maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp

1662 lines
59 KiB
C++
Raw Blame History

//===- X86ISelDAGToDAG.cpp - A DAG pattern matching inst selector for X86 -===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines a DAG pattern matching instruction selector for X86,
// converting from a legalized dag to a X86 dag.
//
//===----------------------------------------------------------------------===//
#define DEBUG_TYPE "x86-isel"
#include "X86.h"
#include "X86InstrBuilder.h"
#include "X86ISelLowering.h"
#include "X86MachineFunctionInfo.h"
#include "X86RegisterInfo.h"
#include "X86Subtarget.h"
#include "X86TargetMachine.h"
#include "llvm/GlobalValue.h"
#include "llvm/Instructions.h"
#include "llvm/Intrinsics.h"
#include "llvm/Support/CFG.h"
#include "llvm/Type.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/SelectionDAGISel.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/Statistic.h"
#include <queue>
#include <set>
using namespace llvm;
STATISTIC(NumFPKill , "Number of FP_REG_KILL instructions added");
STATISTIC(NumLoadMoved, "Number of loads moved below TokenFactor");
//===----------------------------------------------------------------------===//
// Pattern Matcher Implementation
//===----------------------------------------------------------------------===//
namespace {
/// X86ISelAddressMode - This corresponds to X86AddressMode, but uses
/// SDOperand's instead of register numbers for the leaves of the matched
/// tree.
struct X86ISelAddressMode {
enum {
RegBase,
FrameIndexBase
} BaseType;
struct { // This is really a union, discriminated by BaseType!
SDOperand Reg;
int FrameIndex;
} Base;
bool isRIPRel; // RIP as base?
unsigned Scale;
SDOperand IndexReg;
unsigned Disp;
GlobalValue *GV;
Constant *CP;
const char *ES;
int JT;
unsigned Align; // CP alignment.
X86ISelAddressMode()
: BaseType(RegBase), isRIPRel(false), Scale(1), IndexReg(), Disp(0),
GV(0), CP(0), ES(0), JT(-1), Align(0) {
}
};
}
namespace {
//===--------------------------------------------------------------------===//
/// ISel - X86 specific code to select X86 machine instructions for
/// SelectionDAG operations.
///
class VISIBILITY_HIDDEN X86DAGToDAGISel : public SelectionDAGISel {
/// ContainsFPCode - Every instruction we select that uses or defines a FP
/// register should set this to true.
bool ContainsFPCode;
/// FastISel - Enable fast(er) instruction selection.
///
bool FastISel;
/// TM - Keep a reference to X86TargetMachine.
///
X86TargetMachine &TM;
/// X86Lowering - This object fully describes how to lower LLVM code to an
/// X86-specific SelectionDAG.
X86TargetLowering X86Lowering;
/// Subtarget - Keep a pointer to the X86Subtarget around so that we can
/// make the right decision when generating code for different targets.
const X86Subtarget *Subtarget;
/// GlobalBaseReg - keeps track of the virtual register mapped onto global
/// base register.
unsigned GlobalBaseReg;
public:
X86DAGToDAGISel(X86TargetMachine &tm, bool fast)
: SelectionDAGISel(X86Lowering),
ContainsFPCode(false), FastISel(fast), TM(tm),
X86Lowering(*TM.getTargetLowering()),
Subtarget(&TM.getSubtarget<X86Subtarget>()) {}
virtual bool runOnFunction(Function &Fn) {
// Make sure we re-emit a set of the global base reg if necessary
GlobalBaseReg = 0;
return SelectionDAGISel::runOnFunction(Fn);
}
virtual const char *getPassName() const {
return "X86 DAG->DAG Instruction Selection";
}
/// InstructionSelectBasicBlock - This callback is invoked by
/// SelectionDAGISel when it has created a SelectionDAG for us to codegen.
virtual void InstructionSelectBasicBlock(SelectionDAG &DAG);
virtual void EmitFunctionEntryCode(Function &Fn, MachineFunction &MF);
virtual bool CanBeFoldedBy(SDNode *N, SDNode *U, SDNode *Root) const;
// Include the pieces autogenerated from the target description.
#include "X86GenDAGISel.inc"
private:
SDNode *Select(SDOperand N);
bool MatchAddress(SDOperand N, X86ISelAddressMode &AM,
bool isRoot = true, unsigned Depth = 0);
bool MatchAddressBase(SDOperand N, X86ISelAddressMode &AM,
bool isRoot, unsigned Depth);
bool SelectAddr(SDOperand Op, SDOperand N, SDOperand &Base,
SDOperand &Scale, SDOperand &Index, SDOperand &Disp);
bool SelectLEAAddr(SDOperand Op, SDOperand N, SDOperand &Base,
SDOperand &Scale, SDOperand &Index, SDOperand &Disp);
bool SelectScalarSSELoad(SDOperand Op, SDOperand Pred,
SDOperand N, SDOperand &Base, SDOperand &Scale,
SDOperand &Index, SDOperand &Disp,
SDOperand &InChain, SDOperand &OutChain);
bool TryFoldLoad(SDOperand P, SDOperand N,
SDOperand &Base, SDOperand &Scale,
SDOperand &Index, SDOperand &Disp);
void PreprocessForRMW(SelectionDAG &DAG);
void PreprocessForFPConvert(SelectionDAG &DAG);
/// SelectInlineAsmMemoryOperand - Implement addressing mode selection for
/// inline asm expressions.
virtual bool SelectInlineAsmMemoryOperand(const SDOperand &Op,
char ConstraintCode,
std::vector<SDOperand> &OutOps,
SelectionDAG &DAG);
void EmitSpecialCodeForMain(MachineBasicBlock *BB, MachineFrameInfo *MFI);
inline void getAddressOperands(X86ISelAddressMode &AM, SDOperand &Base,
SDOperand &Scale, SDOperand &Index,
SDOperand &Disp) {
Base = (AM.BaseType == X86ISelAddressMode::FrameIndexBase) ?
CurDAG->getTargetFrameIndex(AM.Base.FrameIndex, TLI.getPointerTy()) :
AM.Base.Reg;
Scale = getI8Imm(AM.Scale);
Index = AM.IndexReg;
// These are 32-bit even in 64-bit mode since RIP relative offset
// is 32-bit.
if (AM.GV)
Disp = CurDAG->getTargetGlobalAddress(AM.GV, MVT::i32, AM.Disp);
else if (AM.CP)
Disp = CurDAG->getTargetConstantPool(AM.CP, MVT::i32, AM.Align, AM.Disp);
else if (AM.ES)
Disp = CurDAG->getTargetExternalSymbol(AM.ES, MVT::i32);
else if (AM.JT != -1)
Disp = CurDAG->getTargetJumpTable(AM.JT, MVT::i32);
else
Disp = getI32Imm(AM.Disp);
}
/// getI8Imm - Return a target constant with the specified value, of type
/// i8.
inline SDOperand getI8Imm(unsigned Imm) {
return CurDAG->getTargetConstant(Imm, MVT::i8);
}
/// getI16Imm - Return a target constant with the specified value, of type
/// i16.
inline SDOperand getI16Imm(unsigned Imm) {
return CurDAG->getTargetConstant(Imm, MVT::i16);
}
/// getI32Imm - Return a target constant with the specified value, of type
/// i32.
inline SDOperand getI32Imm(unsigned Imm) {
return CurDAG->getTargetConstant(Imm, MVT::i32);
}
/// getGlobalBaseReg - insert code into the entry mbb to materialize the PIC
/// base register. Return the virtual register that holds this value.
SDNode *getGlobalBaseReg();
/// getTruncate - return an SDNode that implements a subreg based truncate
/// of the specified operand to the the specified value type.
SDNode *getTruncate(SDOperand N0, MVT::ValueType VT);
#ifndef NDEBUG
unsigned Indent;
#endif
};
}
/// findFlagUse - Return use of MVT::Flag value produced by the specified SDNode.
