nn tigerlake

Intel Core i7-1165G7 testing with a Dell 0GG9PT (1.2.5 BIOS) and Intel Xe TGL GT2 3GB on Ubuntu 21.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2106185-IB-NNTIGERLA92&sro.

nn tigerlakeProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads)Dell 0GG9PT (1.2.5 BIOS)Intel Tiger Lake-LP16GBKioxia KBG40ZNS256G NVMe 256GBIntel Xe TGL GT2 3GB (1300MHz)Realtek ALC289Intel Wi-Fi 6 AX201Ubuntu 21.045.11.0-18-generic (x86_64)GNOME Shell 3.38.4X Server + Wayland4.6 Mesa 21.0.11.2.145GCC 10.3.0ext41920x1200OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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-build-config=bootstrap-lto-lean --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: 0x6e - Thermald 2.4.3 Security 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

nn tigerlakemnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.11232.5224.88843.7067.3644.6425.06853.73624.054.834.865.275.659.512.1421.0864.9119.7017.1738.2335.3131.1812.044311.562300.65256.577271.4532.5174.93041.9237.4084.6095.04453.72723.314.784.845.636.119.162.0820.0663.3719.2316.6737.1934.3630.3511.784250.097302.07756.502271.7582.5164.90541.6167.3844.6085.04354.09423.494.795.045.676.149.222.1220.2163.4019.2916.7437.3734.4330.5211.833870.770298.90056.130272.100OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV31230.56751.1351.70252.272.8375SE +/- 0.049, N = 12SE +/- 0.032, N = 12SE +/- 0.056, N = 112.5222.5172.516MIN: 1.89 / MAX: 17.89MIN: 2.08 / MAX: 18.91MIN: 1.89 / MAX: 32.261. (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: squeezenetv1.11231.10932.21863.32794.43725.5465SE +/- 0.092, N = 12SE +/- 0.090, N = 12SE +/- 0.107, N = 114.8884.9304.905MIN: 3.77 / MAX: 20.84MIN: 3.91 / MAX: 24.08MIN: 3.8 / MAX: 21.151. (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-v2-501231020304050SE +/- 1.72, N = 12SE +/- 0.20, N = 12SE +/- 0.24, N = 1143.7141.9241.62MIN: 35.18 / MAX: 213.56MIN: 39.81 / MAX: 66.78MIN: 32.18 / MAX: 85.231. (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: SqueezeNetV1.0123246810SE +/- 0.146, N = 12SE +/- 0.144, N = 12SE +/- 0.162, N = 117.3647.4087.384MIN: 5.37 / MAX: 23.38MIN: 5.34 / MAX: 24.23MIN: 5.46 / MAX: 27.351. (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_2241231.04452.0893.13354.1785.2225SE +/- 0.091, N = 12SE +/- 0.085, N = 12SE +/- 0.095, N = 114.6424.6094.608MIN: 3.54 / MAX: 20.57MIN: 3.5 / MAX: 20.45MIN: 3.59 / MAX: 19.151. (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-v1-1.01231.14032.28063.42094.56125.7015SE +/- 0.097, N = 12SE +/- 0.093, N = 12SE +/- 0.107, N = 115.0685.0445.043MIN: 3.74 / MAX: 20.37MIN: 3.84 / MAX: 21.17MIN: 3.73 / MAX: 21.641. (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-v31231224364860SE +/- 1.39, N = 12SE +/- 1.25, N = 12SE +/- 1.48, N = 1153.7453.7354.09MIN: 35.64 / MAX: 80.38MIN: 36.93 / MAX: 98.94MIN: 36.84 / MAX: 88.861. (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

