[PATCH] D126389: [AMDGPU] Improve codegen of extractelement/insertelement in some cases

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

I wouldn’t really expect there to be a performance difference between gpr indexing and movrel requences. Gfx8 has both so you could directly compare there


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D126389/new/

https://reviews.llvm.org/D126389