[PATCH] D87236: [X86][SSE2] Use smarter instruction patterns for lowering UMIN/UMAX with v8i16 and SMIN/SMAX with v16i8.

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

As a stopgap - would it be possible to split off the v16i8 cases into a new patch? And update this one with just the v8i16 case.

Additionally, please can you update the UMIN/UMAX costs for v8i16 in X86TTIImpl::getTypeBasedIntrinsicInstrCost? You'll need to add entries to SSE2CostTbl as it uses the default expansion atm. This might affect transform tests as well as analysis/costmodel tests.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D87236/new/

https://reviews.llvm.org/D87236