.342.925SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 0.02, N = 3SE +/- 0.04, N = 15SE +/- 0.08, N = 15SE +/- 0.05, N = 15SE +/- 0.03, N = 3SE +/- 0.05, N = 7SE +/- 0.02, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 14SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 41.321.321.331.361.361.391.401.421.441.461.471.511.551.571.601.731.841.862.342.601. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetRTX 2080 TiRTX 2080RTX 2080 SUPERRTX 2070 SUPERGTX 1650 SUPERGTX 1660 TiRTX 2060RTX 2060 SUPERRTX 2070GTX 1660 SUPERGTX 1080GTX 1070GTX 1660GTX 1060RX 5700 XTGTX 1650RX 5700RX 5600 XTRX Vega 56Radeon VII0.70881.41762.12642.83523.544SE +/- 0.04, N = 14SE +/- 0.03, N = 15SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 0.17, N = 2SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 15SE +/- 0.07, N = 7SE +/- 0.03, N = 4SE +/- 0.02, N = 14SE +/- 0.10, N = 4SE +/- 0.00, N = 3SE +/- 0.08, N = 3SE +/- 0.31, N = 3SE +/- 0.01, N = 41.481.511.511.541.631.631.641.681.771.791.931.962.002.072.082.172.252.333.093.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0RTX 2060 SUPERRTX 2070 SUPERRTX 2080 SUPERRTX 2080 TiRTX 2080GTX 1660 TiRTX 2060GTX 1660 SUPERRTX 2070GTX 1660GTX 1650 SUPERGTX 1080GTX 1070GTX 1650GTX 1060RX 5700 XTRX 5600 XTRX 5700RX Vega 56Radeon VII3691215SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 0.08, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 7SE +/- 0.25, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 15SE +/- 0.08, N = 4SE +/- 0.10, N = 4SE +/- 0.05, N = 14SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.06, N = 42.612.692.712.732.762.842.842.872.893.193.213.403.493.503.656.637.257.8510.5411.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceRTX 2060 SUPERRTX 2070GTX 1660 SUPERRTX 2080 SUPERGTX 1650 SUPERGTX 1660 TiRTX 2070 SUPERGTX 1660RTX 2080 TiRTX 2060GTX 1060GTX 1650GTX 1070GTX 1080RTX 2080RX 5700 XTRX 5600 XTRX 5700RX Vega 56Radeon VII0.2070.4140.6210.8281.035SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 15SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.00, N = 7SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.03, N = 15SE +/- 0.05, N = 3SE +/- 0.04, N = 15SE +/- 0.00, N = 14SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 40.620.620.630.630.640.660.660.670.670.690.700.700.710.710.710.730.760.770.870.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetRTX 2080 TiRTX 2070 SUPERRTX 2080 SUPERRTX 2080RTX 2060 SUPERRTX 2060RTX 2070GTX 1660 TiRX 5700 XTGTX 1660 SUPERGTX 1650 SUPERGTX 1080RX 5600 XTRX 5700GTX 1660GTX 1070GTX 1650GTX 1060RX Vega 56Radeon VII246810SE +/- 0.04, N = 15SE +/- 0.06, N = 15SE +/- 0.05, N = 15SE +/- 0.07, N = 15SE +/- 0.09, N = 3SE +/- 0.04, N = 15SE +/- 0.22, N = 3SE +/- 0.04, N = 15SE +/- 0.00, N = 14SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 7SE +/- 0.04, N = 15SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.15, N = 43.053.233.233.333.363.563.713.783.873.944.094.134.244.274.334.585.315.455.747.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2070RTX 2060 SUPERRadeon VIIRTX 2060RX Vega 56RX 5700 XTRX 5700GTX 1070GTX 1080RX 5600 XTGTX 1660 TiGTX 1660 SUPERGTX 1660GTX 1060GTX 1650 SUPERGTX 1650612182430SE +/- 0.03, N = 15SE +/- 0.06, N = 15SE +/- 0.06, N = 15SE +/- 0.03, N = 15SE +/- 0.22, N = 3SE +/- 0.56, N = 3SE +/- 0.11, N = 4SE +/- 0.06, N = 15SE +/- 0.13, N = 3SE +/- 0.08, N = 14SE +/- 0.04, N = 3SE +/- 0.08, N = 15SE +/- 0.14, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 15SE +/- 0.17, N = 3SE +/- 0.12, N = 7SE +/- 0.19, N = 4SE +/- 0.27, N = 3SE +/- 0.03, N = 45.607.638.058.479.6410.3110.4211.0811.5613.7014.9114.9815.0415.2415.3315.4016.9820.2021.5524.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18RTX 2080 TiRTX 2080 SUPERRX 5700 XTRTX 2080RTX 2070 SUPERRX 5700RTX 2060 SUPERRTX 2070RX 5600 XTRTX 2060GTX 1080Radeon VIIRX Vega 56GTX 1660 TiGTX 1660GTX 1660 SUPERGTX 1070GTX 1650 SUPERGTX 1060GTX 16500.75831.51662.27493.03323.7915SE +/- 0.06, N = 14SE +/- 0.02, N = 15SE +/- 0.00, N = 14SE +/- 0.04, N = 14SE +/- 0.04, N = 15SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 15SE +/- 0.01, N = 3SE +/- 0.00, N = 4SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.01, N = 7SE +/- 0.12, N = 3SE +/- 0.03, N = 15SE +/- 0.02, N = 3SE +/- 0.06, N = 4SE +/- 0.06, N = 41.421.511.571.631.681.711.721.731.732.002.012.042.202.262.372.382.392.613.133.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetRTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060GTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1660GTX 1650GTX 1080Radeon VIIGTX 1070RX Vega 56RX 5700 XTRX 5600 XTRX 5700GTX 10601.2152.433.6454.866.075SE +/- 0.02, N = 15SE +/- 0.03, N = 15SE +/- 0.01, N = 14SE +/- 0.02, N = 15SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 7SE +/- 0.03, N = 4SE +/- 0.04, N = 3SE +/- 0.00, N = 4SE +/- 0.04, N = 14SE +/- 0.00, N = 3SE +/- 0.01, N = 14SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 41.611.931.982.062.222.242.432.742.752.953.053.743.783.783.844.384.815.245.385.401. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRTX 2060 SUPERRTX 2070RTX 2060RX 5700 XTGTX 1080GTX 1660 SUPERRX 5600 XTGTX 1660 TiRX 5700GTX 1660GTX 1650 SUPERGTX 1070RX Vega 56Radeon VIIGTX 1060GTX 1650246810SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 15SE +/- 0.00, N = 14SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 14SE +/- 0.16, N = 3SE +/- 0.02, N = 7SE +/- 0.03, N = 3SE +/- 0.04, N = 15SE +/- 0.07, N = 3SE +/- 0.08, N = 4SE +/- 0.09, N = 4SE +/- 0.18, N = 43.143.533.573.753.843.884.264.464.915.025.025.045.245.755.835.916.546.628.008.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyRX Vega 56RTX 2080 TiRTX 2080 SUPERRTX 2080RTX 2070 SUPERRX 5700 XTRTX 2070RX 5700RX 5600 XTRTX 2060 SUPERRTX 2060GTX 1080GTX 1070GTX 1660 SUPERGTX 1660 TiGTX 1660Radeon VIIGTX 1060GTX 1650 SUPERGTX 16503691215SE +/- 0.02, N = 3SE +/- 0.07, N = 15SE +/- 0.08, N = 14SE +/- 0.06, N = 15SE +/- 0.06, N = 15SE +/- 0.01, N = 14SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 15SE +/- 0.11, N = 3SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.04, N = 15SE +/- 0.12, N = 7SE +/- 0.01, N = 4SE +/- 0.08, N = 4SE +/- 0.08, N = 3SE +/- 0.11, N = 47.677.778.128.228.308.328.428.498.538.548.748.849.159.419.459.9210.0010.5210.6711.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

