[PATCH] D136918: [AMDGPU] Scheduler: fix RP calculation for a MBB with one successor

Sat Oct 29 09:27:45 PDT 2022

vpykhtin added a comment.

> ! In D136918#3894272 <https://reviews.llvm.org/D136918#3894272>, @arsenm wrote:
>  The custom pressure tracking's treatment of sub registers always seemed broken to me. The register tuples do have a stronger constraint than the same number of individual registers. Pressure is always going to be a fuzzier metric than exact liveness

When I look into this now I tend to agree. We should always account for the full superreg even if only one subreg is live because RenameIndependentSubregs should split it earlier into individual registers. That would simplify RP tracking a lot.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D136918/new/

https://reviews.llvm.org/D136918