[llvm] r279751 - [X86][SSE] INSERTPS is only combined on v4f32 types. NFCI.
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 25 10:02:00 PDT 2016
Author: rksimon
Date: Thu Aug 25 12:02:00 2016
New Revision: 279751
URL: http://llvm.org/viewvc/llvm-project?rev=279751&view=rev
Log:
[X86][SSE] INSERTPS is only combined on v4f32 types. NFCI.
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=279751&r1=279750&r2=279751&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Thu Aug 25 12:02:00 2016
@@ -25235,8 +25235,7 @@ static bool matchBinaryPermuteVectorShuf
}
// Attempt to combine to INSERTPS.
- if (Subtarget.hasSSE41() && NumMaskElts == 4 &&
- (MaskVT == MVT::v2f64 || MaskVT == MVT::v4f32)) {
+ if (Subtarget.hasSSE41() && MaskVT == MVT::v4f32) {
SmallBitVector Zeroable(4, false);
for (unsigned i = 0; i != NumMaskElts; ++i)
if (Mask[i] < 0)
More information about the llvm-commits
mailing list