ncnn cassie

AMD Ryzen 5 4500U testing with a LENOVO LNVNB161216 (EECN20WW BIOS) and AMD Renoir 512MB on Ubuntu 21.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2107289-IB-NCNNCASSI17&sro.

ncnn cassieProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 5 4500U @ 2.38GHz (6 Cores)LENOVO LNVNB161216 (EECN20WW BIOS)AMD Renoir Root Complex16GB256GB SK hynix HFM256GDHTNI-87A0BAMD Renoir 512MB (1500/400MHz)AMD Renoir Radeon HD AudioRealtek RTL8822CE 802.11ac PCIeUbuntu 21.045.13.0-051300-generic (x86_64)GNOME Shell 3.38.4X Server + Wayland4.6 Mesa 21.2.0-devel (git-c246af0 2021-07-04 hirsute-oibaf-ppa) (LLVM 12.0.0)1.2.182GCC 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: 0x8600102 - ACPI Profile: balanced Java Details- OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)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 cassiencnn: 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_400mcassandra: Readscassandra: Writescassandra: Mixed 1:312325.246.996.054.675.419.281.5723.02107.0223.6817.0341.8139.9236.289.5515.465.566.734.235.7713.451.8912.1862.189.3913.9920.8433.3520.117.721307238142034525.957.026.044.595.369.41.5823.35107.1823.5917.0142.5341.836.679.5514.95.616.624.245.7313.341.9612.1760.289.4413.9720.7225.5221.47.57265062004926.447.126.144.715.469.581.6323.51107.3724.1417.4843.3541.9057.289.7815.405.636.634.345.7713.541.9312.2260.999.5114.0621.2229.7021.407.72178772551317329OpenBenchmarking.org

