[PATCH] D98614: [AMDGPU] Fix shortfalls in WQM marking

[Carl Ritson via Phabricator via llvm-commits]

critson created this revision.
critson added reviewers: foad, piotr.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, arsenm.
critson requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

When tracking defined lanes through phi nodes in the live range
graph each branch of the phi must be handled independently.
Also rewrite the marking algorithm to reduce unnecessary
operations.

Previously a shared set of defined lanes was used which caused
marking to stop prematurely. This was observable in existing lit
tests, but test patterns did not cover this detail.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D98614

Files:
  llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
  llvm/test/CodeGen/AMDGPU/wqm.ll
  llvm/test/CodeGen/AMDGPU/wqm.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D98614.330545.patch
Type: text/x-patch
Size: 7292 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210315/6ad08ae8/attachment.bin>