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&rdt&grs.

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 - resnet50ncnn: CPU - vision_transformerncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - yolov4-tinyncnn: CPU - mobilenetncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - vgg16ncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - FastestDetmnn: mobilenetV3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2mnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1ABC30.30483.6716.551.4130.9923.4212.359.5258.6722.9813.435.281.8035.504.348.875.334.7454.2435.8805.2047.33426.2004.29730.69482.2916.361.4232.0124.0112.429.5359.3523.2313.525.351.7635.474.339.585.675.0260.3256.5335.7658.40130.3075.21623.97380.2713.291.1525.9319.4810.187.8248.7920.0911.714.941.8995.664.457.654.494.1545.7624.8494.3866.24321.2463.546OpenBenchmarking.org

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC714212835SE +/- 0.03, N = 3SE +/- 0.20, N = 1230.3030.6923.97MIN: 28.02 / MAX: 55.59MIN: 28.01 / MAX: 50.51MIN: 23.29 / MAX: 44.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC100200300400500SE +/- 6.80, N = 3SE +/- 0.62, N = 12483.67482.29380.27MIN: 454.72 / MAX: 2796.01MIN: 466.56 / MAX: 530.41MIN: 324.06 / MAX: 487.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC48121620SE +/- 0.17, N = 3SE +/- 0.04, N = 1216.5516.3613.29MIN: 15.25 / MAX: 34.09MIN: 14.84 / MAX: 32.63MIN: 12.82 / MAX: 25.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC0.31950.6390.95851.2781.5975SE +/- 0.02, N = 3SE +/- 0.01, N = 121.411.421.15MIN: 1.29 / MAX: 12.91MIN: 1.29 / MAX: 12.11MIN: 1.1 / MAX: 1.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC714212835SE +/- 0.05, N = 3SE +/- 0.32, N = 1230.9932.0125.93MIN: 30 / MAX: 42.83MIN: 29.98 / MAX: 51.54MIN: 25.2 / MAX: 36.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC612182430SE +/- 0.09, N = 3SE +/- 0.20, N = 1223.4224.0119.48MIN: 22.12 / MAX: 35.14MIN: 21.95 / MAX: 38.02MIN: 18.64 / MAX: 30.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC3691215SE +/- 0.03, N = 3SE +/- 0.05, N = 1212.3512.4210.18MIN: 10.94 / MAX: 24.24MIN: 10.93 / MAX: 28.95MIN: 9.82 / MAX: 21.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC3691215SE +/- 0.04, N = 3SE +/- 0.02, N = 129.529.537.82MIN: 8.29 / MAX: 21.28MIN: 8.25 / MAX: 25.84MIN: 7.56 / MAX: 15.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC1326395265SE +/- 0.03, N = 3SE +/- 0.20, N = 1258.6759.3548.79MIN: 55.88 / MAX: 75.16MIN: 55.74 / MAX: 79.62MIN: 47.57 / MAX: 59.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC612182430SE +/- 0.04, N = 3SE +/- 0.09, N = 1222.9823.2320.09MIN: 21.94 / MAX: 34.81MIN: 21.9 / MAX: 37.58MIN: 19.53 / MAX: 30.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC3691215SE +/- 0.03, N = 3SE +/- 0.07, N = 1213.4313.5211.71MIN: 12.41 / MAX: 25.22MIN: 12.4 / MAX: 30.32MIN: 11.04 / MAX: 21.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetABC1.20382.40763.61144.81526.019SE +/- 0.04, N = 3SE +/- 0.06, N = 125.285.354.94MIN: 4.93 / MAX: 19.96MIN: 4.93 / MAX: 20.31MIN: 4.37 / MAX: 16.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC0.42730.85461.28191.70922.1365SE +/- 0.002, N = 3SE +/- 0.014, N = 31.8031.7631.899MIN: 1.72 / MAX: 13.52MIN: 1.67 / MAX: 13.46MIN: 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

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ABC1.27352.5473.82055.0946.3675SE +/- 0.04, N = 3SE +/- 0.01, N = 125.505.475.66MIN: 5.24 / MAX: 15.72MIN: 5.24 / MAX: 17.26MIN: 5.38 / MAX: 18.341. (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-v3ABC1.00132.00263.00394.00525.0065SE +/- 0.03, N = 3SE +/- 0.01, N = 124.344.334.45MIN: 4.14 / MAX: 15.02MIN: 4.13 / MAX: 17.27MIN: 4.27 / MAX: 14.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC3691215SE +/- 0.63, N = 3SE +/- 0.20, N = 128.879.587.65MIN: 7.33 / MAX: 21.69MIN: 7.19 / MAX: 22.38MIN: 7.39 / MAX: 17.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC1.27582.55163.82745.10326.379SE +/- 0.44, N = 3SE +/- 0.12, N = 125.335.674.49MIN: 4.29 / MAX: 17.46MIN: 4.2 / MAX: 17.84MIN: 4.33 / MAX: 14.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC1.12952.2593.38854.5185.6475SE +/- 0.36, N = 3SE +/- 0.08, N = 124.745.024.15MIN: 3.87 / MAX: 16.57MIN: 3.77 / MAX: 18.76MIN: 3.98 / MAX: 14.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3ABC1428425670SE +/- 4.27, N = 3SE +/- 0.38, N = 354.2460.3345.76MIN: 44.03 / MAX: 97.27MIN: 55.81 / MAX: 85.33MIN: 39.8 / MAX: 62.471. (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-v1-1.0ABC246810SE +/- 0.500, N = 3SE +/- 0.096, N = 35.8806.5334.849MIN: 4.7 / MAX: 20.65MIN: 5.98 / MAX: 25.42MIN: 4.71 / MAX: 17.771. (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_224ABC1.29712.59423.89135.18846.4855SE +/- 0.401, N = 3SE +/- 0.019, N = 35.2045.7654.386MIN: 4.23 / MAX: 20.66MIN: 5.28 / MAX: 22.79MIN: 4.24 / MAX: 17.741. (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: SqueezeNetV1.0ABC246810SE +/- 0.857, N = 3SE +/- 0.731, N = 37.3348.4016.243MIN: 5.45 / MAX: 59.76MIN: 5.61 / MAX: 26.82MIN: 6.02 / MAX: 21.091. (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: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC714212835SE +/- 2.69, N = 3SE +/- 0.03, N = 326.2030.3121.25MIN: 20.02 / MAX: 49.96MIN: 27.66 / MAX: 60.09MIN: 20.57 / MAX: 34.781. (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

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABC1.17362.34723.52084.69445.868SE +/- 0.443, N = 3SE +/- 0.057, N = 34.2975.2163.546MIN: 3.25 / MAX: 49.66MIN: 4.74 / MAX: 23.65MIN: 3.43 / MAX: 13.211. (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