[llvm] [AMDGPU] Post-RA Peephole for latency-hiding and hazard-avoidance bet… (PR #191319)

[Jeffrey Byrnes via llvm-commits]

jrbyrnes wrote:

This seems like a scheduling problem - why doesn't PostRA scheduler do it?

My main concern is that this is not always beneficial - for example, if we want to schedule the mfma after the buffer_load to hide the buffer_load latency.

I'm also unclear on why we're limiting to just mfma - why not any valu for example?

https://github.com/llvm/llvm-project/pull/191319