tgl nn

Intel Core i7-1185G7 testing with a Dell 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 15GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208137-NE-TGLNN614834&sor&grr.

tgl nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCIntel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads)Dell 0DXP1F (3.7.0 BIOS)Intel Tiger Lake-LP16GBMicron 2300 NVMe 512GBIntel Xe TGL GT2 15GB (1350MHz)Realtek ALC289Intel Wi-Fi 6 AX201Ubuntu 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: 0xa4 - Thermald 2.4.9 Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + 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: Not affected + tsx_async_abort: Not affected

tgl nnncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: 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: mobilenetV3ABC16.0617.55715.1915.3814.9443.3610.9611.8630.0617.64.6516.612.5715.3615.6112.1420.225.48385.4913.0821.128.924.657.9511.6151.1914.911.37.94.864.644.485.7420.0638.5193.8853.0054.69817.7522.6521.76316.2617.62708.4215.6912.6341.5610.3211.1830.3616.113.216.5611.9514.9314.549.6321.015.47406.5313.0720.3628.2224.327.7911.148.3514.241.317.864.854.664.545.7119.4638.4394.2833.0884.71918.1952.7521.85515.9117.66707.0215.514.5143.1710.9511.4230.0216.763.8215.9411.4713.3915.548.9420.35.32379.79.9820.2428.1624.286.889.746.3411.810.986.44.924.634.465.7819.4938.9143.783.0544.76518.12.7731.69OpenBenchmarking.org

