Separate X86ISelLowering stuff out from the X86ISelPattern.cpp file. Patch

contributed by Evan Cheng.

llvm-svn: 24358
This commit is contained in:
Chris Lattner 2005-11-15 00:40:23 +00:00
parent bba9c372c1
commit 76ac068568
5 changed files with 1061 additions and 1007 deletions

View File

@ -32,10 +32,16 @@ enum X86VectorEnum {
extern X86VectorEnum X86Vector;
extern bool X86ScalarSSE;
/// createX86PatternInstructionSelector - This pass converts an LLVM function
/// into a machine code representation in a more aggressive way.
/// createX86ISelPattern - This pass converts an LLVM function into a
/// machine code representation using pattern matching and a machine
/// description file.
///
FunctionPass *createX86PatternInstructionSelector(TargetMachine &TM);
FunctionPass *createX86ISelPattern(TargetMachine &TM);
/// createX86ISelDag - This pass converts a legalized DAG into a
/// X86-specific DAG, ready for instruction scheduling.
///
FunctionPass *createX86ISelDag(TargetMachine &TM);
/// createX86SSAPeepholeOptimizerPass - Create a pass to perform SSA-based X86
/// specific peephole optimizations.

View File

@ -0,0 +1,916 @@
//===-- X86ISelLowering.h - X86 DAG Lowering Interface ----------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file was developed by Chris Lattner and is distributed under
// the University of Illinois Open Source License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that X86 uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//
#include "X86.h"
#include "X86ISelLowering.h"
#include "X86TargetMachine.h"
#include "llvm/CallingConv.h"
#include "llvm/Function.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/SSARegMap.h"
#include "llvm/Target/TargetOptions.h"
using namespace llvm;
// FIXME: temporary.
#include "llvm/Support/CommandLine.h"
static cl::opt<bool> EnableFastCC("enable-x86-fastcc", cl::Hidden,
cl::desc("Enable fastcc on X86"));
X86TargetLowering::X86TargetLowering(TargetMachine &TM)
: TargetLowering(TM) {
// Set up the TargetLowering object.
// X86 is weird, it always uses i8 for shift amounts and setcc results.
setShiftAmountType(MVT::i8);
setSetCCResultType(MVT::i8);
setSetCCResultContents(ZeroOrOneSetCCResult);
setShiftAmountFlavor(Mask); // shl X, 32 == shl X, 0
// Set up the register classes.
// FIXME: Eliminate these two classes when legalize can handle promotions
// well.
addRegisterClass(MVT::i1, X86::R8RegisterClass);
addRegisterClass(MVT::i8, X86::R8RegisterClass);
addRegisterClass(MVT::i16, X86::R16RegisterClass);
addRegisterClass(MVT::i32, X86::R32RegisterClass);
// Promote all UINT_TO_FP to larger SINT_TO_FP's, as X86 doesn't have this
// operation.
setOperationAction(ISD::UINT_TO_FP , MVT::i1 , Promote);
setOperationAction(ISD::UINT_TO_FP , MVT::i8 , Promote);
setOperationAction(ISD::UINT_TO_FP , MVT::i16 , Promote);
setOperationAction(ISD::UINT_TO_FP , MVT::i32 , Promote);
// Promote i1/i8 SINT_TO_FP to larger SINT_TO_FP's, as X86 doesn't have
// this operation.
setOperationAction(ISD::SINT_TO_FP , MVT::i1 , Promote);
setOperationAction(ISD::SINT_TO_FP , MVT::i8 , Promote);
if (!X86ScalarSSE) {
// We can handle SINT_TO_FP and FP_TO_SINT from/TO i64 even though i64
// isn't legal.
setOperationAction(ISD::SINT_TO_FP , MVT::i64 , Custom);
setOperationAction(ISD::FP_TO_SINT , MVT::i64 , Custom);
setOperationAction(ISD::FP_TO_SINT , MVT::i32 , Custom);
setOperationAction(ISD::FP_TO_SINT , MVT::i16 , Custom);
}
// Handle FP_TO_UINT by promoting the destination to a larger signed
// conversion.
setOperationAction(ISD::FP_TO_UINT , MVT::i1 , Promote);
setOperationAction(ISD::FP_TO_UINT , MVT::i8 , Promote);
setOperationAction(ISD::FP_TO_UINT , MVT::i16 , Promote);
if (!X86ScalarSSE)
setOperationAction(ISD::FP_TO_UINT , MVT::i32 , Promote);
// Promote i1/i8 FP_TO_SINT to larger FP_TO_SINTS's, as X86 doesn't have
// this operation.
