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

[Hexagon] Start using regmasks on calls 

Reapply r295371 with a fix for the Windows bot failures.

llvm-svn: 295504
This commit is contained in:
Krzysztof Parzyszek 2017-02-17 22:14:51 +00:00
parent bca05df38b
commit 1aaf41af54
20 changed files with 273 additions and 119 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
llvm/lib/Target/Hexagon/HexagonBlockRanges.cpp
View File

@ -306,6 +306,8 @@ void HexagonBlockRanges::computeInitialLiveRanges(InstrIndexMap &IndexMap,
LastUse[R] = LastDef[R] = IndexType::None;
};
RegisterSet Defs, Clobbers;
for (auto &In : B) {
if (In.isDebugValue())
continue;
@ -324,19 +326,68 @@ void HexagonBlockRanges::computeInitialLiveRanges(InstrIndexMap &IndexMap,
closeRange(S);
}
}
// Process defs.
// Process defs and clobbers.
Defs.clear();
Clobbers.clear();
for (auto &Op : In.operands()) {
if (!Op.isReg() || !Op.isDef() || Op.isUndef())
continue;
RegisterRef R = { Op.getReg(), Op.getSubReg() };
if (TargetRegisterInfo::isPhysicalRegister(R.Reg) && Reserved[R.Reg])
continue;
for (auto S : expandToSubRegs(R, MRI, TRI)) {
if (LastDef[S] != IndexType::None || LastUse[S] != IndexType::None)
closeRange(S);
LastDef[S] = Index;
if (TargetRegisterInfo::isPhysicalRegister(S.Reg) && Reserved[S.Reg])
continue;
if (Op.isDead())
Clobbers.insert(S);
else
Defs.insert(S);
}
}
for (auto &Op : In.operands()) {
if (!Op.isRegMask())
continue;
const uint32_t *BM = Op.getRegMask();
for (unsigned PR = 1, N = TRI.getNumRegs(); PR != N; ++PR) {
// Skip registers that have subregisters. A register is preserved
// iff its bit is set in the regmask, so if R1:0 was preserved, both
// R1 and R0 would also be present.
if (MCSubRegIterator(PR, &TRI, false).isValid())
continue;
if (Reserved[PR])
continue;
if (BM[PR/32] & (1u << (PR%32)))
continue;
RegisterRef R = { PR, 0 };
if (!Defs.count(R))
Clobbers.insert(R);
}
}
#ifndef NDEBUG
for (RegisterRef R : Defs)
assert(!Clobbers.count(R));
for (RegisterRef R : Clobbers)
assert(!Defs.count(R));
#endif
// Update maps for defs.
for (RegisterRef S : Defs) {
// Defs should already be expanded into subregs.
assert(!TargetRegisterInfo::isPhysicalRegister(S.Reg) ||
!MCSubRegIterator(S.Reg, &TRI, false).isValid());
if (LastDef[S] != IndexType::None || LastUse[S] != IndexType::None)
closeRange(S);
LastDef[S] = Index;
}
// Update maps for clobbers.
for (RegisterRef S : Clobbers) {
// Clobbers should already be expanded into subregs.
assert(!TargetRegisterInfo::isPhysicalRegister(S.Reg) ||
!MCSubRegIterator(S.Reg, &TRI, false).isValid());
if (LastDef[S] != IndexType::None || LastUse[S] != IndexType::None)
closeRange(S);
// Create a single-instruction range.
LastDef[S] = LastUse[S] = Index;
closeRange(S);
}
}
// Collect live-on-exit.

26
llvm/lib/Target/Hexagon/HexagonCopyToCombine.cpp
View File

@ -440,17 +440,21 @@ HexagonCopyToCombine::findPotentialNewifiableTFRs(MachineBasicBlock &BB) {
// Put instructions that last defined integer or double registers into the
// map.
for (unsigned I = 0, E = MI.getNumOperands(); I != E; ++I) {
MachineOperand &Op = MI.getOperand(I);
if (!Op.isReg() || !Op.isDef() || !Op.getReg())
continue;
unsigned Reg = Op.getReg();
if (Hexagon::DoubleRegsRegClass.contains(Reg)) {
for (MCSubRegIterator SubRegs(Reg, TRI); SubRegs.isValid(); ++SubRegs) {
LastDef[*SubRegs] = &MI;
}
} else if (Hexagon::IntRegsRegClass.contains(Reg))
LastDef[Reg] = &MI;
for (MachineOperand &Op : MI.operands()) {
if (Op.isReg()) {
if (!Op.isDef() || !Op.getReg())
continue;
unsigned Reg = Op.getReg();
if (Hexagon::DoubleRegsRegClass.contains(Reg)) {
for (MCSubRegIterator SubRegs(Reg, TRI); SubRegs.isValid(); ++SubRegs)
LastDef[*SubRegs] = &MI;
} else if (Hexagon::IntRegsRegClass.contains(Reg))
LastDef[Reg] = &MI;
} else if (Op.isRegMask()) {
for (unsigned Reg : Hexagon::IntRegsRegClass)
if (Op.clobbersPhysReg(Reg))
LastDef[Reg] = &MI;
}
}
}
}