///
static SDNode *findFlagUse(SDNode *N) {
unsigned FlagResNo = N->getNumValues()-1;
for (SDNode::use_iterator I = N->use_begin(), E = N->use_end(); I != E; ++I) {
SDNode *User = I->getUser();
for (unsigned i = 0, e = User->getNumOperands(); i != e; ++i) {
SDOperand Op = User->getOperand(i);
if (Op.Val == N && Op.ResNo == FlagResNo)
return User;
}
}
return NULL;
}
/// findNonImmUse - Return true by reference in "found" if "Use" is an
/// non-immediate use of "Def". This function recursively traversing
/// up the operand chain ignoring certain nodes.
static void findNonImmUse(SDNode *Use, SDNode* Def, SDNode *ImmedUse,
SDNode *Root, SDNode *Skip, bool &found,
SmallPtrSet<SDNode*, 16> &Visited) {
if (found ||
Use->getNodeId() > Def->getNodeId() ||
!Visited.insert(Use))
return;
for (unsigned i = 0, e = Use->getNumOperands(); !found && i != e; ++i) {
SDNode *N = Use->getOperand(i).Val;
if (N == Skip)
continue;
if (N == Def) {
if (Use == ImmedUse)
continue; // We are not looking for immediate use.
if (Use == Root) {
assert(Use->getOpcode() == ISD::STORE ||
Use->getOpcode() == X86ISD::CMP ||
Use->getOpcode() == ISD::INTRINSIC_WO_CHAIN ||
Use->getOpcode() == ISD::INTRINSIC_W_CHAIN ||
Use->getOpcode() == ISD::INTRINSIC_VOID);
continue;
}
found = true;
break;
}
// Traverse up the operand chain.
findNonImmUse(N, Def, ImmedUse, Root, Skip, found, Visited);
}
}
/// isNonImmUse - Start searching from Root up the DAG to check is Def can
/// be reached. Return true if that's the case. However, ignore direct uses
/// by ImmedUse (which would be U in the example illustrated in
/// CanBeFoldedBy) and by Root (which can happen in the store case).
/// FIXME: to be really generic, we should allow direct use by any node
/// that is being folded. But realisticly since we only fold loads which
/// have one non-chain use, we only need to watch out for load/op/store
/// and load/op/cmp case where the root (store / cmp) may reach the load via
/// its chain operand.
static inline bool isNonImmUse(SDNode *Root, SDNode *Def, SDNode *ImmedUse,
SDNode *Skip = NULL) {
SmallPtrSet<SDNode*, 16> Visited;
bool found = false;
findNonImmUse(Root, Def, ImmedUse, Root, Skip, found, Visited);
return found;
}
bool X86DAGToDAGISel::CanBeFoldedBy(SDNode *N, SDNode *U, SDNode *Root) const {
if (FastISel) return false;
// If U use can somehow reach N through another path then U can't fold N or
// it will create a cycle. e.g. In the following diagram, U can reach N
// through X. If N is folded into into U, then X is both a predecessor and
// a successor of U.
//
// [ N ]
// ^ ^
// | |
// / \---
// / [X]
// | ^
// [U]--------|
if (isNonImmUse(Root, N, U))
return false;
// If U produces a flag, then it gets (even more) interesting. Since it
// would have been "glued" together with its flag use, we need to check if
// it might reach N:
//
// [ N ]
// ^ ^
// | |
// [U] \--
// ^ [TF]
// | ^
// | |
// \ /
// [FU]
//
// If FU (flag use) indirectly reach N (the load), and U fold N (call it
// NU), then TF is a predecessor of FU and a successor of NU. But since
// NU and FU are flagged together, this effectively creates a cycle.
bool HasFlagUse = false;
MVT::ValueType VT = Root->getValueType(Root->getNumValues()-1);
while ((VT == MVT::Flag && !Root->use_empty())) {
SDNode *FU = findFlagUse(Root);
if (FU == NULL)
break;
else {
Root = FU;
HasFlagUse = true;
}
VT = Root->getValueType(Root->getNumValues()-1);
}
if (HasFlagUse)
return !isNonImmUse(Root, N, Root, U);
return true;
}
/// MoveBelowTokenFactor - Replace TokenFactor operand with load's chain operand
/// and move load below the TokenFactor. Replace store's chain operand with
/// load's chain result.
static void MoveBelowTokenFactor(SelectionDAG &DAG, SDOperand Load,
SDOperand Store, SDOperand TF) {
std::vector<SDOperand> Ops;
for (unsigned i = 0, e = TF.Val->getNumOperands(); i != e; ++i)
if (Load.Val == TF.Val->getOperand(i).Val)
Ops.push_back(Load.Val->getOperand(0));
else
Ops.push_back(TF.Val->getOperand(i));
DAG.UpdateNodeOperands(TF, &Ops[0], Ops.size());
DAG.UpdateNodeOperands(Load, TF, Load.getOperand(1), Load.getOperand(2));
DAG.UpdateNodeOperands(Store, Load.getValue(1), Store.getOperand(1),
Store.getOperand(2), Store.getOperand(3));
}
/// PreprocessForRMW - Preprocess the DAG to make instruction selection better.
/// This is only run if not in -fast mode (aka -O0).
/// This allows the instruction selector to pick more read-modify-write
/// instructions. This is a common case:
///
/// [Load chain]
/// ^
/// |
/// [Load]
/// ^ ^
/// | |
/// / \-
/// / |
/// [TokenFactor] [Op]
/// ^ ^
/// | |
/// \ /
/// \ /
/// [Store]
///
/// The fact the store's chain operand != load's chain will prevent the
/// (store (op (load))) instruction from being selected. We can transform it to:
///
/// [Load chain]
/// ^
/// |
/// [TokenFactor]
/// ^
/// |
/// [Load]
/// ^ ^
/// | |
/// | \-
/// | |
/// | [Op]
/// | ^
/// | |
/// \ /
/// \ /
/// [Store]
void X86DAGToDAGISel::PreprocessForRMW(SelectionDAG &DAG) {
for (SelectionDAG::allnodes_iterator I = DAG.allnodes_begin(),
E = DAG.allnodes_end(); I != E; ++I) {
if (!ISD::isNON_TRUNCStore(I))
continue;
SDOperand Chain = I->getOperand(0);
if (Chain.Val->getOpcode() != ISD::TokenFactor)
continue;
SDOperand N1 = I->getOperand(1);
SDOperand N2 = I->getOperand(2);
if (MVT::isFloatingPoint(N1.getValueType()) ||
MVT::isVector(N1.getValueType()) ||
!N1.hasOneUse())
continue;
bool RModW = false;
SDOperand Load;
unsigned Opcode = N1.Val->getOpcode();
switch (Opcode) {
case ISD::ADD:
case ISD::MUL:
case ISD::AND:
case ISD::OR:
case ISD::XOR:
case ISD::ADDC:
case ISD::ADDE: {
SDOperand N10 = N1.getOperand(0);
SDOperand N11 = N1.getOperand(1);
if (ISD::isNON_EXTLoad(N10.Val))
RModW = true;
else if (ISD::isNON_EXTLoad(N11.Val)) {
RModW = true;
std::swap(N10, N11);
}
RModW = RModW && N10.Val->isOperandOf(Chain.Val) && N10.hasOneUse() &&
(N10.getOperand(1) == N2) &&
(N10.Val->getValueType(0) == N1.getValueType());
if (RModW)
Load = N10;
break;
}
case ISD::SUB:
case ISD::SHL:
case ISD::SRA:
case ISD::SRL:
case ISD::ROTL:
case ISD::ROTR:
case ISD::SUBC:
case ISD::SUBE:
case X86ISD::SHLD:
case X86ISD::SHRD: {
SDOperand N10 = N1.getOperand(0);
if (ISD::isNON_EXTLoad(N10.Val))
RModW = N10.Val->isOperandOf(Chain.Val) && N10.hasOneUse() &&
(N10.getOperand(1) == N2) &&
(N10.Val->getValueType(0) == N1.getValueType());
if (RModW)
Load = N10;
break;
}
}
if (RModW) {
MoveBelowTokenFactor(DAG, Load, SDOperand(I, 0), Chain);
++NumLoadMoved;
}
}
}
/// PreprocessForFPConvert - Walk over the dag lowering fpround and fpextend
/// nodes that target the FP stack to be store and load to the stack. This is a
/// gross hack. We would like to simply mark these as being illegal, but when
/// we do that, legalize produces these when it expands calls, then expands
/// these in the same legalize pass. We would like dag combine to be able to
/// hack on these between the call expansion and the node legalization. As such
/// this pass basically does "really late" legalization of these inline with the
/// X86 isel pass.