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetCAB4812162015.9116.0616.26MIN: 8.26 / MAX: 19.34MIN: 8 / MAX: 19.74MIN: 13.97 / MAX: 19.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABC4812162017.5517.6217.66MIN: 17.08 / MAX: 18.16MIN: 17.14 / MAX: 18.54MIN: 17.17 / MAX: 18.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerCBA150300450600750707.02708.37715.19MIN: 619.12 / MAX: 748.68MIN: 609.09 / MAX: 751.13MIN: 648.07 / MAX: 1449.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mACB4812162015.3815.5015.64MIN: 14.14 / MAX: 15.89MIN: 13.91 / MAX: 15.83MIN: 14.95 / MAX: 16.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdBCA4812162012.6314.5114.94MIN: 11.88 / MAX: 13.8MIN: 11.92 / MAX: 16.25MIN: 14.3 / MAX: 15.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyBCA102030405041.1343.1743.36MIN: 30.66 / MAX: 58.88MIN: 29.38 / MAX: 56.02MIN: 32.22 / MAX: 55.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetBCA369121510.3210.9510.96MIN: 9.85 / MAX: 10.47MIN: 10.51 / MAX: 11.44MIN: 10.56 / MAX: 11.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18BCA369121511.1811.4211.86MIN: 10.41 / MAX: 12.98MIN: 10.96 / MAX: 13.18MIN: 10.5 / MAX: 14.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16CAB71421283530.0230.0630.09MIN: 29.57 / MAX: 30.72MIN: 29.11 / MAX: 30.55MIN: 29.63 / MAX: 30.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetBCA4812162016.1116.7617.60MIN: 15.38 / MAX: 18.36MIN: 15.88 / MAX: 19.53MIN: 17.23 / MAX: 18.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceBCA1.04632.09263.13894.18525.23152.413.824.65MIN: 1.96 / MAX: 3.08MIN: 1.97 / MAX: 4.94MIN: 2.03 / MAX: 5.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0CBA4812162015.9416.5616.60MIN: 9.73 / MAX: 18.12MIN: 15.97 / MAX: 18.68MIN: 14.64 / MAX: 18.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetBCA36912159.7011.4712.57MIN: 8.87 / MAX: 11.48MIN: 9.6 / MAX: 13.18MIN: 9.96 / MAX: 14.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2CBA4812162013.3914.9315.36MIN: 8.41 / MAX: 17.13MIN: 9.5 / MAX: 17.76MIN: 13.22 / MAX: 17.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3BCA4812162014.5415.5415.61MIN: 11.08 / MAX: 16.97MIN: 11.65 / MAX: 18MIN: 11.7 / MAX: 17.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2CBA36912158.949.6312.14MIN: 8.47 / MAX: 11.14MIN: 8.75 / MAX: 10.23MIN: 9.62 / MAX: 13.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetBAC51015202519.6920.2220.30MIN: 17.2 / MAX: 32.21MIN: 14.31 / MAX: 29.33MIN: 14.26 / MAX: 24.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetCBA1.2332.4663.6994.9326.1655.325.475.48MIN: 5.16 / MAX: 15.86MIN: 5.24 / MAX: 10.71MIN: 5.23 / MAX: 14.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerCAB90180270360450379.70385.49406.53MIN: 319.88 / MAX: 425.4MIN: 316.44 / MAX: 423.85MIN: 401.44 / MAX: 418.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mCBA36912159.9813.0713.08MIN: 9.55 / MAX: 19.73MIN: 12.62 / MAX: 22.4MIN: 12.69 / MAX: 22.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdCBA51015202520.2420.3621.10MIN: 19.86 / MAX: 31.7MIN: 19.96 / MAX: 29.51MIN: 20.53 / MAX: 32.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyCBA71421283528.1628.2228.90MIN: 27.5 / MAX: 38.27MIN: 27.58 / MAX: 38.16MIN: 28.47 / MAX: 35.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50CBA61218243024.2824.3224.65MIN: 23.71 / MAX: 34.06MIN: 23.79 / MAX: 35.09MIN: 24.19 / MAX: 34.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetCBA2468106.887.797.95MIN: 6.61 / MAX: 16.27MIN: 7.43 / MAX: 16.75MIN: 7.69 / MAX: 17.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18CBA36912159.7011.1011.61MIN: 9.37 / MAX: 17.41MIN: 10.73 / MAX: 22.83MIN: 11.26 / MAX: 21.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16CBA122436486046.3448.3551.19MIN: 41.59 / MAX: 58.39MIN: 47.07 / MAX: 58.33MIN: 50.23 / MAX: 63.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetCBA4812162011.8114.2414.91MIN: 11.48 / MAX: 22.3MIN: 13.85 / MAX: 23.61MIN: 14.56 / MAX: 24.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceCAB0.29480.58960.88441.17921.4740.981.301.31MIN: 0.91 / MAX: 9.06MIN: 1.26 / MAX: 4.01MIN: 1.26 / MAX: 4.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0CBA2468106.407.867.90MIN: 5.98 / MAX: 16.08MIN: 7.58 / MAX: 15.79MIN: 7.58 / MAX: 17.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetBAC1.1072.2143.3214.4285.5354.854.864.92MIN: 4.68 / MAX: 14.11MIN: 4.64 / MAX: 14.28MIN: 4.65 / MAX: 11.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2CAB1.04852.0973.14554.1945.24254.634.644.66MIN: 4.49 / MAX: 14.4MIN: 4.49 / MAX: 14.14MIN: 4.51 / MAX: 13.841. (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-v3CAB1.02152.0433.06454.0865.10754.464.484.54MIN: 4.32 / MAX: 14.38MIN: 4.35 / MAX: 14.11MIN: 4.37 / MAX: 14.041. (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-v2BAC1.30052.6013.90155.2026.50255.715.745.78MIN: 5.52 / MAX: 14.52MIN: 5.57 / MAX: 15.24MIN: 5.49 / MAX: 15.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetBCA51015202519.4619.4920.06MIN: 19.05 / MAX: 28.45MIN: 19.09 / MAX: 29.18MIN: 19.64 / MAX: 29.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3BAC91827364538.4438.5238.91MIN: 37.67 / MAX: 51.44MIN: 37.75 / MAX: 50.78MIN: 34.86 / MAX: 70.841. (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: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0CAB0.96371.92742.89113.85484.81853.7803.8854.283MIN: 3.69 / MAX: 14.38MIN: 3.68 / MAX: 15.27MIN: 4.16 / MAX: 15.591. (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_224ACB0.69481.38962.08442.77923.4743.0053.0543.088MIN: 2.89 / MAX: 13.65MIN: 2.96 / MAX: 14.33MIN: 2.95 / MAX: 13.91. (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: SqueezeNetV1.0ABC1.07212.14423.21634.28845.36054.6984.7194.765MIN: 4.52 / MAX: 16.41MIN: 4.5 / MAX: 9.92MIN: 4.57 / MAX: 13.931. (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-v2-50ACB4812162017.7518.1018.20MIN: 16.61 / MAX: 31.74MIN: 16.61 / MAX: 33.23MIN: 16.86 / MAX: 33.751. (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: squeezenetv1.1ABC0.62391.24781.87172.49563.11952.6522.7522.773MIN: 2.55 / MAX: 6.22MIN: 2.66 / MAX: 13.51MIN: 2.66 / MAX: 9.671. (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: mobilenetV3CAB0.41740.83481.25221.66962.0871.6901.7631.855MIN: 1.61 / MAX: 14.19MIN: 1.62 / MAX: 13.44MIN: 1.81 / MAX: 13.761. (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