ncnn-test

Intel Core i9-10900F testing with a Alienware 0N43JM (1.0.5 BIOS) and NVIDIA GeForce RTX 2080 Ti Rev. A 11GB on Fedora 34 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2204234-ASAL-NCNNTES14.

ncnn-testProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverFile-SystemScreen Resolutionr11Intel Core i9-10900F @ 5.20GHz (10 Cores / 20 Threads)Alienware 0N43JM (1.0.5 BIOS)Intel Comet Lake PCH64GB1024GB SK hynix PC711 NVMe 1TB + 1000GB Western Digital WD10EZEX-75W + 8GB Cruzer BladeNVIDIA GeForce RTX 2080 Ti Rev. A 11GBRealtek ALC38612 x DELL E2420H + DELL P2417HRealtek Killer E3000 2.5GbE + Intel Comet Lake PCH CNVi WiFiFedora 345.13.19-200.fc34.x86_64 (x86_64)GNOME Shell 40.9X Server 1.20.11NVIDIAxfs800x600OpenBenchmarking.org- Transparent Huge Pages: madvise- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xec- itlb_multihit: KVM: Mitigation of VMX disabled + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ncnn-testncnn: 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 GPUr1116.274.173.423.303.585.811.6213.1158.4514.3812.1524.4823.6819.088.73OpenBenchmarking.org

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetr1148121620SE +/- 0.06, N = 316.27MIN: 15.95 / MAX: 26.81. (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-v2r110.93831.87662.81493.75324.6915SE +/- 0.02, N = 34.17MIN: 4.07 / MAX: 11.181. (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-v3r110.76951.5392.30853.0783.8475SE +/- 0.02, N = 33.42MIN: 3.35 / MAX: 3.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2r110.74251.4852.22752.973.7125SE +/- 0.02, N = 33.30MIN: 3.23 / MAX: 4.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetr110.80551.6112.41653.2224.0275SE +/- 0.19, N = 33.58MIN: 3.16 / MAX: 24.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0r111.30732.61463.92195.22926.5365SE +/- 0.25, N = 35.81MIN: 5.26 / MAX: 14.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefacer110.36450.7291.09351.4581.8225SE +/- 0.09, N = 31.62MIN: 1.4 / MAX: 1.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetr113691215SE +/- 0.66, N = 313.11MIN: 11.69 / MAX: 22.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16r111326395265SE +/- 0.32, N = 358.45MIN: 57.15 / MAX: 107.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18r1148121620SE +/- 0.46, N = 314.38MIN: 13.25 / MAX: 23.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetr113691215SE +/- 0.17, N = 312.15MIN: 11.7 / MAX: 33.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50r11612182430SE +/- 0.30, N = 324.48MIN: 21.94 / MAX: 33.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyr11612182430SE +/- 0.22, N = 323.68MIN: 23.12 / MAX: 41.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdr11510152025SE +/- 0.14, N = 319.08MIN: 18.53 / MAX: 26.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mr11246810SE +/- 0.34, N = 38.73MIN: 7.96 / MAX: 16.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Phoronix Test Suite v10.8.4