setOperationAction(ISD::FP_TO_SINT , MVT::i1 , Promote);
setOperationAction(ISD::FP_TO_SINT , MVT::i8 , Promote);
setOperationAction(ISD::FP_TO_SINT , MVT::i16 , Promote);
setOperationAction(ISD::BRCONDTWOWAY , MVT::Other, Expand);
setOperationAction(ISD::BRTWOWAY_CC , MVT::Other, Expand);
setOperationAction(ISD::MEMMOVE , MVT::Other, Expand);
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::i16 , Expand);
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::i1 , Expand);
setOperationAction(ISD::FP_ROUND_INREG , MVT::f32 , Expand);
setOperationAction(ISD::SEXTLOAD , MVT::i1 , Expand);
setOperationAction(ISD::FREM , MVT::f64 , Expand);
setOperationAction(ISD::CTPOP , MVT::i8 , Expand);
setOperationAction(ISD::CTTZ , MVT::i8 , Expand);
setOperationAction(ISD::CTLZ , MVT::i8 , Expand);
setOperationAction(ISD::CTPOP , MVT::i16 , Expand);
setOperationAction(ISD::CTTZ , MVT::i16 , Expand);
setOperationAction(ISD::CTLZ , MVT::i16 , Expand);
setOperationAction(ISD::CTPOP , MVT::i32 , Expand);
setOperationAction(ISD::CTTZ , MVT::i32 , Expand);
setOperationAction(ISD::CTLZ , MVT::i32 , Expand);
setOperationAction(ISD::READIO , MVT::i1 , Expand);
setOperationAction(ISD::READIO , MVT::i8 , Expand);
setOperationAction(ISD::READIO , MVT::i16 , Expand);
setOperationAction(ISD::READIO , MVT::i32 , Expand);
setOperationAction(ISD::WRITEIO , MVT::i1 , Expand);
setOperationAction(ISD::WRITEIO , MVT::i8 , Expand);
setOperationAction(ISD::WRITEIO , MVT::i16 , Expand);
setOperationAction(ISD::WRITEIO , MVT::i32 , Expand);
// These should be promoted to a larger select which is supported.
setOperationAction(ISD::SELECT , MVT::i1 , Promote);
setOperationAction(ISD::SELECT , MVT::i8 , Promote);
if (X86ScalarSSE) {
// Set up the FP register classes.
addRegisterClass(MVT::f32, X86::V4F4RegisterClass);
addRegisterClass(MVT::f64, X86::V2F8RegisterClass);
// SSE has no load+extend ops
setOperationAction(ISD::EXTLOAD, MVT::f32, Expand);
setOperationAction(ISD::ZEXTLOAD, MVT::f32, Expand);
// SSE has no i16 to fp conversion, only i32
setOperationAction(ISD::SINT_TO_FP, MVT::i16, Promote);
setOperationAction(ISD::FP_TO_SINT, MVT::i16, Promote);
// Expand FP_TO_UINT into a select.
// FIXME: We would like to use a Custom expander here eventually to do
// the optimal thing for SSE vs. the default expansion in the legalizer.
setOperationAction(ISD::FP_TO_UINT , MVT::i32 , Expand);
// We don't support sin/cos/sqrt/fmod
setOperationAction(ISD::FSIN , MVT::f64, Expand);
setOperationAction(ISD::FCOS , MVT::f64, Expand);
setOperationAction(ISD::FABS , MVT::f64, Expand);
setOperationAction(ISD::FNEG , MVT::f64, Expand);
setOperationAction(ISD::FREM , MVT::f64, Expand);
setOperationAction(ISD::FSIN , MVT::f32, Expand);
setOperationAction(ISD::FCOS , MVT::f32, Expand);
setOperationAction(ISD::FABS , MVT::f32, Expand);
setOperationAction(ISD::FNEG , MVT::f32, Expand);
setOperationAction(ISD::FREM , MVT::f32, Expand);
addLegalFPImmediate(+0.0); // xorps / xorpd
} else {
// Set up the FP register classes.
addRegisterClass(MVT::f64, X86::RFPRegisterClass);
if (!UnsafeFPMath) {
setOperationAction(ISD::FSIN , MVT::f64 , Expand);
setOperationAction(ISD::FCOS , MVT::f64 , Expand);
}
addLegalFPImmediate(+0.0); // FLD0
addLegalFPImmediate(+1.0); // FLD1
addLegalFPImmediate(-0.0); // FLD0/FCHS
addLegalFPImmediate(-1.0); // FLD1/FCHS
}
computeRegisterProperties();
maxStoresPerMemSet = 8; // For %llvm.memset -> sequence of stores
maxStoresPerMemCpy = 8; // For %llvm.memcpy -> sequence of stores
maxStoresPerMemMove = 8; // For %llvm.memmove -> sequence of stores
allowUnalignedMemoryAccesses = true; // x86 supports it!