6
llvm/lib/Target/Hexagon/HexagonDepInstrInfo.td
View File

@ -4665,7 +4665,6 @@ let Defs = [PC, R31];
let BaseOpcode = "J2_call";
let isPredicable = 1;
let hasSideEffects = 1;
let Defs = VolatileV3.Regs;
let isExtendable = 1;
let opExtendable = 0;
let isExtentSigned = 1;
@ -4690,7 +4689,6 @@ let Defs = [PC, R31];
let BaseOpcode = "J2_call";
let hasSideEffects = 1;
let isTaken = Inst{12};
let Defs = VolatileV3.Regs;
let isExtendable = 1;
let opExtendable = 1;
let isExtentSigned = 1;
@ -4710,7 +4708,6 @@ let prefersSlot3 = 1;
let Uses = [R29];
let Defs = [PC, R31];
let hasSideEffects = 1;
let Defs = VolatileV3.Regs;
}
def J2_callrf : HInst<
(outs),
@ -4729,7 +4726,6 @@ let Uses = [R29];
let Defs = [PC, R31];
let hasSideEffects = 1;
let isTaken = Inst{12};
let Defs = VolatileV3.Regs;
}
def J2_callrt : HInst<
(outs),
@ -4747,7 +4743,6 @@ let Uses = [R29];
let Defs = [PC, R31];
let hasSideEffects = 1;
let isTaken = Inst{12};
let Defs = VolatileV3.Regs;
}
def J2_callt : HInst<
(outs),
@ -4766,7 +4761,6 @@ let Defs = [PC, R31];
let BaseOpcode = "J2_call";
let hasSideEffects = 1;
let isTaken = Inst{12};
let Defs = VolatileV3.Regs;
let isExtendable = 1;
let opExtendable = 1;
let isExtentSigned = 1;

34
llvm/lib/Target/Hexagon/HexagonFrameLowering.cpp
View File

@ -301,16 +301,30 @@ static bool needsStackFrame(const MachineBasicBlock &MBB, const BitVector &CSR,
// the frame creation/destruction instructions.
if (MO.isFI())
return true;
if (!MO.isReg())
continue;
unsigned R = MO.getReg();
// Virtual registers will need scavenging, which then may require
// a stack slot.
if (TargetRegisterInfo::isVirtualRegister(R))
return true;
for (MCSubRegIterator S(R, &HRI, true); S.isValid(); ++S)
if (CSR[*S])
if (MO.isReg()) {
unsigned R = MO.getReg();
// Virtual registers will need scavenging, which then may require
// a stack slot.
if (TargetRegisterInfo::isVirtualRegister(R))
return true;
for (MCSubRegIterator S(R, &HRI, true); S.isValid(); ++S)
if (CSR[*S])
return true;
continue;
}
if (MO.isRegMask()) {
// A regmask would normally have all callee-saved registers marked
// as preserved, so this check would not be needed, but in case of
// ever having other regmasks (for other calling conventions),
// make sure they would be processed correctly.
const uint32_t *BM = MO.getRegMask();
for (int x = CSR.find_first(); x >= 0; x = CSR.find_next(x)) {
unsigned R = x;
// If this regmask does not preserve a CSR, a frame will be needed.
if (!(BM[R/32] & (1u << (R%32))))
return true;
}
}
}
}
return false;
@ -1651,7 +1665,7 @@ bool HexagonFrameLowering::expandStoreVec2(MachineBasicBlock &B,
// Dead defs are recorded in Clobbers, but are not automatically removed
// from the live set.
for (auto &C : Clobbers)
if (C.second->isDead())
if (C.second->isReg() && C.second->isDead())
LPR.removeReg(C.first);
}

