[PATCH] D72325: [AMDGPU] Fix cluster size threshold calculation

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

In D72325#1937424 <https://reviews.llvm.org/D72325#1937424>, @arsenm wrote:

> Is this needed anymore?


Since D73292 <https://reviews.llvm.org/D73292> landed this is equivalent to fixing the FIXME at the end of `SIInstrInfo::shouldClusterMemOps`. I'll rebase it accordingly. As for whether it's actually needed, I think only benchmarks can tell, and I don't have any up-to-date numbers at the moment.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D72325/new/

https://reviews.llvm.org/D72325