Several investigations were done into performance of matrix multiplication, kernel design, and differences between Apple GPU generations. This document serves to index the research, making it easier to locate old data / code.
Date: 5/24/24
Investigation of Float32 performance before and after dynamic caching on Apple GPUs.
Link: https://gist.github.com/philipturner/3bda14e876a635e73745c42f2eb240c8
Date: 5/27/24
Hacking AIR to open up the Apple GPU to general-purpose linear algebra.
Link: https://gist.github.com/philipturner/fe0621333ab6a827ed0d35c5fa226be6
Date: 5/28/24
Investigating the performance of low- and mixed-precision computations after dynamic caching.
Link: https://gist.github.com/philipturner/40052a700a448b9356b998154cd7e4cd