void X86DAGToDAGISel::PreprocessForFPConvert(SelectionDAG &DAG) {
for (SelectionDAG::allnodes_iterator I = DAG.allnodes_begin(),
E = DAG.allnodes_end(); I != E; ) {
SDNode *N = I++; // Preincrement iterator to avoid invalidation issues.
if (N->getOpcode() != ISD::FP_ROUND && N->getOpcode() != ISD::FP_EXTEND)
continue;
// If the source and destination are SSE registers, then this is a legal
// conversion that should not be lowered.
MVT::ValueType SrcVT = N->getOperand(0).getValueType();
MVT::ValueType DstVT = N->getValueType(0);
bool SrcIsSSE = X86Lowering.isScalarFPTypeInSSEReg(SrcVT);
bool DstIsSSE = X86Lowering.isScalarFPTypeInSSEReg(DstVT);
if (SrcIsSSE && DstIsSSE)
continue;
if (!SrcIsSSE && !DstIsSSE) {
// If this is an FPStack extension, it is a noop.
if (N->getOpcode() == ISD::FP_EXTEND)
continue;
// If this is a value-preserving FPStack truncation, it is a noop.
if (N->getConstantOperandVal(1))
continue;
}
// Here we could have an FP stack truncation or an FPStack <-> SSE convert.
// FPStack has extload and truncstore. SSE can fold direct loads into other
// operations. Based on this, decide what we want to do.
MVT::ValueType MemVT;
if (N->getOpcode() == ISD::FP_ROUND)
MemVT = DstVT; // FP_ROUND must use DstVT, we can't do a 'trunc load'.
else
MemVT = SrcIsSSE ? SrcVT : DstVT;
SDOperand MemTmp = DAG.CreateStackTemporary(MemVT);
// FIXME: optimize the case where the src/dest is a load or store?
SDOperand Store = DAG.getTruncStore(DAG.getEntryNode(), N->getOperand(0),
MemTmp, NULL, 0, MemVT);
SDOperand Result = DAG.getExtLoad(ISD::EXTLOAD, DstVT, Store, MemTmp,
NULL, 0, MemVT);
// We're about to replace all uses of the FP_ROUND/FP_EXTEND with the
// extload we created. This will cause general havok on the dag because
// anything below the conversion could be folded into other existing nodes.
// To avoid invalidating 'I', back it up to the convert node.
--I;
DAG.ReplaceAllUsesOfValueWith(SDOperand(N, 0), Result);
// Now that we did that, the node is dead. Increment the iterator to the
// next node to process, then delete N.
++I;
DAG.DeleteNode(N);
}
}
/// InstructionSelectBasicBlock - This callback is invoked by SelectionDAGISel
/// when it has created a SelectionDAG for us to codegen.
void X86DAGToDAGISel::InstructionSelectBasicBlock(SelectionDAG &DAG) {
DEBUG(BB->dump());
MachineFunction::iterator FirstMBB = BB;
if (!FastISel)
PreprocessForRMW(DAG);
// FIXME: This should only happen when not -fast.
PreprocessForFPConvert(DAG);
// Codegen the basic block.
#ifndef NDEBUG
DOUT << "===== Instruction selection begins:\n";
Indent = 0;
#endif
DAG.setRoot(SelectRoot(DAG.getRoot()));
#ifndef NDEBUG
DOUT << "===== Instruction selection ends:\n";
#endif
DAG.RemoveDeadNodes();
// Emit machine code to BB. This can change 'BB' to the last block being
// inserted into.
ScheduleAndEmitDAG(DAG);
// If we are emitting FP stack code, scan the basic block to determine if this
// block defines any FP values. If so, put an FP_REG_KILL instruction before
// the terminator of the block.
// Note that FP stack instructions are used in all modes for long double,
// so we always need to do this check.
// Also note that it's possible for an FP stack register to be live across
// an instruction that produces multiple basic blocks (SSE CMOV) so we
// must check all the generated basic blocks.
// Scan all of the machine instructions in these MBBs, checking for FP
// stores. (RFP32 and RFP64 will not exist in SSE mode, but RFP80 might.)
MachineFunction::iterator MBBI = FirstMBB;
MachineFunction::iterator EndMBB = BB; ++EndMBB;
for (; MBBI != EndMBB; ++MBBI) {
MachineBasicBlock *MBB = MBBI;
// If this block returns, ignore it. We don't want to insert an FP_REG_KILL
// before the return.
if (!MBB->empty()) {
MachineBasicBlock::iterator EndI = MBB->end();
--EndI;
if (EndI->getDesc().isReturn())
continue;
}
bool ContainsFPCode = false;
for (MachineBasicBlock::iterator I = MBB->begin(), E = MBB->end();
!ContainsFPCode && I != E; ++I) {
if (I->getNumOperands() != 0 && I->getOperand(0).isRegister()) {
const TargetRegisterClass *clas;
for (unsigned op = 0, e = I->getNumOperands(); op != e; ++op) {
if (I->getOperand(op).isRegister() && I->getOperand(op).isDef() &&
TargetRegisterInfo::isVirtualRegister(I->getOperand(op).getReg()) &&
((clas = RegInfo->getRegClass(I->getOperand(0).getReg())) ==
X86::RFP32RegisterClass ||
clas == X86::RFP64RegisterClass ||
clas == X86::RFP80RegisterClass)) {
ContainsFPCode = true;
break;
}
}
}
}
// Check PHI nodes in successor blocks. These PHI's will be lowered to have
// a copy of the input value in this block. In SSE mode, we only care about
// 80-bit values.
if (!ContainsFPCode) {
// Final check, check LLVM BB's that are successors to the LLVM BB
// corresponding to BB for FP PHI nodes.
const BasicBlock *LLVMBB = BB->getBasicBlock();
const PHINode *PN;
for (succ_const_iterator SI = succ_begin(LLVMBB), E = succ_end(LLVMBB);
!ContainsFPCode && SI != E; ++SI) {
for (BasicBlock::const_iterator II = SI->begin();
(PN = dyn_cast<PHINode>(II)); ++II) {
if (PN->getType()==Type::X86_FP80Ty ||
(!Subtarget->hasSSE1() && PN->getType()->isFloatingPoint()) ||
(!Subtarget->hasSSE2() && PN->getType()==Type::DoubleTy)) {
ContainsFPCode = true;
break;
}
}
}
}
// Finally, if we found any FP code, emit the FP_REG_KILL instruction.
if (ContainsFPCode) {
BuildMI(*MBB, MBBI->getFirstTerminator(),
TM.getInstrInfo()->get(X86::FP_REG_KILL));
++NumFPKill;
}
}
}
/// EmitSpecialCodeForMain - Emit any code that needs to be executed only in
/// the main function.
void X86DAGToDAGISel::EmitSpecialCodeForMain(MachineBasicBlock *BB,
MachineFrameInfo *MFI) {
const TargetInstrInfo *TII = TM.getInstrInfo();
if (Subtarget->isTargetCygMing())
BuildMI(BB, TII->get(X86::CALLpcrel32)).addExternalSymbol("__main");
}
void X86DAGToDAGISel::EmitFunctionEntryCode(Function &Fn, MachineFunction &MF) {
// If this is main, emit special code for main.
