xeon ncnn cpu

Intel Xeon E3-1260L v5 testing with a ASRock E3V5 WS (P7.10 BIOS) and llvmpipe on Ubuntu 20.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012194-HA-XEONNCNNC67&sor.

xeon ncnn cpuProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionIntel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS234Intel Xeon E3-1260L v5 @ 3.90GHz (4 Cores / 8 Threads)ASRock E3V5 WS (P7.10 BIOS)Intel Xeon E3-1200 v5/E3-15008GB120GB INTEL SSDSC2BW12llvmpipeRealtek ALC892Intel I219-LMUbuntu 20.105.8.0-20-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.8modesetting 1.20.84.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits)GCC 10.2.0ext41024x768OpenBenchmarking.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: 0xdc - Thermald 2.3Security 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: Mitigation of Clear buffers; SMT vulnerable

xeon ncnn cpuncnn: 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_400mIntel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS23430.427.986.539.796.7710.892.6921.6688.8621.8719.4646.5540.8231.2417.6730.467.976.549.766.7510.872.6321.6889.0021.8619.4846.5546.2631.2617.6830.557.986.519.776.7810.892.6321.6689.0021.8819.4546.6540.7431.1917.6830.457.986.529.816.7710.782.6321.6788.9721.8219.4646.5740.8631.2617.72OpenBenchmarking.org

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetIntel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS423714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 330.4230.4530.4630.55MIN: 30.22 / MAX: 31.87MIN: 30.29 / MAX: 32.19MIN: 30.22 / MAX: 30.69MIN: 29.79 / MAX: 86.951. (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-v22Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS34246810SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 37.977.987.987.98MIN: 7.81 / MAX: 9.89MIN: 7.81 / MAX: 9.71MIN: 7.82 / MAX: 9.79MIN: 7.81 / MAX: 9.831. (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-v334Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS2246810SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 36.516.526.536.54MIN: 6.42 / MAX: 8.01MIN: 6.42 / MAX: 8.08MIN: 6.44 / MAX: 8.23MIN: 6.44 / MAX: 15.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v223Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS43691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 39.769.779.799.81MIN: 9.44 / MAX: 11.52MIN: 9.42 / MAX: 11.1MIN: 9.66 / MAX: 11.51MIN: 9.45 / MAX: 18.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet2Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS43246810SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 36.756.776.776.78MIN: 6.61 / MAX: 6.92MIN: 6.62 / MAX: 6.96MIN: 6.62 / MAX: 6.95MIN: 6.6 / MAX: 15.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b042Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS33691215SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 310.7810.8710.8910.89MIN: 10.64 / MAX: 11.18MIN: 10.7 / MAX: 14.51MIN: 10.74 / MAX: 13.1MIN: 10.71 / MAX: 11.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface234Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS0.60531.21061.81592.42123.0265SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 32.632.632.632.69MIN: 2.6 / MAX: 2.67MIN: 2.6 / MAX: 2.69MIN: 2.6 / MAX: 2.74MIN: 2.59 / MAX: 11.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetIntel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS342510152025SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 321.6621.6621.6721.68MIN: 21.1 / MAX: 22.4MIN: 21.09 / MAX: 22.24MIN: 21.11 / MAX: 22.71MIN: 21.07 / MAX: 30.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS42320406080100SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 388.8688.9789.0089.00MIN: 88.56 / MAX: 95.34MIN: 88.73 / MAX: 97.22MIN: 88.73 / MAX: 97.43MIN: 88.73 / MAX: 90.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet1842Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS3510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 321.8221.8621.8721.88MIN: 21.59 / MAX: 23.24MIN: 21.6 / MAX: 24.17MIN: 21.59 / MAX: 23.69MIN: 21.58 / MAX: 30.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet3Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS42510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 319.4519.4619.4619.48MIN: 19.1 / MAX: 21.7MIN: 19.17 / MAX: 19.62MIN: 19.34 / MAX: 19.61MIN: 19.1 / MAX: 19.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS2431122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 346.5546.5546.5746.65MIN: 45.25 / MAX: 54.38MIN: 45.26 / MAX: 53.54MIN: 45.28 / MAX: 47.66MIN: 45.33 / MAX: 55.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny3Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS421020304050SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 5.48, N = 340.7440.8240.8646.26MIN: 40.42 / MAX: 42.37MIN: 40.55 / MAX: 49.26MIN: 40.52 / MAX: 49.15MIN: 40.4 / MAX: 2527.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd3Intel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS24714212835SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 331.1931.2431.2631.26MIN: 31.07 / MAX: 31.54MIN: 31.1 / MAX: 32.65MIN: 31.05 / MAX: 40.18MIN: 31.16 / MAX: 39.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mIntel Xeon E3-1260L v5 - llvmpipe - ASRock E3V5 WS23448121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 317.6717.6817.6817.72MIN: 17.57 / MAX: 17.94MIN: 17.61 / MAX: 18.39MIN: 17.62 / MAX: 19.25MIN: 17.62 / MAX: 17.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4