[PATCH] D14399: [X86][SSE] Combine UNPCKL with vector_shuffle into UNPCKH to save one instruction for sext from v16i8 to v16i16 and v8i16 to v8i32.

[Cong Hou via llvm-commits]

congh marked an inline comment as done.
congh added a comment.

Thank you very much for the review, Simon!


================
Comment at: lib/Target/X86/X86ISelLowering.cpp:22774
@@ +22773,3 @@
+    if (Op0.getOpcode() == ISD::UNDEF &&
+        Op1.getNode()->getOpcode() == ISD::VECTOR_SHUFFLE) {
+      ArrayRef<int> Mask = cast<ShuffleVectorSDNode>(Op1.getNode())->getMask();
----------------
RKSimon wrote:
> Are you just seeing cases with ISD::VECTOR_SHUFFLE? I'd have expected some to be using X86 shuffle nodes as well.
Yes. I could not see X86's shuffle from my experiments in which integers are promoted.


http://reviews.llvm.org/D14399