[PATCH] D103755: [DAG] Fold neg(bvsplat(neg(x)) -> bvsplat(x)

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

Funnily enough I was wondering about this pattern the other day as a followup to D98778 <https://reviews.llvm.org/D98778>...

Should we always be folding unaryop(splat(x)) -> splat(unaryop(x)) if the unaryop is legal/custom on the scalar type? And then maybe extend that to binop(splat(x),splat(y)) -> splat(binop(x,y)) as well?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D103755/new/

https://reviews.llvm.org/D103755