24
llvm/lib/Target/Hexagon/HexagonHardwareLoops.cpp
View File

@ -100,6 +100,7 @@ namespace {
MachineRegisterInfo *MRI;
MachineDominatorTree *MDT;
const HexagonInstrInfo *TII;
const HexagonRegisterInfo *TRI;
#ifndef NDEBUG
static int Counter;
#endif
@ -381,7 +382,9 @@ bool HexagonHardwareLoops::runOnMachineFunction(MachineFunction &MF) {
MLI = &getAnalysis<MachineLoopInfo>();
MRI = &MF.getRegInfo();
MDT = &getAnalysis<MachineDominatorTree>();
TII = MF.getSubtarget<HexagonSubtarget>().getInstrInfo();
const HexagonSubtarget &HST = MF.getSubtarget<HexagonSubtarget>();
TII = HST.getInstrInfo();
TRI = HST.getRegisterInfo();
for (auto &L : *MLI)
if (!L->getParentLoop()) {
@ -960,24 +963,21 @@ CountValue *HexagonHardwareLoops::computeCount(MachineLoop *Loop,
/// \brief Return true if the operation is invalid within hardware loop.
bool HexagonHardwareLoops::isInvalidLoopOperation(const MachineInstr *MI,
bool IsInnerHWLoop) const {
// Call is not allowed because the callee may use a hardware loop except for
// the case when the call never returns.
if (MI->getDesc().isCall())
return !TII->doesNotReturn(*MI);
// Check if the instruction defines a hardware loop register.
for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
const MachineOperand &MO = MI->getOperand(i);
if (!MO.isReg() || !MO.isDef())
continue;
unsigned R = MO.getReg();
if (IsInnerHWLoop && (R == Hexagon::LC0 || R == Hexagon::SA0 ||
R == Hexagon::LC1 || R == Hexagon::SA1))
using namespace Hexagon;
static const unsigned Regs01[] = { LC0, SA0, LC1, SA1 };
static const unsigned Regs1[] = { LC1, SA1 };
auto CheckRegs = IsInnerHWLoop ? makeArrayRef(Regs01, array_lengthof(Regs01))
: makeArrayRef(Regs1, array_lengthof(Regs1));
for (unsigned R : CheckRegs)
if (MI->modifiesRegister(R, TRI))
return true;
if (!IsInnerHWLoop && (R == Hexagon::LC1 || R == Hexagon::SA1))
return true;
}
return false;
}

