[PATCH] D115229: [AMDGPU] In SIMemoryLegalizer assume all atomic ops have memoperands

[Jay Foad via Phabricator via llvm-commits]

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

Remove the conservative handling of maybeAtomic ops with no
memoperands. In practice this path is untested because all maybeAtomic
ops do have memoperands. Remove various unused default values for fields
in SIMemOpInfo.

If we add new ops without memoperands in future it's better to hit the
assertion in constructFromMIWithMMO early than to have them handled
conservatively (which is correct but slow) and only find out about the
performance problem later.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D115229

Files:
  llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
  llvm/test/CodeGen/AMDGPU/expand-si-indirect.mir
  llvm/test/CodeGen/AMDGPU/shrink-carry.mir
  llvm/test/CodeGen/AMDGPU/subvector-test.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D115229.392323.patch
Type: text/x-patch
Size: 8727 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211207/4b48d29a/attachment.bin>