[PATCH] D119475: [AMDGPU] Add scheduler pass to rematerialize trivial defs

[Vang Thao via Phabricator via llvm-commits]

vangthao updated this revision to Diff 408000.
vangthao marked 4 inline comments as done.
vangthao added a comment.

Reduce patch to only handle one region. Remove sinking of subreg defs. Only collect trivially rematerializable defs in high RP region.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D119475/new/

https://reviews.llvm.org/D119475

Files:
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
  llvm/test/CodeGen/AMDGPU/dbg-value-ends-sched-region.mir
  llvm/test/CodeGen/AMDGPU/debug-value-scheduler-crash.mir
  llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir
  llvm/test/CodeGen/AMDGPU/sched-assert-dead-def-subreg-use-other-subreg.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D119475.408000.patch
Type: text/x-patch
Size: 357670 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220211/791e3e95/attachment-0001.bin>