MachineBasicBlock *BB = MF.begin();
if (Fn.hasExternalLinkage() && Fn.getName() == "main")
EmitSpecialCodeForMain(BB, MF.getFrameInfo());
}
/// MatchAddress - Add the specified node to the specified addressing mode,
/// returning true if it cannot be done. This just pattern matches for the
/// addressing mode.
bool X86DAGToDAGISel::MatchAddress(SDOperand N, X86ISelAddressMode &AM,
bool isRoot, unsigned Depth) {
// Limit recursion.
if (Depth > 5)
return MatchAddressBase(N, AM, isRoot, Depth);
// RIP relative addressing: %rip + 32-bit displacement!
if (AM.isRIPRel) {
if (!AM.ES && AM.JT != -1 && N.getOpcode() == ISD::Constant) {
int64_t Val = cast<ConstantSDNode>(N)->getSignExtended();
if (isInt32(AM.Disp + Val)) {
AM.Disp += Val;
return false;
}
}
return true;
}
int id = N.Val->getNodeId();
bool AlreadySelected = isSelected(id); // Already selected, not yet replaced.
switch (N.getOpcode()) {
default: break;
case ISD::Constant: {
int64_t Val = cast<ConstantSDNode>(N)->getSignExtended();
if (isInt32(AM.Disp + Val)) {
AM.Disp += Val;
return false;
}
break;
}
case X86ISD::Wrapper: {
bool is64Bit = Subtarget->is64Bit();
// Under X86-64 non-small code model, GV (and friends) are 64-bits.
// Also, base and index reg must be 0 in order to use rip as base.
if (is64Bit && (TM.getCodeModel() != CodeModel::Small ||
AM.Base.Reg.Val || AM.IndexReg.Val))
break;
if (AM.GV != 0 || AM.CP != 0 || AM.ES != 0 || AM.JT != -1)
break;
// If value is available in a register both base and index components have
// been picked, we can't fit the result available in the register in the
// addressing mode. Duplicate GlobalAddress or ConstantPool as displacement.
if (!AlreadySelected || (AM.Base.Reg.Val && AM.IndexReg.Val)) {
SDOperand N0 = N.getOperand(0);
if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(N0)) {
GlobalValue *GV = G->getGlobal();
AM.GV = GV;
AM.Disp += G->getOffset();
AM.isRIPRel = TM.getRelocationModel() != Reloc::Static &&
Subtarget->isPICStyleRIPRel();
return false;
} else if (ConstantPoolSDNode *CP = dyn_cast<ConstantPoolSDNode>(N0)) {
AM.CP = CP->getConstVal();
AM.Align = CP->getAlignment();
AM.Disp += CP->getOffset();
AM.isRIPRel = TM.getRelocationModel() != Reloc::Static &&
Subtarget->isPICStyleRIPRel();
return false;
} else if (ExternalSymbolSDNode *S =dyn_cast<ExternalSymbolSDNode>(N0)) {
AM.ES = S->getSymbol();
AM.isRIPRel = TM.getRelocationModel() != Reloc::Static &&
Subtarget->isPICStyleRIPRel();
return false;
} else if (JumpTableSDNode *J = dyn_cast<JumpTableSDNode>(N0)) {
AM.JT = J->getIndex();
AM.isRIPRel = TM.getRelocationModel() != Reloc::Static &&
Subtarget->isPICStyleRIPRel();
return false;
}
}
break;
}
case ISD::FrameIndex:
if (AM.BaseType == X86ISelAddressMode::RegBase && AM.Base.Reg.Val == 0) {
AM.BaseType = X86ISelAddressMode::FrameIndexBase;
AM.Base.FrameIndex = cast<FrameIndexSDNode>(N)->getIndex();
return false;
}
break;
case ISD::SHL:
if (AlreadySelected || AM.IndexReg.Val != 0 || AM.Scale != 1 || AM.isRIPRel)
break;
if (ConstantSDNode *CN = dyn_cast<ConstantSDNode>(N.Val->getOperand(1))) {
unsigned Val = CN->getValue();
if (Val == 1 || Val == 2 || Val == 3) {
AM.Scale = 1 << Val;
SDOperand ShVal = N.Val->getOperand(0);
// Okay, we know that we have a scale by now. However, if the scaled
// value is an add of something and a constant, we can fold the
// constant into the disp field here.
if (ShVal.Val->getOpcode() == ISD::ADD && ShVal.hasOneUse() &&
isa<ConstantSDNode>(ShVal.Val->getOperand(1))) {
AM.IndexReg = ShVal.Val->getOperand(0);
ConstantSDNode *AddVal =
cast<ConstantSDNode>(ShVal.Val->getOperand(1));
uint64_t Disp = AM.Disp + (AddVal->getValue() << Val);
if (isInt32(Disp))
AM.Disp = Disp;
else
AM.IndexReg = ShVal;
} else {
AM.IndexReg = ShVal;
}
return false;
}
break;
}
case ISD::SMUL_LOHI:
case ISD::UMUL_LOHI:
// A mul_lohi where we need the low part can be folded as a plain multiply.
if (N.ResNo != 0) break;
// FALL THROUGH
case ISD::MUL:
// X*[3,5,9] -> X+X*[2,4,8]
if (!AlreadySelected &&
AM.BaseType == X86ISelAddressMode::RegBase &&
AM.Base.Reg.Val == 0 &&
AM.IndexReg.Val == 0 &&
!AM.isRIPRel) {
if (ConstantSDNode *CN = dyn_cast<ConstantSDNode>(N.Val->getOperand(1)))
if (CN->getValue() == 3 || CN->getValue() == 5 || CN->getValue() == 9) {
AM.Scale = unsigned(CN->getValue())-1;
SDOperand MulVal = N.Val->getOperand(0);
SDOperand Reg;
// Okay, we know that we have a scale by now. However, if the scaled
// value is an add of something and a constant, we can fold the
// constant into the disp field here.
if (MulVal.Val->getOpcode() == ISD::ADD && MulVal.hasOneUse() &&
isa<ConstantSDNode>(MulVal.Val->getOperand(1))) {
Reg = MulVal.Val->getOperand(0);
ConstantSDNode *AddVal =
cast<ConstantSDNode>(MulVal.Val->getOperand(1));
uint64_t Disp = AM.Disp + AddVal->getValue() * CN->getValue();
if (isInt32(Disp))
AM.Disp = Disp;
else
Reg = N.Val->getOperand(0);
} else {
Reg = N.Val->getOperand(0);
}
AM.IndexReg = AM.Base.Reg = Reg;
return false;
}
}
break;
case ISD::ADD:
if (!AlreadySelected) {
X86ISelAddressMode Backup = AM;
if (!MatchAddress(N.Val->getOperand(0), AM, false, Depth+1) &&
!MatchAddress(N.Val->getOperand(1), AM, false, Depth+1))
return false;
AM = Backup;
if (!MatchAddress(N.Val->getOperand(1), AM, false, Depth+1) &&
!MatchAddress(N.Val->getOperand(0), AM, false, Depth+1))
return false;
AM = Backup;
}
break;
case ISD::OR:
// Handle "X | C" as "X + C" iff X is known to have C bits clear.
if (AlreadySelected) break;
if (ConstantSDNode *CN = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
X86ISelAddressMode Backup = AM;
// Start with the LHS as an addr mode.
if (!MatchAddress(N.getOperand(0), AM, false) &&
// Address could not have picked a GV address for the displacement.
AM.GV == NULL &&
// On x86-64, the resultant disp must fit in 32-bits.
isInt32(AM.Disp + CN->getSignExtended()) &&
// Check to see if the LHS & C is zero.