}
std::vector<SDOperand>
X86TargetLowering::LowerArguments(Function &F, SelectionDAG &DAG) {
if (F.getCallingConv() == CallingConv::Fast && EnableFastCC)
return LowerFastCCArguments(F, DAG);
return LowerCCCArguments(F, DAG);
}
std::pair<SDOperand, SDOperand>
X86TargetLowering::LowerCallTo(SDOperand Chain, const Type *RetTy,
bool isVarArg, unsigned CallingConv,
bool isTailCall,
SDOperand Callee, ArgListTy &Args,
SelectionDAG &DAG) {
assert((!isVarArg || CallingConv == CallingConv::C) &&
"Only C takes varargs!");
if (CallingConv == CallingConv::Fast && EnableFastCC)
return LowerFastCCCallTo(Chain, RetTy, isTailCall, Callee, Args, DAG);
return LowerCCCCallTo(Chain, RetTy, isVarArg, isTailCall, Callee, Args, DAG);
}
//===----------------------------------------------------------------------===//
// C Calling Convention implementation
//===----------------------------------------------------------------------===//
std::vector<SDOperand>
X86TargetLowering::LowerCCCArguments(Function &F, SelectionDAG &DAG) {
std::vector<SDOperand> ArgValues;
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo *MFI = MF.getFrameInfo();
// Add DAG nodes to load the arguments... On entry to a function on the X86,
// the stack frame looks like this:
//
// [ESP] -- return address
// [ESP + 4] -- first argument (leftmost lexically)
// [ESP + 8] -- second argument, if first argument is four bytes in size
// ...
//
unsigned ArgOffset = 0; // Frame mechanisms handle retaddr slot
for (Function::arg_iterator I = F.arg_begin(), E = F.arg_end(); I != E; ++I) {
MVT::ValueType ObjectVT = getValueType(I->getType());
unsigned ArgIncrement = 4;
unsigned ObjSize;
switch (ObjectVT) {
default: assert(0 && "Unhandled argument type!");
case MVT::i1:
case MVT::i8: ObjSize = 1; break;
case MVT::i16: ObjSize = 2; break;
case MVT::i32: ObjSize = 4; break;
case MVT::i64: ObjSize = ArgIncrement = 8; break;
case MVT::f32: ObjSize = 4; break;
case MVT::f64: ObjSize = ArgIncrement = 8; break;
}
// Create the frame index object for this incoming parameter...
int FI = MFI->CreateFixedObject(ObjSize, ArgOffset);
// Create the SelectionDAG nodes corresponding to a load from this parameter
SDOperand FIN = DAG.getFrameIndex(FI, MVT::i32);
// Don't codegen dead arguments. FIXME: remove this check when we can nuke
// dead loads.
SDOperand ArgValue;
if (!I->use_empty())
ArgValue = DAG.getLoad(ObjectVT, DAG.getEntryNode(), FIN,
DAG.getSrcValue(NULL));
else {
if (MVT::isInteger(ObjectVT))
ArgValue = DAG.getConstant(0, ObjectVT);
else
ArgValue = DAG.getConstantFP(0, ObjectVT);
}
ArgValues.push_back(ArgValue);
ArgOffset += ArgIncrement; // Move on to the next argument...
}
// If the function takes variable number of arguments, make a frame index for
// the start of the first vararg value... for expansion of llvm.va_start.
if (F.isVarArg())
VarArgsFrameIndex = MFI->CreateFixedObject(1, ArgOffset);
ReturnAddrIndex = 0; // No return address slot generated yet.
BytesToPopOnReturn = 0; // Callee pops nothing.
BytesCallerReserves = ArgOffset;
// Finally, inform the code generator which regs we return values in.
switch (getValueType(F.getReturnType())) {
default: assert(0 && "Unknown type!");
case MVT::isVoid: break;
case MVT::i1:
case MVT::i8:
case MVT::i16:
case MVT::i32:
MF.addLiveOut(X86::EAX);
break;
case MVT::i64:
MF.addLiveOut(X86::EAX);
MF.addLiveOut(X86::EDX);
break;
case MVT::f32:
case MVT::f64:
MF.addLiveOut(X86::ST0);
break;
}
return ArgValues;
}
std::pair<SDOperand, SDOperand>
X86TargetLowering::LowerCCCCallTo(SDOperand Chain, const Type *RetTy,
bool isVarArg, bool isTailCall,
SDOperand Callee, ArgListTy &Args,
SelectionDAG &DAG) {
// Count how many bytes are to be pushed on the stack.
unsigned NumBytes = 0;
if (Args.empty()) {
// Save zero bytes.
Chain = DAG.getNode(ISD::CALLSEQ_START, MVT::Other, Chain,
DAG.getConstant(0, getPointerTy()));
} else {
for (unsigned i = 0, e = Args.size(); i != e; ++i)
switch (getValueType(Args[i].second)) {
default: assert(0 && "Unknown value type!");
case MVT::i1:
case MVT::i8:
case MVT::i16:
case MVT::i32:
case MVT::f32:
NumBytes += 4;
break;
case MVT::i64:
case MVT::f64:
NumBytes += 8;
break;
}
Chain = DAG.getNode(ISD::CALLSEQ_START, MVT::Other, Chain,
DAG.getConstant(NumBytes, getPointerTy()));
// Arguments go on the stack in reverse order, as specified by the ABI.
unsigned ArgOffset = 0;
SDOperand StackPtr = DAG.getCopyFromReg(DAG.getEntryNode(),
X86::ESP, MVT::i32);
std::vector<SDOperand> Stores;
for (unsigned i = 0, e = Args.size(); i != e; ++i) {
SDOperand PtrOff = DAG.getConstant(ArgOffset, getPointerTy());
PtrOff = DAG.getNode(ISD::ADD, MVT::i32, StackPtr, PtrOff);
switch (getValueType(Args[i].second)) {
default: assert(0 && "Unexpected ValueType for argument!");
case MVT::i1:
case MVT::i8:
case MVT::i16:
// Promote the integer to 32 bits. If the input type is signed use a
// sign extend, otherwise use a zero extend.
