[PATCH] D144099: [WIP][AMDGPU] Fold more AGPR copies/PHIs in SIFoldOperands

[Pierre van Houtryve via Phabricator via llvm-commits]

Pierre-vh updated this revision to Diff 498329.
Pierre-vh added a comment.

Fix remaining cases, add MIR test

Note that the MIR test is just a basic test, most of the interesting testing is
done in D143731 <https://reviews.llvm.org/D143731> with mfma-loop.ll


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144099/new/

https://reviews.llvm.org/D144099

Files:
  llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
  llvm/test/CodeGen/AMDGPU/fold-agpr-phis.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D144099.498329.patch
Type: text/x-patch
Size: 33751 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230217/8a26094e/attachment.bin>