ncnn old

Intel Core i7-8550U testing with a Dell 0H0VG3 (1.10.0 BIOS) and Intel UHD 620 3GB on Ubuntu 20.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012187-PTS-NCNNOLD794&grw.

ncnn oldProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution123Intel Core i7-8550U @ 4.00GHz (4 Cores / 8 Threads)Dell 0H0VG3 (1.10.0 BIOS)Intel Xeon E3-1200 v6/7th8GBPM961 NVMe SAMSUNG 256GBIntel UHD 620 3GB (1150MHz)Realtek ALC3271Qualcomm Atheros QCA6174 802.11acUbuntu 20.105.8.0-33-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.94.6 Mesa 20.2.11.2.145GCC 10.2.0ext41920x1080OpenBenchmarking.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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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: intel_pstate powersave - CPU Microcode: 0xe0 - Thermald 2.3 Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

ncnn oldncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: 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-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400m12340.5110.018.3312.928.9814.513.6129.06132.5231.1429.5563.2352.8937.4621.6539.719.978.3112.348.7014.643.6429.56133.5531.1929.7763.3752.6837.4922.2640.299.968.3912.188.6814.273.4528.80134.2031.2429.89183.2753.0437.9321.0540.3910.018.2712.208.6814.113.3828.90133.6431.1229.9163.4352.8537.1321.1740.1510.018.3912.278.6814.343.4328.53133.0831.0829.6063.2952.9637.9021.1639.779.998.4812.198.6914.223.4428.91133.7831.1929.5263.3154.0937.1421.48OpenBenchmarking.org

