[PATCH] D68585: AMDGPU/GlobalISel: Handle flat/global G_ATOMIC_CMPXCHG

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: tstellar, nhaehnle, kerbowa.
Herald added subscribers: Petar.Avramovic, jfb, t-tye, tpr, dstuttard, rovka, yaxunl, wdng, jvesely, kzhuravl.

Custom lower this to a target instruction with the merge operands. I
think it might be better to directly select this and emit a
REG_SEQUENCE, but this would be more work since it would require
splitting the tablegen patterns for these cases from the other
atomics.


https://reviews.llvm.org/D68585

Files:
  lib/Target/AMDGPU/AMDGPUInstructions.td
  lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
  lib/Target/AMDGPU/FLATInstructions.td
  test/CodeGen/AMDGPU/GlobalISel/inst-select-amdgpu-atomic-cmpxchg-global.mir
  test/CodeGen/AMDGPU/GlobalISel/legalize-atomic-cmpxchg-with-success.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D68585.223627.patch
Type: text/x-patch
Size: 36900 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191007/0b52216d/attachment.bin>