icelake nn

Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208136-NE-ICELAKENN94&grr&sor.

icelake nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Ice Lake-LP DRAM16GBToshiba KBG40ZPZ512G NVMe 512GBIntel Iris Plus ICL GT2 16GB (1100MHz)Realtek ALC289Intel Ice Lake-LP PCH CNVi WiFiUbuntu 22.045.18.8-051808-generic (x86_64)GNOME Shell 42.2X Server + Wayland4.6 Mesa 22.0.11.3.204GCC 11.2.0ext41920x1200OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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 (EPP: balance_performance) - CPU Microcode: 0xb0 - Thermald 2.4.9 Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

icelake nnncnn: CPU - FastestDetncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3ABC5.28483.6713.4322.9830.9930.309.5212.3558.6716.551.418.875.334.744.345.5023.4254.2435.8805.2047.33426.2004.2971.8035.35482.2913.5223.2332.0130.699.5312.4259.3516.361.429.585.675.024.335.4724.0160.3256.5335.7658.40130.3075.2161.7634.94380.2711.7120.0925.9323.977.8210.1848.7913.291.157.654.494.154.455.6619.4845.7624.8494.3866.24321.2463.5461.899OpenBenchmarking.org

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetCAB1.20382.40763.61144.81526.019SE +/- 0.04, N = 3SE +/- 0.06, N = 124.945.285.35MIN: 4.37 / MAX: 16.79MIN: 4.93 / MAX: 19.96MIN: 4.93 / MAX: 20.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerCBA100200300400500SE +/- 0.62, N = 12SE +/- 6.80, N = 3380.27482.29483.67MIN: 324.06 / MAX: 487.74MIN: 466.56 / MAX: 530.41MIN: 454.72 / MAX: 2796.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mCAB3691215SE +/- 0.03, N = 3SE +/- 0.07, N = 1211.7113.4313.52MIN: 11.04 / MAX: 21.36MIN: 12.41 / MAX: 25.22MIN: 12.4 / MAX: 30.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdCAB612182430SE +/- 0.04, N = 3SE +/- 0.09, N = 1220.0922.9823.23MIN: 19.53 / MAX: 30.9MIN: 21.94 / MAX: 34.81MIN: 21.9 / MAX: 37.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyCAB714212835SE +/- 0.05, N = 3SE +/- 0.32, N = 1225.9330.9932.01MIN: 25.2 / MAX: 36.21MIN: 30 / MAX: 42.83MIN: 29.98 / MAX: 51.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50CAB714212835SE +/- 0.03, N = 3SE +/- 0.20, N = 1223.9730.3030.69MIN: 23.29 / MAX: 44.9MIN: 28.02 / MAX: 55.59MIN: 28.01 / MAX: 50.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetCAB3691215SE +/- 0.04, N = 3SE +/- 0.02, N = 127.829.529.53MIN: 7.56 / MAX: 15.4MIN: 8.29 / MAX: 21.28MIN: 8.25 / MAX: 25.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18CAB3691215SE +/- 0.03, N = 3SE +/- 0.05, N = 1210.1812.3512.42MIN: 9.82 / MAX: 21.36MIN: 10.94 / MAX: 24.24MIN: 10.93 / MAX: 28.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16CAB1326395265SE +/- 0.03, N = 3SE +/- 0.20, N = 1248.7958.6759.35MIN: 47.57 / MAX: 59.03MIN: 55.88 / MAX: 75.16MIN: 55.74 / MAX: 79.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetCBA48121620SE +/- 0.04, N = 12SE +/- 0.17, N = 313.2916.3616.55MIN: 12.82 / MAX: 25.26MIN: 14.84 / MAX: 32.63MIN: 15.25 / MAX: 34.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceCAB0.31950.6390.95851.2781.5975SE +/- 0.02, N = 3SE +/- 0.01, N = 121.151.411.42MIN: 1.1 / MAX: 1.53MIN: 1.29 / MAX: 12.91MIN: 1.29 / MAX: 12.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0CAB3691215SE +/- 0.63, N = 3SE +/- 0.20, N = 127.658.879.58MIN: 7.39 / MAX: 17.74MIN: 7.33 / MAX: 21.69MIN: 7.19 / MAX: 22.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetCAB1.27582.55163.82745.10326.379SE +/- 0.44, N = 3SE +/- 0.12, N = 124.495.335.67MIN: 4.33 / MAX: 14.86MIN: 4.29 / MAX: 17.46MIN: 4.2 / MAX: 17.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2CAB1.12952.2593.38854.5185.6475SE +/- 0.36, N = 3SE +/- 0.08, N = 124.154.745.02MIN: 3.98 / MAX: 14.25MIN: 3.87 / MAX: 16.57MIN: 3.77 / MAX: 18.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3BAC1.00132.00263.00394.00525.0065SE +/- 0.01, N = 12SE +/- 0.03, N = 34.334.344.45MIN: 4.13 / MAX: 17.27MIN: 4.14 / MAX: 15.02MIN: 4.27 / MAX: 14.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2BAC1.27352.5473.82055.0946.3675SE +/- 0.01, N = 12SE +/- 0.04, N = 35.475.505.66MIN: 5.24 / MAX: 17.26MIN: 5.24 / MAX: 15.72MIN: 5.38 / MAX: 18.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetCAB612182430SE +/- 0.09, N = 3SE +/- 0.20, N = 1219.4823.4224.01MIN: 18.64 / MAX: 30.04MIN: 22.12 / MAX: 35.14MIN: 21.95 / MAX: 38.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3CAB1428425670SE +/- 4.27, N = 3SE +/- 0.38, N = 345.7654.2460.33MIN: 39.8 / MAX: 62.47MIN: 44.03 / MAX: 97.27MIN: 55.81 / MAX: 85.331. (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 2.0Model: mobilenet-v1-1.0CAB246810SE +/- 0.500, N = 3SE +/- 0.096, N = 34.8495.8806.533MIN: 4.71 / MAX: 17.77MIN: 4.7 / MAX: 20.65MIN: 5.98 / MAX: 25.421. (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 2.0Model: MobileNetV2_224CAB1.29712.59423.89135.18846.4855SE +/- 0.401, N = 3SE +/- 0.019, N = 34.3865.2045.765MIN: 4.24 / MAX: 17.74MIN: 4.23 / MAX: 20.66MIN: 5.28 / MAX: 22.791. (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: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0CAB246810SE +/- 0.857, N = 3SE +/- 0.731, N = 36.2437.3348.401MIN: 6.02 / MAX: 21.09MIN: 5.45 / MAX: 59.76MIN: 5.61 / MAX: 26.821. (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 2.0Model: resnet-v2-50CAB714212835SE +/- 2.69, N = 3SE +/- 0.03, N = 321.2526.2030.31MIN: 20.57 / MAX: 34.78MIN: 20.02 / MAX: 49.96MIN: 27.66 / MAX: 60.091. (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 2.0Model: squeezenetv1.1CAB1.17362.34723.52084.69445.868SE +/- 0.443, N = 3SE +/- 0.057, N = 33.5464.2975.216MIN: 3.43 / MAX: 13.21MIN: 3.25 / MAX: 49.66MIN: 4.74 / MAX: 23.651. (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: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3BAC0.42730.85461.28191.70922.1365SE +/- 0.014, N = 3SE +/- 0.002, N = 31.7631.8031.899MIN: 1.67 / MAX: 13.46MIN: 1.72 / MAX: 13.52MIN: 1.82 / MAX: 7.691. (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

Phoronix Test Suite v10.8.4