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

[X86][AVX] combineConcatVectorOps - use getBROADCAST_LOAD helper. NFCI. 

This is part of rG1cfecf4fc427 that was reverted to fix PR51226 - concating the broadcasts is OK, its the splatted loads that crash (we're not detecting extloads). I'm still creating a reduced test case so haven't added the load handling again yet.
This commit is contained in:
Simon Pilgrim 2021-11-02 17:54:26 +00:00
parent e2a6c08bbc
commit 82e0eb22af
1 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -51669,16 +51669,17 @@ static SDValue combineConcatVectorOps(const SDLoc &DL, MVT VT,
// a larger broadcast_load. Update other uses to use an extracted subvector.
if (Op0.getOpcode() == X86ISD::VBROADCAST_LOAD ||
Op0.getOpcode() == X86ISD::SUBV_BROADCAST_LOAD) {
auto *MemIntr = cast<MemIntrinsicSDNode>(Op0);
SDVTList Tys = DAG.getVTList(VT, MVT::Other);
SDValue Ops[] = {MemIntr->getChain(), MemIntr->getBasePtr()};
SDValue BcastLd = DAG.getMemIntrinsicNode(Op0.getOpcode(), DL, Tys, Ops,
MemIntr->getMemoryVT(),
MemIntr->getMemOperand());
DAG.ReplaceAllUsesOfValueWith(
Op0, extractSubVector(BcastLd, 0, DAG, DL, Op0.getValueSizeInBits()));
DAG.ReplaceAllUsesOfValueWith(SDValue(MemIntr, 1), BcastLd.getValue(1));
return BcastLd;
auto *Mem = cast<MemSDNode>(Op0);
unsigned Opc = Op0.getOpcode() == X86ISD::VBROADCAST_LOAD
? X86ISD::VBROADCAST_LOAD
: X86ISD::SUBV_BROADCAST_LOAD;
if (SDValue BcastLd =
getBROADCAST_LOAD(Opc, DL, VT, Mem->getMemoryVT(), Mem, 0, DAG)) {
SDValue BcastSrc =
extractSubVector(BcastLd, 0, DAG, DL, Op0.getValueSizeInBits());
DAG.ReplaceAllUsesOfValueWith(Op0, BcastSrc);
return BcastLd;
}
}
// If this is a simple subvector load repeated across multiple lanes, then