NCNN Haswell

Intel Core i7-4558U testing with a ASUS UX301LAA v1.0 (UX301LAA.209 BIOS) and ASUS Intel Iris 5100 2GB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2009241-FI-NCNNHASWE87.

NCNN HaswellProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionHSW 1HSW 2HSW 3Intel Core i7-4558U @ 3.30GHz (2 Cores / 4 Threads)ASUS UX301LAA v1.0 (UX301LAA.209 BIOS)Intel Haswell-ULT DRAM8GB2 x 128GB SanDisk SD6SP1M1ASUS Intel Iris 5100 2GB (1200MHz)Intel Haswell-ULT HD AudioLQ133T1JW14Intel 7260Ubuntu 20.045.9.0-050900rc6daily20200922-generic (x86_64) 20200921GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.5 Mesa 20.0.8GCC 9.3.0ext42560x1440OpenBenchmarking.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 -v Processor Details- Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0x26Security Details- itlb_multihit: KVM: Mitigation of VMX unsupported + l1tf: Mitigation of PTE Inversion + 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 Haswellncnn: CPU - squeezenetncnn: 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-tinyHSW 1HSW 2HSW 387.1360.0115.1813.339.1214.0022.063.71119.03634.8685.0739.72253.7882.2986.9360.0215.2313.399.1213.9822.043.72119.19637.0484.9139.83254.2283.5787.3259.9715.1513.279.1713.9322.063.72119.05637.7384.8839.64254.0381.90OpenBenchmarking.org

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetHSW 1HSW 2HSW 320406080100SE +/- 0.32, N = 3SE +/- 0.24, N = 3SE +/- 0.32, N = 387.1386.9387.32MIN: 85.97 / MAX: 106.19MIN: 85.88 / MAX: 107.27MIN: 86.1 / MAX: 107.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetHSW 1HSW 2HSW 31326395265SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.33, N = 360.0160.0259.97MIN: 59.06 / MAX: 82.07MIN: 59.09 / MAX: 82.03MIN: 58.97 / MAX: 80.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2HSW 1HSW 2HSW 348121620SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 315.1815.2315.15MIN: 14.77 / MAX: 38.85MIN: 14.88 / MAX: 20.65MIN: 14.7 / MAX: 37.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3HSW 1HSW 2HSW 33691215SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 313.3313.3913.27MIN: 12.91 / MAX: 17.38MIN: 12.93 / MAX: 33.66MIN: 13.04 / MAX: 15.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2HSW 1HSW 2HSW 33691215SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 39.129.129.17MIN: 8.95 / MAX: 12.86MIN: 8.96 / MAX: 11.36MIN: 9.03 / MAX: 11.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetHSW 1HSW 2HSW 348121620SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 314.0013.9813.93MIN: 13.66 / MAX: 27.2MIN: 13.58 / MAX: 17.05MIN: 13.68 / MAX: 18.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0HSW 1HSW 2HSW 3510152025SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.05, N = 322.0622.0422.06MIN: 21.71 / MAX: 25.52MIN: 21.6 / MAX: 27.12MIN: 21.69 / MAX: 41.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceHSW 1HSW 2HSW 30.8371.6742.5113.3484.185SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 33.713.723.72MIN: 3.61 / MAX: 6.26MIN: 3.61 / MAX: 6.1MIN: 3.62 / MAX: 9.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetHSW 1HSW 2HSW 3306090120150SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3119.03119.19119.05MIN: 117.98 / MAX: 140.93MIN: 118.04 / MAX: 144.95MIN: 117.86 / MAX: 181.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16HSW 1HSW 2HSW 3140280420560700SE +/- 3.58, N = 3SE +/- 1.46, N = 3SE +/- 2.20, N = 3634.86637.04637.73MIN: 625.9 / MAX: 664.01MIN: 632.43 / MAX: 665.9MIN: 630.45 / MAX: 668.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18HSW 1HSW 2HSW 320406080100SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 385.0784.9184.88MIN: 84.18 / MAX: 133.7MIN: 84.04 / MAX: 104.37MIN: 84.12 / MAX: 103.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetHSW 1HSW 2HSW 3918273645SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 339.7239.8339.64MIN: 39.22 / MAX: 59.68MIN: 39.16 / MAX: 55.99MIN: 39.22 / MAX: 60.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50HSW 1HSW 2HSW 360120180240300SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.22, N = 3253.78254.22254.03MIN: 252.24 / MAX: 273.05MIN: 252.27 / MAX: 359.83MIN: 252.18 / MAX: 274.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyHSW 1HSW 2HSW 320406080100SE +/- 0.45, N = 3SE +/- 0.41, N = 3SE +/- 0.23, N = 382.2983.5781.90MIN: 80.49 / MAX: 104.51MIN: 81.93 / MAX: 102.86MIN: 80.6 / MAX: 97.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4