3400g nn

AMD Ryzen 5 3400G testing with a ASUS PRIME B450M-A (2006 BIOS) and ASUS AMD Picasso on Ubuntu 19.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2106184-IB-3400GNN2727&grt.

3400g nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 5 3400G @ 3.70GHz (4 Cores / 8 Threads)ASUS PRIME B450M-A (2006 BIOS)AMD Raven/Raven22 x 8192 MB DDR4-3000MT/s CRUCIAL29GB INTEL MEMPEK1W032GA + 4 x 6001GB Seagate ST6000VN0033-2EEASUS AMD Picasso (1400/1500MHz)AMD Raven/Raven2/FenghuangSyncMasterRealtek RTL8111/8168/8411Ubuntu 19.105.3.0-46-generic (x86_64)GNOME Shell 3.34.1X Server1.1.107GCC 9.2.1 20191008ext41280x800OpenBenchmarking.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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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 ondemand (Boost: Enabled) - CPU Microcode: 0x8108109Security 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 STIBP: disabled RSB filling + tsx_async_abort: Not affected

3400g 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 v1.11232.4725.76054.3509.6845.9986.87969.88734.408.607.325.168.2612.541.8826.08100.2124.0320.5551.5948.2536.1813.6134.518.597.335.157.5912.632.0025.28100.2924.1820.7851.6048.1134.7714.593717.757299.83071.803260.0562.4735.85954.3819.6275.8336.86270.67735.208.267.285.137.5212.551.9025.85101.0624.7320.3051.6048.5734.9813.6234.358.207.255.157.7412.651.8926.37100.1024.0120.8351.5447.8034.9414.243733.171300.30071.579259.6582.4835.98854.7449.6785.8936.95270.18632.748.707.535.187.7912.732.0825.32101.1524.0920.4652.6648.5935.2213.6734.778.547.345.177.9712.782.0225.41101.5324.0720.9051.8848.8435.3913.763733.516301.70672.507260.010OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV31230.55871.11741.67612.23482.7935SE +/- 0.006, N = 3SE +/- 0.004, N = 3SE +/- 0.013, N = 32.4722.4732.483MIN: 2.43 / MAX: 5.18MIN: 2.44 / MAX: 4.87MIN: 2.43 / MAX: 2.681. (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: squeezenetv1.11231.34732.69464.04195.38926.7365SE +/- 0.011, N = 3SE +/- 0.132, N = 3SE +/- 0.121, N = 35.7605.8595.988MIN: 5.67 / MAX: 9.81MIN: 5.62 / MAX: 63.87MIN: 5.62 / MAX: 66.451. (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-v2-501231224364860SE +/- 0.30, N = 3SE +/- 0.02, N = 3SE +/- 0.77, N = 354.3554.3854.74MIN: 53.19 / MAX: 154.56MIN: 53.2 / MAX: 146.41MIN: 53.14 / MAX: 145.951. (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: SqueezeNetV1.01233691215SE +/- 0.087, N = 3SE +/- 0.071, N = 3SE +/- 0.126, N = 39.6849.6279.678MIN: 9.35 / MAX: 84.73MIN: 9.42 / MAX: 55.33MIN: 9.42 / MAX: 82.91. (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: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_2241231.34962.69924.04885.39846.748SE +/- 0.169, N = 3SE +/- 0.008, N = 3SE +/- 0.044, N = 35.9985.8335.893MIN: 5.77 / MAX: 96.39MIN: 5.76 / MAX: 8.26MIN: 5.77 / MAX: 9.911. (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-v1-1.0123246810SE +/- 0.018, N = 3SE +/- 0.014, N = 3SE +/- 0.077, N = 36.8796.8626.952MIN: 6.8 / MAX: 15.25MIN: 6.8 / MAX: 10.9MIN: 6.79 / MAX: 63.271. (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-v31231632486480SE +/- 0.76, N = 3SE +/- 1.02, N = 3SE +/- 0.67, N = 369.8970.6870.19MIN: 67.59 / MAX: 180.29MIN: 67.51 / MAX: 204.3MIN: 67.44 / MAX: 207.771. (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

