ncnn mnn rembrandyt

AMD Ryzen 7 PRO 6850U testing with a LENOVO 21CM0001US (R22ET46W 1.16 BIOS) and AMD Radeon 680M 1GB on Ubuntu 22.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208130-NE-NCNNMNNRE44&grr&sor.

ncnn mnn rembrandytProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCDAMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads)LENOVO 21CM0001US (R22ET46W 1.16 BIOS)AMD Device 14b516GB512GB Micron MTFDKBA512TFKAMD Radeon 680M 1GB (2200/400MHz)AMD Rembrandt Radeon HD AudioQualcomm QCNFA765Ubuntu 22.105.19.0-051900-generic (x86_64)GNOME Shell 42.3.1X Server + Wayland4.6 Mesa 22.1.3 (LLVM 14.0.6 DRM 3.47)1.3.211GCC 11.3.0ext41920x1200OpenBenchmarking.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-11-7Xaroy/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-7Xaroy/gcc-11-11.3.0/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: amd-pstate schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ncnn mnn rembrandytncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: 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 - mobilenetmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3ncnn: 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 - mobilenetABCD2.77744.863.2814.8016.588.755.974.2418.075.243.656.282.131.692.392.249.5037.1063.0183.1355.98126.8453.4081.5903.04258.197.7615.2921.3919.988.159.9547.3610.990.926.022.962.413.023.6813.012.67749.583.2714.6716.368.895.524.0618.485.043.685.972.201.732.462.109.3836.9633.0283.0926.02626.9103.4661.5922.99257.957.7115.0921.6720.188.189.9847.4810.920.915.912.882.43.003.6413.032.68749.993.2014.6216.468.715.694.2218.404.943.665.862.301.712.342.139.4436.9653.0213.1196.01426.9643.4021.5893.05258.167.6915.1621.2920.038.249.9947.3010.860.906.053.012.423.043.7012.892.67744.713.1515.4316.148.785.603.9918.484.933.595.452.221.712.422.129.3636.8633.0333.1355.95726.8773.3601.5932.93259.507.7115.1421.3019.868.179.8447.2710.870.905.922.852.403.023.6512.78OpenBenchmarking.org

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetBDCA0.62331.24661.86992.49323.1165SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 32.672.672.682.77MIN: 2.41 / MAX: 4.12MIN: 2.45 / MAX: 4.12MIN: 2.44 / MAX: 4.22MIN: 2.45 / MAX: 3.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerDABC160320480640800SE +/- 0.95, N = 3SE +/- 2.21, N = 3SE +/- 3.91, N = 3SE +/- 1.07, N = 3744.71744.86749.58749.99MIN: 688.87 / MAX: 827.15MIN: 689.04 / MAX: 986.61MIN: 687.82 / MAX: 819.16MIN: 691.69 / MAX: 816.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mDCBA0.7381.4762.2142.9523.69SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 33.153.203.273.28MIN: 2.67 / MAX: 4.4MIN: 2.64 / MAX: 4.34MIN: 2.65 / MAX: 4.74MIN: 2.58 / MAX: 4.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdCBAD48121620SE +/- 0.11, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.73, N = 314.6214.6714.8015.43MIN: 11.51 / MAX: 31.57MIN: 11.81 / MAX: 19.58MIN: 11.69 / MAX: 29.38MIN: 11.57 / MAX: 20.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyDBCA48121620SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.29, N = 3SE +/- 0.14, N = 316.1416.3616.4616.58MIN: 15.2 / MAX: 25.61MIN: 15.12 / MAX: 19.7MIN: 15 / MAX: 30.3MIN: 15.11 / MAX: 30.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50CADB246810SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 38.718.758.788.89MIN: 7.9 / MAX: 9.91MIN: 8.17 / MAX: 9.66MIN: 8.02 / MAX: 9.94MIN: 8.23 / MAX: 10.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetBDCA1.34332.68664.02995.37326.7165SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.10, N = 35.525.605.695.97MIN: 5.14 / MAX: 7.5MIN: 5.11 / MAX: 8.26MIN: 5.16 / MAX: 9.13MIN: 5.11 / MAX: 6.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18DBCA0.9541.9082.8623.8164.77SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 33.994.064.224.24MIN: 3.65 / MAX: 6.81MIN: 3.65 / MAX: 7.1MIN: 3.7 / MAX: 5.59MIN: 3.5 / MAX: 7.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ACBD510152025SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 318.0718.4018.4818.48MIN: 17.25 / MAX: 18.93MIN: 17.68 / MAX: 21.67MIN: 17.65 / MAX: 20.6MIN: 17.7 / MAX: 21.