5500u nn

AMD Ryzen 5 5500U testing with a LENOVO LNVNB161216 (GLCN22WW BIOS) and AMD Lucienne 2GB on Ubuntu 21.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2106186-GIT-5500UNN971.

5500u nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 5 5500U @ 2.10GHz (6 Cores / 12 Threads)LENOVO LNVNB161216 (GLCN22WW BIOS)AMD Renoir Root Complex6GB256GB SAMSUNG MZALQ256HBJD-00BL2AMD Lucienne 2GB (1800/400MHz)AMD Device 1637Qualcomm Atheros QCA6174 802.11acUbuntu 21.045.11.0-18-generic (x86_64)GNOME Shell 3.38.4X Server 1.20.11 + Wayland4.6 Mesa 21.0.1 (LLVM 11.0.1)1.2.145GCC 10.3.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8608102 Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

5500u 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: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.11233.2805.69345.0648.7485.3665.96150.09930.178.607.115.536.3811.212.0824.77112.9124.8918.7946.0845.3833.0112.4830.168.637.105.566.3811.312.0724.94113.1724.8718.8846.1645.5033.0012.623495.184282.47771.473252.4943.3065.62745.6328.7035.3155.95649.89330.138.667.135.576.4011.312.0624.66112.6724.6618.4546.7145.4733.3712.4929.898.597.125.566.4111.312.0724.79112.9324.7718.4446.1546.1632.8412.543491.262280.63871.638252.7783.2165.63045.6138.5675.2485.97650.08330.088.587.155.556.4011.252.0724.83112.8824.7118.7246.3645.4733.2912.5530.238.657.095.536.3911.292.0724.82112.7224.7319.0046.2945.8432.9012.563484.781280.44071.294252.980OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV31230.74391.48782.23172.97563.7195SE +/- 0.044, N = 3SE +/- 0.091, N = 9SE +/- 0.037, N = 43.2803.3063.216MIN: 2.86 / MAX: 58.49MIN: 2.71 / MAX: 51MIN: 2.73 / MAX: 16.691. (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

