addRegisterClass(MVT::f128, &SystemZ::FP128BitRegClass);
// Compute derived properties from the register classes
- computeRegisterProperties();
+ computeRegisterProperties(Subtarget.getRegisterInfo());
// Set up special registers.
setExceptionPointerRegister(SystemZ::R6D);
// available, or if the operand is constant.
setOperationAction(ISD::ATOMIC_LOAD_SUB, VT, Custom);
+ // Use POPCNT on z196 and above.
+ if (Subtarget.hasPopulationCount())
+ setOperationAction(ISD::CTPOP, VT, Custom);
+ else
+ setOperationAction(ISD::CTPOP, VT, Expand);
+
// No special instructions for these.
- setOperationAction(ISD::CTPOP, VT, Expand);
setOperationAction(ISD::CTTZ, VT, Expand);
setOperationAction(ISD::CTTZ_ZERO_UNDEF, VT, Expand);
setOperationAction(ISD::CTLZ_ZERO_UNDEF, VT, Expand);
return Imm.isZero() || Imm.isNegZero();
}
+bool SystemZTargetLowering::isLegalICmpImmediate(int64_t Imm) const {
+ // We can use CGFI or CLGFI.
+ return isInt<32>(Imm) || isUInt<32>(Imm);
+}
+
+bool SystemZTargetLowering::isLegalAddImmediate(int64_t Imm) const {
+ // We can use ALGFI or SLGFI.
+ return isUInt<32>(Imm) || isUInt<32>(-Imm);
+}
+
bool SystemZTargetLowering::allowsMisalignedMemoryAccesses(EVT VT,
unsigned,
unsigned,
return std::make_pair(0U, nullptr);
}
-std::pair<unsigned, const TargetRegisterClass *> SystemZTargetLowering::
-getRegForInlineAsmConstraint(const std::string &Constraint, MVT VT) const {
+std::pair<unsigned, const TargetRegisterClass *>
+SystemZTargetLowering::getRegForInlineAsmConstraint(
+ const TargetRegisterInfo *TRI, const std::string &Constraint,
+ MVT VT) const {
if (Constraint.size() == 1) {
// GCC Constraint Letters
switch (Constraint[0]) {
SystemZMC::FP64Regs);
}
}
- return TargetLowering::getRegForInlineAsmConstraint(Constraint, VT);
+ return TargetLowering::getRegForInlineAsmConstraint(TRI, Constraint, VT);
}
void SystemZTargetLowering::
// Add a register mask operand representing the call-preserved registers.
const TargetRegisterInfo *TRI = Subtarget.getRegisterInfo();
- const uint32_t *Mask = TRI->getCallPreservedMask(CallConv);
+ const uint32_t *Mask = TRI->getCallPreservedMask(MF, CallConv);
assert(Mask && "Missing call preserved mask for calling convention");
Ops.push_back(DAG.getRegisterMask(Mask));
MaskVal = -(CmpVal & -CmpVal);
NewC.ICmpType = SystemZICMP::UnsignedOnly;
}
+ if (!MaskVal)
+ return;
// Check whether the combination of mask, comparison value and comparison
// type are suitable.
}
}
- SmallVector<SDValue, 5> Ops;
- Ops.push_back(TrueOp);
- Ops.push_back(FalseOp);
- Ops.push_back(DAG.getConstant(C.CCValid, MVT::i32));
- Ops.push_back(DAG.getConstant(C.CCMask, MVT::i32));
- Ops.push_back(Glue);
+ SDValue Ops[] = {TrueOp, FalseOp, DAG.getConstant(C.CCValid, MVT::i32),
+ DAG.getConstant(C.CCMask, MVT::i32), Glue};
SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
return DAG.getNode(SystemZISD::SELECT_CCMASK, DL, VTs, Ops);
// Add a register mask operand representing the call-preserved registers.
const TargetRegisterInfo *TRI = Subtarget.getRegisterInfo();
- const uint32_t *Mask = TRI->getCallPreservedMask(CallingConv::C);
+ const uint32_t *Mask =
+ TRI->getCallPreservedMask(DAG.getMachineFunction(), CallingConv::C);
assert(Mask && "Missing call preserved mask for calling convention");
Ops.push_back(DAG.getRegisterMask(Mask));
Offset, MachinePointerInfo::getConstantPool(),
false, false, false, 0);
break;
- }
-
- default:
- llvm_unreachable("Unknown TLS model.");
+ }
}
// Add the base and offset together.
MVT::i64, HighOp, Low32);
}
+SDValue SystemZTargetLowering::lowerCTPOP(SDValue Op,
+ SelectionDAG &DAG) const {
+ EVT VT = Op.getValueType();
+ int64_t OrigBitSize = VT.getSizeInBits();
+ SDLoc DL(Op);
+
+ // Get the known-zero mask for the operand.
+ Op = Op.getOperand(0);
+ APInt KnownZero, KnownOne;
+ DAG.computeKnownBits(Op, KnownZero, KnownOne);
+ uint64_t Mask = ~KnownZero.getZExtValue();
+
+ // Skip known-zero high parts of the operand.
+ int64_t BitSize = OrigBitSize;
+ while ((Mask & ((((uint64_t)1 << (BitSize / 2)) - 1) << (BitSize / 2))) == 0)
+ BitSize = BitSize / 2;
+
+ // The POPCNT instruction counts the number of bits in each byte.
+ Op = DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, Op);
+ Op = DAG.getNode(SystemZISD::POPCNT, DL, MVT::i64, Op);
+ Op = DAG.getNode(ISD::TRUNCATE, DL, VT, Op);
+
+ // Add up per-byte counts in a binary tree. All bits of Op at
+ // position larger than BitSize remain zero throughout.
+ for (int64_t I = BitSize / 2; I >= 8; I = I / 2) {
+ SDValue Tmp = DAG.getNode(ISD::SHL, DL, VT, Op, DAG.getConstant(I, VT));
+ if (BitSize != OrigBitSize)
+ Tmp = DAG.getNode(ISD::AND, DL, VT, Tmp,
+ DAG.getConstant(((uint64_t)1 << BitSize) - 1, VT));
+ Op = DAG.getNode(ISD::ADD, DL, VT, Op, Tmp);
+ }
+
+ // Extract overall result from high byte.
+ if (BitSize > 8)
+ Op = DAG.getNode(ISD::SRL, DL, VT, Op, DAG.getConstant(BitSize - 8, VT));
+
+ return Op;
+}
+
// Op is an atomic load. Lower it into a normal volatile load.
SDValue SystemZTargetLowering::lowerATOMIC_LOAD(SDValue Op,
SelectionDAG &DAG) const {
return lowerUDIVREM(Op, DAG);
case ISD::OR:
return lowerOR(Op, DAG);
+ case ISD::CTPOP:
+ return lowerCTPOP(Op, DAG);
case ISD::ATOMIC_SWAP:
return lowerATOMIC_LOAD_OP(Op, DAG, SystemZISD::ATOMIC_SWAPW);
case ISD::ATOMIC_STORE: