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.

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 nnmnn: 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_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetABC1.7632.65217.7524.6983.0053.88538.51920.065.744.484.644.867.91.314.9151.1911.617.9524.6528.921.113.08385.495.4820.2212.1415.6115.3612.5716.64.6517.630.0611.8610.9617.5543.3614.9415.38715.1916.061.8552.75218.1954.7193.0884.28338.43919.465.714.544.664.857.861.3114.2448.3511.17.7924.3228.2220.3613.07406.535.4721.019.6314.5414.9311.9516.563.216.1130.3611.1810.3217.6241.5612.6315.69708.4216.261.692.77318.14.7653.0543.7838.91419.495.784.464.634.926.40.9811.8146.349.76.8824.2828.1620.249.98379.75.3220.38.9415.5413.3911.4715.943.8216.7630.0211.4210.9517.6643.1714.5115.5707.0215.91OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC0.41740.83481.25221.66962.0871.7631.8551.690MIN: 1.62 / MAX: 13.44MIN: 1.81 / MAX: 13.76MIN: 1.61 / MAX: 14.191. (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: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC4812162017.7518.2018.10MIN: 16.61 / MAX: 31.74MIN: 16.86 / MAX: 33.75MIN: 16.61 / MAX: 33.231. (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 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: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224ABC0.69481.38962.08442.77923.4743.0053.0883.054MIN: 2.89 / MAX: 13.65MIN: 2.95 / MAX: 13.9MIN: 2.96 / MAX: 14.331. (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-v1-1.0ABC0.96371.92742.89113.85484.81853.8854.2833.780MIN: 3.68 / MAX: 15.27MIN: 4.16 / MAX: 15.59MIN: 3.69 / MAX: 14.381. (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 2.0Model: inception-v3ABC91827364538.5238.4438.91MIN: 37.75 / MAX: 50.78MIN: 37.67 / MAX: 51.44MIN: 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

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC51015202520.0619.4619.49MIN: 19.64 / MAX: 29.35MIN: 19.05 / MAX: 28.45MIN: 19.09 / MAX: 29.181. (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-v2ABC1.30052.6013.90155.2026.50255.745.715.78MIN: 5.57 / MAX: 15.24MIN: 5.52 / MAX: 14.52MIN: 5.49 / MAX: 15.661. (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-v3ABC1.02152.0433.06454.0865.10754.484.544.46MIN: 4.35 / MAX: 14.11MIN: 4.37 / MAX: 14.04MIN: 4.32 / MAX: 14.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC1.04852.0973.14554.1945.24254.644.664.63MIN: 4.49 / MAX: 14.14MIN: 4.51 / MAX: 13.84MIN: 4.49 / MAX: 14.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC1.1072.2143.3214.4285.5354.864.854.92MIN: 4.64 / MAX: 14.28MIN: 4.68 / MAX: 14.11MIN: 4.65 / MAX: 11.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC2468107.907.866.40MIN: 7.58 / MAX: 17.27MIN: 7.58 / MAX: 15.79MIN: 5.98 / MAX: 16.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC0.29480.58960.88441.17921.4741.301.310.98MIN: 1.26 / MAX: 4.01MIN: 1.26 / MAX: 4.17MIN: 0.91 / MAX: 9.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC4812162014.9114.2411.81MIN: 14.56 / MAX: 24.56MIN: 13.85 / MAX: 23.61MIN: 11.48 / MAX: 22.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC122436486051.1948.3546.34MIN: 50.23 / MAX: 63.37MIN: 47.07 / MAX: 58.33MIN: 41.59 / MAX: 58.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC369121511.6111.109.70MIN: 11.26 / MAX: 21.8MIN: 10.73 / MAX: 22.83MIN: 9.37 / MAX: 17.