ARMv8 Cortex-A76 testing on Debian 12 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2404281-NE-TESTNCNNC38 testncnncpu - Phoronix Test Suite testncnncpu ARMv8 Cortex-A76 testing on Debian 12 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2404281-NE-TESTNCNNC38&grs .
testncnncpu Processor Motherboard Memory Disk Network OS Kernel OpenGL Compiler File-System cpu test ARMv8 Cortex-A76 @ 2.40GHz (4 Cores) Raspberry Pi 5 Model B Rev 1.0 8GB 31GB SD32G Device 1de4:0001 Debian 12 6.6.28+rpt-rpi-2712 (aarch64) 4.5 Mesa 23.2.1-1~bpo12+rpt3 (LLVM 15.0.6 128 bits) GCC 12.2.0 ext4 OpenBenchmarking.org - cfg80211.ieee80211_regdom=US - --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - Scaling Governor: cpufreq-dt ondemand - 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: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Not affected + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 but not BHB + srbds: Not affected + tsx_async_abort: Not affected
testncnncpu ncnn: CPU - FastestDet ncnn: CPU - vision_transformer ncnn: CPU - regnety_400m ncnn: CPU - squeezenet_ssd ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - alexnet ncnn: CPU - resnet18 ncnn: CPU - vgg16 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - mobilenet cpu test 5.49 603.94 10.48 38.21 53.09 52.57 24.67 22.53 155.73 30.81 1.59 14.08 8.06 3.36 8.71 12.35 43.86 OpenBenchmarking.org
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet cpu test 1.2353 2.4706 3.7059 4.9412 6.1765 SE +/- 0.08, N = 3 5.49 MIN: 5.2 / MAX: 18.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer cpu test 130 260 390 520 650 SE +/- 1.31, N = 3 603.94 MIN: 576.88 / MAX: 648.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m cpu test 3 6 9 12 15 SE +/- 0.05, N = 3 10.48 MIN: 10.2 / MAX: 19.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd cpu test 9 18 27 36 45 SE +/- 0.06, N = 3 38.21 MIN: 37.6 / MAX: 44.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny cpu test 12 24 36 48 60 SE +/- 0.31, N = 2 53.09 MIN: 52.06 / MAX: 88.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 cpu test 12 24 36 48 60 SE +/- 0.10, N = 3 52.57 MIN: 51.09 / MAX: 91.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet cpu test 6 12 18 24 30 SE +/- 0.03, N = 3 24.67 MIN: 24.15 / MAX: 29.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 cpu test 5 10 15 20 25 SE +/- 0.10, N = 3 22.53 MIN: 21.93 / MAX: 61.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 cpu test 30 60 90 120 150 SE +/- 0.43, N = 3 155.73 MIN: 152.26 / MAX: 191.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet cpu test 7 14 21 28 35 SE +/- 0.11, N = 3 30.81 MIN: 30.1 / MAX: 69.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface cpu test 0.3578 0.7156 1.0734 1.4312 1.789 SE +/- 0.01, N = 3 1.59 MIN: 1.51 / MAX: 2.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 cpu test 4 8 12 16 20 SE +/- 0.08, N = 3 14.08 MIN: 13.71 / MAX: 49.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet cpu test 2 4 6 8 10 SE +/- 0.05, N = 3 8.06 MIN: 7.74 / MAX: 18.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 cpu test 0.756 1.512 2.268 3.024 3.78 SE +/- 0.01, N = 3 3.36 MIN: 3.28 / MAX: 4.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 cpu test 2 4 6 8 10 SE +/- 0.05, N = 3 8.71 MIN: 8.42 / MAX: 28.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 cpu test 3 6 9 12 15 SE +/- 0.04, N = 3 12.35 MIN: 11.95 / MAX: 27.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet cpu test 10 20 30 40 50 SE +/- 0.12, N = 3 43.86 MIN: 43.09 / MAX: 79.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.4