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetDCBA1.1792.3583.5374.7165.895SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 34.934.945.045.24MIN: 4.52 / MAX: 6.53MIN: 4.57 / MAX: 6.47MIN: 4.52 / MAX: 6.4MIN: 4.51 / MAX: 8.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceDACB0.8281.6562.4843.3124.14SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 33.593.653.663.68MIN: 2.3 / MAX: 4.81MIN: 2.29 / MAX: 4.3MIN: 2.8 / MAX: 10.32MIN: 2.81 / MAX: 5.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0DCBA246810SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.33, N = 3SE +/- 0.15, N = 35.455.865.976.28MIN: 5.2 / MAX: 6.56MIN: 5.2 / MAX: 7.64MIN: 5.22 / MAX: 7.38MIN: 5.4 / MAX: 8.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABDC0.51751.0351.55252.072.5875SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 32.132.202.222.30MIN: 1.93 / MAX: 3.13MIN: 1.94 / MAX: 3.25MIN: 1.98 / MAX: 3.35MIN: 1.96 / MAX: 3.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ACDB0.38930.77861.16791.55721.9465SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 31.691.711.711.73MIN: 1.48 / MAX: 2.66MIN: 1.49 / MAX: 2.6MIN: 1.5 / MAX: 2.6MIN: 1.47 / MAX: 2.681. (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-v3CADB0.55351.1071.66052.2142.7675SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 32.342.392.422.46MIN: 2.09 / MAX: 3.34MIN: 2.02 / MAX: 5.72MIN: 2.09 / MAX: 4.74MIN: 2.07 / MAX: 3.731. (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-v2BDCA0.5041.0081.5122.0162.52SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.17, N = 32.102.122.132.24MIN: 1.92 / MAX: 3.23MIN: 1.95 / MAX: 3.33MIN: 1.95 / MAX: 3.18MIN: 1.9 / MAX: 3.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetDBCA3691215SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 39.369.389.449.50MIN: 8.2 / MAX: 10.62MIN: 8.32 / MAX: 14.57MIN: 8.24 / MAX: 13.02MIN: 8.25 / MAX: 11.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3DBCA918273645SE +/- 0.46, N = 3SE +/- 0.32, N = 3SE +/- 0.35, N = 3SE +/- 0.20, N = 636.8636.9636.9737.11MIN: 32.19 / MAX: 58.72MIN: 32.27 / MAX: 62.73MIN: 32.4 / MAX: 58.25MIN: 31.04 / MAX: 88.361. (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-v1-1.0ACBD0.68241.36482.04722.72963.412SE +/- 0.005, N = 6SE +/- 0.011, N = 3SE +/- 0.013, N = 3SE +/- 0.018, N = 33.0183.0213.0283.033MIN: 2.78 / MAX: 25.86MIN: 2.75 / MAX: 41.57MIN: 2.76 / MAX: 39.49MIN: 2.81 / MAX: 44.021. (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_224BCAD0.70541.41082.11622.82163.527SE +/- 0.012, N = 3SE +/- 0.014, N = 3SE +/- 0.020, N = 6SE +/- 0.017, N = 33.0923.1193.1353.135MIN: 2.9 / MAX: 4.09MIN: 2.9 / MAX: 25.93MIN: 2.78 / MAX: 29.16MIN: 3 / MAX: 18.721. (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: SqueezeNetV1.0DACB246810SE +/- 0.065, N = 3SE +/- 0.032, N = 6SE +/- 0.006, N = 3SE +/- 0.015, N = 35.9575.9816.0146.026MIN: 5.67 / MAX: 24.65MIN: 5.59 / MAX: 26.15MIN: 5.71 / MAX: 23.38MIN: 5.59 / MAX: 43.371. (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-v2-50ADBC612182430SE +/- 0.07, N = 6SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 326.8526.8826.9126.96MIN: 25.53 / MAX: 67.31MIN: 25.7 / MAX: 62.52MIN: 25.91 / MAX: 63.84MIN: 25.97 / MAX: 65.211. (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

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1DCAB0.77991.55982.33973.11963.8995SE +/- 0.011, N = 3SE +/- 0.022, N = 3SE +/- 0.017, N = 6SE +/- 0.009, N = 33.3603.4023.4083.466MIN: 3.03 / MAX: 27.44MIN: 3.2 / MAX: 4.6MIN: 3.19 / MAX: 15.38MIN: 3.16 / MAX: 41.661. (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: mobilenetV3CABD0.35840.71681.07521.43361.792SE +/- 0.013, N = 3SE +/- 0.016, N = 6SE +/- 0.019, N = 3SE +/- 0.010, N = 31.5891.5901.5921.593MIN: 1.52 / MAX: 38.48MIN: 1.5 / MAX: 25.15MIN: 1.49 / MAX: 31.15MIN: 1.53 / MAX: 10.131. (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: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetDBAC0.68631.37262.05892.74523.4315SE +/- 0.01, N = 3SE +/- 0.04, N = 5SE +/- 0.04, N = 32.932.993.043.05MIN: 2.83 / MAX: 3.63MIN: 2.85 / MAX: 3.71MIN: 2.82 / MAX: 3.67MIN: 2.92 / MAX: 4.