CurDAG->MaskedValueIsZero(N.getOperand(0), CN->getAPIntValue())) {
AM.Disp += CN->getValue();
return false;
}
AM = Backup;
}
break;
case ISD::AND: {
// Handle "(x << C1) & C2" as "(X & (C2>>C1)) << C1" if safe and if this
// allows us to fold the shift into this addressing mode.
if (AlreadySelected) break;
SDOperand Shift = N.getOperand(0);
if (Shift.getOpcode() != ISD::SHL) break;
// Scale must not be used already.
if (AM.IndexReg.Val != 0 || AM.Scale != 1) break;
// Not when RIP is used as the base.
if (AM.isRIPRel) break;
ConstantSDNode *C2 = dyn_cast<ConstantSDNode>(N.getOperand(1));
ConstantSDNode *C1 = dyn_cast<ConstantSDNode>(Shift.getOperand(1));
if (!C1 || !C2) break;
// Not likely to be profitable if either the AND or SHIFT node has more
// than one use (unless all uses are for address computation). Besides,
// isel mechanism requires their node ids to be reused.
if (!N.hasOneUse() || !Shift.hasOneUse())
break;
// Verify that the shift amount is something we can fold.
unsigned ShiftCst = C1->getValue();
if (ShiftCst != 1 && ShiftCst != 2 && ShiftCst != 3)
break;
// Get the new AND mask, this folds to a constant.
SDOperand NewANDMask = CurDAG->getNode(ISD::SRL, N.getValueType(),
SDOperand(C2, 0), SDOperand(C1, 0));
SDOperand NewAND = CurDAG->getNode(ISD::AND, N.getValueType(),
Shift.getOperand(0), NewANDMask);
NewANDMask.Val->setNodeId(Shift.Val->getNodeId());
NewAND.Val->setNodeId(N.Val->getNodeId());
AM.Scale = 1 << ShiftCst;
AM.IndexReg = NewAND;
return false;
}
}
return MatchAddressBase(N, AM, isRoot, Depth);
}
/// MatchAddressBase - Helper for MatchAddress. Add the specified node to the
/// specified addressing mode without any further recursion.
bool X86DAGToDAGISel::MatchAddressBase(SDOperand N, X86ISelAddressMode &AM,
bool isRoot, unsigned Depth) {
// Is the base register already occupied?
if (AM.BaseType != X86ISelAddressMode::RegBase || AM.Base.Reg.Val) {
// If so, check to see if the scale index register is set.
if (AM.IndexReg.Val == 0 && !AM.isRIPRel) {
AM.IndexReg = N;
AM.Scale = 1;
return false;
}
// Otherwise, we cannot select it.
return true;
}
// Default, generate it as a register.
AM.BaseType = X86ISelAddressMode::RegBase;
AM.Base.Reg = N;
return false;
}
/// SelectAddr - returns true if it is able pattern match an addressing mode.
/// It returns the operands which make up the maximal addressing mode it can
/// match by reference.
bool X86DAGToDAGISel::SelectAddr(SDOperand Op, SDOperand N, SDOperand &Base,
SDOperand &Scale, SDOperand &Index,
SDOperand &Disp) {
X86ISelAddressMode AM;
if (MatchAddress(N, AM))
return false;
MVT::ValueType VT = N.getValueType();
if (AM.BaseType == X86ISelAddressMode::RegBase) {
if (!AM.Base.Reg.Val)
AM.Base.Reg = CurDAG->getRegister(0, VT);
}
if (!AM.IndexReg.Val)
AM.IndexReg = CurDAG->getRegister(0, VT);
getAddressOperands(AM, Base, Scale, Index, Disp);
return true;
}
/// isZeroNode - Returns true if Elt is a constant zero or a floating point
/// constant +0.0.
static inline bool isZeroNode(SDOperand Elt) {
return ((isa<ConstantSDNode>(Elt) &&
cast<ConstantSDNode>(Elt)->getValue() == 0) ||
(isa<ConstantFPSDNode>(Elt) &&
cast<ConstantFPSDNode>(Elt)->getValueAPF().isPosZero()));
}
/// SelectScalarSSELoad - Match a scalar SSE load. In particular, we want to
/// match a load whose top elements are either undef or zeros. The load flavor
/// is derived from the type of N, which is either v4f32 or v2f64.
bool X86DAGToDAGISel::SelectScalarSSELoad(SDOperand Op, SDOperand Pred,
SDOperand N, SDOperand &Base,
SDOperand &Scale, SDOperand &Index,
SDOperand &Disp, SDOperand &InChain,
SDOperand &OutChain) {
if (N.getOpcode() == ISD::SCALAR_TO_VECTOR) {
InChain = N.getOperand(0).getValue(1);
if (ISD::isNON_EXTLoad(InChain.Val) &&
InChain.getValue(0).hasOneUse() &&
N.hasOneUse() &&
CanBeFoldedBy(N.Val, Pred.Val, Op.Val)) {
LoadSDNode *LD = cast<LoadSDNode>(InChain);
if (!SelectAddr(Op, LD->getBasePtr(), Base, Scale, Index, Disp))
return false;
OutChain = LD->getChain();
return true;
}
}
// Also handle the case where we explicitly require zeros in the top
// elements. This is a vector shuffle from the zero vector.
if (N.getOpcode() == ISD::VECTOR_SHUFFLE && N.Val->hasOneUse() &&
// Check to see if the top elements are all zeros (or bitcast of zeros).
ISD::isBuildVectorAllZeros(N.getOperand(0).Val) &&
N.getOperand(1).getOpcode() == ISD::SCALAR_TO_VECTOR &&
N.getOperand(1).Val->hasOneUse() &&
ISD::isNON_EXTLoad(N.getOperand(1).getOperand(0).Val) &&
N.getOperand(1).getOperand(0).hasOneUse()) {
// Check to see if the shuffle mask is 4/L/L/L or 2/L, where L is something
// from the LHS.
unsigned VecWidth=MVT::getVectorNumElements(N.getOperand(0).getValueType());
SDOperand ShufMask = N.getOperand(2);
assert(ShufMask.getOpcode() == ISD::BUILD_VECTOR && "Invalid shuf mask!");
if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(ShufMask.getOperand(0))) {
if (C->getValue() == VecWidth) {
for (unsigned i = 1; i != VecWidth; ++i) {
if (ShufMask.getOperand(i).getOpcode() == ISD::UNDEF) {
// ok.
} else {
ConstantSDNode *C = cast<ConstantSDNode>(ShufMask.getOperand(i));
if (C->getValue() >= VecWidth) return false;
}
}
}
// Okay, this is a zero extending load. Fold it.
LoadSDNode *LD = cast<LoadSDNode>(N.getOperand(1).getOperand(0));
if (!SelectAddr(Op, LD->getBasePtr(), Base, Scale, Index, Disp))
return false;
OutChain = LD->getChain();
InChain = SDOperand(LD, 1);
return true;
}
}
return false;
}
/// SelectLEAAddr - it calls SelectAddr and determines if the maximal addressing
/// mode it matches can be cost effectively emitted as an LEA instruction.
bool X86DAGToDAGISel::SelectLEAAddr(SDOperand Op, SDOperand N,
SDOperand &Base, SDOperand &Scale,
SDOperand &Index, SDOperand &Disp) {
X86ISelAddressMode AM;
if (MatchAddress(N, AM))
return false;
MVT::ValueType VT = N.getValueType();
unsigned Complexity = 0;
if (AM.BaseType == X86ISelAddressMode::RegBase)
if (AM.Base.Reg.Val)
Complexity = 1;
else
AM.Base.Reg = CurDAG->getRegister(0, VT);
else if (AM.BaseType == X86ISelAddressMode::FrameIndexBase)
Complexity = 4;
if (AM.IndexReg.Val)
Complexity++;
else
AM.IndexReg = CurDAG->getRegister(0, VT);
// Don't match just leal(,%reg,2). It's cheaper to do addl %reg, %reg, or with
// a simple shift.
if (AM.Scale > 1)
Complexity++;
// FIXME: We are artificially lowering the criteria to turn ADD %reg, $GA
// to a LEA. This is determined with some expermentation but is by no means
// optimal (especially for code size consideration). LEA is nice because of
// its three-address nature. Tweak the cost function again when we can run
// convertToThreeAddress() at register allocation time.
if (AM.GV || AM.CP || AM.ES || AM.JT != -1) {
// For X86-64, we should always use lea to materialize RIP relative
// addresses.
if (Subtarget->is64Bit())
Complexity = 4;
else
Complexity += 2;
}
if (AM.Disp && (AM.Base.Reg.Val || AM.IndexReg.Val))
Complexity++;
if (Complexity > 2) {
getAddressOperands(AM, Base, Scale, Index, Disp);
return true;
}
return false;
}
bool X86DAGToDAGISel::TryFoldLoad(SDOperand P, SDOperand N,
SDOperand &Base, SDOperand &Scale,
SDOperand &Index, SDOperand &Disp) {
if (ISD::isNON_EXTLoad(N.Val) &&
N.hasOneUse() &&
CanBeFoldedBy(N.Val, P.Val, P.Val))
return SelectAddr(P, N.getOperand(1), Base, Scale, Index, Disp);
return false;
}
/// getGlobalBaseReg - Output the instructions required to put the
/// base address to use for accessing globals into a register.