if (Args[i].second->isSigned())
Args[i].first =DAG.getNode(ISD::SIGN_EXTEND, MVT::i32, Args[i].first);
else
Args[i].first =DAG.getNode(ISD::ZERO_EXTEND, MVT::i32, Args[i].first);
// FALL THROUGH
case MVT::i32:
case MVT::f32:
Stores.push_back(DAG.getNode(ISD::STORE, MVT::Other, Chain,
Args[i].first, PtrOff,
DAG.getSrcValue(NULL)));
ArgOffset += 4;
break;
case MVT::i64:
case MVT::f64:
Stores.push_back(DAG.getNode(ISD::STORE, MVT::Other, Chain,
Args[i].first, PtrOff,
DAG.getSrcValue(NULL)));
ArgOffset += 8;
break;
}
}
Chain = DAG.getNode(ISD::TokenFactor, MVT::Other, Stores);
}
std::vector<MVT::ValueType> RetVals;
MVT::ValueType RetTyVT = getValueType(RetTy);
RetVals.push_back(MVT::Other);
// The result values produced have to be legal. Promote the result.
switch (RetTyVT) {
case MVT::isVoid: break;
default:
RetVals.push_back(RetTyVT);
break;
case MVT::i1:
case MVT::i8:
case MVT::i16:
RetVals.push_back(MVT::i32);
break;
case MVT::f32:
if (X86ScalarSSE)
RetVals.push_back(MVT::f32);
else
RetVals.push_back(MVT::f64);
break;
case MVT::i64:
RetVals.push_back(MVT::i32);
RetVals.push_back(MVT::i32);
break;
}
std::vector<SDOperand> Ops;
Ops.push_back(Chain);
Ops.push_back(Callee);
Ops.push_back(DAG.getConstant(NumBytes, getPointerTy()));
Ops.push_back(DAG.getConstant(0, getPointerTy()));
SDOperand TheCall = DAG.getNode(isTailCall ? X86ISD::TAILCALL : X86ISD::CALL,
RetVals, Ops);
Chain = DAG.getNode(ISD::CALLSEQ_END, MVT::Other, TheCall);
SDOperand ResultVal;
switch (RetTyVT) {
case MVT::isVoid: break;
default:
ResultVal = TheCall.getValue(1);
break;
case MVT::i1:
case MVT::i8:
case MVT::i16:
ResultVal = DAG.getNode(ISD::TRUNCATE, RetTyVT, TheCall.getValue(1));
break;
case MVT::f32:
// FIXME: we would really like to remember that this FP_ROUND operation is
// okay to eliminate if we allow excess FP precision.
ResultVal = DAG.getNode(ISD::FP_ROUND, MVT::f32, TheCall.getValue(1));
break;
case MVT::i64:
ResultVal = DAG.getNode(ISD::BUILD_PAIR, MVT::i64, TheCall.getValue(1),
TheCall.getValue(2));
break;
}
return std::make_pair(ResultVal, Chain);
}
SDOperand
X86TargetLowering::LowerVAStart(SDOperand Chain, SDOperand VAListP,
Value *VAListV, SelectionDAG &DAG) {
// vastart just stores the address of the VarArgsFrameIndex slot.
SDOperand FR = DAG.getFrameIndex(VarArgsFrameIndex, MVT::i32);
return DAG.getNode(ISD::STORE, MVT::Other, Chain, FR, VAListP,
DAG.getSrcValue(VAListV));
}
std::pair<SDOperand,SDOperand>
X86TargetLowering::LowerVAArg(SDOperand Chain, SDOperand VAListP,
Value *VAListV, const Type *ArgTy,
SelectionDAG &DAG) {
MVT::ValueType ArgVT = getValueType(ArgTy);
SDOperand Val = DAG.getLoad(MVT::i32, Chain,
VAListP, DAG.getSrcValue(VAListV));
SDOperand Result = DAG.getLoad(ArgVT, Chain, Val,
DAG.getSrcValue(NULL));
unsigned Amt;
if (ArgVT == MVT::i32)
Amt = 4;
else {
assert((ArgVT == MVT::i64 || ArgVT == MVT::f64) &&
"Other types should have been promoted for varargs!");
Amt = 8;
}
Val = DAG.getNode(ISD::ADD, Val.getValueType(), Val,
DAG.getConstant(Amt, Val.getValueType()));
Chain = DAG.getNode(ISD::STORE, MVT::Other, Chain,
Val, VAListP, DAG.getSrcValue(VAListV));
return std::make_pair(Result, Chain);
}
//===----------------------------------------------------------------------===//
// Fast Calling Convention implementation
//===----------------------------------------------------------------------===//
//
// The X86 'fast' calling convention passes up to two integer arguments in
// registers (an appropriate portion of EAX/EDX), passes arguments in C order,
// and requires that the callee pop its arguments off the stack (allowing proper
// tail calls), and has the same return value conventions as C calling convs.
