[PATCH] D89187: [AMDGPU] Minimize number of s_mov generated by copyPhysReg
Carl Ritson via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Oct 14 20:35:33 PDT 2020
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
More information about the llvm-commits
mailing list