[PATCH] D62826: AMDGPU: Expand < 32-bit atomics

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added a reviewer: rampitec.
Herald added subscribers: jfb, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.

Also fix AtomicExpand asserting on atomicrmw fadd/fsub.


https://reviews.llvm.org/D62826

Files:
  lib/CodeGen/AtomicExpandPass.cpp
  lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll
  test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i8.ll
  test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fsub.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D62826.202806.patch
Type: text/x-patch
Size: 27723 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190603/123d41df/attachment.bin>