[PATCH] D111646: [AMDGPU] Enable load clustering in the post-RA scheduler

Joe Nash via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Oct 13 08:25:24 PDT 2021


Joe_Nash accepted this revision.
Joe_Nash added a comment.

In D111646#3060926 <https://reviews.llvm.org/D111646#3060926>, @foad wrote:

> In D111646#3058632 <https://reviews.llvm.org/D111646#3058632>, @Joe_Nash wrote:
>
>> Any data on compile time? Other than potential compile time/ runtime tradeoff LGTM
>
> We see an average 0.11% slow down in internal compile time testing on a bunch of graphics pipelines. Does that seem acceptable?

Seems acceptable to me.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D111646/new/

https://reviews.llvm.org/D111646



More information about the llvm-commits mailing list