ncnn mnn alderlake p

Intel Core i7-1280P testing with a MSI MS-14C6 (E14C6IMS.115 BIOS) and MSI Intel ADL GT2 15GB on Arch rolling via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208135-NE-NCNNMNNAL41&sor.

ncnn mnn alderlake pProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCIntel Core i7-1280P @ 4.80GHz (14 Cores / 20 Threads)MSI MS-14C6 (E14C6IMS.115 BIOS)Intel Alder Lake PCH16GB1024GB Micron_3400_MTFDKBA1T0TFHMSI Intel ADL GT2 15GB (1450MHz)Intel Alder Lake PCH-P HD AudioIntel Alder Lake-P PCH CNVi WiFiArch rolling5.18.16-arch1-1 (x86_64)KDE Plasma 5.25.4X Server 1.21.1.4 + Wayland4.6 Mesa 22.1.41.3.211GCC 12.1.1 20220730ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu Processor Details- Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0x41cSecurity 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ncnn mnn alderlake pmnn: 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 - FastestDetABC3.1056.64454.10410.4085.8567.00156.99116.723.523.254.314.237.981.6713.6544.8810.677.6623.5125.1015.8014.00332.685.6211.724.024.533.054.089.281.1713.3472.6713.1110.8023.2645.6510.026.12508.634.593.0926.84742.59310.5685.7937.06357.27315.853.562.983.353.155.871.6712.9141.2210.157.3222.2223.6714.813.47322.165.3512.273.894.942.694.539.041.1414.573.6312.8911.2623.869.4610.585.42509.424.82.8535.58335.4249.5545.6616.15149.28615.863.592.983.383.155.361.5812.8441.1410.137.3122.2623.5914.7813.35321.3711.653.734.252.573.89.031.1413.6970.6412.8110.7521.4729.829.895.42489.734.33OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3CBA0.69861.39722.09582.79443.493SE +/- 0.034, N = 122.8533.0923.105MIN: 2.68 / MAX: 3.27MIN: 2.82 / MAX: 6.95MIN: 2.64 / MAX: 7.341. (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: squeezenetv1.1CAB246810SE +/- 0.103, N = 125.5836.6446.847MIN: 5.46 / MAX: 5.9MIN: 5.69 / MAX: 12.68MIN: 6.71 / MAX: 11.631. (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-v2-50CBA1224364860SE +/- 1.74, N = 1235.4242.5954.10MIN: 25.55 / MAX: 46.82MIN: 29.52 / MAX: 53.86MIN: 25.35 / MAX: 63.961. (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: SqueezeNetV1.0CAB3691215SE +/- 0.117, N = 129.55410.40810.568MIN: 9.44 / MAX: 10.43MIN: 9.15 / MAX: 15.71MIN: 10.3 / MAX: 14.691. (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_224CBA1.31762.63523.95285.27046.588SE +/- 0.033, N = 125.6615.7935.856MIN: 5.55 / MAX: 6.04MIN: 5.7 / MAX: 6.18MIN: 5.41 / MAX: 26.241. (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-v1-1.0CAB246810SE +/- 0.091, N = 126.1517.0017.063MIN: 5.64 / MAX: 6.56MIN: 6.16 / MAX: 11.52MIN: 6.75 / MAX: 12.291. (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: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3CAB1326395265SE +/- 0.71, N = 1249.2956.9957.27MIN: 48.8 / MAX: 59.33MIN: 50.82 / MAX: 79.99MIN: 51.21 / MAX: 62.841. (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: mobilenetCBA48121620SE +/- 0.17, N = 314.5515.8516.72MIN: 14.24 / MAX: 14.76MIN: 15.19 / MAX: 16.79MIN: 16.2 / MAX: 20.541. (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-v2ACB0.80781.61562.42343.23124.039SE +/- 0.04, N = 33.523.553.56MIN: 3.43 / MAX: 3.77MIN: 3.51 / MAX: 3.69MIN: 3.52 / MAX: 3.761. (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-v3CBA0.73131.46262.19392.92523.6565SE +/- 0.21, N = 32.962.983.25MIN: 2.93 / MAX: 3.11MIN: 2.94 / MAX: 3.33MIN: 2.96 / MAX: 4.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2CBA0.96981.93962.90943.87924.849SE +/- 0.48, N = 33.323.354.31MIN: 3.29 / MAX: 3.42MIN: 3.31 / MAX: 3.43MIN: 3.32 / MAX: 5.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetBCA0.95181.90362.85543.80724.759SE +/- 0.53, N = 33.153.154.23MIN: 3.12 / MAX: 3.38MIN: 3.1 / MAX: 3.32MIN: 3.14 / MAX: 5.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0CBA246810SE +/- 0.05, N = 35.365.877.98MIN: 5.31 / MAX: 5.54MIN: 5.32 / MAX: 7.74MIN: 7.65 / MAX: 8.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceCAB0.37580.75161.12741.50321.879SE +/- 0.02, N = 31.451.671.67MIN: 1.41 / MAX: 1.63MIN: 1.57 / MAX: 2MIN: 1.59 / MAX: 1.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetCBA48121620SE +/- 0.05, N = 311.7312.9113.65MIN: 11.21 / MAX: 20.19MIN: 12.2 / MAX: 24.6MIN: 12.66 / MAX: 14.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16CBA1020304050SE +/- 0.19, N = 337.4041.2244.88MIN: 36.67 / MAX: 37.9MIN: 38.97 / MAX: 41.77MIN: 40.62 / MAX: 52.