51
llvm/lib/Target/Hexagon/HexagonISelLowering.cpp
View File

@ -644,11 +644,11 @@ bool HexagonTargetLowering::mayBeEmittedAsTailCall(CallInst *CI) const {
/// LowerCallResult - Lower the result values of an ISD::CALL into the
/// appropriate copies out of appropriate physical registers. This assumes that
/// Chain/InFlag are the input chain/flag to use, and that TheCall is the call
/// Chain/Glue are the input chain/glue to use, and that TheCall is the call
/// being lowered. Returns a SDNode with the same number of values as the
/// ISD::CALL.
SDValue HexagonTargetLowering::LowerCallResult(
SDValue Chain, SDValue InFlag, CallingConv::ID CallConv, bool isVarArg,
SDValue Chain, SDValue Glue, CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals,
const SmallVectorImpl<SDValue> &OutVals, SDValue Callee) const {
@ -671,21 +671,24 @@ SDValue HexagonTargetLowering::LowerCallResult(
// predicate register as the call result.
auto &MRI = DAG.getMachineFunction().getRegInfo();
SDValue FR0 = DAG.getCopyFromReg(Chain, dl, RVLocs[i].getLocReg(),
MVT::i32, InFlag);
MVT::i32, Glue);
// FR0 = (Value, Chain, Glue)
unsigned PredR = MRI.createVirtualRegister(&Hexagon::PredRegsRegClass);
SDValue TPR = DAG.getCopyToReg(FR0.getValue(1), dl, PredR,
FR0.getValue(0), FR0.getValue(2));
// TPR = (Chain, Glue)
RetVal = DAG.getCopyFromReg(TPR.getValue(0), dl, PredR, MVT::i1,
TPR.getValue(1));
// Don't glue this CopyFromReg, because it copies from a virtual
// register. If it is glued to the call, InstrEmitter will add it
// as an implicit def to the call (EmitMachineNode).
RetVal = DAG.getCopyFromReg(TPR.getValue(0), dl, PredR, MVT::i1);
Glue = TPR.getValue(1);
} else {
RetVal = DAG.getCopyFromReg(Chain, dl, RVLocs[i].getLocReg(),
RVLocs[i].getValVT(), InFlag);
RVLocs[i].getValVT(), Glue);
Glue = RetVal.getValue(2);
}
InVals.push_back(RetVal.getValue(0));
Chain = RetVal.getValue(1);
InFlag = RetVal.getValue(2);
}
return Chain;
@ -840,16 +843,17 @@ HexagonTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
if (!MemOpChains.empty())
Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, MemOpChains);
SDValue Glue;
if (!IsTailCall) {
SDValue C = DAG.getConstant(NumBytes, dl, PtrVT, true);
Chain = DAG.getCALLSEQ_START(Chain, C, dl);
Glue = Chain.getValue(1);
}
// Build a sequence of copy-to-reg nodes chained together with token
// chain and flag operands which copy the outgoing args into registers.
// The Glue is necessary since all emitted instructions must be
// stuck together.
SDValue Glue;
if (!IsTailCall) {
for (unsigned i = 0, e = RegsToPass.size(); i != e; ++i) {
Chain = DAG.getCopyToReg(Chain, dl, RegsToPass[i].first,
@ -902,6 +906,10 @@ HexagonTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
RegsToPass[i].second.getValueType()));
}
const uint32_t *Mask = HRI.getCallPreservedMask(MF, CallConv);
assert(Mask && "Missing call preserved mask for calling convention");
Ops.push_back(DAG.getRegisterMask(Mask));
if (Glue.getNode())
Ops.push_back(Glue);
@ -1571,9 +1579,10 @@ HexagonTargetLowering::LowerGLOBAL_OFFSET_TABLE(SDValue Op, SelectionDAG &DAG)
SDValue
HexagonTargetLowering::GetDynamicTLSAddr(SelectionDAG &DAG, SDValue Chain,
GlobalAddressSDNode *GA, SDValue *InFlag, EVT PtrVT, unsigned ReturnReg,
GlobalAddressSDNode *GA, SDValue Glue, EVT PtrVT, unsigned ReturnReg,
unsigned char OperandFlags) const {
MachineFrameInfo &MFI = DAG.getMachineFunction().getFrameInfo();
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo &MFI = MF.getFrameInfo();
SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
SDLoc dl(GA);
SDValue TGA = DAG.getTargetGlobalAddress(GA->getGlobal(), dl,
@ -1585,23 +1594,21 @@ HexagonTargetLowering::GetDynamicTLSAddr(SelectionDAG &DAG, SDValue Chain,
// 2. Callee which in this case is the Global address value.
// 3. Registers live into the call.In this case its R0, as we
// have just one argument to be passed.
// 4. InFlag if there is any.
// 4. Glue.
// Note: The order is important.
if (InFlag) {
SDValue Ops[] = { Chain, TGA,
DAG.getRegister(Hexagon::R0, PtrVT), *InFlag };
Chain = DAG.getNode(HexagonISD::CALL, dl, NodeTys, Ops);
} else {
SDValue Ops[] = { Chain, TGA, DAG.getRegister(Hexagon::R0, PtrVT)};
Chain = DAG.getNode(HexagonISD::CALL, dl, NodeTys, Ops);
}
const auto &HRI = *Subtarget.getRegisterInfo();
const uint32_t *Mask = HRI.getCallPreservedMask(MF, CallingConv::C);
assert(Mask && "Missing call preserved mask for calling convention");
SDValue Ops[] = { Chain, TGA, DAG.getRegister(Hexagon::R0, PtrVT),
DAG.getRegisterMask(Mask), Glue };
Chain = DAG.getNode(HexagonISD::CALL, dl, NodeTys, Ops);
// Inform MFI that function has calls.
MFI.setAdjustsStack(true);
SDValue Flag = Chain.getValue(1);
return DAG.getCopyFromReg(Chain, dl, ReturnReg, PtrVT, Flag);
Glue = Chain.getValue(1);
return DAG.getCopyFromReg(Chain, dl, ReturnReg, PtrVT, Glue);
}
//
@ -1694,7 +1701,7 @@ HexagonTargetLowering::LowerToTLSGeneralDynamicModel(GlobalAddressSDNode *GA,
Chain = DAG.getCopyToReg(DAG.getEntryNode(), dl, Hexagon::R0, Chain, InFlag);
InFlag = Chain.getValue(1);
return GetDynamicTLSAddr(DAG, Chain, GA, &InFlag, PtrVT,
return GetDynamicTLSAddr(DAG, Chain, GA, InFlag, PtrVT,
Hexagon::R0, HexagonII::MO_GDPLT);
}

2
llvm/lib/Target/Hexagon/HexagonISelLowering.h
View File

@ -163,7 +163,7 @@ namespace HexagonISD {
SDValue LowerToTLSLocalExecModel(GlobalAddressSDNode *GA,
SelectionDAG &DAG) const;
SDValue GetDynamicTLSAddr(SelectionDAG &DAG, SDValue Chain,
GlobalAddressSDNode *GA, SDValue *InFlag, EVT PtrVT,
GlobalAddressSDNode *GA, SDValue InFlag, EVT PtrVT,
unsigned ReturnReg, unsigned char OperandFlags) const;
SDValue LowerGLOBAL_OFFSET_TABLE(SDValue Op, SelectionDAG &DAG) const;

