ncnn mnn rembrandyt

AMD Ryzen 7 PRO 6850U testing with a LENOVO 21CM0001US (R22ET46W 1.16 BIOS) and AMD Radeon 680M 1GB on Ubuntu 22.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208130-NE-NCNNMNNRE44&grw.

ncnn mnn rembrandytProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCDAMD Ryzen 7 PRO 6850U @ 4.77GHz (8 Cores / 16 Threads)LENOVO 21CM0001US (R22ET46W 1.16 BIOS)AMD Device 14b516GB512GB Micron MTFDKBA512TFKAMD Radeon 680M 1GB (2200/400MHz)AMD Rembrandt Radeon HD AudioQualcomm QCNFA765Ubuntu 22.105.19.0-051900-generic (x86_64)GNOME Shell 42.3.1X Server + Wayland4.6 Mesa 22.1.3 (LLVM 14.0.6 DRM 3.47)1.3.211GCC 11.3.0ext41920x1200OpenBenchmarking.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-11-7Xaroy/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-7Xaroy/gcc-11-11.3.0/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: amd-pstate schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced 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

ncnn mnn rembrandytmnn: 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 - FastestDetABCD1.5903.40826.8455.9813.1353.01837.10613.013.683.022.412.966.020.9210.9947.369.958.1519.9821.3915.297.76258.193.049.502.242.391.692.136.283.655.2418.074.245.978.7516.5814.803.28744.862.771.5923.46626.9106.0263.0923.02836.96313.033.643.002.42.885.910.9110.9247.489.988.1820.1821.6715.097.71257.952.999.382.102.461.732.205.973.685.0418.484.065.528.8916.3614.673.27749.582.671.5893.40226.9646.0143.1193.02136.96512.893.703.042.423.016.050.9010.8647.309.998.2420.0321.2915.167.69258.163.059.442.132.341.712.305.863.664.9418.404.225.698.7116.4614.623.20749.992.681.5933.36026.8775.9573.1353.03336.86312.783.653.022.402.855.920.9010.8747.279.848.1719.8621.3015.147.71259.502.939.362.122.421.712.225.453.594.9318.483.995.608.7816.1415.433.15744.712.67OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABCD0.35840.71681.07521.43361.792SE +/- 0.016, N = 6SE +/- 0.019, N = 3SE +/- 0.013, N = 3SE +/- 0.010, N = 31.5901.5921.5891.593MIN: 1.5 / MAX: 25.15MIN: 1.49 / MAX: 31.15MIN: 1.52 / MAX: 38.48MIN: 1.53 / MAX: 10.131. (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: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABCD0.77991.55982.33973.11963.8995SE +/- 0.017, N = 6SE +/- 0.009, N = 3SE +/- 0.022, N = 3SE +/- 0.011, N = 33.4083.4663.4023.360MIN: 3.19 / MAX: 15.38MIN: 3.16 / MAX: 41.66MIN: 3.2 / MAX: 4.6MIN: 3.03 / MAX: 27.441. (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-v2-50ABCD612182430SE +/- 0.07, N = 6SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 326.8526.9126.9626.88MIN: 25.53 / MAX: 67.31MIN: 25.91 / MAX: 63.84MIN: 25.97 / MAX: 65.21MIN: 25.7 / MAX: 62.521. (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: SqueezeNetV1.0ABCD246810SE +/- 0.032, N = 6SE +/- 0.015, N = 3SE +/- 0.006, N = 3SE +/- 0.065, N = 35.9816.0266.0145.957MIN: 5.59 / MAX: 26.15MIN: 5.59 / MAX: 43.37MIN: 5.71 / MAX: 23.38MIN: 5.67 / MAX: 24.651. (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_224ABCD0.70541.41082.11622.82163.527SE +/- 0.020, N = 6SE +/- 0.012, N = 3SE +/- 0.014, N = 3SE +/- 0.017, N = 33.1353.0923.1193.135MIN: 2.78 / MAX: 29.16MIN: 2.9 / MAX: 4.09MIN: 2.9 / MAX: 25.93MIN: 3 / MAX: 18.721. (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-v1-1.0ABCD0.68241.36482.04722.72963.412SE +/- 0.005, N = 6SE +/- 0.013, N = 3SE +/- 0.011, N = 3SE +/- 0.018, N = 33.0183.0283.0213.033MIN: 2.78 / MAX: 25.86MIN: 2.76 / MAX: 39.49MIN: 2.75 / MAX: 41.57MIN: 2.81 / MAX: 44.021. (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-v3ABCD918273645SE +/- 0.20, N = 6SE +/- 0.32, N = 3SE +/- 0.35, N = 3SE +/- 0.46, N = 337.1136.9636.9736.86MIN: 31.04 / MAX: 88.36MIN: 32.27 / MAX: 62.73MIN: 32.4 / MAX: 58.25MIN: 32.19 / MAX: 58.721. (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: mobilenetABCD3691215SE +/- 0.14, N = 5SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 313.0113.0312.8912.78MIN: 12.38 / MAX: 30.48MIN: 12.57 / MAX: 49.75MIN: 12.31 / MAX: 23.48MIN: 12.3 / MAX: 13.971. (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-v2ABCD0.83251.6652.49753.334.1625SE +/- 0.02, N = 5SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 33.683.643.703.65MIN: 3.37 / MAX: 16.17MIN: 3.38 / MAX: 5.28MIN: 3.43 / MAX: 5.6MIN: 3.41 / MAX: 5.271. (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-v3ABCD0.6841.3682.0522.7363.42SE +/- 0.01, N = 5SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.023.003.043.02MIN: 2.73 / MAX: 4.86MIN: 2.73 / MAX: 6.51MIN: 2.87 / MAX: 4.85MIN: 2.75 / MAX: 4.