maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Use getUnpackl helper to create an ISD::VECTOR_SHUFFLE instead of using X86ISD::UNPCKL in reduceVMULWidth. 

This runs fairly early, we should use target independent nodes if possible.

llvm-svn: 311873
This commit is contained in:
Craig Topper 2017-08-28 05:14:38 +00:00
parent 2c77011d15
commit 33681161c4
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -31373,7 +31373,7 @@ static SDValue reduceVMULWidth(SDNode *N, SelectionDAG &DAG,
// Repack the lower part and higher part result of mul into a wider // Repack the lower part and higher part result of mul into a wider
// result. Make sure the type of mul result is VT. // result. Make sure the type of mul result is VT.
MVT ResVT = MVT::getVectorVT(MVT::i32, RegSize / 32); MVT ResVT = MVT::getVectorVT(MVT::i32, RegSize / 32);
SDValue Res = DAG.getNode(X86ISD::UNPCKL, DL, OpsVT, MulLo, MulHi); SDValue Res = getUnpackl(DAG, DL, OpsVT, MulLo, MulHi);
Res = DAG.getNode(ISD::BITCAST, DL, ResVT, Res); Res = DAG.getNode(ISD::BITCAST, DL, ResVT, Res);
return DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, VT, Res, return DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, VT, Res,
DAG.getIntPtrConstant(0, DL)); DAG.getIntPtrConstant(0, DL));