///
SDNode *X86DAGToDAGISel::getGlobalBaseReg() {
assert(!Subtarget->is64Bit() && "X86-64 PIC uses RIP relative addressing");
if (!GlobalBaseReg) {
// Insert the set of GlobalBaseReg into the first MBB of the function
MachineFunction *MF = BB->getParent();
MachineBasicBlock &FirstMBB = MF->front();
MachineBasicBlock::iterator MBBI = FirstMBB.begin();
MachineRegisterInfo &RegInfo = MF->getRegInfo();
unsigned PC = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
const TargetInstrInfo *TII = TM.getInstrInfo();
// Operand of MovePCtoStack is completely ignored by asm printer. It's
// only used in JIT code emission as displacement to pc.
BuildMI(FirstMBB, MBBI, TII->get(X86::MOVPC32r), PC).addImm(0);
// If we're using vanilla 'GOT' PIC style, we should use relative addressing
// not to pc, but to _GLOBAL_ADDRESS_TABLE_ external
if (TM.getRelocationModel() == Reloc::PIC_ &&
Subtarget->isPICStyleGOT()) {
GlobalBaseReg = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
BuildMI(FirstMBB, MBBI, TII->get(X86::ADD32ri), GlobalBaseReg)
.addReg(PC).addExternalSymbol("_GLOBAL_OFFSET_TABLE_");
} else {
GlobalBaseReg = PC;
}
}
return CurDAG->getRegister(GlobalBaseReg, TLI.getPointerTy()).Val;
}
static SDNode *FindCallStartFromCall(SDNode *Node) {
if (Node->getOpcode() == ISD::CALLSEQ_START) return Node;
assert(Node->getOperand(0).getValueType() == MVT::Other &&
"Node doesn't have a token chain argument!");
return FindCallStartFromCall(Node->getOperand(0).Val);
}
SDNode *X86DAGToDAGISel::getTruncate(SDOperand N0, MVT::ValueType VT) {
SDOperand SRIdx;
switch (VT) {
case MVT::i8:
SRIdx = CurDAG->getTargetConstant(1, MVT::i32); // SubRegSet 1
// Ensure that the source register has an 8-bit subreg on 32-bit targets
if (!Subtarget->is64Bit()) {
unsigned Opc;
MVT::ValueType VT;
switch (N0.getValueType()) {
default: assert(0 && "Unknown truncate!");
case MVT::i16:
Opc = X86::MOV16to16_;
VT = MVT::i16;
break;
case MVT::i32:
Opc = X86::MOV32to32_;
VT = MVT::i32;
break;
}
N0 = SDOperand(CurDAG->getTargetNode(Opc, VT, MVT::Flag, N0), 0);
return CurDAG->getTargetNode(X86::EXTRACT_SUBREG,
VT, N0, SRIdx, N0.getValue(1));
}
break;
case MVT::i16:
SRIdx = CurDAG->getTargetConstant(2, MVT::i32); // SubRegSet 2
break;
case MVT::i32:
SRIdx = CurDAG->getTargetConstant(3, MVT::i32); // SubRegSet 3
break;
default: assert(0 && "Unknown truncate!"); break;
}
return CurDAG->getTargetNode(X86::EXTRACT_SUBREG, VT, N0, SRIdx);
}
SDNode *X86DAGToDAGISel::Select(SDOperand N) {
SDNode *Node = N.Val;
MVT::ValueType NVT = Node->getValueType(0);
unsigned Opc, MOpc;
unsigned Opcode = Node->getOpcode();
#ifndef NDEBUG
DOUT << std::string(Indent, ' ') << "Selecting: ";
DEBUG(Node->dump(CurDAG));
DOUT << "\n";
Indent += 2;
#endif
if (Opcode >= ISD::BUILTIN_OP_END && Opcode < X86ISD::FIRST_NUMBER) {
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "== ";
DEBUG(Node->dump(CurDAG));
DOUT << "\n";
Indent -= 2;
#endif
return NULL; // Already selected.
}
switch (Opcode) {
default: break;
case X86ISD::GlobalBaseReg:
return getGlobalBaseReg();
// FIXME: This is a workaround for a tblgen problem: rdar://5791600
case X86ISD::RET_FLAG:
if (ConstantSDNode *Amt = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
if (Amt->getSignExtended() != 0) break;
// Match (X86retflag 0).
SDOperand Chain = N.getOperand(0);
bool HasInFlag = N.getOperand(N.getNumOperands()-1).getValueType()
== MVT::Flag;
SmallVector<SDOperand, 8> Ops0;
AddToISelQueue(Chain);
SDOperand InFlag(0, 0);
if (HasInFlag) {
InFlag = N.getOperand(N.getNumOperands()-1);
AddToISelQueue(InFlag);
}
for (unsigned i = 2, e = N.getNumOperands()-(HasInFlag?1:0); i != e;
++i) {
AddToISelQueue(N.getOperand(i));
Ops0.push_back(N.getOperand(i));
}
Ops0.push_back(Chain);
if (HasInFlag)
Ops0.push_back(InFlag);
return CurDAG->getTargetNode(X86::RET, MVT::Other,
&Ops0[0], Ops0.size());
}
break;
case ISD::ADD: {
// Turn ADD X, c to MOV32ri X+c. This cannot be done with tblgen'd
// code and is matched first so to prevent it from being turned into
// LEA32r X+c.
// In 64-bit small code size mode, use LEA to take advantage of
// RIP-relative addressing.
if (TM.getCodeModel() != CodeModel::Small)
break;
MVT::ValueType PtrVT = TLI.getPointerTy();
SDOperand N0 = N.getOperand(0);
SDOperand N1 = N.getOperand(1);
if (N.Val->getValueType(0) == PtrVT &&
N0.getOpcode() == X86ISD::Wrapper &&
N1.getOpcode() == ISD::Constant) {
unsigned Offset = (unsigned)cast<ConstantSDNode>(N1)->getValue();
SDOperand C(0, 0);
// TODO: handle ExternalSymbolSDNode.
if (GlobalAddressSDNode *G =
dyn_cast<GlobalAddressSDNode>(N0.getOperand(0))) {
C = CurDAG->getTargetGlobalAddress(G->getGlobal(), PtrVT,
G->getOffset() + Offset);
} else if (ConstantPoolSDNode *CP =
dyn_cast<ConstantPoolSDNode>(N0.getOperand(0))) {
C = CurDAG->getTargetConstantPool(CP->getConstVal(), PtrVT,
CP->getAlignment(),
CP->getOffset()+Offset);
}
if (C.Val) {
if (Subtarget->is64Bit()) {
SDOperand Ops[] = { CurDAG->getRegister(0, PtrVT), getI8Imm(1),
CurDAG->getRegister(0, PtrVT), C };
return CurDAG->SelectNodeTo(N.Val, X86::LEA64r, MVT::i64, Ops, 4);
} else
return CurDAG->SelectNodeTo(N.Val, X86::MOV32ri, PtrVT, C);
}
}
// Other cases are handled by auto-generated code.