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABCD0.54451.0891.63352.1782.7225SE +/- 0.01, N = 5SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.412.402.422.40MIN: 2.19 / MAX: 4.56MIN: 2.26 / MAX: 4.09MIN: 2.16 / MAX: 3.8MIN: 2.26 / MAX: 3.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABCD0.67731.35462.03192.70923.3865SE +/- 0.02, N = 5SE +/- 0.02, N = 3SE +/- 0.02, N = 2SE +/- 0.02, N = 32.962.883.012.85MIN: 2.66 / MAX: 6.1MIN: 2.57 / MAX: 13.42MIN: 2.77 / MAX: 4.54MIN: 2.67 / MAX: 4.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABCD246810SE +/- 0.06, N = 5SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 36.025.916.055.92MIN: 5.53 / MAX: 7.9MIN: 5.61 / MAX: 7.75MIN: 5.64 / MAX: 8.1MIN: 5.59 / MAX: 7.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABCD0.2070.4140.6210.8281.035SE +/- 0.01, N = 5SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 30.920.910.900.90MIN: 0.86 / MAX: 1.9MIN: 0.83 / MAX: 1.57MIN: 0.85 / MAX: 1.81MIN: 0.77 / MAX: 1.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABCD3691215SE +/- 0.09, N = 5SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 310.9910.9210.8610.87MIN: 10.36 / MAX: 26.09MIN: 10.18 / MAX: 19.54MIN: 10.14 / MAX: 12.82MIN: 10.43 / MAX: 22.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABCD1122334455SE +/- 0.09, N = 5SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 347.3647.4847.3047.27MIN: 46.44 / MAX: 62.61MIN: 46.55 / MAX: 60.89MIN: 46.39 / MAX: 59.66MIN: 46.41 / MAX: 60.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABCD3691215SE +/- 0.07, N = 5SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 39.959.989.999.84MIN: 9.17 / MAX: 23.38MIN: 9.33 / MAX: 23.59MIN: 9.27 / MAX: 19.64MIN: 9.23 / MAX: 12.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABCD246810SE +/- 0.03, N = 5SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 38.158.188.248.17MIN: 7.62 / MAX: 20.7MIN: 7.83 / MAX: 10.05MIN: 7.79 / MAX: 9.94MIN: 7.82 / MAX: 19.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABCD510152025SE +/- 0.15, N = 5SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 319.9820.1820.0319.86MIN: 19.02 / MAX: 24.43MIN: 19.51 / MAX: 22.73MIN: 19.24 / MAX: 22.52MIN: 18.93 / MAX: 33.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABCD510152025SE +/- 0.14, N = 5SE +/- 0.19, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 321.3921.6721.2921.30MIN: 20.67 / MAX: 35.04MIN: 20.9 / MAX: 63.12MIN: 20.62 / MAX: 22.98MIN: 20.71 / MAX: 58.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABCD48121620SE +/- 0.07, N = 5SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 315.2915.0915.1615.14MIN: 14.48 / MAX: 29.84MIN: 14.57 / MAX: 26.07MIN: 14.51 / MAX: 27.53MIN: 14.51 / MAX: 26.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABCD246810SE +/- 0.10, N = 5SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 37.767.717.697.71MIN: 7.05 / MAX: 11.36MIN: 7.15 / MAX: 9.2MIN: 7.06 / MAX: 19.39MIN: 7.08 / MAX: 9.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABCD60120180240300SE +/- 0.37, N = 5SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.63, N = 3258.19257.95258.16259.50MIN: 252.82 / MAX: 289.02MIN: 252.71 / MAX: 287.92MIN: 254.14 / MAX: 285.51MIN: 253.94 / MAX: 366.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetABCD0.68631.37262.05892.74523.4315SE +/- 0.04, N = 5SE +/- 0.01, N = 3SE +/- 0.04, N = 33.042.993.052.93MIN: 2.82 / MAX: 3.67MIN: 2.85 / MAX: 3.71MIN: 2.92 / MAX: 4.08MIN: 2.83 / MAX: 3.