[PATCH] D155080: [AMDGPU] Corrrectly emit AGPR copies in tryFoldPhiAGPR

[Pierre van Houtryve via Phabricator via llvm-commits]

Pierre-vh created this revision.
Pierre-vh added reviewers: AMDGPU, arsenm.
Herald added subscribers: foad, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
Pierre-vh requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

- Don't create COPY instructions between PHI nodes.
- Don't create V_ACCVGPR_WRITE with operands that aren't AGPR_32

Solves SWDEV-410408


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D155080

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

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D155080.539530.patch
Type: text/x-patch
Size: 24829 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230712/3e833592/attachment.bin>