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet123918273645SE +/- 0.40, N = 12SE +/- 0.22, N = 3SE +/- 0.07, N = 340.5140.2940.15MIN: 36.45 / MAX: 286.91MIN: 37.77 / MAX: 65.91MIN: 37.03 / MAX: 66.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v21233691215SE +/- 0.02, N = 12SE +/- 0.08, N = 3SE +/- 0.07, N = 310.019.9610.01MIN: 8.54 / MAX: 36.43MIN: 8.68 / MAX: 23.81MIN: 8.61 / MAX: 24.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.02, N = 12SE +/- 0.16, N = 3SE +/- 0.05, N = 38.338.398.39MIN: 6.99 / MAX: 23.83MIN: 7.16 / MAX: 23.83MIN: 7.16 / MAX: 23.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v21233691215SE +/- 0.17, N = 12SE +/- 0.90, N = 3SE +/- 0.84, N = 312.9212.1812.27MIN: 9.71 / MAX: 28.84MIN: 9.45 / MAX: 28.52MIN: 9.43 / MAX: 28.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet1233691215SE +/- 0.10, N = 12SE +/- 0.31, N = 3SE +/- 0.39, N = 38.988.688.68MIN: 6.97 / MAX: 25.5MIN: 7.01 / MAX: 24.67MIN: 6.93 / MAX: 24.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b012348121620SE +/- 0.11, N = 12SE +/- 0.40, N = 3SE +/- 0.38, N = 314.5114.2714.34MIN: 11.77 / MAX: 34.11MIN: 12.12 / MAX: 30.57MIN: 11.78 / MAX: 34.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface1230.81231.62462.43693.24924.0615SE +/- 0.02, N = 12SE +/- 0.18, N = 3SE +/- 0.22, N = 33.613.453.43MIN: 2.84 / MAX: 19.41MIN: 2.7 / MAX: 21.74MIN: 2.61 / MAX: 11.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet123714212835SE +/- 0.09, N = 12SE +/- 0.60, N = 3SE +/- 0.53, N = 329.0628.8028.53MIN: 25.5 / MAX: 83.56MIN: 25.37 / MAX: 66.87MIN: 24.72 / MAX: 56.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16123306090120150SE +/- 0.20, N = 12SE +/- 0.41, N = 3SE +/- 0.25, N = 3132.52134.20133.08MIN: 124.67 / MAX: 245.92MIN: 127.02 / MAX: 185.55MIN: 126.15 / MAX: 159.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18123714212835SE +/- 0.05, N = 12SE +/- 0.13, N = 3SE +/- 0.08, N = 331.1431.2431.08MIN: 27.66 / MAX: 48.76MIN: 28.01 / MAX: 45.64MIN: 27.26 / MAX: 45.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet123714212835SE +/- 0.06, N = 12SE +/- 0.14, N = 3SE +/- 0.10, N = 329.5529.8929.60MIN: 24.09 / MAX: 68.69MIN: 26.7 / MAX: 45.75MIN: 27.07 / MAX: 44.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet501234080120160200SE +/- 0.12, N = 12SE +/- 120.42, N = 3SE +/- 0.22, N = 363.23183.2763.29MIN: 57.43 / MAX: 92.33MIN: 57.38 / MAX: 5248.49MIN: 58.47 / MAX: 78.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny1231224364860SE +/- 0.09, N = 12SE +/- 0.25, N = 3SE +/- 0.35, N = 352.8953.0452.96MIN: 50.06 / MAX: 82.31MIN: 50.29 / MAX: 69.4MIN: 50.26 / MAX: 74.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd123918273645SE +/- 0.21, N = 12SE +/- 0.91, N = 3SE +/- 0.28, N = 337.4637.9337.90MIN: 33.99 / MAX: 73.27MIN: 35.27 / MAX: 64.4MIN: 35.51 / MAX: 58.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m123510152025SE +/- 0.12, N = 12SE +/- 0.72, N = 3SE +/- 0.62, N = 321.6521.0521.16MIN: 18.98 / MAX: 40.75MIN: 19 / MAX: 50.31MIN: 19.06 / MAX: 36.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenet123918273645SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.19, N = 339.7140.3939.77MIN: 36.85 / MAX: 67.05MIN: 37.86 / MAX: 64.28MIN: 37.9 / MAX: 58.471. (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-v21233691215SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 39.9710.019.99MIN: 8.64 / MAX: 23.26MIN: 8.67 / MAX: 26.57MIN: 8.73 / MAX: 24.091. (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-v3123246810SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 38.318.278.48MIN: 7.19 / MAX: 22.47MIN: 7.23 / MAX: 21.6MIN: 7.18 / MAX: 24.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v21233691215SE +/- 0.73, N = 3SE +/- 0.85, N = 3SE +/- 0.86, N = 312.3412.2012.19MIN: 9.5 / MAX: 28.6MIN: 9.45 / MAX: 30.97MIN: 9.37 / MAX: 28.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnet123246810SE +/- 0.35, N = 3SE +/- 0.41, N = 3SE +/- 0.41, N = 38.708.688.69MIN: 6.97 / MAX: 25.16MIN: 6.96 / MAX: 23.35MIN: 6.95 / MAX: 24.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b012348121620SE +/- 0.08, N = 3SE +/- 0.40, N = 3SE +/- 0.35, N = 314.6414.1114.22MIN: 12.3 / MAX: 29.12MIN: 11.64 / MAX: 29.38MIN: 11.95 / MAX: 29.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazeface1230.8191.6382.4573.2764.095SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.12, N = 33.643.383.44MIN: 3.11 / MAX: 17.7MIN: 2.62 / MAX: 19.3MIN: 2.64 / MAX: 19.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenet123714212835SE +/- 0.20, N = 3SE +/- 0.52, N = 3SE +/- 1.00, N = 329.5628.9028.91MIN: 26.21 / MAX: 55.13MIN: 25.36 / MAX: 106.56MIN: 25.51 / MAX: 88.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16123306090120150SE +/- 0.34, N = 3SE +/- 0.33, N = 3SE +/- 0.16, N = 3133.55133.64133.78MIN: 126.95 / MAX: 157.33MIN: 125.93 / MAX: 164.15MIN: 126.48 / MAX: 160.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18123714212835SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 331.1931.1231.19MIN: 27.87 / MAX: 83.85MIN: 28.37 / MAX: 45.27MIN: 27.83 / MAX: 53.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnet123714212835SE +/- 0.08, N = 3SE +/- 0.22, N = 3SE +/- 0.13, N = 329.7729.9129.52MIN: 26.79 / MAX: 45.61MIN: 26.22 / MAX: 59.14MIN: 26.45 / MAX: 45.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet501231428425670SE +/- 0.32, N = 3SE +/- 0.29, N = 3SE +/- 0.26, N = 363.3763.4363.31MIN: 58.47 / MAX: 83.88MIN: 58.96 / MAX: 79.57MIN: 58.97 / MAX: 95.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tiny1231224364860SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.91, N = 352.6852.8554.09MIN: 50.36 / MAX: 66.57MIN: 50.22 / MAX: 67.09MIN: 49.96 / MAX: 83.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssd123918273645SE +/- 0.41, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 337.4937.1337.14MIN: 35.34 / MAX: 56.78MIN: 35.28 / MAX: 51.57MIN: 35.2 / MAX: 61.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400m123510152025SE +/- 0.40, N = 3SE +/- 0.71, N = 3SE +/- 0.68, N = 322.2621.1721.48MIN: 20.22 / MAX: 48.74MIN: 18.96 / MAX: 36.8MIN: 19.09 / MAX: 40.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4