testoutputncnn

ARMv8 Cortex-A76 testing on Debian 12 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2406097-NE-2404282NE52&sor&grs.

testoutputncnnProcessorMotherboardMemoryDiskNetworkOSKernelOpenGLCompilerFile-System1ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.0ARMv8 Cortex-A76 @ 2.40GHz (4 Cores)Raspberry Pi 5 Model B Rev 1.08GB31GB SD32GDevice 1de4:0001Debian 126.6.28+rpt-rpi-2712 (aarch64)4.5 Mesa 23.2.1-1~bpo12+rpt3 (LLVM 15.0.6 128 bits)GCC 12.2.0ext44096MB6.6.31+rpt-rpi-2712 (aarch64)OpenBenchmarking.orgKernel Details- cfg80211.ieee80211_regdom=USCompiler Details- --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 Processor Details- Scaling Governor: cpufreq-dt ondemandSecurity Details- 1: 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 - ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.0: 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: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected

testoutputncnnncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov31ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.0155.1712.3938.3752.7252.5531.068.7614.248.135.5443.8922.3824.791.610.563.34600.40136.0811.2535.0148.5848.7328.828.1313.267.585.1741.0320.9823.321.5610.343.30598.1341.03OpenBenchmarking.org

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01306090120150SE +/- 0.57, N = 3SE +/- 0.11, N = 3136.08155.17MIN: 132.28 / MAX: 172.42MIN: 151.67 / MAX: 190.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.013691215SE +/- 0.10, N = 3SE +/- 0.06, N = 311.2512.39MIN: 10.81 / MAX: 18.3MIN: 11.98 / MAX: 24.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01918273645SE +/- 0.16, N = 3SE +/- 0.10, N = 335.0138.37MIN: 34.15 / MAX: 72.64MIN: 37.76 / MAX: 45.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.011224364860SE +/- 0.31, N = 3SE +/- 0.07, N = 348.5852.72MIN: 47.56 / MAX: 85.36MIN: 51.92 / MAX: 86.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.011224364860SE +/- 0.32, N = 3SE +/- 0.13, N = 348.7352.55MIN: 47.39 / MAX: 87.54MIN: 51.41 / MAX: 93.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01714212835SE +/- 0.18, N = 3SE +/- 0.21, N = 328.8231.06MIN: 27.94 / MAX: 61.36MIN: 30.13 / MAX: 62.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01246810SE +/- 0.02, N = 3SE +/- 0.01, N = 38.138.76MIN: 7.86 / MAX: 40.21MIN: 8.49 / MAX: 18.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.0148121620SE +/- 0.13, N = 3SE +/- 0.06, N = 313.2614.24MIN: 12.8 / MAX: 34.05MIN: 13.8 / MAX: 53.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01246810SE +/- 0.06, N = 3SE +/- 0.03, N = 37.588.13MIN: 7.27 / MAX: 33.09MIN: 7.74 / MAX: 16.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.011.24652.4933.73954.9866.2325SE +/- 0.05, N = 3SE +/- 0.07, N = 35.175.54MIN: 4.89 / MAX: 6.04MIN: 5.28 / MAX: 14.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.011020304050SE +/- 0.16, N = 3SE +/- 0.14, N = 341.0343.89MIN: 40.31 / MAX: 77.21MIN: 42.94 / MAX: 80.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01510152025SE +/- 0.03, N = 3SE +/- 0.13, N = 320.9822.38MIN: 20.39 / MAX: 35.46MIN: 21.66 / MAX: 31.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01612182430SE +/- 0.09, N = 3SE +/- 0.04, N = 323.3224.79MIN: 22.67 / MAX: 53.59MIN: 24.28 / MAX: 37.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.010.360.721.081.441.8SE +/- 0.01, N = 3SE +/- 0.00, N = 31.561.60MIN: 1.52 / MAX: 1.98MIN: 1.52 / MAX: 10.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.013691215SE +/- 0.07, N = 3SE +/- 0.04, N = 310.3410.56MIN: 10.05 / MAX: 37.4MIN: 10.31 / MAX: 22.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.010.75151.5032.25453.0063.7575SE +/- 0.01, N = 3SE +/- 0.00, N = 33.303.34MIN: 3.25 / MAX: 3.9MIN: 3.29 / MAX: 4.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.01130260390520650SE +/- 3.62, N = 3SE +/- 1.09, N = 3598.13600.40MIN: 563.05 / MAX: 652.35MIN: 573.15 / MAX: 645.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3ARMv8 Cortex-A76 - - Raspberry Pi 5 Model B Rev 1.0918273645SE +/- 0.16, N = 341.03MIN: 40.31 / MAX: 77.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread


Phoronix Test Suite v10.8.4