[PATCH] D56784: [X86][SSE] Use PSLLDQ/PSRLDQ to mask out zeroable ends of a shuffle

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon marked an inline comment as done.
RKSimon added inline comments.


================
Comment at: lib/Target/X86/X86ISelLowering.cpp:10921-10924
+  ArrayRef<int> StubMask = Mask.slice(ZeroLo, Len);
+  if (!isUndefOrInRange(StubMask, 0, NumElts) &&
+      !isUndefOrInRange(StubMask, NumElts, 2 * NumElts))
+    return SDValue();
----------------
spatel wrote:
> Could we do the simpler check/assert that V2 has been canonicalized to a zero constant?
Not easily, our shuffle mask canonicalization doesn't try to account for zero ops as it regresses shuffles in cases where we can't make use of it being zero.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D56784/new/

https://reviews.llvm.org/D56784