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerBCAD60120180240300SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.37, N = 5SE +/- 0.63, N = 3257.95258.16258.19259.50MIN: 252.71 / MAX: 287.92MIN: 254.14 / MAX: 285.51MIN: 252.82 / MAX: 289.02MIN: 253.94 / MAX: 366.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mCBDA246810SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 57.697.717.717.76MIN: 7.06 / MAX: 19.39MIN: 7.15 / MAX: 9.2MIN: 7.08 / MAX: 9.27MIN: 7.05 / MAX: 11.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdBDCA48121620SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 515.0915.1415.1615.29MIN: 14.57 / MAX: 26.07MIN: 14.51 / MAX: 26.41MIN: 14.51 / MAX: 27.53MIN: 14.48 / MAX: 29.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyCDAB510152025SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 5SE +/- 0.19, N = 321.2921.3021.3921.67MIN: 20.62 / MAX: 22.98MIN: 20.71 / MAX: 58.09MIN: 20.67 / MAX: 35.04MIN: 20.9 / MAX: 63.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50DACB510152025SE +/- 0.12, N = 3SE +/- 0.15, N = 5SE +/- 0.15, N = 3SE +/- 0.11, N = 319.8619.9820.0320.18MIN: 18.93 / MAX: 33.33MIN: 19.02 / MAX: 24.43MIN: 19.24 / MAX: 22.52MIN: 19.51 / MAX: 22.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetADBC246810SE +/- 0.03, N = 5SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 38.158.178.188.24MIN: 7.62 / MAX: 20.7MIN: 7.82 / MAX: 19.17MIN: 7.83 / MAX: 10.05MIN: 7.79 / MAX: 9.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18DABC3691215SE +/- 0.04, N = 3SE +/- 0.07, N = 5SE +/- 0.17, N = 3SE +/- 0.16, N = 39.849.959.989.99MIN: 9.23 / MAX: 12.34MIN: 9.17 / MAX: 23.38MIN: 9.33 / MAX: 23.59MIN: 9.27 / MAX: 19.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16DCAB1122334455SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 5SE +/- 0.02, N = 347.2747.3047.3647.48MIN: 46.41 / MAX: 60.73MIN: 46.39 / MAX: 59.66MIN: 46.44 / MAX: 62.61MIN: 46.55 / MAX: 60.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetCDBA3691215SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 510.8610.8710.9210.99MIN: 10.14 / MAX: 12.82MIN: 10.43 / MAX: 22.43MIN: 10.18 / MAX: 19.54MIN: 10.36 / MAX: 26.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceCDBA0.2070.4140.6210.8281.035SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 50.900.900.910.92MIN: 0.85 / MAX: 1.81MIN: 0.77 / MAX: 1.61MIN: 0.83 / MAX: 1.57MIN: 0.86 / MAX: 1.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0BDAC246810SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 5SE +/- 0.01, N = 35.915.926.026.05MIN: 5.61 / MAX: 7.75MIN: 5.59 / MAX: 7.49MIN: 5.53 / MAX: 7.9MIN: 5.64 / MAX: 8.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetDBAC0.67731.35462.03192.70923.3865SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 5SE +/- 0.02, N = 22.852.882.963.01MIN: 2.67 / MAX: 4.27MIN: 2.57 / MAX: 13.42MIN: 2.66 / MAX: 6.1MIN: 2.77 / MAX: 4.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2BDAC0.54451.0891.63352.1782.7225SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 32.402.402.412.42MIN: 2.26 / MAX: 4.09MIN: 2.26 / MAX: 3.6MIN: 2.19 / MAX: 4.56MIN: 2.16 / MAX: 3.81. (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-v3BADC0.6841.3682.0522.7363.42SE +/- 0.02, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 3SE +/- 0.00, N = 33.003.023.023.04MIN: 2.73 / MAX: 6.51MIN: 2.73 / MAX: 4.86MIN: 2.75 / MAX: 4.94MIN: 2.87 / MAX: 4.851. (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-v2BDAC0.83251.6652.49753.334.1625SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 5SE +/- 0.03, N = 33.643.653.683.70MIN: 3.38 / MAX: 5.28MIN: 3.41 / MAX: 5.27MIN: 3.37 / MAX: 16.17MIN: 3.43 / MAX: 5.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetDCAB3691215SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 5SE +/- 0.09, N = 312.7812.8913.0113.03MIN: 12.3 / MAX: 13.97MIN: 12.31 / MAX: 23.48MIN: 12.38 / MAX: 30.48MIN: 12.57 / MAX: 49.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.5