RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-01-30 15:22:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[x86] Make the single-input v8i16 lowering directly recurse rather than

Browse Source 
going back through the entire vector shuffle lowering.

This is an important step to being able to re-use this logic.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230743 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chandler Carruth 2015-02-27 09:11:38 +00:00
parent 912e816cc2
commit b1961a3896
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Target/X86/X86ISelLowering.cpp
View File

@ -7859,8 +7859,8 @@ static SDValue lowerV8I16GeneralSingleInputVectorShuffle(
// Recurse back into this routine to re-compute state now that this isn't
// a 3 and 1 problem.
return DAG.getVectorShuffle(MVT::v8i16, DL, V, DAG.getUNDEF(MVT::v8i16),
Mask);
return lowerV8I16GeneralSingleInputVectorShuffle(DL, V, Mask, Subtarget,
DAG);
};
if ((NumLToL == 3 && NumHToL == 1) || (NumLToL == 1 && NumHToL == 3))
return balanceSides(LToLInputs, HToLInputs, HToHInputs, LToHInputs, 0, 4);