[PATCH] D123622: [AMDGPU] Allow sinking defs with multiple uses in PreRARemterialize scheduling stage

[Vang Thao via Phabricator via llvm-commits]

vangthao created this revision.
Herald added subscribers: hsmhsm, foad, kerbowa, javed.absar, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, arsenm.
Herald added a project: All.
vangthao requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

In further attempts to reduce RP and increase occupancy in the
PreRARematerialize stage, we can widen the criteria for sinking trivially
rematerializable defs to include defs with multiple uses and sink a copy
directly to each use if occupancy would be improved in doing so.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D123622

Files:
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
  llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D123622.422277.patch
Type: text/x-patch
Size: 69069 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220412/4290dabb/attachment.bin>