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet123816243240SE +/- 0.27, N = 3SE +/- 0.26, N = 3SE +/- 0.55, N = 334.4035.2032.74MIN: 31.82 / MAX: 124.12MIN: 31.77 / MAX: 121.37MIN: 31.85 / MAX: 36.461. (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 +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.22, N = 38.608.268.70MIN: 8.18 / MAX: 8.88MIN: 8.12 / MAX: 10.62MIN: 8.15 / MAX: 13.271. (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 +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.16, N = 37.327.287.53MIN: 7.2 / MAX: 7.61MIN: 7.15 / MAX: 7.65MIN: 7.18 / MAX: 15.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21231.16552.3313.49654.6625.8275SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 35.165.135.18MIN: 5.09 / MAX: 6.53MIN: 5.06 / MAX: 5.21MIN: 5.08 / MAX: 5.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810SE +/- 0.68, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 38.267.527.79MIN: 7.43 / MAX: 86.05MIN: 7.35 / MAX: 7.72MIN: 7.4 / MAX: 10.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.25, N = 312.5412.5512.73MIN: 12.19 / MAX: 13.12MIN: 12.1 / MAX: 13.74MIN: 12.18 / MAX: 13.251. (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 +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 31.881.902.08MIN: 1.82 / MAX: 1.97MIN: 1.86 / MAX: 1.99MIN: 1.82 / MAX: 2.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet123612182430SE +/- 1.05, N = 3SE +/- 0.14, N = 3SE +/- 0.22, N = 326.0825.8525.32MIN: 24.77 / MAX: 102.44MIN: 24.81 / MAX: 104.83MIN: 24.72 / MAX: 27.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg1612320406080100SE +/- 0.09, N = 3SE +/- 0.67, N = 3SE +/- 0.65, N = 3100.21101.06101.15MIN: 98.6 / MAX: 110.29MIN: 98.8 / MAX: 187.95MIN: 98.86 / MAX: 184.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18123612182430SE +/- 0.01, N = 3SE +/- 0.63, N = 3SE +/- 0.04, N = 324.0324.7324.09MIN: 23.82 / MAX: 29.33MIN: 23.83 / MAX: 111.94MIN: 23.81 / MAX: 25.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet123510152025SE +/- 0.23, N = 3SE +/- 0.10, N = 3SE +/- 0.35, N = 320.5520.3020.46MIN: 19.92 / MAX: 58.1MIN: 19.9 / MAX: 27.66MIN: 19.92 / MAX: 58.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet501231224364860SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.54, N = 351.5951.6052.66MIN: 51.37 / MAX: 53.6MIN: 51.34 / MAX: 53.45MIN: 51.5 / MAX: 147.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny1231122334455SE +/- 0.18, N = 3SE +/- 0.58, N = 3SE +/- 0.24, N = 348.2548.5748.59MIN: 44.93 / MAX: 54.91MIN: 44.08 / MAX: 126.72MIN: 44.69 / MAX: 118.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123816243240SE +/- 0.61, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 336.1834.9835.22MIN: 34.08 / MAX: 146.4MIN: 34.09 / MAX: 39.61MIN: 34.22 / MAX: 40.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m12348121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 313.6113.6213.67MIN: 13.56 / MAX: 13.9MIN: 13.56 / MAX: 13.94MIN: 13.54 / MAX: 14.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mobilenet123816243240SE +/- 0.40, N = 3SE +/- 0.28, N = 3SE +/- 0.51, N = 434.5134.3534.77MIN: 31.77 / MAX: 127.76MIN: 31.68 / MAX: 122.44MIN: 31.88 / MAX: 153.341. (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 +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 48.598.208.54MIN: 8.18 / MAX: 9.16MIN: 8.1 / MAX: 9.19MIN: 8.21 / MAX: 8.91. (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 +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 47.337.257.34MIN: 7.19 / MAX: 7.47MIN: 7.15 / MAX: 11.51MIN: 7.23 / MAX: 7.651. (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-v21231.16332.32663.48994.65325.8165SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 45.155.155.17MIN: 5.09 / MAX: 5.44MIN: 5.05 / MAX: 6.21MIN: 5.07 / MAX: 5.