ncnn 103 renoir

AMD Ryzen 5 4500U testing with a LENOVO LNVNB161216 (EECN20WW BIOS) and AMD Renoir 512MB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2009259-FI-NCNN103RE45.

ncnn 103 renoirProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution12\3AMD Ryzen 5 4500U @ 2.38GHz (6 Cores)LENOVO LNVNB161216 (EECN20WW BIOS)AMD Renoir Root Complex16GB256GB SKHynix_HFM256GDHTNI-87A0BAMD Renoir 512MB (1500/400MHz)AMD Device 1637Realtek RTL8822CE 802.11ac PCIeUbuntu 20.045.9.0-050900rc6-generic (x86_64) 20200920GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.8 (LLVM 10.0.0)1.2.128GCC 9.3.0ext41920x1080OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --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 - CPU Microcode: 0x8600102 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: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ncnn 103 renoirncnn: CPU - squeezenetncnn: 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: Vulkan GPU - squeezenetncnn: 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-tiny12\325.4027.968.337.665.647.1311.712.1230.69109.7827.8622.8351.5247.7858.3540.2313.8514.748.5814.7826.283.0145.12341.4543.9041.0394.0088.4727.0527.838.728.006.087.5612.182.2334.42109.9729.6522.5955.5848.0259.0941.3413.9214.748.6314.8826.143.0245.10341.6143.9740.9694.0288.6025.5527.868.317.705.597.0211.011.9932.06110.1428.3522.7051.4747.5559.5541.3413.8514.848.7014.8026.152.9145.08341.5143.9341.1594.1588.14OpenBenchmarking.org

