[PATCH] D89316: [AMDGPU][GlobalISel] Compute known bits for zero-extending loads

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

This could do better by checking the range metadata on the memory operand, but I don't think that's wired into the IR->MIR lowering now (if we ever even attach this to intrinsic calls)


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D89316/new/

https://reviews.llvm.org/D89316