#asahi-gpu · 2021-01-12 02:51
icecream95brentr123[m]: AFAIK the plan is to write a native OpenGL and/or Vulkan driver with no Metal involved#asahi-gpu · 2021-01-12 01:07
icecream95The matrix coprocessor probably has an instruction for tiling anyway#asahi-gpu · 2021-01-12 01:03
icecream95Memory access patterns are also important. Ideally you want to write entire cache lines at once, but I think Aarch64 dropped that instruction#asahi-gpu · 2021-01-12 01:02
icecream95"Oddly NEON is making things slower". Because GCC's handling of ARM vector intrinsics sucks?#asahi-gpu · 2021-01-11 00:39
icecream95bloom: IIRC My NEON tiling routine was "only" about 3x faster#asahi-gpu · 2021-01-11 00:34
icecream95https://www.sevarg.net/generated/images/2021-qemu-m1/mbw-1200-b48fbb189.png