mnn ncnn apple m1 Apple M1 testing with a Apple Mac mini (M1 2020) and llvmpipe on Arch Linux ARM via the Phoronix Test Suite. A: Processor: Apple M1 @ 2.06GHz (4 Cores / 8 Threads), Motherboard: Apple Mac mini (M1 2020), Memory: 8GB, Disk: 251GB APPLE SSD AP0256Q + 2 x 0GB APPLE SSD AP0256Q, Graphics: llvmpipe, Network: Broadcom NetXtreme BCM57762 PCIe + Broadcom BRCM4378 + Broadcom Device 5f69 OS: Arch Linux ARM, Kernel: 5.19.0-rc7-asahi-2-1-ARCH (aarch64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits), Compiler: GCC 12.1.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1080 B: Processor: Apple M1 @ 2.06GHz (4 Cores / 8 Threads), Motherboard: Apple Mac mini (M1 2020), Memory: 8GB, Disk: 251GB APPLE SSD AP0256Q + 2 x 0GB APPLE SSD AP0256Q, Graphics: llvmpipe, Network: Broadcom NetXtreme BCM57762 PCIe + Broadcom BRCM4378 + Broadcom Device 5f69 OS: Arch Linux ARM, Kernel: 5.19.0-rc7-asahi-2-1-ARCH (aarch64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits), Compiler: GCC 12.1.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1080 C: Processor: Apple M1 @ 2.06GHz (4 Cores / 8 Threads), Motherboard: Apple Mac mini (M1 2020), Memory: 8GB, Disk: 251GB APPLE SSD AP0256Q + 2 x 0GB APPLE SSD AP0256Q, Graphics: llvmpipe, Network: Broadcom NetXtreme BCM57762 PCIe + Broadcom BRCM4378 + Broadcom Device 5f69 OS: Arch Linux ARM, Kernel: 5.19.0-rc7-asahi-2-1-ARCH (aarch64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits), Compiler: GCC 12.1.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1080 D: Processor: Apple M1 @ 2.06GHz (4 Cores / 8 Threads), Motherboard: Apple Mac mini (M1 2020), Memory: 8GB, Disk: 251GB APPLE SSD AP0256Q + 2 x 0GB APPLE SSD AP0256Q, Graphics: llvmpipe, Network: Broadcom NetXtreme BCM57762 PCIe + Broadcom BRCM4378 + Broadcom Device 5f69 OS: Arch Linux ARM, Kernel: 5.19.0-rc7-asahi-2-1-ARCH (aarch64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits), Compiler: GCC 12.1.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1080 NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better A . 2.55 |===================================================================== B . 2.52 |==================================================================== C . 2.43 |================================================================= D . 2.56 |===================================================================== NCNN 20220729 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better A . 10.94 |================================================================= B . 11.13 |=================================================================== C . 11.38 |==================================================================== D . 11.10 |================================================================== NCNN 20220729 Target: CPU - Model: resnet18 ms < Lower Is Better A . 6.63 |=================================================================== B . 6.82 |===================================================================== C . 6.56 |================================================================== D . 6.78 |===================================================================== NCNN 20220729 Target: CPU - Model: googlenet ms < Lower Is Better A . 14.38 |================================================================== B . 14.77 |==================================================================== C . 14.32 |================================================================== D . 14.28 |================================================================== NCNN 20220729 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better A . 2.13 |=================================================================== B . 2.18 |===================================================================== C . 2.19 |===================================================================== D . 2.16 |==================================================================== NCNN 20220729 Target: CPU - Model: mobilenet ms < Lower Is Better A . 14.51 |================================================================== B . 14.67 |=================================================================== C . 14.89 |==================================================================== D . 14.62 |=================================================================== NCNN 20220729 Target: CPU - Model: blazeface ms < Lower Is Better A . 2.83 |==================================================================== B . 2.79 |=================================================================== C . 2.81 |==================================================================== D . 2.86 |===================================================================== NCNN 20220729 Target: CPU - Model: regnety_400m ms < Lower Is Better A . 5.81 |=================================================================== B . 5.82 |=================================================================== C . 5.86 |==================================================================== D . 5.95 |===================================================================== NCNN 20220729 Target: CPU - Model: alexnet ms < Lower Is Better A . 13.43 |=================================================================== B . 13.62 |=================================================================== C . 13.73 |==================================================================== D . 13.60 |=================================================================== NCNN 20220729 Target: CPU - Model: resnet50 ms < Lower Is Better A . 17.69 |==================================================================== B . 17.54 |=================================================================== C . 17.56 |=================================================================== D . 17.81 |==================================================================== Mobile Neural Network 2.0 Model: inception-v3 ms < Lower Is Better A . 44.48 |==================================================================== B . 43.88 |=================================================================== C . 44.07 |=================================================================== D . 43.93 |=================================================================== NCNN 20220729 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better A . 3.85 |==================================================================== B . 3.86 |==================================================================== C . 3.90 |===================================================================== D . 3.90 |===================================================================== NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better A . 2.49 |===================================================================== B . 2.46 |==================================================================== C . 2.46 |==================================================================== D . 2.48 |===================================================================== NCNN 20220729 Target: CPU - Model: yolov4-tiny ms < Lower Is Better A . 16.93 |=================================================================== B . 17.09 |==================================================================== C . 17.04 |==================================================================== D . 17.13 |==================================================================== Mobile Neural Network 2.0 Model: SqueezeNetV1.0 ms < Lower Is Better A . 7.202 |==================================================================== B . 7.225 |==================================================================== C . 7.166 |=================================================================== D . 7.165 |=================================================================== Mobile Neural Network 2.0 Model: resnet-v2-50 ms < Lower Is Better A . 31.27 |=================================================================== B . 31.51 |==================================================================== C . 31.35 |==================================================================== D . 31.33 |==================================================================== NCNN 20220729 Target: CPU - Model: vgg16 ms < Lower Is Better A . 34.13 |==================================================================== B . 34.07 |==================================================================== C . 33.91 |==================================================================== D . 33.94 |==================================================================== Mobile Neural Network 2.0 Model: squeezenetv1.1 ms < Lower Is Better A . 4.120 |==================================================================== B . 4.139 |==================================================================== C . 4.115 |==================================================================== D . 4.119 |==================================================================== NCNN 20220729 Target: CPU - Model: vision_transformer ms < Lower Is Better A . 556.15 |=================================================================== B . 557.83 |=================================================================== C . 558.92 |=================================================================== D . 557.34 |=================================================================== Mobile Neural Network 2.0 Model: mobilenet-v1-1.0 ms < Lower Is Better A . 5.752 |==================================================================== B . 5.741 |==================================================================== C . 5.735 |==================================================================== D . 5.749 |==================================================================== NCNN 20220729 Target: CPU - Model: FastestDet ms < Lower Is Better A . 1.91 |============================================================= B . 2.15 |===================================================================== C . 2.01 |================================================================= D . 2.00 |================================================================ NCNN 20220729 Target: CPU - Model: mnasnet ms < Lower Is Better A . 2.63 |===================================================================== B . 2.45 |================================================================ C . 2.56 |=================================================================== D . 2.43 |================================================================ Mobile Neural Network 2.0 Model: MobileNetV2_224 ms < Lower Is Better A . 4.678 |=============================================================== B . 5.025 |==================================================================== C . 4.511 |============================================================= D . 4.536 |============================================================= Mobile Neural Network 2.0 Model: mobilenetV3 ms < Lower Is Better A . 2.012 |================================================================ B . 2.122 |==================================================================== C . 1.929 |============================================================== D . 1.976 |===============================================================