//
// This calling convention always arranges for the callee pop value to be 8n+4
// bytes, which is needed for tail recursion elimination and stack alignment
// reasons.
//
// Note that this can be enhanced in the future to pass fp vals in registers
// (when we have a global fp allocator) and do other tricks.
//
/// AddLiveIn - This helper function adds the specified physical register to the
/// MachineFunction as a live in value. It also creates a corresponding virtual
/// register for it.
static unsigned AddLiveIn(MachineFunction &MF, unsigned PReg,
TargetRegisterClass *RC) {
assert(RC->contains(PReg) && "Not the correct regclass!");
unsigned VReg = MF.getSSARegMap()->createVirtualRegister(RC);
MF.addLiveIn(PReg, VReg);
return VReg;
}
std::vector<SDOperand>
X86TargetLowering::LowerFastCCArguments(Function &F, SelectionDAG &DAG) {
std::vector<SDOperand> ArgValues;
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo *MFI = MF.getFrameInfo();
// Add DAG nodes to load the arguments... On entry to a function the stack
// frame looks like this:
//
// [ESP] -- return address
// [ESP + 4] -- first nonreg argument (leftmost lexically)
// [ESP + 8] -- second nonreg argument, if first argument is 4 bytes in size
// ...
unsigned ArgOffset = 0; // Frame mechanisms handle retaddr slot
// Keep track of the number of integer regs passed so far. This can be either
// 0 (neither EAX or EDX used), 1 (EAX is used) or 2 (EAX and EDX are both
// used).
unsigned NumIntRegs = 0;
for (Function::arg_iterator I = F.arg_begin(), E = F.arg_end(); I != E; ++I) {
MVT::ValueType ObjectVT = getValueType(I->getType());
unsigned ArgIncrement = 4;
unsigned ObjSize = 0;
SDOperand ArgValue;
switch (ObjectVT) {
default: assert(0 && "Unhandled argument type!");
case MVT::i1:
case MVT::i8:
if (NumIntRegs < 2) {
if (!I->use_empty()) {
unsigned VReg = AddLiveIn(MF, NumIntRegs ? X86::DL : X86::AL,
X86::R8RegisterClass);
ArgValue = DAG.getCopyFromReg(DAG.getRoot(), VReg, MVT::i8);
DAG.setRoot(ArgValue.getValue(1));
}
++NumIntRegs;
break;
}
ObjSize = 1;
break;
case MVT::i16:
if (NumIntRegs < 2) {
if (!I->use_empty()) {
unsigned VReg = AddLiveIn(MF, NumIntRegs ? X86::DX : X86::AX,
X86::R16RegisterClass);
ArgValue = DAG.getCopyFromReg(DAG.getRoot(), VReg, MVT::i16);
DAG.setRoot(ArgValue.getValue(1));
}
++NumIntRegs;
break;
}
ObjSize = 2;
break;
case MVT::i32:
if (NumIntRegs < 2) {
if (!I->use_empty()) {
unsigned VReg = AddLiveIn(MF,NumIntRegs ? X86::EDX : X86::EAX,
X86::R32RegisterClass);
ArgValue = DAG.getCopyFromReg(DAG.getRoot(), VReg, MVT::i32);
DAG.setRoot(ArgValue.getValue(1));
}
++NumIntRegs;
break;
}
ObjSize = 4;
break;
case MVT::i64:
if (NumIntRegs == 0) {
if (!I->use_empty()) {
unsigned BotReg = AddLiveIn(MF, X86::EAX, X86::R32RegisterClass);
unsigned TopReg = AddLiveIn(MF, X86::EDX, X86::R32RegisterClass);
SDOperand Low = DAG.getCopyFromReg(DAG.getRoot(), BotReg, MVT::i32);
SDOperand Hi = DAG.getCopyFromReg(Low.getValue(1), TopReg, MVT::i32);
DAG.setRoot(Hi.getValue(1));
ArgValue = DAG.getNode(ISD::BUILD_PAIR, MVT::i64, Low, Hi);
}
NumIntRegs = 2;
break;
} else if (NumIntRegs == 1) {
if (!I->use_empty()) {
unsigned BotReg = AddLiveIn(MF, X86::EDX, X86::R32RegisterClass);
SDOperand Low = DAG.getCopyFromReg(DAG.getRoot(), BotReg, MVT::i32);
DAG.setRoot(Low.getValue(1));
// Load the high part from memory.
// Create the frame index object for this incoming parameter...
int FI = MFI->CreateFixedObject(4, ArgOffset);
SDOperand FIN = DAG.getFrameIndex(FI, MVT::i32);
SDOperand Hi = DAG.getLoad(MVT::i32, DAG.getEntryNode(), FIN,
DAG.getSrcValue(NULL));
ArgValue = DAG.getNode(ISD::BUILD_PAIR, MVT::i64, Low, Hi);
}
ArgOffset += 4;
NumIntRegs = 2;
break;
}
ObjSize = ArgIncrement = 8;
break;
case MVT::f32: ObjSize = 4; break;
case MVT::f64: ObjSize = ArgIncrement = 8; break;
}
// Don't codegen dead arguments. FIXME: remove this check when we can nuke
// dead loads.
if (ObjSize && !I->use_empty()) {
// Create the frame index object for this incoming parameter...
int FI = MFI->CreateFixedObject(ObjSize, ArgOffset);
// Create the SelectionDAG nodes corresponding to a load from this
// parameter.
