[llvm] r218217 - [x86] With the stronger canonicalization of shuffles added in r218216,

Chandler Carruth chandlerc at gmail.com
Sun Sep 21 06:37:52 PDT 2014


Author: chandlerc
Date: Sun Sep 21 08:37:51 2014
New Revision: 218217

URL: http://llvm.org/viewvc/llvm-project?rev=218217&view=rev
Log:
[x86] With the stronger canonicalization of shuffles added in r218216,
the new vector shuffle lowering no longer needs to check both symmetric
forms of UNPCK patterns for v4f64.

Modified:
    llvm/trunk/lib/Target/X86/X86ISelLowering.cpp

Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=218217&r1=218216&r2=218217&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Sun Sep 21 08:37:51 2014
@@ -9257,10 +9257,6 @@ static SDValue lowerV4F64VectorShuffle(S
     return DAG.getNode(X86ISD::UNPCKL, DL, MVT::v4f64, V1, V2);
   if (isShuffleEquivalent(Mask, 1, 5, 3, 7))
     return DAG.getNode(X86ISD::UNPCKH, DL, MVT::v4f64, V1, V2);
-  if (isShuffleEquivalent(Mask, 4, 0, 6, 2))
-    return DAG.getNode(X86ISD::UNPCKL, DL, MVT::v4f64, V2, V1);
-  if (isShuffleEquivalent(Mask, 5, 1, 7, 3))
-    return DAG.getNode(X86ISD::UNPCKH, DL, MVT::v4f64, V2, V1);
 
   // If we have a single input to the zero element, insert that into V1 if we
   // can do so cheaply.





More information about the llvm-commits mailing list