[PATCH] D150947: [AMDGPU] Fix odd implicit operand handling in clause breaking

[Jay Foad via Phabricator via llvm-commits]

foad created this revision.
foad added reviewers: AMDGPU, arsenm, tstellar, rampitec, barannikov88.
Herald added subscribers: StephenFan, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl, qcolombet.
Herald added a project: All.
foad requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

By inspection. Because of the strange behaviour of MI.uses(), this was
adding implicit defs to the clause *uses* set, and then wrongly
detecting a conflict between explicit defs and implicit defs.

For example it would detect a conflict on this pair of instructions:

  $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, 0, 4088, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1 :: (load (s32) from %stack.1, addrspace 5)
  $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, 0, 4092, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1 :: (load (s32) from %stack.1 + 4, addrspace 5)


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D150947

Files:
  llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
  llvm/test/CodeGen/AMDGPU/agpr-copy-no-free-registers.ll
  llvm/test/CodeGen/AMDGPU/mubuf-legalize-operands.ll
  llvm/test/CodeGen/AMDGPU/spill-offset-calculation.ll
  llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D150947.523702.patch
Type: text/x-patch
Size: 15940 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230519/431cbf78/attachment.bin>