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18CBA3691215SE +/- 0.02, N = 39.3410.1510.67MIN: 8.94 / MAX: 9.69MIN: 9.65 / MAX: 12.03MIN: 10.06 / MAX: 11.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetCBA246810SE +/- 0.02, N = 36.817.327.66MIN: 6.33 / MAX: 9.78MIN: 6.96 / MAX: 10.38MIN: 7.19 / MAX: 7.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50CBA612182430SE +/- 0.05, N = 320.3722.2223.51MIN: 19.92 / MAX: 20.61MIN: 21.82 / MAX: 22.67MIN: 22.4 / MAX: 24.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyCBA612182430SE +/- 0.22, N = 321.8523.6725.10MIN: 21.44 / MAX: 22.49MIN: 23.36 / MAX: 26.66MIN: 24.42 / MAX: 26.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdCBA48121620SE +/- 0.08, N = 313.7014.8015.80MIN: 13.45 / MAX: 14.42MIN: 14.52 / MAX: 15.22MIN: 15.35 / MAX: 20.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mCBA48121620SE +/- 0.07, N = 312.0613.4714.00MIN: 10.07 / MAX: 12.5MIN: 13.23 / MAX: 14.67MIN: 13.54 / MAX: 24.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerCBA70140210280350SE +/- 3.40, N = 3310.75322.16332.68MIN: 304.99 / MAX: 326.4MIN: 320.38 / MAX: 331.08MIN: 328.62 / MAX: 346.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetBA1.26452.5293.79355.0586.3225SE +/- 0.03, N = 35.355.62MIN: 5.24 / MAX: 5.55MIN: 5.41 / MAX: 6.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetCAB3691215SE +/- 0.28, N = 1211.6511.7212.27MIN: 10.75 / MAX: 13.1MIN: 9.53 / MAX: 24.46MIN: 10.89 / MAX: 19.931. (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-v2CBA0.90451.8092.71353.6184.5225SE +/- 0.14, N = 123.733.894.02MIN: 3.44 / MAX: 3.93MIN: 3.57 / MAX: 4.1MIN: 3.32 / MAX: 6.91. (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-v3CAB1.11152.2233.33454.4465.5575SE +/- 0.12, N = 124.254.534.94MIN: 4.01 / MAX: 6.79MIN: 3.95 / MAX: 6.26MIN: 4.17 / MAX: 7.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2CBA0.68631.37262.05892.74523.4315SE +/- 0.18, N = 122.572.693.05MIN: 2.36 / MAX: 2.89MIN: 2.48 / MAX: 2.99MIN: 2.42 / MAX: 5.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetCAB1.01932.03863.05794.07725.0965SE +/- 0.11, N = 123.804.084.53MIN: 3.6 / MAX: 3.99MIN: 3.57 / MAX: 5.6MIN: 3.68 / MAX: 5.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0CBA3691215SE +/- 0.09, N = 129.039.049.28MIN: 8.83 / MAX: 9.18MIN: 8.85 / MAX: 11.19MIN: 8.19 / MAX: 121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceBCA0.26330.52660.78991.05321.3165SE +/- 0.03, N = 121.141.141.17MIN: 0.98 / MAX: 1.52MIN: 0.98 / MAX: 1.56MIN: 0.92 / MAX: 2.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetACB48121620SE +/- 0.16, N = 1213.3413.6914.50MIN: 10.54 / MAX: 16.98MIN: 12.06 / MAX: 15.98MIN: 12.38 / MAX: 161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16CAB1632486480SE +/- 0.28, N = 1270.6472.6773.63MIN: 63.52 / MAX: 71.69MIN: 43.07 / MAX: 78.48MIN: 69.53 / MAX: 74.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18CBA3691215SE +/- 0.09, N = 1212.8112.8913.11MIN: 12.12 / MAX: 13.13MIN: 12.25 / MAX: 15.33MIN: 11.19 / MAX: 16.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetCAB3691215SE +/- 0.02, N = 1210.7510.8011.26MIN: 10.41 / MAX: 11.1MIN: 7.28 / MAX: 13.01MIN: 7.89 / MAX: 13.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50CAB612182430SE +/- 0.32, N = 1221.4723.2623.80MIN: 20.74 / MAX: 24.51MIN: 20.63 / MAX: 26.52MIN: 21.07 / MAX: 25.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyCAB1530456075SE +/- 3.07, N = 1229.8245.6569.46MIN: 20.72 / MAX: 68.14MIN: 19.69 / MAX: 108.9MIN: 21.1 / MAX: 108.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdCAB3691215SE +/- 0.10, N = 129.8910.0210.58MIN: 9.64 / MAX: 10.47MIN: 9.28 / MAX: 40.24MIN: 9.75 / MAX: 12.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mBCA246810SE +/- 0.21, N = 125.425.426.12MIN: 5.18 / MAX: 8.31MIN: 4.77 / MAX: 7.34MIN: 5.16 / MAX: 9.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerCAB110220330440550SE +/- 3.55, N = 12489.73508.63509.42MIN: 353.26 / MAX: 601.68MIN: 335.21 / MAX: 1310.95MIN: 386.46 / MAX: 1081.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetCAB1.082.163.244.325.4SE +/- 0.17, N = 124.334.594.80MIN: 4.09 / MAX: 4.65MIN: 3.21 / MAX: 7.11MIN: 4.52 / MAX: 5.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4