[PATCH] D17483: [X86][SSE41] Combine insertion of zero scalars into vector blends with zero

[Quentin Colombet via llvm-commits]

qcolombet accepted this revision.
qcolombet added a comment.
This revision is now accepted and ready to land.

Hi Simon,

LGTM.

Thanks,
-Quentin


================
Comment at: lib/Target/X86/X86ISelLowering.cpp:23685
@@ +23684,3 @@
+
+    if (isSequentialOrUndefOrZeroInRange(Mask, 0, Mask.size(), 0) &&
+        Mask.size() <= ShuffleVT.getVectorNumElements()) {
----------------
May be useful to specify the arguments with comments, e.g., /*Pos*/, etc.


Repository:
  rL LLVM

http://reviews.llvm.org/D17483