SDOperand FIN = DAG.getFrameIndex(FI, MVT::i32);
ArgValue = DAG.getLoad(ObjectVT, DAG.getEntryNode(), FIN,
DAG.getSrcValue(NULL));
} else if (ArgValue.Val == 0) {
if (MVT::isInteger(ObjectVT))
ArgValue = DAG.getConstant(0, ObjectVT);
else
ArgValue = DAG.getConstantFP(0, ObjectVT);
}
ArgValues.push_back(ArgValue);
if (ObjSize)
ArgOffset += ArgIncrement; // Move on to the next argument.
}
// Make sure the instruction takes 8n+4 bytes to make sure the start of the
// arguments and the arguments after the retaddr has been pushed are aligned.
if ((ArgOffset & 7) == 0)
ArgOffset += 4;
VarArgsFrameIndex = 0xAAAAAAA; // fastcc functions can't have varargs.
ReturnAddrIndex = 0; // No return address slot generated yet.
BytesToPopOnReturn = ArgOffset; // Callee pops all stack arguments.
BytesCallerReserves = 0;
// Finally, inform the code generator which regs we return values in.
switch (getValueType(F.getReturnType())) {
default: assert(0 && "Unknown type!");
case MVT::isVoid: break;
case MVT::i1:
case MVT::i8:
case MVT::i16:
case MVT::i32:
MF.addLiveOut(X86::EAX);
break;
case MVT::i64:
MF.addLiveOut(X86::EAX);
MF.addLiveOut(X86::EDX);
break;
case MVT::f32:
case MVT::f64:
MF.addLiveOut(X86::ST0);
break;
}
return ArgValues;
}
std::pair<SDOperand, SDOperand>
X86TargetLowering::LowerFastCCCallTo(SDOperand Chain, const Type *RetTy,
bool isTailCall, SDOperand Callee,
ArgListTy &Args, SelectionDAG &DAG) {
// Count how many bytes are to be pushed on the stack.
unsigned NumBytes = 0;
// Keep track of the number of integer regs passed so far. This can be either
// 0 (neither EAX or EDX used), 1 (EAX is used) or 2 (EAX and EDX are both
// used).
unsigned NumIntRegs = 0;
for (unsigned i = 0, e = Args.size(); i != e; ++i)
switch (getValueType(Args[i].second)) {
default: assert(0 && "Unknown value type!");
case MVT::i1:
case MVT::i8:
case MVT::i16:
case MVT::i32:
if (NumIntRegs < 2) {
++NumIntRegs;
break;
}
// fall through
case MVT::f32:
NumBytes += 4;
break;
case MVT::i64:
if (NumIntRegs == 0) {
NumIntRegs = 2;
break;
} else if (NumIntRegs == 1) {
NumIntRegs = 2;
NumBytes += 4;
break;
}
// fall through
case MVT::f64:
NumBytes += 8;
break;
}
// Make sure the instruction takes 8n+4 bytes to make sure the start of the
// arguments and the arguments after the retaddr has been pushed are aligned.
if ((NumBytes & 7) == 0)
NumBytes += 4;
Chain = DAG.getNode(ISD::CALLSEQ_START, MVT::Other, Chain,
DAG.getConstant(NumBytes, getPointerTy()));
// Arguments go on the stack in reverse order, as specified by the ABI.
unsigned ArgOffset = 0;
SDOperand StackPtr = DAG.getCopyFromReg(DAG.getEntryNode(),
X86::ESP, MVT::i32);
NumIntRegs = 0;
std::vector<SDOperand> Stores;
std::vector<SDOperand> RegValuesToPass;
for (unsigned i = 0, e = Args.size(); i != e; ++i) {
switch (getValueType(Args[i].second)) {
default: assert(0 && "Unexpected ValueType for argument!");
case MVT::i1:
case MVT::i8:
case MVT::i16:
case MVT::i32:
if (NumIntRegs < 2) {
RegValuesToPass.push_back(Args[i].first);
++NumIntRegs;
break;
}
// Fall through
case MVT::f32: {
SDOperand PtrOff = DAG.getConstant(ArgOffset, getPointerTy());
PtrOff = DAG.getNode(ISD::ADD, MVT::i32, StackPtr, PtrOff);
Stores.push_back(DAG.getNode(ISD::STORE, MVT::Other, Chain,
Args[i].first, PtrOff,
DAG.getSrcValue(NULL)));
ArgOffset += 4;
break;
}
case MVT::i64:
if (NumIntRegs < 2) { // Can pass part of it in regs?
