[PATCH] D89187: [AMDGPU] Minimize number of s_mov generated by copyPhysReg

[Carl Ritson via Phabricator via llvm-commits]

critson added a comment.

In D89187#2331204 <https://reviews.llvm.org/D89187#2331204>, @nhaehnle wrote:

> How about splitting this change into two parts? Limit this change to generating mixes of 64- and 32-bit moves, and then separately consider what to do about those moves of registers where subregisters are overwritten immediately.

That was my plan.
I was just hoping I could get some input on where would be considered acceptable for the overwrite dedup to go.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D89187/new/

https://reviews.llvm.org/D89187