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABCD3691215SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 39.509.389.449.36MIN: 8.25 / MAX: 11.29MIN: 8.32 / MAX: 14.57MIN: 8.24 / MAX: 13.02MIN: 8.2 / MAX: 10.621. (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-v2ABCD0.5041.0081.5122.0162.52SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 32.242.102.132.12MIN: 1.9 / MAX: 3.72MIN: 1.92 / MAX: 3.23MIN: 1.95 / MAX: 3.18MIN: 1.95 / MAX: 3.331. (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-v3ABCD0.55351.1071.66052.2142.7675SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 32.392.462.342.42MIN: 2.02 / MAX: 5.72MIN: 2.07 / MAX: 3.73MIN: 2.09 / MAX: 3.34MIN: 2.09 / MAX: 4.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABCD0.38930.77861.16791.55721.9465SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 31.691.731.711.71MIN: 1.48 / MAX: 2.66MIN: 1.47 / MAX: 2.68MIN: 1.49 / MAX: 2.6MIN: 1.5 / MAX: 2.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABCD0.51751.0351.55252.072.5875SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 32.132.202.302.22MIN: 1.93 / MAX: 3.13MIN: 1.94 / MAX: 3.25MIN: 1.96 / MAX: 3.37MIN: 1.98 / MAX: 3.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABCD246810SE +/- 0.15, N = 3SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 36.285.975.865.45MIN: 5.4 / MAX: 8.07MIN: 5.22 / MAX: 7.38MIN: 5.2 / MAX: 7.64MIN: 5.2 / MAX: 6.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABCD0.8281.6562.4843.3124.14SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 33.653.683.663.59MIN: 2.29 / MAX: 4.3MIN: 2.81 / MAX: 5.29MIN: 2.8 / MAX: 10.32MIN: 2.3 / MAX: 4.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABCD1.1792.3583.5374.7165.895SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 35.245.044.944.93MIN: 4.51 / MAX: 8.28MIN: 4.52 / MAX: 6.4MIN: 4.57 / MAX: 6.47MIN: 4.52 / MAX: 6.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABCD510152025SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 318.0718.4818.4018.48MIN: 17.25 / MAX: 18.93MIN: 17.65 / MAX: 20.6MIN: 17.68 / MAX: 21.67MIN: 17.7 / MAX: 21.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABCD0.9541.9082.8623.8164.77SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 34.244.064.223.99MIN: 3.5 / MAX: 7.28MIN: 3.65 / MAX: 7.1MIN: 3.7 / MAX: 5.59MIN: 3.65 / MAX: 6.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABCD1.34332.68664.02995.37326.7165SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 35.975.525.695.60MIN: 5.11 / MAX: 6.7MIN: 5.14 / MAX: 7.5MIN: 5.16 / MAX: 9.13MIN: 5.11 / MAX: 8.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABCD246810SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 38.758.898.718.78MIN: 8.17 / MAX: 9.66MIN: 8.23 / MAX: 10.46MIN: 7.9 / MAX: 9.91MIN: 8.02 / MAX: 9.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABCD48121620SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.29, N = 3SE +/- 0.03, N = 316.5816.3616.4616.14MIN: 15.11 / MAX: 30.63MIN: 15.12 / MAX: 19.7MIN: 15 / MAX: 30.3MIN: 15.2 / MAX: 25.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABCD48121620SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.11, N = 3SE +/- 0.73, N = 314.8014.6714.6215.43MIN: 11.69 / MAX: 29.38MIN: 11.81 / MAX: 19.58MIN: 11.51 / MAX: 31.57MIN: 11.57 / MAX: 20.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABCD0.7381.4762.2142.9523.69SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 33.283.273.203.15MIN: 2.58 / MAX: 4.89MIN: 2.65 / MAX: 4.74MIN: 2.64 / MAX: 4.34MIN: 2.67 / MAX: 4.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABCD160320480640800SE +/- 2.21, N = 3SE +/- 3.91, N = 3SE +/- 1.07, N = 3SE +/- 0.95, N = 3744.86749.58749.99744.71MIN: 689.04 / MAX: 986.61MIN: 687.82 / MAX: 819.16MIN: 691.69 / MAX: 816.76MIN: 688.87 / MAX: 827.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABCD0.62331.24661.86992.49323.1165SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 32.772.672.682.67MIN: 2.45 / MAX: 3.69MIN: 2.41 / MAX: 4.12MIN: 2.44 / MAX: 4.22MIN: 2.45 / MAX: 4.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.5