20
llvm/lib/Target/Hexagon/HexagonInstrInfo.cpp
View File

@ -1413,12 +1413,22 @@ bool HexagonInstrInfo::DefinesPredicate(
auto &HRI = getRegisterInfo();
for (unsigned oper = 0; oper < MI.getNumOperands(); ++oper) {
MachineOperand MO = MI.getOperand(oper);
if (MO.isReg() && MO.isDef()) {
if (MO.isReg()) {
if (!MO.isDef())
continue;
const TargetRegisterClass* RC = HRI.getMinimalPhysRegClass(MO.getReg());
if (RC == &Hexagon::PredRegsRegClass) {
Pred.push_back(MO);
return true;
}
continue;
} else if (MO.isRegMask()) {
for (unsigned PR : Hexagon::PredRegsRegClass) {
if (!MI.modifiesRegister(PR, &HRI))
continue;
Pred.push_back(MO);
return true;
}
}
}
return false;
@ -3009,10 +3019,12 @@ bool HexagonInstrInfo::producesStall(const MachineInstr &MI,
bool HexagonInstrInfo::predCanBeUsedAsDotNew(const MachineInstr &MI,
unsigned PredReg) const {
for (unsigned opNum = 0; opNum < MI.getNumOperands(); opNum++) {
const MachineOperand &MO = MI.getOperand(opNum);
for (const MachineOperand &MO : MI.operands()) {
// Predicate register must be explicitly defined.
if (MO.isRegMask() && MO.clobbersPhysReg(PredReg))
return false;
if (MO.isReg() && MO.isDef() && MO.isImplicit() && (MO.getReg() == PredReg))
return false; // Predicate register must be explicitly defined.
return false;
}
// Hexagon Programmer's Reference says that decbin, memw_locked, and

5
llvm/lib/Target/Hexagon/HexagonMCInstLower.cpp
View File

@ -111,9 +111,12 @@ void llvm::HexagonLowerToMC(const MCInstrInfo &MCII, const MachineInstr *MI,
default:
MI->print(errs());
llvm_unreachable("unknown operand type");
case MachineOperand::MO_RegisterMask:
continue;
case MachineOperand::MO_Register:
// Ignore all implicit register operands.
if (MO.isImplicit()) continue;
if (MO.isImplicit())
continue;
MCO = MCOperand::createReg(MO.getReg());
break;
case MachineOperand::MO_FPImmediate: {

