kaby nn

Intel Core i7-8550U testing with a Dell 0H0VG3 (1.10.0 BIOS) and Intel UHD 620 KBL GT2 3GB on Ubuntu 20.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2106186-IB-KABYNN76146&grw&rdt.

kaby nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-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 KBL GT2 3GB (1150MHz)Realtek ALC3271Qualcomm Atheros QCA6174 802.11acUbuntu 20.105.8.0-53-generic (x86_64)GNOME Shell 3.38.2X Server 1.20.94.6 Mesa 20.2.6OpenCL 2.11.2.145GCC 10.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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

kaby nnmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3tnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1ncnn: 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_400m1233.8516.95162.84110.0136.9496.10377.1405006.764376.92879.294339.94836.188.967.585.877.5612.852.6627.78133.3031.4730.2058.8249.5937.5515.673.7906.99962.58410.2416.9906.16576.5354992.840375.78579.881338.98335.949.067.585.767.6012.972.5227.72133.1331.8629.9659.2248.8836.8315.393.8927.37561.89410.0036.9876.14176.8354996.255379.20379.395340.25535.968.947.586.167.6613.122.6327.79133.4131.7030.1658.6049.8837.6015.38OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV31230.87571.75142.62713.50284.3785SE +/- 0.017, N = 3SE +/- 0.040, N = 8SE +/- 0.005, N = 33.8513.7903.892MIN: 2.89 / MAX: 26.72MIN: 2.76 / MAX: 30.8MIN: 2.77 / MAX: 26.791. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1123246810SE +/- 0.160, N = 3SE +/- 0.061, N = 8SE +/- 0.059, N = 36.9516.9997.375MIN: 5.42 / MAX: 30.09MIN: 5.15 / MAX: 31.68MIN: 5.48 / MAX: 34.841. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-501231428425670SE +/- 0.48, N = 3SE +/- 0.31, N = 8SE +/- 0.24, N = 362.8462.5861.89MIN: 50.2 / MAX: 103.53MIN: 49.87 / MAX: 107.75MIN: 53.66 / MAX: 102.971. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.01233691215SE +/- 0.61, N = 3SE +/- 0.27, N = 8SE +/- 0.62, N = 310.0110.2410.00MIN: 7.05 / MAX: 33.25MIN: 7.02 / MAX: 51.79MIN: 7.07 / MAX: 34.681. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224123246810SE +/- 0.052, N = 3SE +/- 0.039, N = 8SE +/- 0.088, N = 36.9496.9906.987MIN: 5.39 / MAX: 29.84MIN: 5.39 / MAX: 36.2MIN: 5.54 / MAX: 31.161. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0123246810SE +/- 0.191, N = 3SE +/- 0.102, N = 8SE +/- 0.206, N = 36.1036.1656.141MIN: 4.7 / MAX: 29.98MIN: 4.58 / MAX: 31.52MIN: 4.71 / MAX: 29.41. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v312320406080100SE +/- 0.49, N = 3SE +/- 0.40, N = 8SE +/- 0.42, N = 377.1476.5476.84MIN: 65.68 / MAX: 116.1MIN: 66.12 / MAX: 141.3MIN: 67.69 / MAX: 129.781. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet12311002200330044005500SE +/- 11.08, N = 3SE +/- 1.33, N = 3SE +/- 13.68, N = 35006.764992.844996.26MIN: 4956 / MAX: 5193.44MIN: 4745.09 / MAX: 5079.85MIN: 4752.14 / MAX: 53611. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212380160240320400SE +/- 0.77, N = 3SE +/- 1.75, N = 3SE +/- 2.20, N = 3376.93375.79379.20MIN: 372.37 / MAX: 387.76MIN: 371.2 / MAX: 391.88MIN: 371.69 / MAX: 392.071. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v212320406080100SE +/- 0.13, N = 3SE +/- 0.35, N = 3SE +/- 0.10, N = 379.2979.8879.40MIN: 78.41 / MAX: 80.63MIN: 78.68 / MAX: 85.56MIN: 78.69 / MAX: 81.471. