[PATCH] D57340: AMDGPU: Add DS append/consume intrinsics

[Brian Sumner via Phabricator via llvm-commits]

b-sumner added a comment.

I think it is perfectly reasonable to treat these as essentially relaxed-only atomic RMW operations and require the application to use fences or barriers if necessary.  The ordering and scope are only needed if we ever need this operation to act as a non-relaxed atomic RMW.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57340/new/

https://reviews.llvm.org/D57340