35
llvm/lib/Target/Hexagon/HexagonPseudo.td
View File

@ -141,13 +141,12 @@ defm J2_loop1 : LOOP_ri<"loop1">;
let isCall = 1, hasSideEffects = 1, isPredicable = 0,
isExtended = 0, isExtendable = 1, opExtendable = 0,
isExtentSigned = 1, opExtentBits = 24, opExtentAlign = 2 in
class T_Call<bit CSR, string ExtStr>
class T_Call<string ExtStr>
: JInst<(outs), (ins a30_2Imm:$dst),
"call " # ExtStr # "$dst", [], "", J_tc_2early_SLOT23> {
let BaseOpcode = "call";
bits<24> dst;
let Defs = !if (CSR, VolatileV3.Regs, []);
let IClass = 0b0101;
let Inst{27-25} = 0b101;
let Inst{24-16,13-1} = dst{23-2};
@ -156,11 +155,11 @@ class T_Call<bit CSR, string ExtStr>
let isCodeGenOnly = 1, isCall = 1, hasSideEffects = 1, Defs = [R16],
isPredicable = 0 in
def CALLProfile : T_Call<1, "">;
def CALLProfile : T_Call<"">;
let isCodeGenOnly = 1, isCall = 1, hasSideEffects = 1,
Defs = [PC, R31, R6, R7, P0] in
def PS_call_stk : T_Call<0, "">;
def PS_call_stk : T_Call<"">;
let isCall = 1, hasSideEffects = 1, cofMax1 = 1 in
class JUMPR_MISC_CALLR<bit isPred, bit isPredNot,
@ -185,11 +184,11 @@ class JUMPR_MISC_CALLR<bit isPred, bit isPredNot,
}
let isCodeGenOnly = 1, Defs = VolatileV3.Regs in {
let isCodeGenOnly = 1 in {
def PS_callr_nr : JUMPR_MISC_CALLR<0, 1>; // Call, no return.
}
let isCall = 1, hasSideEffects = 1, Defs = VolatileV3.Regs,
let isCall = 1, hasSideEffects = 1,
isExtended = 0, isExtendable = 1, opExtendable = 0, isCodeGenOnly = 1,
BaseOpcode = "PS_call_nr", isExtentSigned = 1, opExtentAlign = 2,
Itinerary = J_tc_2early_SLOT23 in
@ -375,43 +374,43 @@ let isCall = 1, isBarrier = 1, isReturn = 1, isTerminator = 1,
// Restore registers and dealloc frame before a tail call.
let isCall = 1, Defs = [R29, R30, R31, PC], isAsmParserOnly = 1 in {
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4 : T_Call<0, "">, PredRel;
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4 : T_Call<"">, PredRel;
let isExtended = 1, opExtendable = 0 in
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4_EXT : T_Call<0, "">, PredRel;
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4_EXT : T_Call<"">, PredRel;
let Defs = [R14, R15, R28, R29, R30, R31, PC] in {
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4_PIC : T_Call<0, "">, PredRel;
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4_PIC : T_Call<"">, PredRel;
let isExtended = 1, opExtendable = 0 in
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4_EXT_PIC : T_Call<0, "">, PredRel;
def RESTORE_DEALLOC_BEFORE_TAILCALL_V4_EXT_PIC : T_Call<"">, PredRel;
}
}
// Save registers function call.
let isCall = 1, Uses = [R29, R31], isAsmParserOnly = 1 in {
def SAVE_REGISTERS_CALL_V4 : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4 : T_Call<"">, PredRel;
let isExtended = 1, opExtendable = 0 in
def SAVE_REGISTERS_CALL_V4_EXT : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4_EXT : T_Call<"">, PredRel;
let Defs = [P0] in
def SAVE_REGISTERS_CALL_V4STK : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4STK : T_Call<"">, PredRel;
let Defs = [P0], isExtended = 1, opExtendable = 0 in
def SAVE_REGISTERS_CALL_V4STK_EXT : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4STK_EXT : T_Call<"">, PredRel;
let Defs = [R14, R15, R28] in
def SAVE_REGISTERS_CALL_V4_PIC : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4_PIC : T_Call<"">, PredRel;
let Defs = [R14, R15, R28], isExtended = 1, opExtendable = 0 in
def SAVE_REGISTERS_CALL_V4_EXT_PIC : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4_EXT_PIC : T_Call<"">, PredRel;
let Defs = [R14, R15, R28, P0] in
def SAVE_REGISTERS_CALL_V4STK_PIC : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4STK_PIC : T_Call<"">, PredRel;
let Defs = [R14, R15, R28, P0], isExtended = 1, opExtendable = 0 in
def SAVE_REGISTERS_CALL_V4STK_EXT_PIC : T_Call<0, "">, PredRel;
def SAVE_REGISTERS_CALL_V4STK_EXT_PIC : T_Call<"">, PredRel;
}
// Vector load/store pseudos

12
llvm/lib/Target/Hexagon/HexagonRegisterInfo.cpp
View File

@ -36,6 +36,9 @@
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#define GET_REGINFO_TARGET_DESC
#include "HexagonGenRegisterInfo.inc"
using namespace llvm;
HexagonRegisterInfo::HexagonRegisterInfo()
@ -134,6 +137,12 @@ HexagonRegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
}
const uint32_t *HexagonRegisterInfo::getCallPreservedMask(
const MachineFunction &MF, CallingConv::ID) const {
return HexagonCSR_RegMask;
}
BitVector HexagonRegisterInfo::getReservedRegs(const MachineFunction &MF)
const {
BitVector Reserved(getNumRegs());
@ -284,6 +293,3 @@ unsigned HexagonRegisterInfo::getFirstCallerSavedNonParamReg() const {
return Hexagon::R6;
}
#define GET_REGINFO_TARGET_DESC
#include "HexagonGenRegisterInfo.inc"

3
llvm/lib/Target/Hexagon/HexagonRegisterInfo.h
View File

@ -35,7 +35,8 @@ public:
/// Code Generation virtual methods...
const MCPhysReg *getCalleeSavedRegs(const MachineFunction *MF)
const override;
const uint32_t *getCallPreservedMask(const MachineFunction &MF,
CallingConv::ID) const override;
BitVector getReservedRegs(const MachineFunction &MF) const override;

17
llvm/lib/Target/Hexagon/HexagonRegisterInfo.td
View File

@ -301,16 +301,7 @@ def V62Regs : RegisterClass<"Hexagon", [i32], 32,
PKTCOUNTLO, PKTCOUNTHI, PKTCOUNT,
UTIMERLO, UTIMERHI, UTIMER)>;
def VolatileV3 {
list<Register> Regs = [D0, D1, D2, D3, D4, D5, D6, D7,
R28, R31,
P0, P1, P2, P3,
M0, M1,
LC0, LC1, SA0, SA1, USR, USR_OVF, CS0, CS1,
V0, V1, V2, V3, V4, V5, V6, V7, V8, V9, V10, V11,
V12, V13, V14, V15, V16, V17, V18, V19, V20, V21,
V22, V23, V24, V25, V26, V27, V28, V29, V30, V31,
W0, W1, W2, W3, W4, W5, W6, W7, W8, W9, W10, W11,
W12, W13, W14, W15,
Q0, Q1, Q2, Q3];
}
def HexagonCSR
: CalleeSavedRegs<(add R16, R17, R18, R19, R20, R21, R22, R23,
R24, R25, R26, R27)>;