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112370140210280350SE +/- 0.50, N = 3SE +/- 0.15, N = 3SE +/- 0.95, N = 3339.95338.98340.26MIN: 336.87 / MAX: 343.52MIN: 336.42 / MAX: 345.25MIN: 337.19 / MAX: 345.771. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet123816243240SE +/- 0.27, N = 3SE +/- 0.06, N = 3SE +/- 0.20, N = 336.1835.9435.96MIN: 33.73 / MAX: 71.88MIN: 33.01 / MAX: 62MIN: 33.86 / MAX: 51.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v21233691215SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 38.969.068.94MIN: 7.77 / MAX: 22.28MIN: 7.69 / MAX: 36.02MIN: 7.79 / MAX: 22.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 37.587.587.58MIN: 6.54 / MAX: 23.62MIN: 6.54 / MAX: 22.56MIN: 6.52 / MAX: 21.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v2123246810SE +/- 0.30, N = 3SE +/- 0.21, N = 3SE +/- 0.33, N = 35.875.766.16MIN: 4.86 / MAX: 20.58MIN: 4.84 / MAX: 21.24MIN: 4.89 / MAX: 20.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810SE +/- 0.34, N = 3SE +/- 0.39, N = 3SE +/- 0.40, N = 37.567.607.66MIN: 6.06 / MAX: 24.63MIN: 6.06 / MAX: 23.83MIN: 6.1 / MAX: 23.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215SE +/- 0.26, N = 3SE +/- 0.20, N = 3SE +/- 0.36, N = 312.8512.9713.12MIN: 10.85 / MAX: 33.31MIN: 10.89 / MAX: 37.7MIN: 11 / MAX: 31.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.59851.1971.79552.3942.9925SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 32.662.522.63MIN: 2.23 / MAX: 19.74MIN: 1.94 / MAX: 14.4MIN: 2.05 / MAX: 26.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet123714212835SE +/- 0.11, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 327.7827.7227.79MIN: 25.08 / MAX: 63.71MIN: 24.31 / MAX: 47.49MIN: 24.99 / MAX: 62.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg16123306090120150SE +/- 0.33, N = 3SE +/- 0.09, N = 3SE +/- 0.39, N = 3133.30133.13133.41MIN: 125.05 / MAX: 194.75MIN: 126.92 / MAX: 154.77MIN: 125.9 / MAX: 173.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18123714212835SE +/- 0.14, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 331.4731.8631.70MIN: 28.31 / MAX: 62.34MIN: 28.73 / MAX: 69.18MIN: 29.4 / MAX: 46.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet123714212835SE +/- 0.27, N = 3SE +/- 0.20, N = 3SE +/- 0.10, N = 330.2029.9630.16MIN: 24.13 / MAX: 75.3MIN: 26.84 / MAX: 45.79MIN: 27.88 / MAX: 47.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet501231326395265SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 358.8259.2258.60MIN: 53.99 / MAX: 84.29MIN: 54.43 / MAX: 79.03MIN: 52.78 / MAX: 74.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny1231122334455SE +/- 0.46, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 349.5948.8849.88MIN: 46.5 / MAX: 76.54MIN: 46.17 / MAX: 71.09MIN: 46.63 / MAX: 92.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123918273645SE +/- 0.30, N = 3SE +/- 0.21, N = 3SE +/- 0.25, N = 337.5536.8337.60MIN: 33.99 / MAX: 86.86MIN: 33.96 / MAX: 55.96MIN: 34.47 / MAX: 64.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m12348121620SE +/- 0.03, N = 3SE +/- 0.55, N = 3SE +/- 0.37, N = 315.6715.3915.38MIN: 13.79 / MAX: 39.24MIN: 12.92 / MAX: 34.77MIN: 12.83 / MAX: 33.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Phoronix Test Suite v10.8.4