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet123612182430SE +/- 0.25, N = 3SE +/- 0.30, N = 12SE +/- 0.34, N = 1424.0523.3123.49MIN: 22.92 / MAX: 35.65MIN: 19.56 / MAX: 35.52MIN: 18.84 / MAX: 48.931. (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-v21231.08682.17363.26044.34725.434SE +/- 0.10, N = 3SE +/- 0.01, N = 12SE +/- 0.02, N = 144.834.784.79MIN: 4.61 / MAX: 14.39MIN: 4.6 / MAX: 17.7MIN: 4.6 / MAX: 17.141. (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-v31231.1342.2683.4024.5365.67SE +/- 0.39, N = 3SE +/- 0.11, N = 12SE +/- 0.11, N = 144.864.845.04MIN: 3.94 / MAX: 18.07MIN: 3.94 / MAX: 17.03MIN: 3.93 / MAX: 21.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21231.27582.55163.82745.10326.379SE +/- 0.45, N = 3SE +/- 0.12, N = 12SE +/- 0.11, N = 145.275.635.67MIN: 4.23 / MAX: 15.19MIN: 4.21 / MAX: 16MIN: 4.17 / MAX: 17.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810SE +/- 0.64, N = 3SE +/- 0.16, N = 12SE +/- 0.14, N = 145.656.116.14MIN: 4.22 / MAX: 17.83MIN: 4.22 / MAX: 18.3MIN: 4.23 / MAX: 18.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215SE +/- 0.09, N = 3SE +/- 0.23, N = 12SE +/- 0.20, N = 149.519.169.22MIN: 8.98 / MAX: 21.98MIN: 6.55 / MAX: 21.3MIN: 6.55 / MAX: 23.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.48150.9631.44451.9262.4075SE +/- 0.01, N = 3SE +/- 0.04, N = 12SE +/- 0.04, N = 142.142.082.12MIN: 2 / MAX: 9.34MIN: 1.6 / MAX: 11.35MIN: 1.59 / MAX: 13.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet123510152025SE +/- 0.15, N = 3SE +/- 0.55, N = 12SE +/- 0.48, N = 1421.0820.0620.21MIN: 18.84 / MAX: 98.33MIN: 13.91 / MAX: 34.72MIN: 13.9 / MAX: 41.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg161231428425670SE +/- 0.25, N = 3SE +/- 1.15, N = 12SE +/- 1.00, N = 1464.9163.3763.40MIN: 61.82 / MAX: 86.57MIN: 49.84 / MAX: 80.12MIN: 49.31 / MAX: 88.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18123510152025SE +/- 0.03, N = 3SE +/- 0.49, N = 12SE +/- 0.42, N = 1419.7019.2319.29MIN: 17.55 / MAX: 32.7MIN: 13.64 / MAX: 34.33MIN: 13.6 / MAX: 33.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet12348121620SE +/- 0.10, N = 3SE +/- 0.34, N = 12SE +/- 0.30, N = 1417.1716.6716.74MIN: 15.16 / MAX: 29.41MIN: 12.68 / MAX: 30.48MIN: 12.65 / MAX: 29.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123918273645SE +/- 0.10, N = 3SE +/- 0.78, N = 12SE +/- 0.68, N = 1438.2337.1937.37MIN: 35.21 / MAX: 57.11MIN: 27.55 / MAX: 59.64MIN: 26.32 / MAX: 55.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny123816243240SE +/- 0.28, N = 3SE +/- 0.43, N = 12SE +/- 0.46, N = 1435.3134.3634.43MIN: 33.42 / MAX: 52.32MIN: 28.26 / MAX: 48.04MIN: 27.61 / MAX: 48.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123714212835SE +/- 0.13, N = 3SE +/- 0.48, N = 12SE +/- 0.40, N = 1431.1830.3530.52MIN: 29.85 / MAX: 43.52MIN: 23.91 / MAX: 42.52MIN: 24.67 / MAX: 43.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m1233691215SE +/- 0.05, N = 3SE +/- 0.22, N = 12SE +/- 0.19, N = 1412.0411.7811.83MIN: 11.53 / MAX: 23.65MIN: 9.3 / MAX: 23.65MIN: 9.31 / MAX: 23.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1239001800270036004500SE +/- 21.76, N = 3SE +/- 60.03, N = 9SE +/- 48.05, N = 44311.564250.103870.77MIN: 4221.28 / MAX: 4431.6MIN: 3687.92 / MAX: 4426.47MIN: 3636.2 / MAX: 3991.031. (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 v212370140210280350SE +/- 0.37, N = 3SE +/- 2.68, N = 3SE +/- 0.54, N = 3300.65302.08298.90MIN: 295.95 / MAX: 307.25MIN: 295.89 / MAX: 470.74MIN: 295.46 / MAX: 308.711. (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 v21231326395265SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 356.5856.5056.13MIN: 55.4 / MAX: 59.25MIN: 55.31 / MAX: 64.58MIN: 55.05 / MAX: 60.061. (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 v1.112360120180240300SE +/- 0.21, N = 3SE +/- 0.11, N = 3SE +/- 0.24, N = 3271.45271.76272.10MIN: 266.58 / MAX: 278.81MIN: 267.75 / MAX: 279.55MIN: 267.33 / MAX: 280.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Phoronix Test Suite v10.8.4