57
llvm/lib/Target/Hexagon/HexagonVLIWPacketizer.cpp
View File

@ -720,6 +720,8 @@ bool HexagonPacketizerList::canPromoteToNewValueStore(const MachineInstr &MI,
// %R9<def> = ZXTH %R12, %D6<imp-use>, %R12<imp-def>
// S2_storerh_io %R8, 2, %R12<kill>; mem:ST2[%scevgep343]
for (auto &MO : PacketMI.operands()) {
if (MO.isRegMask() && MO.clobbersPhysReg(DepReg))
return false;
if (!MO.isReg() || !MO.isDef() || !MO.isImplicit())
continue;
unsigned R = MO.getReg();
@ -759,9 +761,12 @@ bool HexagonPacketizerList::canPromoteToNewValue(const MachineInstr &MI,
}
static bool isImplicitDependency(const MachineInstr &I, unsigned DepReg) {
for (auto &MO : I.operands())
for (auto &MO : I.operands()) {
if (MO.isRegMask() && MO.clobbersPhysReg(DepReg))
return true;
if (MO.isReg() && MO.isDef() && (MO.getReg() == DepReg) && MO.isImplicit())
return true;
}
return false;
}
@ -1173,6 +1178,36 @@ bool HexagonPacketizerList::hasControlDependence(const MachineInstr &I,
(J.isBranch() || J.isCall() || J.isBarrier());
}
bool HexagonPacketizerList::hasRegMaskDependence(const MachineInstr &I,
const MachineInstr &J) {
// Adding I to a packet that has J.
// Regmasks are not reflected in the scheduling dependency graph, so
// we need to check them manually. This code assumes that regmasks only
// occur on calls, and the problematic case is when we add an instruction
// defining a register R to a packet that has a call that clobbers R via
// a regmask. Those cannot be packetized together, because the call will
// be executed last. That's also a reson why it is ok to add a call
// clobbering R to a packet that defines R.
// Look for regmasks in J.
for (const MachineOperand &OpJ : J.operands()) {
if (!OpJ.isRegMask())
continue;
assert((J.isCall() || HII->isTailCall(J)) && "Regmask on a non-call");
for (const MachineOperand &OpI : I.operands()) {
if (OpI.isReg()) {
if (OpJ.clobbersPhysReg(OpI.getReg()))
return true;
} else if (OpI.isRegMask()) {
// Both are regmasks. Assume that they intersect.
return true;
}
}
}
return false;
}
bool HexagonPacketizerList::hasV4SpecificDependence(const MachineInstr &I,
const MachineInstr &J) {
bool SysI = isSystemInstr(I), SysJ = isSystemInstr(J);
@ -1219,6 +1254,14 @@ bool HexagonPacketizerList::isLegalToPacketizeTogether(SUnit *SUI, SUnit *SUJ) {
if (Dependence)
return false;
// Regmasks are not accounted for in the scheduling graph, so we need
// to explicitly check for dependencies caused by them. They should only
// appear on calls, so it's not too pessimistic to reject all regmask
// dependencies.
Dependence = hasRegMaskDependence(I, J);
if (Dependence)
return false;
// V4 allows dual stores. It does not allow second store, if the first
// store is not in SLOT0. New value store, new value jump, dealloc_return
// and memop always take SLOT0. Arch spec 3.4.4.2.
@ -1467,13 +1510,19 @@ bool HexagonPacketizerList::isLegalToPacketizeTogether(SUnit *SUI, SUnit *SUJ) {
// R0 = ... ; SUI
// Those cannot be packetized together, since the call will observe
// the effect of the assignment to R0.
if (DepType == SDep::Anti && J.isCall()) {
if ((DepType == SDep::Anti || DepType == SDep::Output) && J.isCall()) {
// Check if I defines any volatile register. We should also check
// registers that the call may read, but these happen to be a
// subset of the volatile register set.
for (const MCPhysReg *P = J.getDesc().ImplicitDefs; P && *P; ++P) {
if (!I.modifiesRegister(*P, HRI))
for (const MachineOperand &Op : I.operands()) {
if (Op.isReg() && Op.isDef()) {
unsigned R = Op.getReg();
if (!J.readsRegister(R, HRI) && !J.modifiesRegister(R, HRI))
continue;
} else if (!Op.isRegMask()) {
// If I has a regmask assume dependency.
continue;
}
FoundSequentialDependence = true;
break;
}

