hp dev one mnn ncnn

AMD Ryzen 7 PRO 5850U testing with a HP 8A78 (F.04 BIOS) and AMD Cezanne 512MB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208132-PTS-HPDEVONE31&grt.

hp dev one mnn ncnnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCAMD Ryzen 7 PRO 5850U @ 1.90GHz (8 Cores / 16 Threads)HP 8A78 (F.04 BIOS)AMD Renoir/Cezanne16GB1024GB SK hynix PC711 HFS001TDE9X073NAMD Cezanne 512MB (2000/400MHz)AMD Renoir Radeon HD AudioRealtek RTL8822CE 802.11ac PCIeUbuntu 22.045.19.0-051900rc7-generic (x86_64)GNOME Shell 42.2X Server + Wayland4.6 Mesa 22.0.5 (LLVM 13.0.1 DRM 3.47)1.3.204GCC 11.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-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: 0xa50000c Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

hp dev one mnn ncnnmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: 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: CPU - vision_transformerncnn: CPU - FastestDetncnn: 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_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetABC1.5403.11026.1866.0713.0302.91635.85115.764.113.322.653.256.520.9112.7761.2911.639.8022.2525.7318.508.29230.003.2611.093.563.802.633.4510.301.828.2027.075.956.7213.0018.8415.725.05588.874.011.5553.14026.2366.1153.0572.93136.01215.834.163.302.733.306.560.9112.6961.5611.369.7822.2325.5018.408.32231.453.2110.883.443.772.653.4810.231.888.5827.115.626.8212.7419.1615.684.87589.034.141.5463.11326.3106.0953.0092.91836.06215.304.293.412.643.496.630.9612.9461.4211.649.8722.4925.4118.378.31231.243.2710.993.533.782.623.5410.391.878.9427.235.926.8813.3118.9315.735.03592.193.95OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC0.34990.69981.04971.39961.7495SE +/- 0.013, N = 3SE +/- 0.008, N = 3SE +/- 0.001, N = 31.5401.5551.546MIN: 1.47 / MAX: 6.46MIN: 1.49 / MAX: 17.85MIN: 1.48 / MAX: 16.321. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABC0.70651.4132.11952.8263.5325SE +/- 0.046, N = 3SE +/- 0.053, N = 3SE +/- 0.037, N = 33.1103.1403.113MIN: 2.82 / MAX: 7.63MIN: 2.8 / MAX: 7.78MIN: 2.83 / MAX: 17.361. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC612182430SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 326.1926.2426.31MIN: 25.22 / MAX: 41.46MIN: 25.21 / MAX: 40.76MIN: 25.35 / MAX: 41.291. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0ABC246810SE +/- 0.014, N = 3SE +/- 0.038, N = 3SE +/- 0.016, N = 36.0716.1156.095MIN: 5.75 / MAX: 22.06MIN: 5.83 / MAX: 10.78MIN: 5.85 / MAX: 21.051. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224ABC0.68781.37562.06342.75123.439SE +/- 0.045, N = 3SE +/- 0.029, N = 3SE +/- 0.011, N = 33.0303.0573.009MIN: 2.83 / MAX: 19.33MIN: 2.87 / MAX: 19.5MIN: 2.85 / MAX: 12.581. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0ABC0.65951.3191.97852.6383.2975SE +/- 0.010, N = 3SE +/- 0.016, N = 3SE +/- 0.004, N = 32.9162.9312.918MIN: 2.73 / MAX: 19.55MIN: 2.77 / MAX: 19.44MIN: 2.79 / MAX: 11.131. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3ABC816243240SE +/- 0.24, N = 3SE +/- 0.25, N = 3SE +/- 0.18, N = 335.8536.0136.06MIN: 32.74 / MAX: 51.07MIN: 32.7 / MAX: 53.04MIN: 33.17 / MAX: 55.191. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC48121620SE +/- 0.15, N = 3SE +/- 0.23, N = 3SE +/- 0.17, N = 315.7615.8315.30MIN: 14.75 / MAX: 28.99MIN: 14.55 / MAX: 27.15MIN: 14.41 / MAX: 26.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ABC0.96531.93062.89593.86124.8265SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 34.114.164.29MIN: 3.88 / MAX: 8.26MIN: 3.88 / MAX: 15.77MIN: 3.89 / MAX: 8.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3ABC0.76731.53462.30193.06923.8365SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 33.323.303.41MIN: 3.11 / MAX: 7.73MIN: 3.12 / MAX: 7.89MIN: 3.12 / MAX: 7.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC0.61431.22861.84292.45723.0715SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 32.652.732.64MIN: 2.47 / MAX: 6.83MIN: 2.58 / MAX: 6.79MIN: 2.48 / MAX: 6.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC0.78531.57062.35593.14123.9265SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.21, N = 23.253.303.49MIN: 2.96 / MAX: 8.17MIN: 2.96 / MAX: 11.21MIN: 3 / MAX: 7.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC246810SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 36.526.566.63MIN: 6.26 / MAX: 16.65MIN: 6.27 / MAX: 20.14MIN: 6.28 / MAX: 10.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC0.2160.4320.6480.8641.08SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 30.910.910.96MIN: 0.86 / MAX: 5.42MIN: 0.86 / MAX: 4.21MIN: 0.86 / MAX: 4.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC3691215SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.25, N = 312.7712.6912.94MIN: 12.19 / MAX: 20.18MIN: 12.16 / MAX: 24.09MIN: 12.16 / MAX: 25.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC1428425670SE +/- 0.19, N = 3SE +/- 0.21, N = 3SE +/- 0.29, N = 361.2961.5661.42MIN: 59.89 / MAX: 74.13MIN: 59.87 / MAX: 74.67MIN: 59.85 / MAX: 80.