RealSR-NCNN

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRadeon VIIRTX 2080 TiRTX 2080 SUPERRX 5700 XTRX 5700RTX 2080RTX 2070 SUPERRX Vega 56RTX 2070RTX 2060 SUPERRX 5600 XTRTX 2060GTX 1070GTX 1080GTX 1660 TiGTX 1660 SUPERGTX 1660GTX 1060GTX 1650 SUPERGTX 165050100150200250SE +/- 0.12, N = 3SE +/- 0.23, N = 3SE +/- 0.19, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 0.38, N = 3SE +/- 0.31, N = 3SE +/- 0.08, N = 3SE +/- 0.56, N = 3SE +/- 0.43, N = 3SE +/- 0.13, N = 3SE +/- 0.26, N = 3SE +/- 0.36, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.27, N = 3SE +/- 0.33, N = 3SE +/- 0.09, N = 3SE +/- 0.29, N = 341.2944.9954.8455.6858.9360.3663.8666.1175.4476.3780.2686.37102.79116.45117.67120.15138.72143.95186.18215.52

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRadeon VIIRTX 2080 TiRX 5700 XTRX 5700RTX 2080 SUPERRTX 2080RX Vega 56RTX 2070 SUPERRTX 2070RX 5600 XTRTX 2060 SUPERRTX 2060GTX 1070GTX 1660 TiGTX 1080GTX 1660 SUPERGTX 1660GTX 1060GTX 1650 SUPERGTX 1650714212835SE +/- 0.018, N = 6SE +/- 0.020, N = 6SE +/- 0.020, N = 5SE +/- 0.035, N = 5SE +/- 0.041, N = 5SE +/- 0.038, N = 5SE +/- 0.021, N = 5SE +/- 0.034, N = 5SE +/- 0.039, N = 4SE +/- 0.024, N = 4SE +/- 0.039, N = 4SE +/- 0.021, N = 4SE +/- 0.035, N = 4SE +/- 0.030, N = 3SE +/- 0.068, N = 3SE +/- 0.010, N = 3SE +/- 0.045, N = 3SE +/- 0.020, N = 3SE +/- 0.050, N = 3SE +/- 0.039, N = 37.1778.2608.9829.3589.46310.06110.25410.61512.00712.07912.12913.40015.37417.15017.21417.53819.89320.54325.65829.372