[PATCH] D71367: [AMDGPU] Fold 64 bit immediates

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added a comment.

In D71367#1780848 <https://reviews.llvm.org/D71367#1780848>, @arsenm wrote:

> I would also expect the immediate selection to understand the expanded set of immediates before the folding


That's a separate optimization. I can also see how this folding can be converted into an s_mov_b64 in a constant limited case, but it is again a separate optimization.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D71367/new/

https://reviews.llvm.org/D71367