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.11231.28092.56183.84275.12366.4045SE +/- 0.059, N = 3SE +/- 0.034, N = 9SE +/- 0.042, N = 45.6935.6275.630MIN: 5.16 / MAX: 18.87MIN: 4.99 / MAX: 20.47MIN: 5.03 / MAX: 18.431. (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 1.2Model: resnet-v2-501231020304050SE +/- 0.13, N = 3SE +/- 0.29, N = 9SE +/- 0.06, N = 445.0645.6345.61MIN: 43.04 / MAX: 58.57MIN: 42.54 / MAX: 107.37MIN: 43.5 / MAX: 59.191. (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: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0123246810SE +/- 0.016, N = 3SE +/- 0.070, N = 9SE +/- 0.074, N = 48.7488.7038.567MIN: 7.97 / MAX: 22.06MIN: 7.67 / MAX: 35.07MIN: 7.72 / MAX: 22.741. (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: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_2241231.20742.41483.62224.82966.037SE +/- 0.087, N = 3SE +/- 0.050, N = 9SE +/- 0.052, N = 45.3665.3155.248MIN: 4.65 / MAX: 34.61MIN: 4.54 / MAX: 18.86MIN: 4.55 / MAX: 18.621. (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 1.2Model: mobilenet-v1-1.01231.34462.68924.03385.37846.723SE +/- 0.030, N = 3SE +/- 0.036, N = 9SE +/- 0.020, N = 45.9615.9565.976MIN: 5.41 / MAX: 18.59MIN: 5.37 / MAX: 20.83MIN: 5.43 / MAX: 20.321. (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 1.2Model: inception-v31231122334455SE +/- 0.01, N = 3SE +/- 0.15, N = 9SE +/- 0.01, N = 450.1049.8950.08MIN: 48.53 / MAX: 66.06MIN: 46.73 / MAX: 66.1MIN: 48.26 / MAX: 63.941. (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 20210525Target: CPU - Model: mobilenet123714212835SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 330.1730.1330.08MIN: 28.78 / MAX: 77.06MIN: 28.69 / MAX: 76.05MIN: 28.58 / MAX: 40.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 38.608.668.58MIN: 7.74 / MAX: 18.04MIN: 7.77 / MAX: 18.83MIN: 7.68 / MAX: 12.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 37.117.137.15MIN: 6.42 / MAX: 8.23MIN: 6.46 / MAX: 11.13MIN: 6.36 / MAX: 54.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21231.25332.50663.75995.01326.2665SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 35.535.575.55MIN: 5.07 / MAX: 9.52MIN: 5.09 / MAX: 16.31MIN: 5.07 / MAX: 13.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 36.386.406.40MIN: 5.71 / MAX: 16.86MIN: 5.68 / MAX: 7.47MIN: 5.62 / MAX: 16.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 311.2111.3111.25MIN: 10.22 / MAX: 14.04MIN: 10.1 / MAX: 46.64MIN: 10.18 / MAX: 12.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.4680.9361.4041.8722.34SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 32.082.062.07MIN: 1.83 / MAX: 3.08MIN: 1.85 / MAX: 2.97MIN: 1.87 / MAX: 3.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet123612182430SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 324.7724.6624.83MIN: 23.56 / MAX: 36.41MIN: 23.68 / MAX: 35.88MIN: 23.71 / MAX: 34.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg16123306090120150SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.16, N = 3112.91112.67112.88MIN: 109.59 / MAX: 161.73MIN: 109.8 / MAX: 188.53MIN: 109.55 / MAX: 165.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18123612182430SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 324.8924.6624.71MIN: 23.6 / MAX: 72.09MIN: 23.49 / MAX: 32.67MIN: 23.57 / MAX: 72.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet123510152025SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.27, N = 318.7918.4518.72MIN: 17.33 / MAX: 22.05MIN: 17.22 / MAX: 46.16MIN: 17.26 / MAX: 21.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet501231122334455SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.11, N = 346.0846.7146.36MIN: 44.2 / MAX: 58.53MIN: 45.23 / MAX: 58.49MIN: 44.96 / MAX: 57.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny1231020304050SE +/- 0.35, N = 3SE +/- 0.14, N = 3SE +/- 0.20, N = 345.3845.4745.47MIN: 43.87 / MAX: 70.45MIN: 44.13 / MAX: 56.81MIN: 44.09 / MAX: 55.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123816243240SE +/- 0.24, N = 3SE +/- 0.06, N = 3SE +/- 0.20, N = 333.0133.3733.29MIN: 31.66 / MAX: 68.05MIN: 31.97 / MAX: 63.52MIN: 31.69 / MAX: 43.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m1233691215SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 312.4812.4912.55MIN: 11.52 / MAX: 22.72MIN: 11.46 / MAX: 22.58MIN: 11.59 / MAX: 22.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mobilenet123714212835SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.16, N = 330.1629.8930.23MIN: 28.62 / MAX: 40.92MIN: 28.65 / MAX: 60.11MIN: 28.68 / MAX: 79.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 38.638.598.65MIN: 7.71 / MAX: 18.62MIN: 7.75 / MAX: 9.8MIN: 7.71 / MAX: 9.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 37.107.127.09MIN: 6.48 / MAX: 8.15MIN: 6.43 / MAX: 14.96MIN: 6.39 / MAX: 8.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: shufflenet-v21231.2512.5023.7535.0046.255SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.565.565.53MIN: 5.1 / MAX: 6.45MIN: 5.09 / MAX: 10.01MIN: 5.07 / MAX: 6.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mnasnet123246810SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 36.386.416.39MIN: 5.78 / MAX: 7.57MIN: 5.78 / MAX: 7.75MIN: 5.73 / MAX: 7.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: efficientnet-b01233691215SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 311.3111.3111.29MIN: 10.25 / MAX: 36.48MIN: 10.25 / MAX: 21.66MIN: 10.2 / MAX: 20.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: blazeface1230.46580.93161.39741.86322.329SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 32.072.072.07MIN: 1.87 / MAX: 2.96MIN: 1.87 / MAX: 3.16MIN: 1.85 / MAX: 3.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: googlenet123612182430SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 324.9424.7924.82MIN: 23.78 / MAX: 36.73MIN: 23.71 / MAX: 41.62MIN: 23.71 / MAX: 57.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: vgg16123306090120150SE +/- 0.48, N = 3SE +/- 0.43, N = 3SE +/- 0.26, N = 3113.17112.93112.72MIN: 109.26 / MAX: 173.8MIN: 109.49 / MAX: 184.22MIN: 109.78 / MAX: 148.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet18123612182430SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 324.8724.7724.73MIN: 23.65 / MAX: 34.58MIN: 23.62 / MAX: 42.74MIN: 23.63 / MAX: 35.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: alexnet123510152025SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 318.8818.4419.00MIN: 17.74 / MAX: 29.45MIN: 17.09 / MAX: 71.44MIN: 17.82 / MAX: 43.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet501231020304050SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.10, N = 346.1646.1546.29MIN: 44.83 / MAX: 58.1MIN: 44.83 / MAX: 68.77MIN: 44.95 / MAX: 57.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: yolov4-tiny1231020304050SE +/- 0.12, N = 3SE +/- 0.40, N = 3SE +/- 0.55, N = 345.5046.1645.84MIN: 44.21 / MAX: 56.39MIN: 44.35 / MAX: 64.24MIN: 44.26 / MAX: 55.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: squeezenet_ssd123816243240SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.19, N = 333.0032.8432.90MIN: 31.56 / MAX: 67.66MIN: 31.13 / MAX: 65.65MIN: 31.49 / MAX: 59.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: regnety_400m1233691215SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 312.6212.5412.56MIN: 11.69 / MAX: 23.53MIN: 11.58 / MAX: 13.31MIN: 11.6 / MAX: 22.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1237001400210028003500SE +/- 7.58, N = 3SE +/- 6.26, N = 3SE +/- 3.47, N = 33495.183491.263484.78MIN: 3408.49 / MAX: 3598.11MIN: 3398.45 / MAX: 3592.6MIN: 3402 / MAX: 3575.851. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212360120180240300SE +/- 0.09, N = 3SE +/- 0.41, N = 3SE +/- 0.87, N = 3282.48280.64280.44MIN: 276.85 / MAX: 289.71MIN: 276.31 / MAX: 286.72MIN: 276.47 / MAX: 287.421. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231632486480SE +/- 0.15, N = 3SE +/- 0.43, N = 3SE +/- 0.19, N = 371.4771.6471.29MIN: 70.88 / MAX: 72.03MIN: 70.27 / MAX: 72.9MIN: 70.6 / MAX: 71.871. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112360120180240300SE +/- 0.07, N = 3SE +/- 0.45, N = 3SE +/- 0.14, N = 3252.49252.78252.98MIN: 251.98 / MAX: 253.8MIN: 251.65 / MAX: 257.27MIN: 251.96 / MAX: 255.481. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Phoronix Test Suite v10.8.4