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenet123612182430SE +/- 0.24, N = 325.2425.9526.44MIN: 24.85 / MAX: 30.18MIN: 25.51 / MAX: 31.01MIN: 25.6 / MAX: 35.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.02, N = 36.997.027.12MIN: 6.85 / MAX: 7.68MIN: 6.89 / MAX: 8.77MIN: 6.89 / MAX: 16.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.05, N = 36.056.046.14MIN: 5.92 / MAX: 8.43MIN: 5.94 / MAX: 9.03MIN: 5.94 / MAX: 10.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v21231.05982.11963.17944.23925.299SE +/- 0.06, N = 34.674.594.71MIN: 4.57 / MAX: 14.52MIN: 4.54 / MAX: 4.85MIN: 4.54 / MAX: 9.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnet1231.22852.4573.68554.9146.1425SE +/- 0.07, N = 35.415.365.46MIN: 5.28 / MAX: 6.81MIN: 5.27 / MAX: 9.51MIN: 5.27 / MAX: 61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b01233691215SE +/- 0.11, N = 39.289.409.58MIN: 9.1 / MAX: 13.65MIN: 9.26 / MAX: 14.67MIN: 9.23 / MAX: 19.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazeface1230.36680.73361.10041.46721.834SE +/- 0.03, N = 31.571.581.63MIN: 1.54 / MAX: 1.66MIN: 1.53 / MAX: 5.56MIN: 1.53 / MAX: 3.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenet123612182430SE +/- 0.23, N = 323.0223.3523.51MIN: 22.74 / MAX: 27.68MIN: 22.88 / MAX: 82.5MIN: 22.86 / MAX: 28.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg1612320406080100SE +/- 0.32, N = 3107.02107.18107.37MIN: 105.55 / MAX: 139.02MIN: 105.94 / MAX: 140.9MIN: 105.16 / MAX: 144.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18123612182430SE +/- 0.25, N = 323.6823.5924.14MIN: 23.44 / MAX: 28.99MIN: 23.32 / MAX: 28.1MIN: 23.21 / MAX: 64.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnet12348121620SE +/- 0.23, N = 317.0317.0117.48MIN: 16.61 / MAX: 26.66MIN: 16.74 / MAX: 20.99MIN: 16.75 / MAX: 41.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet501231020304050SE +/- 0.51, N = 341.8142.5343.35MIN: 41.3 / MAX: 76.09MIN: 42.02 / MAX: 47.44MIN: 41.78 / MAX: 53.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tiny1231020304050SE +/- 0.18, N = 339.9241.8041.90MIN: 39.58 / MAX: 44.99MIN: 41.2 / MAX: 51.86MIN: 41.15 / MAX: 51.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssd1231326395265SE +/- 10.36, N = 336.2836.6757.28MIN: 35.92 / MAX: 41.47MIN: 35.8 / MAX: 68.69MIN: 36.05 / MAX: 295.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400m1233691215SE +/- 0.12, N = 39.559.559.78MIN: 9.38 / MAX: 20.04MIN: 9.43 / MAX: 14.1MIN: 9.42 / MAX: 19.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenet12348121620SE +/- 0.30, N = 1515.4614.9015.40MIN: 13.97 / MAX: 27.92MIN: 13.98 / MAX: 31.02MIN: 13.53 / MAX: 34.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21231.26682.53363.80045.06726.334SE +/- 0.02, N = 155.565.615.63MIN: 5.01 / MAX: 7.86MIN: 5.16 / MAX: 6.49MIN: 4.98 / MAX: 20.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.01, N = 156.736.626.63MIN: 6.07 / MAX: 7.67MIN: 6.06 / MAX: 7.45MIN: 5.9 / MAX: 17.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v21230.97651.9532.92953.9064.8825SE +/- 0.02, N = 154.234.244.34MIN: 3.68 / MAX: 5.32MIN: 3.66 / MAX: 5.38MIN: 3.58 / MAX: 19.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnet1231.29832.59663.89495.19326.4915SE +/- 0.02, N = 155.775.735.77MIN: 5.19 / MAX: 6.76MIN: 5.29 / MAX: 6.38MIN: 5.04 / MAX: 22.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b01233691215SE +/- 0.05, N = 1513.4513.3413.54MIN: 13.02 / MAX: 14.46MIN: 12.95 / MAX: 14.11MIN: 12.78 / MAX: 32.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazeface1230.4410.8821.3231.7642.205SE +/- 0.01, N = 151.891.961.93MIN: 1.64 / MAX: 2.2MIN: 1.7 / MAX: 2.27MIN: 1.59 / MAX: 10.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenet1233691215SE +/- 0.07, N = 1512.1812.1712.22MIN: 11.56 / MAX: 32.88MIN: 11.66 / MAX: 13.09MIN: 11.32 / MAX: 32.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg161231428425670SE +/- 0.62, N = 1562.1860.2860.99MIN: 59.46 / MAX: 99.55MIN: 59.21 / MAX: 81.12MIN: 59.11 / MAX: 100.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet181233691215SE +/- 0.08, N = 159.399.449.51MIN: 8.85 / MAX: 10.52MIN: 8.9 / MAX: 10.42MIN: 8.77 / MAX: 29.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnet12348121620SE +/- 0.04, N = 1513.9913.9714.06MIN: 13.6 / MAX: 14.6MIN: 13.52 / MAX: 14.72MIN: 13.39 / MAX: 31.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50123510152025SE +/- 0.26, N = 1520.8420.7221.22MIN: 20.09 / MAX: 21.74MIN: 19.96 / MAX: 21.49MIN: 19.96 / MAX: 44.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tiny123816243240SE +/- 0.88, N = 1533.3525.5229.70MIN: 25.22 / MAX: 52.36MIN: 24 / MAX: 44.66MIN: 23.87 / MAX: 69.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssd123510152025SE +/- 0.31, N = 1520.1121.4021.40MIN: 19.51 / MAX: 34.24MIN: 20.87 / MAX: 27.83MIN: 19.2 / MAX: 51.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400m123246810SE +/- 0.03, N = 157.707.577.72MIN: 6.97 / MAX: 8.56MIN: 6.93 / MAX: 8.38MIN: 6.81 / MAX: 24.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Apache Cassandra

Test: Reads

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: Reads135K10K15K20K25KSE +/- 792.84, N = 92130717877

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: Writes1236K12K18K24K30KSE +/- 214.60, N = 3238142650625513

Apache Cassandra

Test: Mixed 1:3

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: Mixed 1:31234K8K12K16K20KSE +/- 368.44, N = 12203452004917329


Phoronix Test Suite v10.8.4