Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[RISCV] Fold vector shift of sext/zext to widening multiply #121563

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
80 changes: 78 additions & 2 deletions llvm/lib/Target/RISCV/RISCVISelLowering.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -17341,6 +17341,82 @@ static SDValue combineScalarCTPOPToVCPOP(SDNode *N, SelectionDAG &DAG,
return DAG.getZExtOrTrunc(Pop, DL, VT);
}

static SDValue combineSHL(SDNode *N, TargetLowering::DAGCombinerInfo &DCI,
const RISCVSubtarget &Subtarget) {
// (shl (zext x), y) -> (vwsll x, y)
if (SDValue V = combineOp_VLToVWOp_VL(N, DCI, Subtarget))
return V;

// (shl (sext x), C) -> (vwmulsu x, 1u << C)
// (shl (zext x), C) -> (vwmulu x, 1u << C)

if (!DCI.isAfterLegalizeDAG())
return SDValue();

SDValue LHS = N->getOperand(0);
if (!LHS.hasOneUse())
return SDValue();
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For now, this only handles single-use of sext/zext.
I can rewrite it to be part of combineOp_VLToVWOp_VL so that it handles multi-use too.

unsigned Opcode;
switch (LHS.getOpcode()) {
case ISD::SIGN_EXTEND:
lukel97 marked this conversation as resolved.
Show resolved Hide resolved
case RISCVISD::VSEXT_VL:
Opcode = RISCVISD::VWMULSU_VL;
break;
case ISD::ZERO_EXTEND:
case RISCVISD::VZEXT_VL:
Opcode = RISCVISD::VWMULU_VL;
break;
default:
return SDValue();
}

SDValue RHS = N->getOperand(1);
APInt ShAmt;
uint64_t ShAmtInt;
if (ISD::isConstantSplatVector(RHS.getNode(), ShAmt))
ShAmtInt = ShAmt.getZExtValue();
else if (RHS.getOpcode() == RISCVISD::VMV_V_X_VL &&
RHS.getOperand(1).getOpcode() == ISD::Constant)
ShAmtInt = RHS.getConstantOperandVal(1);
else
return SDValue();

// Better foldings:
// (shl (sext x), 1) -> (vwadd x, x)
// (shl (zext x), 1) -> (vwaddu x, x)
if (ShAmtInt <= 1)
return SDValue();

SDValue NarrowOp = LHS.getOperand(0);
MVT NarrowVT = NarrowOp.getSimpleValueType();
uint64_t NarrowBits = NarrowVT.getScalarSizeInBits();
if (ShAmtInt >= NarrowBits)
return SDValue();
MVT VT = N->getSimpleValueType(0);
if (NarrowBits * 2 != VT.getScalarSizeInBits())
return SDValue();

SelectionDAG &DAG = DCI.DAG;
SDLoc DL(N);
SDValue Passthru, Mask, VL;
switch (N->getOpcode()) {
case ISD::SHL:
Passthru = DAG.getUNDEF(VT);
lukel97 marked this conversation as resolved.
Show resolved Hide resolved
std::tie(Mask, VL) = getDefaultScalableVLOps(VT, DL, DAG, Subtarget);
break;
case RISCVISD::SHL_VL:
Passthru = N->getOperand(2);
Mask = N->getOperand(3);
VL = N->getOperand(4);
break;
default:
llvm_unreachable("Expected SHL");
}
return DAG.getNode(Opcode, DL, VT, NarrowOp,
DAG.getConstant(1ULL << ShAmtInt, SDLoc(RHS), NarrowVT),
Passthru, Mask, VL);
}

SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
DAGCombinerInfo &DCI) const {
SelectionDAG &DAG = DCI.DAG;
Expand Down Expand Up @@ -17970,7 +18046,7 @@ SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
break;
}
case RISCVISD::SHL_VL:
if (SDValue V = combineOp_VLToVWOp_VL(N, DCI, Subtarget))
if (SDValue V = combineSHL(N, DCI, Subtarget))
return V;
[[fallthrough]];
case RISCVISD::SRA_VL:
Expand All @@ -17995,7 +18071,7 @@ SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
case ISD::SRL:
case ISD::SHL: {
if (N->getOpcode() == ISD::SHL) {
if (SDValue V = combineOp_VLToVWOp_VL(N, DCI, Subtarget))
if (SDValue V = combineSHL(N, DCI, Subtarget))
return V;
}
SDValue ShAmt = N->getOperand(1);
Expand Down
Loading
Loading