ncnn 0905

2 x Hygon C86 7280 32-core testing with a Suma R6240H0 62DB32 v24002826 (CXYH051031 BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2409067-NE-NCNN0905439&grw.

ncnn 0905ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen Resolution2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H02 x Hygon C86 7280 32-core (64 Cores / 128 Threads)Suma R6240H0 62DB32 v24002826 (CXYH051031 BIOS)Chengdu Haiguang IC Design Root Complex1008GB256GB MR9361-8i + 1920GB MR9361-8i + 12001GB MR9361-8iASPEED2 x Intel I350 + 4 x Mellanox MT27710Ubuntu 24.046.8.0-41-generic (x86_64)GCC 13.2.0ext41024x768OpenBenchmarking.org- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-gcn/usr --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 - CPU Microcode: 0x80901047- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines; IBPB: conditional; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

ncnn 0905ncnn: 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: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDet2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H050.7326.6725.7132.1723.8536.7215.0358.2798.3135.0828.4371.5950.7367.5959.87120.00211.2236.71OpenBenchmarking.org

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenet2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H01122334455SE +/- 0.95, N = 950.73MIN: 45.83 / MAX: 229.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v22 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0612182430SE +/- 0.34, N = 926.67MIN: 23.41 / MAX: 254.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v32 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0612182430SE +/- 0.34, N = 925.71MIN: 23.77 / MAX: 207.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v22 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0714212835SE +/- 0.77, N = 932.17MIN: 29.14 / MAX: 345.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnet2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0612182430SE +/- 0.38, N = 923.85MIN: 21.13 / MAX: 204.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b02 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0816243240SE +/- 0.53, N = 936.72MIN: 33.27 / MAX: 59.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazeface2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H048121620SE +/- 0.20, N = 915.03MIN: 13.48 / MAX: 96.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenet2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H01326395265SE +/- 1.21, N = 958.27MIN: 50.1 / MAX: 409.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg162 x Hygon C86 7280 32-core - ASPEED - Suma R6240H020406080100SE +/- 2.13, N = 998.31MIN: 72.58 / MAX: 286.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet182 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0816243240SE +/- 0.68, N = 935.08MIN: 30.67 / MAX: 237.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnet2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0714212835SE +/- 0.33, N = 928.43MIN: 25.25 / MAX: 112.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet502 x Hygon C86 7280 32-core - ASPEED - Suma R6240H01632486480SE +/- 1.36, N = 971.59MIN: 63.49 / MAX: 249.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov32 x Hygon C86 7280 32-core - ASPEED - Suma R6240H01122334455SE +/- 0.95, N = 950.73MIN: 45.83 / MAX: 229.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tiny2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H01530456075SE +/- 0.95, N = 967.59MIN: 57.85 / MAX: 220.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssd2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H01326395265SE +/- 1.44, N = 959.87MIN: 53.94 / MAX: 395.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400m2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0306090120150SE +/- 1.35, N = 9120.00MIN: 112.41 / MAX: 1708.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformer2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H050100150200250SE +/- 3.89, N = 9211.22MIN: 151.15 / MAX: 3455.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDet2 x Hygon C86 7280 32-core - ASPEED - Suma R6240H0816243240SE +/- 1.00, N = 936.71MIN: 32.19 / MAX: 358.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.5