qwq Intel Core i7-4790K testing with a Apple Mac-42FD25EABCABB274 (IM151.88Z.0207.B01.1411201235 BIOS) and AMD Radeon R7 370 R9 270X/370X 2GB on Fedora 32 via the Phoronix Test Suite. qwq: Processor: Intel Core i7-4790K @ 4.40GHz (4 Cores / 8 Threads), Motherboard: Apple Mac-42FD25EABCABB274 (IM151.88Z.0207.B01.1411201235 BIOS), Chipset: Intel 4th Gen Core DRAM, Memory: 16384MB, Disk: 1000GB APPLE HDD ST1000 + 121GB APPLE SSD SD0128 + 2000GB Basic, Graphics: AMD Radeon R7 370 R9 270X/370X 2GB, Audio: Cirrus Logic CS4206, Monitor: iMac, Network: Broadcom NetXtreme BCM57766 PCIe + Broadcom BCM4360 802.11ac OS: Fedora 32, Kernel: 5.8.4-200.fc32.x86_64 (x86_64), Desktop: KDE Plasma 5.18.5, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.1.6 (LLVM 10.0.0), OpenCL: OpenCL 1.1 Mesa 20.1.6 + OpenCL 1.2 pocl 1.5 RelWithDebInfo LLVM 10.0.0 RELOC SLEEF DISTRO POCL_DEBUG + OpenCL 2.0 beignet 1.3, Vulkan: 1.2.131, Compiler: Clang 10.0.0 + LLVM 10.0.1, File-System: ext4, Screen Resolution: 3840x2160 NCNN 20200916 Target: CPU - Model: squeezenet ms < Lower Is Better qwq . 44.03 |================================================================== NCNN 20200916 Target: CPU - Model: mobilenet ms < Lower Is Better qwq . 31.60 |================================================================== NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better qwq . 8.56 |=================================================================== NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better qwq . 7.26 |=================================================================== NCNN 20200916 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better qwq . 4.84 |=================================================================== NCNN 20200916 Target: CPU - Model: mnasnet ms < Lower Is Better qwq . 6.84 |=================================================================== NCNN 20200916 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better qwq . 11.42 |================================================================== NCNN 20200916 Target: CPU - Model: blazeface ms < Lower Is Better qwq . 1.92 |=================================================================== NCNN 20200916 Target: CPU - Model: googlenet ms < Lower Is Better qwq . 69.26 |================================================================== NCNN 20200916 Target: CPU - Model: vgg16 ms < Lower Is Better qwq . 249.01 |================================================================= NCNN 20200916 Target: CPU - Model: resnet18 ms < Lower Is Better qwq . 39.59 |================================================================== NCNN 20200916 Target: CPU - Model: alexnet ms < Lower Is Better qwq . 26.24 |================================================================== NCNN 20200916 Target: CPU - Model: resnet50 ms < Lower Is Better qwq . 139.84 |================================================================= NCNN 20200916 Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 ms < Lower Is Better qwq . 31.60 |================================================================== NCNN 20200916 Target: CPU - Model: yolov4-tiny ms < Lower Is Better qwq . 46.97 |================================================================== NCNN 20200916 Target: GPU - Model: squeezenet ms < Lower Is Better qwq . 44.85 |================================================================== NCNN 20200916 Target: GPU - Model: mobilenet ms < Lower Is Better qwq . 20.03 |================================================================== NCNN 20200916 Target: GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better qwq . 9.16 |=================================================================== NCNN 20200916 Target: GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better qwq . 11.44 |================================================================== NCNN 20200916 Target: GPU - Model: shufflenet-v2 ms < Lower Is Better qwq . 5.86 |=================================================================== NCNN 20200916 Target: GPU - Model: mnasnet ms < Lower Is Better qwq . 9.63 |=================================================================== NCNN 20200916 Target: GPU - Model: efficientnet-b0 ms < Lower Is Better qwq . 22.26 |================================================================== NCNN 20200916 Target: GPU - Model: blazeface ms < Lower Is Better qwq . 2.10 |=================================================================== NCNN 20200916 Target: GPU - Model: googlenet ms < Lower Is Better qwq . 69.14 |================================================================== NCNN 20200916 Target: GPU - Model: vgg16 ms < Lower Is Better qwq . 246.60 |================================================================= NCNN 20200916 Target: GPU - Model: resnet18 ms < Lower Is Better qwq . 40.06 |================================================================== NCNN 20200916 Target: GPU - Model: alexnet ms < Lower Is Better qwq . 21.40 |================================================================== NCNN 20200916 Target: GPU - Model: resnet50 ms < Lower Is Better qwq . 141.09 |================================================================= NCNN 20200916 Target: GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 ms < Lower Is Better qwq . 20.03 |================================================================== NCNN 20200916 Target: GPU - Model: yolov4-tiny ms < Lower Is Better qwq . 42.59 |==================================================================