1
llvm/lib/Target/Hexagon/HexagonVLIWPacketizer.h
View File

@ -112,6 +112,7 @@ protected:
void reserveResourcesForConstExt();
bool hasDeadDependence(const MachineInstr &I, const MachineInstr &J);
bool hasControlDependence(const MachineInstr &I, const MachineInstr &J);
bool hasRegMaskDependence(const MachineInstr &I, const MachineInstr &J);
bool hasV4SpecificDependence(const MachineInstr &I, const MachineInstr &J);
bool producesStall(const MachineInstr &MI);
};

12
llvm/lib/Target/Hexagon/RDFDeadCode.cpp
View File

@ -62,9 +62,19 @@ bool DeadCodeElimination::isLiveInstr(const MachineInstr *MI) const {
return true;
if (MI->isPHI())
return false;
for (auto &Op : MI->operands())
for (auto &Op : MI->operands()) {
if (Op.isReg() && MRI.isReserved(Op.getReg()))
return true;
if (Op.isRegMask()) {
const uint32_t *BM = Op.getRegMask();
for (unsigned R = 0, RN = DFG.getTRI().getNumRegs(); R != RN; ++R) {
if (BM[R/32] & (1u << (R%32)))
continue;
if (MRI.isReserved(R))
return true;
}
}
}
return false;
}

15
llvm/lib/Target/Hexagon/RDFRegisters.cpp
View File

@ -70,18 +70,27 @@ std::set<RegisterId> PhysicalRegisterInfo::getAliasSet(RegisterId Reg) const {
assert(isRegMaskId(Reg) || TargetRegisterInfo::isPhysicalRegister(Reg));
if (isRegMaskId(Reg)) {
// XXX SLOW
// XXX Add other regmasks to the set.
const uint32_t *MB = getRegMaskBits(Reg);
for (unsigned i = 1, e = TRI.getNumRegs(); i != e; ++i) {
if (MB[i/32] & (1u << (i%32)))
continue;
AS.insert(i);
}
for (const uint32_t *RM : RegMasks) {
RegisterId MI = getRegMaskId(RM);
if (MI != Reg && aliasMM(RegisterRef(Reg), RegisterRef(MI)))
AS.insert(MI);
}
return AS;
}
for (MCRegAliasIterator AI(Reg, &TRI, false); AI.isValid(); ++AI)
AS.insert(*AI);
for (const uint32_t *RM : RegMasks) {
RegisterId MI = getRegMaskId(RM);
if (aliasRM(RegisterRef(Reg), RegisterRef(MI)))
AS.insert(MI);
}
return AS;
}
@ -153,10 +162,10 @@ bool PhysicalRegisterInfo::aliasRM(RegisterRef RR, RegisterRef RM) const {
// is a superset of the lane mask from the register class, check the regmask
// bit directly.
if (RR.Mask == LaneBitmask::getAll())
return Preserved;
return !Preserved;
const TargetRegisterClass *RC = RegInfos[RR.Reg].RegClass;
if (RC != nullptr && (RR.Mask & RC->LaneMask) == RC->LaneMask)
return Preserved;
return !Preserved;
// Otherwise, check all subregisters whose lane mask overlaps the given
// mask. For each such register, if it is preserved by the regmask, then

4
llvm/lib/Target/Hexagon/RDFRegisters.h
View File

@ -51,6 +51,10 @@ namespace rdf {
return F - Map.begin() + 1;
}
typedef typename std::vector<T>::const_iterator const_iterator;
const_iterator begin() const { return Map.begin(); }
const_iterator end() const { return Map.end(); }
private:
std::vector<T> Map;
};

1
llvm/test/CodeGen/Hexagon/avoid-predspill-calleesaved.ll
View File

@ -7,7 +7,6 @@
; without adding an extra spill of that register.
;
; CHECK: PredSpill:
; CHECK: memd(r29{{.*}}) = r17:16
; CHECK-DAG: r{{[0-9]+}} = p0
; CHECK-DAG: p0 = r{{[0-9]+}}
; CHECK-NOT: = memw(r29

4
llvm/test/CodeGen/Hexagon/compound.ll
View File

@ -1,4 +1,4 @@
; RUN: llc -march=hexagon -filetype=obj -o - %s | llvm-objdump -d - | FileCheck %s
; RUN: llc -march=hexagon -filetype=obj -ifcvt-limit=0 -o - %s | llvm-objdump -d - | FileCheck %s
; CHECK: p0 = cmp.gt(r0,#-1); if (!p0.new) jump:nt
@ -14,4 +14,4 @@ ret void
y:
call void @b()
ret void
}
}