break;
}
case ISD::SMUL_LOHI:
case ISD::UMUL_LOHI: {
SDOperand N0 = Node->getOperand(0);
SDOperand N1 = Node->getOperand(1);
bool isSigned = Opcode == ISD::SMUL_LOHI;
if (!isSigned)
switch (NVT) {
default: assert(0 && "Unsupported VT!");
case MVT::i8: Opc = X86::MUL8r; MOpc = X86::MUL8m; break;
case MVT::i16: Opc = X86::MUL16r; MOpc = X86::MUL16m; break;
case MVT::i32: Opc = X86::MUL32r; MOpc = X86::MUL32m; break;
case MVT::i64: Opc = X86::MUL64r; MOpc = X86::MUL64m; break;
}
else
switch (NVT) {
default: assert(0 && "Unsupported VT!");
case MVT::i8: Opc = X86::IMUL8r; MOpc = X86::IMUL8m; break;
case MVT::i16: Opc = X86::IMUL16r; MOpc = X86::IMUL16m; break;
case MVT::i32: Opc = X86::IMUL32r; MOpc = X86::IMUL32m; break;
case MVT::i64: Opc = X86::IMUL64r; MOpc = X86::IMUL64m; break;
}
unsigned LoReg, HiReg;
switch (NVT) {
default: assert(0 && "Unsupported VT!");
case MVT::i8: LoReg = X86::AL; HiReg = X86::AH; break;
case MVT::i16: LoReg = X86::AX; HiReg = X86::DX; break;
case MVT::i32: LoReg = X86::EAX; HiReg = X86::EDX; break;
case MVT::i64: LoReg = X86::RAX; HiReg = X86::RDX; break;
}
SDOperand Tmp0, Tmp1, Tmp2, Tmp3;
bool foldedLoad = TryFoldLoad(N, N1, Tmp0, Tmp1, Tmp2, Tmp3);
// multiplty is commmutative
if (!foldedLoad) {
foldedLoad = TryFoldLoad(N, N0, Tmp0, Tmp1, Tmp2, Tmp3);
if (foldedLoad)
std::swap(N0, N1);
}
AddToISelQueue(N0);
SDOperand InFlag = CurDAG->getCopyToReg(CurDAG->getEntryNode(), LoReg,
N0, SDOperand()).getValue(1);
if (foldedLoad) {
AddToISelQueue(N1.getOperand(0));
AddToISelQueue(Tmp0);
AddToISelQueue(Tmp1);
AddToISelQueue(Tmp2);
AddToISelQueue(Tmp3);
SDOperand Ops[] = { Tmp0, Tmp1, Tmp2, Tmp3, N1.getOperand(0), InFlag };
SDNode *CNode =
CurDAG->getTargetNode(MOpc, MVT::Other, MVT::Flag, Ops, 6);
InFlag = SDOperand(CNode, 1);
// Update the chain.
ReplaceUses(N1.getValue(1), SDOperand(CNode, 0));
} else {
AddToISelQueue(N1);
InFlag =
SDOperand(CurDAG->getTargetNode(Opc, MVT::Flag, N1, InFlag), 0);
}
// Copy the low half of the result, if it is needed.
if (!N.getValue(0).use_empty()) {
SDOperand Result = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
LoReg, NVT, InFlag);
InFlag = Result.getValue(2);
ReplaceUses(N.getValue(0), Result);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(Result.Val->dump(CurDAG));
DOUT << "\n";
#endif
}
// Copy the high half of the result, if it is needed.
if (!N.getValue(1).use_empty()) {
SDOperand Result;
if (HiReg == X86::AH && Subtarget->is64Bit()) {
// Prevent use of AH in a REX instruction by referencing AX instead.
// Shift it down 8 bits.
Result = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
X86::AX, MVT::i16, InFlag);
InFlag = Result.getValue(2);
Result = SDOperand(CurDAG->getTargetNode(X86::SHR16ri, MVT::i16, Result,
CurDAG->getTargetConstant(8, MVT::i8)), 0);
// Then truncate it down to i8.
SDOperand SRIdx = CurDAG->getTargetConstant(1, MVT::i32); // SubRegSet 1
Result = SDOperand(CurDAG->getTargetNode(X86::EXTRACT_SUBREG,
MVT::i8, Result, SRIdx), 0);
} else {
Result = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
HiReg, NVT, InFlag);
InFlag = Result.getValue(2);
}
ReplaceUses(N.getValue(1), Result);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(Result.Val->dump(CurDAG));
DOUT << "\n";
#endif
}
#ifndef NDEBUG
Indent -= 2;
#endif
return NULL;
}
case ISD::SDIVREM:
case ISD::UDIVREM: {
SDOperand N0 = Node->getOperand(0);
SDOperand N1 = Node->getOperand(1);
bool isSigned = Opcode == ISD::SDIVREM;
if (!isSigned)
switch (NVT) {
default: assert(0 && "Unsupported VT!");
case MVT::i8: Opc = X86::DIV8r; MOpc = X86::DIV8m; break;
case MVT::i16: Opc = X86::DIV16r; MOpc = X86::DIV16m; break;
case MVT::i32: Opc = X86::DIV32r; MOpc = X86::DIV32m; break;
case MVT::i64: Opc = X86::DIV64r; MOpc = X86::DIV64m; break;
}
else
switch (NVT) {
default: assert(0 && "Unsupported VT!");
case MVT::i8: Opc = X86::IDIV8r; MOpc = X86::IDIV8m; break;
case MVT::i16: Opc = X86::IDIV16r; MOpc = X86::IDIV16m; break;
case MVT::i32: Opc = X86::IDIV32r; MOpc = X86::IDIV32m; break;
case MVT::i64: Opc = X86::IDIV64r; MOpc = X86::IDIV64m; break;
}
unsigned LoReg, HiReg;
unsigned ClrOpcode, SExtOpcode;
switch (NVT) {
default: assert(0 && "Unsupported VT!");
case MVT::i8:
LoReg = X86::AL; HiReg = X86::AH;
ClrOpcode = 0;
SExtOpcode = X86::CBW;
break;
case MVT::i16:
LoReg = X86::AX; HiReg = X86::DX;
ClrOpcode = X86::MOV16r0;
SExtOpcode = X86::CWD;
break;
case MVT::i32:
LoReg = X86::EAX; HiReg = X86::EDX;
ClrOpcode = X86::MOV32r0;
SExtOpcode = X86::CDQ;
break;
case MVT::i64:
LoReg = X86::RAX; HiReg = X86::RDX;
ClrOpcode = X86::MOV64r0;
SExtOpcode = X86::CQO;
break;
}
SDOperand Tmp0, Tmp1, Tmp2, Tmp3;
bool foldedLoad = TryFoldLoad(N, N1, Tmp0, Tmp1, Tmp2, Tmp3);
SDOperand InFlag;
if (NVT == MVT::i8 && !isSigned) {
// Special case for div8, just use a move with zero extension to AX to
// clear the upper 8 bits (AH).
SDOperand Tmp0, Tmp1, Tmp2, Tmp3, Move, Chain;
if (TryFoldLoad(N, N0, Tmp0, Tmp1, Tmp2, Tmp3)) {
SDOperand Ops[] = { Tmp0, Tmp1, Tmp2, Tmp3, N0.getOperand(0) };
AddToISelQueue(N0.getOperand(0));
AddToISelQueue(Tmp0);
AddToISelQueue(Tmp1);
AddToISelQueue(Tmp2);
AddToISelQueue(Tmp3);
Move =
SDOperand(CurDAG->getTargetNode(X86::MOVZX16rm8, MVT::i16, MVT::Other,
Ops, 5), 0);
Chain = Move.getValue(1);
ReplaceUses(N0.getValue(1), Chain);
} else {
AddToISelQueue(N0);
Move =
SDOperand(CurDAG->getTargetNode(X86::MOVZX16rr8, MVT::i16, N0), 0);
Chain = CurDAG->getEntryNode();
}
Chain = CurDAG->getCopyToReg(Chain, X86::AX, Move, SDOperand());
InFlag = Chain.getValue(1);
} else {
AddToISelQueue(N0);
InFlag =
CurDAG->getCopyToReg(CurDAG->getEntryNode(),
LoReg, N0, SDOperand()).getValue(1);
if (isSigned) {
// Sign extend the low part into the high part.
