[PATCH] D105511: [AMDGPU] Move atomic expand past infer address spaces

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec updated this revision to Diff 356830.
rampitec added a comment.

Added codegen test. On gfx90a it allows to produce global_atomic_add_f32 instead of CAS loop.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D105511/new/

https://reviews.llvm.org/D105511

Files:
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
  llvm/test/CodeGen/AMDGPU/llc-pipeline.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D105511.356830.patch
Type: text/x-patch
Size: 8509 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210706/dfda7e65/attachment-0001.bin>