[PATCH] D64328: [AMDGPU] Optimize atomic max/min

[Jay Foad via Phabricator via llvm-commits]

foad created this revision.
foad added reviewers: arsenm, sheredom, critson, rampitec.
Herald added subscribers: jfb, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

Extend the atomic optimizer to handle signed and unsigned max and min
operations, as well as add and subtract.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D64328

Files:
  llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D64328.208380.patch
Type: text/x-patch
Size: 12452 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190708/bcc56e43/attachment.bin>