[PATCH] D134433: [AMDGPU][GISel] Enable Matching of V2S16 G_BUILD_VECTOR

[Petar Avramovic via Phabricator via llvm-commits]

Petar.Avramovic added a comment.

You don't want `(<2 x s16>)` but only `s16` `G_FMAXNUM_IEEE`when lowering larger vectors, also you remove `G_BUILD_VECTOR_TRUNC` but use `G_BUILD_VECTOR` instead.
Can you point me to the test case that requires those changes? (You didn't change legalization rules for other `<2 x s16>` instructions).
To be more precise what D134354 <https://reviews.llvm.org/D134354> requires from Legalizer (and pre/post legalizer combiner). Maybe there is simpler way to achieve it.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D134433/new/

https://reviews.llvm.org/D134433