[PATCH] D98587: [X86] Optimize vXi8 MULHS on targets where we can't sign_extend to the next register size.

[Craig Topper via Phabricator via llvm-commits]

craig.topper added inline comments.


================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:27515
   SDValue BLo, BHi;
   if (ISD::isBuildVectorOfConstantSDNodes(B.getNode())) {
     // If the RHS is a constant, manually unpackl/unpackh and extend.
----------------
craig.topper wrote:
> RKSimon wrote:
> > Do we need this constant path any more? It seemed to be to avoid problems with the SSE41 path that's been removed.
> Maybe not. I'll check.
I think the constant path is still needed. Instruction counts increased on some tests I checked.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98587/new/

https://reviews.llvm.org/D98587