[llvm] r364313 - [X86] lowerShuffleAsSpecificZeroOrAnyExtend - add ANY_EXTEND TODO.

[Simon Pilgrim via llvm-commits]

Author: rksimon
Date: Tue Jun 25 06:36:53 2019
New Revision: 364313

URL: http://llvm.org/viewvc/llvm-project?rev=364313&view=rev
Log:
[X86] lowerShuffleAsSpecificZeroOrAnyExtend - add ANY_EXTEND TODO.

lowerShuffleAsSpecificZeroOrAnyExtend should be able to lower to ANY_EXTEND_VECTOR_INREG as well as ZER_EXTEND_VECTOR_INREG.

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=364313&r1=364312&r2=364313&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Tue Jun 25 06:36:53 2019
@@ -11662,6 +11662,7 @@ static SDValue lowerShuffleAsSpecificZer
 
   // Found a valid zext mask! Try various lowering strategies based on the
   // input type and available ISA extensions.
+  // TODO: Add AnyExt support.
   if (Subtarget.hasSSE41()) {
     // Not worth offsetting 128-bit vectors if scale == 2, a pattern using
     // PUNPCK will catch this in a later shuffle match.