[PATCH] D123833: AMDGPU/SDAG: Factor out the fold (add (mul x, y), y) --> mad_[iu]64_[iu]32

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Apr 20 16:11:43 PDT 2022


arsenm added a comment.

In D123833#3463404 <https://reviews.llvm.org/D123833#3463404>, @nhaehnle wrote:

> In D123833#3454014 <https://reviews.llvm.org/D123833#3454014>, @arsenm wrote:
>
>> LGTM. Can I convince you to port this optimization to GlobalISel?
>
> Does this apply to the second part as well? I'll start taking a look at the GlobalISel part over the next week or so, but I'm pretty sure it should be a separate change.

Of course, just need to start chipping away at the deltas


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D123833/new/

https://reviews.llvm.org/D123833



More information about the llvm-commits mailing list