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC3691215SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 0.29, N = 311.6311.3611.64MIN: 10.95 / MAX: 24.9MIN: 10.95 / MAX: 26.08MIN: 10.94 / MAX: 22.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC3691215SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 39.809.789.87MIN: 9.26 / MAX: 20.43MIN: 9.27 / MAX: 14.54MIN: 9.25 / MAX: 20.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC510152025SE +/- 0.32, N = 3SE +/- 0.21, N = 3SE +/- 0.11, N = 322.2522.2322.49MIN: 20.96 / MAX: 36.19MIN: 21.17 / MAX: 35.71MIN: 21.31 / MAX: 40.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC612182430SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.18, N = 325.7325.5025.41MIN: 24.27 / MAX: 39.93MIN: 23.9 / MAX: 38.15MIN: 24.26 / MAX: 34.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC510152025SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 318.5018.4018.37MIN: 17.72 / MAX: 28.95MIN: 17.67 / MAX: 23.76MIN: 17.58 / MAX: 26.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC246810SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 38.298.328.31MIN: 7.9 / MAX: 12.53MIN: 7.93 / MAX: 12.94MIN: 7.95 / MAX: 12.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC50100150200250SE +/- 0.28, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3230.00231.45231.24MIN: 225.46 / MAX: 242.01MIN: 227.44 / MAX: 242.39MIN: 227.39 / MAX: 240.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetABC0.73581.47162.20742.94323.679SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 33.263.213.27MIN: 3.01 / MAX: 6.48MIN: 2.96 / MAX: 14.96MIN: 3.02 / MAX: 7.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABC3691215SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 311.0910.8810.99MIN: 9.84 / MAX: 15.36MIN: 9.71 / MAX: 14.4MIN: 9.97 / MAX: 13.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ABC0.8011.6022.4033.2044.005SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 33.563.443.53MIN: 3.26 / MAX: 4.22MIN: 3.23 / MAX: 4.24MIN: 3.23 / MAX: 4.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ABC0.8551.712.5653.424.275SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.803.773.78MIN: 3.55 / MAX: 4.58MIN: 3.59 / MAX: 4.31MIN: 3.51 / MAX: 4.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABC0.59631.19261.78892.38522.9815SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 32.632.652.62MIN: 2.26 / MAX: 3.32MIN: 2.26 / MAX: 3.64MIN: 2.26 / MAX: 4.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABC0.79651.5932.38953.1863.9825SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 23.453.483.54MIN: 3.33 / MAX: 4.15MIN: 3.31 / MAX: 4.17MIN: 3.23 / MAX: 4.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABC3691215SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 310.3010.2310.39MIN: 8.57 / MAX: 11.57MIN: 8.83 / MAX: 11.69MIN: 8.61 / MAX: 11.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABC0.4230.8461.2691.6922.115SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 31.821.881.87MIN: 1.53 / MAX: 4.96MIN: 1.51 / MAX: 5.28MIN: 1.59 / MAX: 2.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABC246810SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.43, N = 38.208.588.94MIN: 7.41 / MAX: 9.84MIN: 7.48 / MAX: 10.45MIN: 7.46 / MAX: 10.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABC612182430SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 327.0727.1127.23MIN: 26.11 / MAX: 28.41MIN: 26.36 / MAX: 30.16MIN: 26.26 / MAX: 30.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABC1.33882.67764.01645.35526.694SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 35.955.625.92MIN: 5.4 / MAX: 7.62MIN: 5.3 / MAX: 7.12MIN: 5.41 / MAX: 7.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABC246810SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 36.726.826.88MIN: 6.2 / MAX: 8.38MIN: 6.24 / MAX: 8.8MIN: 6.26 / MAX: 8.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABC3691215SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 313.0012.7413.31MIN: 11.71 / MAX: 14.71MIN: 11.52 / MAX: 14.22MIN: 11.85 / MAX: 14.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABC510152025SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.09, N = 318.8419.1618.93MIN: 17.57 / MAX: 20.77MIN: 17.74 / MAX: 28.41MIN: 17.55 / MAX: 22.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABC48121620SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 315.7215.6815.73MIN: 13.56 / MAX: 20.72MIN: 13.43 / MAX: 20.03MIN: 13.51 / MAX: 19.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABC1.13632.27263.40894.54525.6815SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 35.054.875.03MIN: 4.51 / MAX: 6.86MIN: 4.51 / MAX: 5.84MIN: 4.67 / MAX: 6.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABC130260390520650SE +/- 4.55, N = 3SE +/- 0.70, N = 3SE +/- 1.96, N = 3588.87589.03592.19MIN: 565.59 / MAX: 626.82MIN: 567.34 / MAX: 640.15MIN: 563.63 / MAX: 634.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABC0.93151.8632.79453.7264.6575SE +/- 0.07, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 34.014.143.95MIN: 3.29 / MAX: 5.05MIN: 3.37 / MAX: 5.59MIN: 3.26 / MAX: 4.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.5