[X86][SSE] Dropped old INSERT_VECTOR_ELT lowering TODO

Target shuffle combining now supports the matching of INSERT_VECTOR_ELT/PINSRW/PINSRB for merging multiple insertions into shuffles/bitmasks.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305788 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 172eba0002d4f58b8d6fcb860fa19778b4aaaf1a..a604a8bf78908550296707ae17e43f53ef48cf9f 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -14272,8 +14272,6 @@ SDValue X86TargetLowering::LowerINSERT_VECTOR_ELT(SDValue Op,
   // If we are inserting a element, see if we can do this more efficiently with
   // a blend shuffle with a rematerializable vector than a costly integer
   // insertion.
-  // TODO: pre-SSE41 targets will tend to use bit masking - this could still
-  // be beneficial if we are inserting several zeros and can combine the masks.
   if ((IsZeroElt || IsAllOnesElt) && Subtarget.hasSSE41() && NumElts <= 8) {
     SmallVector<int, 8> BlendMask;
     for (unsigned i = 0; i != NumElts; ++i)