InFlag =
SDOperand(CurDAG->getTargetNode(SExtOpcode, MVT::Flag, InFlag), 0);
} else {
// Zero out the high part, effectively zero extending the input.
SDOperand ClrNode = SDOperand(CurDAG->getTargetNode(ClrOpcode, NVT), 0);
InFlag = CurDAG->getCopyToReg(CurDAG->getEntryNode(), HiReg,
ClrNode, InFlag).getValue(1);
}
}
if (foldedLoad) {
AddToISelQueue(N1.getOperand(0));
AddToISelQueue(Tmp0);
AddToISelQueue(Tmp1);
AddToISelQueue(Tmp2);
AddToISelQueue(Tmp3);
SDOperand Ops[] = { Tmp0, Tmp1, Tmp2, Tmp3, N1.getOperand(0), InFlag };
SDNode *CNode =
CurDAG->getTargetNode(MOpc, MVT::Other, MVT::Flag, Ops, 6);
InFlag = SDOperand(CNode, 1);
// Update the chain.
ReplaceUses(N1.getValue(1), SDOperand(CNode, 0));
} else {
AddToISelQueue(N1);
InFlag =
SDOperand(CurDAG->getTargetNode(Opc, MVT::Flag, N1, InFlag), 0);
}
// Copy the division (low) result, if it is needed.
if (!N.getValue(0).use_empty()) {
SDOperand Result = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
LoReg, NVT, InFlag);
InFlag = Result.getValue(2);
ReplaceUses(N.getValue(0), Result);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(Result.Val->dump(CurDAG));
DOUT << "\n";
#endif
}
// Copy the remainder (high) result, if it is needed.
if (!N.getValue(1).use_empty()) {
SDOperand Result;
if (HiReg == X86::AH && Subtarget->is64Bit()) {
// Prevent use of AH in a REX instruction by referencing AX instead.
// Shift it down 8 bits.
Result = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
X86::AX, MVT::i16, InFlag);
InFlag = Result.getValue(2);
Result = SDOperand(CurDAG->getTargetNode(X86::SHR16ri, MVT::i16, Result,
CurDAG->getTargetConstant(8, MVT::i8)), 0);
// Then truncate it down to i8.
SDOperand SRIdx = CurDAG->getTargetConstant(1, MVT::i32); // SubRegSet 1
Result = SDOperand(CurDAG->getTargetNode(X86::EXTRACT_SUBREG,
MVT::i8, Result, SRIdx), 0);
} else {
Result = CurDAG->getCopyFromReg(CurDAG->getEntryNode(),
HiReg, NVT, InFlag);
InFlag = Result.getValue(2);
}
ReplaceUses(N.getValue(1), Result);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(Result.Val->dump(CurDAG));
DOUT << "\n";
#endif
}
#ifndef NDEBUG
Indent -= 2;
#endif
return NULL;
}
case ISD::ANY_EXTEND: {
// Check if the type extended to supports subregs.
if (NVT == MVT::i8)
break;
SDOperand N0 = Node->getOperand(0);
// Get the subregsiter index for the type to extend.
MVT::ValueType N0VT = N0.getValueType();
unsigned Idx = (N0VT == MVT::i32) ? X86::SUBREG_32BIT :
(N0VT == MVT::i16) ? X86::SUBREG_16BIT :
(Subtarget->is64Bit()) ? X86::SUBREG_8BIT : 0;
// If we don't have a subreg Idx, let generated ISel have a try.
if (Idx == 0)
break;
// If we have an index, generate an insert_subreg into undef.
AddToISelQueue(N0);
SDOperand Undef =
SDOperand(CurDAG->getTargetNode(X86::IMPLICIT_DEF, NVT), 0);
SDOperand SRIdx = CurDAG->getTargetConstant(Idx, MVT::i32);
SDNode *ResNode = CurDAG->getTargetNode(X86::INSERT_SUBREG,
NVT, Undef, N0, SRIdx);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(ResNode->dump(CurDAG));
DOUT << "\n";
Indent -= 2;
#endif
return ResNode;
}
case ISD::SIGN_EXTEND_INREG: {
SDOperand N0 = Node->getOperand(0);
AddToISelQueue(N0);
MVT::ValueType SVT = cast<VTSDNode>(Node->getOperand(1))->getVT();
SDOperand TruncOp = SDOperand(getTruncate(N0, SVT), 0);
unsigned Opc = 0;
switch (NVT) {
case MVT::i16:
if (SVT == MVT::i8) Opc = X86::MOVSX16rr8;
else assert(0 && "Unknown sign_extend_inreg!");
break;
case MVT::i32:
switch (SVT) {
case MVT::i8: Opc = X86::MOVSX32rr8; break;
case MVT::i16: Opc = X86::MOVSX32rr16; break;
default: assert(0 && "Unknown sign_extend_inreg!");
}
break;
case MVT::i64:
switch (SVT) {
case MVT::i8: Opc = X86::MOVSX64rr8; break;
case MVT::i16: Opc = X86::MOVSX64rr16; break;
case MVT::i32: Opc = X86::MOVSX64rr32; break;
default: assert(0 && "Unknown sign_extend_inreg!");
}
break;
default: assert(0 && "Unknown sign_extend_inreg!");
}
SDNode *ResNode = CurDAG->getTargetNode(Opc, NVT, TruncOp);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(TruncOp.Val->dump(CurDAG));
DOUT << "\n";
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(ResNode->dump(CurDAG));
DOUT << "\n";
Indent -= 2;
#endif
return ResNode;
break;
}
case ISD::TRUNCATE: {
SDOperand Input = Node->getOperand(0);
AddToISelQueue(Node->getOperand(0));
SDNode *ResNode = getTruncate(Input, NVT);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
DEBUG(ResNode->dump(CurDAG));
DOUT << "\n";
Indent -= 2;
#endif
return ResNode;
break;
}
}
SDNode *ResNode = SelectCode(N);
#ifndef NDEBUG
DOUT << std::string(Indent-2, ' ') << "=> ";
if (ResNode == NULL || ResNode == N.Val)
DEBUG(N.Val->dump(CurDAG));
else
DEBUG(ResNode->dump(CurDAG));
DOUT << "\n";
Indent -= 2;
#endif
return ResNode;
}
bool X86DAGToDAGISel::
SelectInlineAsmMemoryOperand(const SDOperand &Op, char ConstraintCode,
std::vector<SDOperand> &OutOps, SelectionDAG &DAG){
SDOperand Op0, Op1, Op2, Op3;
switch (ConstraintCode) {
case 'o': // offsetable ??
case 'v': // not offsetable ??
default: return true;
case 'm': // memory
if (!SelectAddr(Op, Op, Op0, Op1, Op2, Op3))
return true;
break;
}
OutOps.push_back(Op0);
OutOps.push_back(Op1);
OutOps.push_back(Op2);
OutOps.push_back(Op3);
AddToISelQueue(Op0);
AddToISelQueue(Op1);
AddToISelQueue(Op2);
AddToISelQueue(Op3);
return false;
}
/// createX86ISelDag - This pass converts a legalized DAG into a
/// X86-specific DAG, ready for instruction scheduling.
///
FunctionPass *llvm::createX86ISelDag(X86TargetMachine &TM, bool Fast) {
return new X86DAGToDAGISel(TM, Fast);
}
Reference in New Issue View Git Blame Copy Permalink