[PATCH] D83844: AMDGPU: Make saturating add/sub legal for DAG path

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp:576
 
 // Return true if there's a potential benefit from using v2f16 instructions for
 // an intrinsic, even if it requires nontrivial legalization.
----------------
Can you update the comment? "v2f16" is not relevant to saturated arithmetic.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D83844/new/

https://reviews.llvm.org/D83844