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet12\3612182430SE +/- 0.82, N = 15SE +/- 1.29, N = 15SE +/- 0.50, N = 1225.4027.0525.55MIN: 22.3 / MAX: 78.12MIN: 22.56 / MAX: 74.76MIN: 22.78 / MAX: 82.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet12\3714212835SE +/- 0.20, N = 15SE +/- 0.31, N = 15SE +/- 0.14, N = 1227.9627.8327.86MIN: 25.24 / MAX: 84.63MIN: 25.22 / MAX: 90.5MIN: 25.33 / MAX: 80.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v212\3246810SE +/- 0.45, N = 15SE +/- 0.63, N = 15SE +/- 0.54, N = 128.338.728.31MIN: 6.85 / MAX: 52.01MIN: 6.91 / MAX: 28.78MIN: 7.03 / MAX: 75.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v312\3246810SE +/- 0.57, N = 15SE +/- 0.70, N = 15SE +/- 0.68, N = 127.668.007.70MIN: 5.86 / MAX: 42.15MIN: 5.96 / MAX: 27.25MIN: 6.14 / MAX: 35.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v212\3246810SE +/- 0.51, N = 15SE +/- 0.59, N = 15SE +/- 0.56, N = 125.646.085.59MIN: 4 / MAX: 40.47MIN: 4.05 / MAX: 45.96MIN: 4.15 / MAX: 41.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet12\3246810SE +/- 0.61, N = 15SE +/- 0.70, N = 15SE +/- 0.59, N = 117.137.567.02MIN: 5.37 / MAX: 39.85MIN: 5.44 / MAX: 65.85MIN: 5.41 / MAX: 56.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b012\33691215SE +/- 0.88, N = 15SE +/- 1.06, N = 15SE +/- 0.81, N = 1211.7112.1811.01MIN: 9.08 / MAX: 64.34MIN: 9.12 / MAX: 56MIN: 9.23 / MAX: 28.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface12\30.50181.00361.50542.00722.509SE +/- 0.23, N = 15SE +/- 0.26, N = 15SE +/- 0.24, N = 122.122.231.99MIN: 1.4 / MAX: 25.87MIN: 1.41 / MAX: 18.29MIN: 1.4 / MAX: 12.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet12\3816243240SE +/- 2.14, N = 15SE +/- 2.90, N = 15SE +/- 2.58, N = 1230.6934.4232.06MIN: 25.02 / MAX: 78.91MIN: 24.98 / MAX: 84.54MIN: 25.06 / MAX: 87.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg1612\320406080100SE +/- 0.16, N = 15SE +/- 0.11, N = 15SE +/- 0.12, N = 12109.78109.97110.14MIN: 107.35 / MAX: 165.01MIN: 107.94 / MAX: 171.02MIN: 108.22 / MAX: 166.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet1812\3714212835SE +/- 0.45, N = 15SE +/- 1.38, N = 15SE +/- 0.80, N = 1227.8629.6528.35MIN: 25.55 / MAX: 73.66MIN: 25.78 / MAX: 103.77MIN: 25.75 / MAX: 67.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet12\3510152025SE +/- 0.08, N = 15SE +/- 0.06, N = 15SE +/- 0.12, N = 1222.8322.5922.70MIN: 21.56 / MAX: 55.14MIN: 21.5 / MAX: 72.7MIN: 21.54 / MAX: 81.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet5012\31224364860SE +/- 2.30, N = 15SE +/- 3.32, N = 15SE +/- 1.51, N = 1251.5255.5851.47MIN: 43.66 / MAX: 127.16MIN: 43.74 / MAX: 150.58MIN: 43.61 / MAX: 114.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny12\31122334455SE +/- 0.11, N = 15SE +/- 0.60, N = 15SE +/- 0.24, N = 1247.7848.0247.55MIN: 44.57 / MAX: 106.09MIN: 44.37 / MAX: 106.39MIN: 44.49 / MAX: 103.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet12\31326395265SE +/- 0.28, N = 3SE +/- 0.52, N = 3SE +/- 0.36, N = 358.3559.0959.55MIN: 54.44 / MAX: 82.33MIN: 54.96 / MAX: 82.53MIN: 55.21 / MAX: 89.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet12\3918273645SE +/- 0.14, N = 3SE +/- 0.34, N = 3SE +/- 0.44, N = 340.2341.3441.34MIN: 37.07 / MAX: 49.33MIN: 36.51 / MAX: 63.34MIN: 36.53 / MAX: 63.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v212\348121620SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 313.8513.9213.85MIN: 13.53 / MAX: 14.73MIN: 13.4 / MAX: 14.63MIN: 13.5 / MAX: 35.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v312\348121620SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 314.7414.7414.84MIN: 14.31 / MAX: 15.67MIN: 14.35 / MAX: 16.12MIN: 14.43 / MAX: 16.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v212\3246810SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 38.588.638.70MIN: 8.01 / MAX: 9.73MIN: 8.17 / MAX: 9.48MIN: 8.23 / MAX: 27.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet12\348121620SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 214.7814.8814.80MIN: 14.42 / MAX: 15.55MIN: 14.5 / MAX: 37.09MIN: 14.5 / MAX: 15.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b012\3612182430SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 326.2826.1426.15MIN: 25.83 / MAX: 27.38MIN: 25.77 / MAX: 27.43MIN: 25.76 / MAX: 49.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface12\30.67951.3592.03852.7183.3975SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 33.013.022.91MIN: 2.85 / MAX: 3.13MIN: 2.86 / MAX: 3.56MIN: 2.85 / MAX: 3.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet12\31020304050SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 345.1245.1045.08MIN: 44.57 / MAX: 46.4MIN: 44.47 / MAX: 45.95MIN: 44.43 / MAX: 46.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg1612\370140210280350SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3341.45341.61341.51MIN: 339.9 / MAX: 342.89MIN: 339.88 / MAX: 364.66MIN: 339.68 / MAX: 362.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet1812\31020304050SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 343.9043.9743.93MIN: 42.99 / MAX: 44.76MIN: 42.99 / MAX: 65.03MIN: 42.94 / MAX: 45.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet12\3918273645SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 341.0340.9641.15MIN: 38.21 / MAX: 43.48MIN: 38.03 / MAX: 62.17MIN: 38.4 / MAX: 64.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet5012\320406080100SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 394.0094.0294.15MIN: 92.98 / MAX: 95.21MIN: 92.75 / MAX: 95.06MIN: 93.06 / MAX: 116.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny12\320406080100SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.61, N = 388.4788.6088.14MIN: 81.35 / MAX: 178.76MIN: 82.72 / MAX: 112.4MIN: 81.92 / MAX: 112.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4