[PATCH] D85887: [AMDGPU] Add A16/G16 to InstCombine

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll:3815
+  ret void
+}
----------------
Can you add a test making sure this preserves fast math flags? We should be able to mark these as nnan / ninf etc. and have it be preserved


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85887/new/

https://reviews.llvm.org/D85887