SDOperand Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, MVT::i32,
Args[i].first, DAG.getConstant(1, MVT::i32));
SDOperand Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, MVT::i32,
Args[i].first, DAG.getConstant(0, MVT::i32));
RegValuesToPass.push_back(Lo);
++NumIntRegs;
if (NumIntRegs < 2) { // Pass both parts in regs?
RegValuesToPass.push_back(Hi);
++NumIntRegs;
} else {
// Pass the high part in memory.
SDOperand PtrOff = DAG.getConstant(ArgOffset, getPointerTy());
PtrOff = DAG.getNode(ISD::ADD, MVT::i32, StackPtr, PtrOff);
Stores.push_back(DAG.getNode(ISD::STORE, MVT::Other, Chain,
Hi, PtrOff, DAG.getSrcValue(NULL)));
ArgOffset += 4;
}
break;
}
// Fall through
case MVT::f64:
SDOperand PtrOff = DAG.getConstant(ArgOffset, getPointerTy());
PtrOff = DAG.getNode(ISD::ADD, MVT::i32, StackPtr, PtrOff);
Stores.push_back(DAG.getNode(ISD::STORE, MVT::Other, Chain,
Args[i].first, PtrOff,
DAG.getSrcValue(NULL)));
ArgOffset += 8;
break;
}
}
if (!Stores.empty())
Chain = DAG.getNode(ISD::TokenFactor, MVT::Other, Stores);
// Make sure the instruction takes 8n+4 bytes to make sure the start of the
// arguments and the arguments after the retaddr has been pushed are aligned.
if ((ArgOffset & 7) == 0)
ArgOffset += 4;
std::vector<MVT::ValueType> RetVals;
MVT::ValueType RetTyVT = getValueType(RetTy);
RetVals.push_back(MVT::Other);
// The result values produced have to be legal. Promote the result.
switch (RetTyVT) {
case MVT::isVoid: break;
default:
RetVals.push_back(RetTyVT);
break;
case MVT::i1:
case MVT::i8:
case MVT::i16:
RetVals.push_back(MVT::i32);
break;
case MVT::f32:
if (X86ScalarSSE)
RetVals.push_back(MVT::f32);
else
RetVals.push_back(MVT::f64);
break;
case MVT::i64:
RetVals.push_back(MVT::i32);
RetVals.push_back(MVT::i32);
break;
}
std::vector<SDOperand> Ops;
Ops.push_back(Chain);
Ops.push_back(Callee);
Ops.push_back(DAG.getConstant(ArgOffset, getPointerTy()));
// Callee pops all arg values on the stack.
Ops.push_back(DAG.getConstant(ArgOffset, getPointerTy()));
// Pass register arguments as needed.
Ops.insert(Ops.end(), RegValuesToPass.begin(), RegValuesToPass.end());
SDOperand TheCall = DAG.getNode(isTailCall ? X86ISD::TAILCALL : X86ISD::CALL,
RetVals, Ops);
Chain = DAG.getNode(ISD::CALLSEQ_END, MVT::Other, TheCall);
SDOperand ResultVal;
switch (RetTyVT) {
case MVT::isVoid: break;
default:
ResultVal = TheCall.getValue(1);
break;
case MVT::i1:
case MVT::i8:
case MVT::i16:
ResultVal = DAG.getNode(ISD::TRUNCATE, RetTyVT, TheCall.getValue(1));
break;
case MVT::f32:
// FIXME: we would really like to remember that this FP_ROUND operation is
// okay to eliminate if we allow excess FP precision.
ResultVal = DAG.getNode(ISD::FP_ROUND, MVT::f32, TheCall.getValue(1));
break;
case MVT::i64:
ResultVal = DAG.getNode(ISD::BUILD_PAIR, MVT::i64, TheCall.getValue(1),
TheCall.getValue(2));
break;
}
return std::make_pair(ResultVal, Chain);
}
SDOperand X86TargetLowering::getReturnAddressFrameIndex(SelectionDAG &DAG) {
if (ReturnAddrIndex == 0) {
// Set up a frame object for the return address.
MachineFunction &MF = DAG.getMachineFunction();
ReturnAddrIndex = MF.getFrameInfo()->CreateFixedObject(4, -4);
}
return DAG.getFrameIndex(ReturnAddrIndex, MVT::i32);
}
std::pair<SDOperand, SDOperand> X86TargetLowering::
LowerFrameReturnAddress(bool isFrameAddress, SDOperand Chain, unsigned Depth,
SelectionDAG &DAG) {
SDOperand Result;
if (Depth) // Depths > 0 not supported yet!
Result = DAG.getConstant(0, getPointerTy());
else {
SDOperand RetAddrFI = getReturnAddressFrameIndex(DAG);
if (!isFrameAddress)
// Just load the return address
Result = DAG.getLoad(MVT::i32, DAG.getEntryNode(), RetAddrFI,
DAG.getSrcValue(NULL));
else
Result = DAG.getNode(ISD::SUB, MVT::i32, RetAddrFI,
DAG.getConstant(4, MVT::i32));
}
return std::make_pair(Result, Chain);
}
//===----------------------------------------------------------------------===//
// X86 Custom Lowering Hooks
//===----------------------------------------------------------------------===//
/// LowerOperation - Provide custom lowering hooks for some operations.
