[PATCH] D105390: [X86] Lower insertions into upper half of an 256-bit vector as broadcast+blend (PR50971)

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri added inline comments.


================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:19006
+    // then prefer the broadcast+blend sequence.
+    if (VT.is256BitVector() && IdxVal >= NumEltsIn128 &&
+        ((Subtarget.hasAVX2() && EltVT != MVT::i8) ||
----------------
RKSimon wrote:
> Maybe generalize the IdxVal >= NumEltsIn128 limit to insert with broadcast if the scalar is already used in a (a) another insertelement/psinrw/pinsrb, (b) scalar_to_vector or (c) broadcast.
How about now?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D105390/new/

https://reviews.llvm.org/D105390