[PATCH] D144612: [AMDGPU] Move V_FMA_MIX pattern matching into tablegen. NFC

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

Looks like a great cleanup, thanks!



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp:555
-
-  // TODO: We can select this with f32 denormals enabled if all the sources are
-  // converted from f16 (in which case fmad isn't legal).
----------------
Is it worth preserving the TODO somewhere?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144612/new/

https://reviews.llvm.org/D144612