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mnasnet123246810SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.25, N = 47.597.747.97MIN: 7.43 / MAX: 7.81MIN: 7.44 / MAX: 13.53MIN: 7.45 / MAX: 52.791. (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 +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 412.6312.6512.78MIN: 12.22 / MAX: 14.26MIN: 12.51 / MAX: 16.18MIN: 12.21 / MAX: 14.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: blazeface1230.45450.9091.36351.8182.2725SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 42.001.892.02MIN: 1.83 / MAX: 3.28MIN: 1.84 / MAX: 1.98MIN: 1.83 / MAX: 2.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: googlenet123612182430SE +/- 0.20, N = 3SE +/- 0.97, N = 3SE +/- 0.31, N = 425.2826.3725.41MIN: 24.76 / MAX: 26.77MIN: 24.67 / MAX: 110.11MIN: 24.78 / MAX: 26.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: vgg1612320406080100SE +/- 0.32, N = 3SE +/- 0.24, N = 3SE +/- 0.69, N = 4100.29100.10101.53MIN: 98.81 / MAX: 181.28MIN: 98.46 / MAX: 184.41MIN: 98.81 / MAX: 203.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet18123612182430SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 424.1824.0124.07MIN: 23.8 / MAX: 77.17MIN: 23.77 / MAX: 25.74MIN: 23.85 / MAX: 29.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: alexnet123510152025SE +/- 0.67, N = 3SE +/- 0.64, N = 3SE +/- 0.36, N = 420.7820.8320.90MIN: 19.93 / MAX: 82.41MIN: 19.83 / MAX: 70.68MIN: 19.94 / MAX: 78.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet501231224364860SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.20, N = 451.6051.5451.88MIN: 51.34 / MAX: 52.32MIN: 51.24 / MAX: 56.94MIN: 51.43 / MAX: 54.661. (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-tiny1231122334455SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.47, N = 448.1147.8048.84MIN: 44.53 / MAX: 55.39MIN: 44 / MAX: 52.65MIN: 44.14 / MAX: 150.181. (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 +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.26, N = 434.7734.9435.39MIN: 34.09 / MAX: 38.83MIN: 34.13 / MAX: 42.12MIN: 34.21 / MAX: 98.391. (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_400m12348121620SE +/- 0.56, N = 3SE +/- 0.61, N = 3SE +/- 0.11, N = 414.5914.2413.76MIN: 13.57 / MAX: 93.11MIN: 13.51 / MAX: 107.31MIN: 13.55 / MAX: 15.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1238001600240032004000SE +/- 2.46, N = 3SE +/- 0.92, N = 3SE +/- 11.15, N = 33717.763733.173733.52MIN: 3634.62 / MAX: 3859.41MIN: 3622.3 / MAX: 3911.91MIN: 3643.81 / MAX: 3873.561. (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 v212370140210280350SE +/- 0.44, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3299.83300.30301.71MIN: 290.93 / MAX: 313.93MIN: 291.46 / MAX: 337.46MIN: 292.13 / MAX: 315.721. (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 +/- 0.83, N = 3SE +/- 0.40, N = 3SE +/- 0.27, N = 371.8071.5872.51MIN: 68.91 / MAX: 92.69MIN: 68.17 / MAX: 91.35MIN: 69.84 / MAX: 91.761. (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 +/- 0.65, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 3260.06259.66260.01MIN: 257.94 / MAX: 335.11MIN: 258.41 / MAX: 274.91MIN: 259.34 / MAX: 276.81. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Phoronix Test Suite v10.8.4