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC2468107.957.796.88MIN: 7.69 / MAX: 17.15MIN: 7.43 / MAX: 16.75MIN: 6.61 / MAX: 16.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC61218243024.6524.3224.28MIN: 24.19 / MAX: 34.33MIN: 23.79 / MAX: 35.09MIN: 23.71 / MAX: 34.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC71421283528.9028.2228.16MIN: 28.47 / MAX: 35.59MIN: 27.58 / MAX: 38.16MIN: 27.5 / MAX: 38.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC51015202521.1020.3620.24MIN: 20.53 / MAX: 32.23MIN: 19.96 / MAX: 29.51MIN: 19.86 / MAX: 31.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC369121513.0813.079.98MIN: 12.69 / MAX: 22.99MIN: 12.62 / MAX: 22.4MIN: 9.55 / MAX: 19.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC90180270360450385.49406.53379.70MIN: 316.44 / MAX: 423.85MIN: 401.44 / MAX: 418.39MIN: 319.88 / MAX: 425.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetABC1.2332.4663.6994.9326.1655.485.475.32MIN: 5.23 / MAX: 14.85MIN: 5.24 / MAX: 10.71MIN: 5.16 / MAX: 15.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABC51015202520.2219.6920.30MIN: 14.31 / MAX: 29.33MIN: 17.2 / MAX: 32.21MIN: 14.26 / MAX: 24.781. (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-v2ABC369121512.149.688.94MIN: 9.62 / MAX: 13.59MIN: 8.76 / MAX: 11.26MIN: 8.47 / MAX: 11.141. (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-v3ABC4812162015.6115.8415.54MIN: 11.7 / MAX: 17.21MIN: 14.05 / MAX: 17.8MIN: 11.65 / MAX: 181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABC4812162015.3615.1013.39MIN: 13.22 / MAX: 17.83MIN: 7.93 / MAX: 17.24MIN: 8.41 / MAX: 17.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABC369121512.579.7011.47MIN: 9.96 / MAX: 14.89MIN: 8.87 / MAX: 11.48MIN: 9.6 / MAX: 13.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABC4812162016.6016.5715.94MIN: 14.64 / MAX: 18.84MIN: 15.57 / MAX: 18.58MIN: 9.73 / MAX: 18.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABC1.04632.09263.13894.18525.23154.652.413.82MIN: 2.03 / MAX: 5.19MIN: 1.96 / MAX: 3.08MIN: 1.97 / MAX: 4.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABC4812162017.6016.1416.76MIN: 17.23 / MAX: 18.97MIN: 15.69 / MAX: 18.26MIN: 15.88 / MAX: 19.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABC71421283530.0630.0930.02MIN: 29.11 / MAX: 30.55MIN: 29.63 / MAX: 30.7MIN: 29.57 / MAX: 30.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABC369121511.8611.5411.42MIN: 10.5 / MAX: 14.58MIN: 10.99 / MAX: 13.73MIN: 10.96 / MAX: 13.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABC369121510.9610.4610.95MIN: 10.56 / MAX: 11.27MIN: 10.16 / MAX: 11.07MIN: 10.51 / MAX: 11.441. (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: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABC102030405043.3641.1343.17MIN: 32.22 / MAX: 55.31MIN: 30.66 / MAX: 58.88MIN: 29.38 / MAX: 56.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABC4812162014.9414.9514.51MIN: 14.3 / MAX: 15.7MIN: 12.64 / MAX: 22.32MIN: 11.92 / MAX: 16.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABC4812162015.3815.6415.50MIN: 14.14 / MAX: 15.89MIN: 14.95 / MAX: 16.14MIN: 13.91 / MAX: 15.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABC150300450600750715.19708.37707.02MIN: 648.07 / MAX: 1449.35MIN: 609.09 / MAX: 751.13MIN: 619.12 / MAX: 748.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABC4812162016.0616.2615.91MIN: 8 / MAX: 19.74MIN: 13.97 / MAX: 19.35MIN: 8.26 / MAX: 19.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4