///
SDOperand X86TargetLowering::LowerOperation(SDOperand Op, SelectionDAG &DAG) {
switch (Op.getOpcode()) {
default: assert(0 && "Should not custom lower this!");
case ISD::SINT_TO_FP: {
assert(Op.getValueType() == MVT::f64 &&
Op.getOperand(0).getValueType() == MVT::i64 &&
"Unknown SINT_TO_FP to lower!");
// We lower sint64->FP into a store to a temporary stack slot, followed by a
// FILD64m node.
MachineFunction &MF = DAG.getMachineFunction();
int SSFI = MF.getFrameInfo()->CreateStackObject(8, 8);
SDOperand StackSlot = DAG.getFrameIndex(SSFI, getPointerTy());
SDOperand Store = DAG.getNode(ISD::STORE, MVT::Other, DAG.getEntryNode(),
Op.getOperand(0), StackSlot, DAG.getSrcValue(NULL));
std::vector<MVT::ValueType> RTs;
RTs.push_back(MVT::f64);
RTs.push_back(MVT::Other);
std::vector<SDOperand> Ops;
Ops.push_back(Store);
Ops.push_back(StackSlot);
return DAG.getNode(X86ISD::FILD64m, RTs, Ops);
}
case ISD::FP_TO_SINT: {
assert(Op.getValueType() <= MVT::i64 && Op.getValueType() >= MVT::i16 &&
Op.getOperand(0).getValueType() == MVT::f64 &&
"Unknown FP_TO_SINT to lower!");
// We lower FP->sint64 into FISTP64, followed by a load, all to a temporary
// stack slot.
MachineFunction &MF = DAG.getMachineFunction();
unsigned MemSize = MVT::getSizeInBits(Op.getValueType())/8;
int SSFI = MF.getFrameInfo()->CreateStackObject(MemSize, MemSize);
SDOperand StackSlot = DAG.getFrameIndex(SSFI, getPointerTy());
unsigned Opc;
switch (Op.getValueType()) {
default: assert(0 && "Invalid FP_TO_SINT to lower!");
case MVT::i16: Opc = X86ISD::FP_TO_INT16_IN_MEM; break;
case MVT::i32: Opc = X86ISD::FP_TO_INT32_IN_MEM; break;
case MVT::i64: Opc = X86ISD::FP_TO_INT64_IN_MEM; break;
}
// Build the FP_TO_INT*_IN_MEM
std::vector<SDOperand> Ops;
Ops.push_back(DAG.getEntryNode());
Ops.push_back(Op.getOperand(0));
Ops.push_back(StackSlot);
SDOperand FIST = DAG.getNode(Opc, MVT::Other, Ops);
// Load the result.
return DAG.getLoad(Op.getValueType(), FIST, StackSlot,
DAG.getSrcValue(NULL));
}
}
}

View File

@ -0,0 +1,131 @@
//===-- X86ISelLowering.h - X86 DAG Lowering Interface ----------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file was developed by Chris Lattner and is distributed under
// the University of Illinois Open Source License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that X86 uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//
#ifndef X86ISELLOWERING_H
#define X86ISELLOWERING_H
#include "llvm/Target/TargetLowering.h"
#include "llvm/CodeGen/SelectionDAG.h"
namespace llvm {
// X86 Specific DAG Nodes
namespace X86ISD {
enum NodeType {
// Start the numbering where the builtin ops leave off.
FIRST_NUMBER = ISD::BUILTIN_OP_END,
/// FILD64m - This instruction implements SINT_TO_FP with a
/// 64-bit source in memory and a FP reg result. This corresponds to
/// the X86::FILD64m instruction. It has two inputs (token chain and
/// address) and two outputs (FP value and token chain).
FILD64m,
/// FP_TO_INT*_IN_MEM - This instruction implements FP_TO_SINT with the
/// integer destination in memory and a FP reg source. This corresponds
/// to the X86::FIST*m instructions and the rounding mode change stuff. It
/// has two inputs (token chain and address) and two outputs (FP value and
/// token chain).
FP_TO_INT16_IN_MEM,
FP_TO_INT32_IN_MEM,
FP_TO_INT64_IN_MEM,
/// CALL/TAILCALL - These operations represent an abstract X86 call
/// instruction, which includes a bunch of information. In particular the
/// operands of these node are:
///
/// #0 - The incoming token chain
/// #1 - The callee
/// #2 - The number of arg bytes the caller pushes on the stack.
/// #3 - The number of arg bytes the callee pops off the stack.
/// #4 - The value to pass in AL/AX/EAX (optional)
/// #5 - The value to pass in DL/DX/EDX (optional)
///
/// The result values of these nodes are:
///
/// #0 - The outgoing token chain
/// #1 - The first register result value (optional)
/// #2 - The second register result value (optional)
///
/// The CALL vs TAILCALL distinction boils down to whether the callee is
/// known not to modify the caller's stack frame, as is standard with
/// LLVM.
CALL,
TAILCALL,
};
}
//===----------------------------------------------------------------------===//
// X86TargetLowering - X86 Implementation of the TargetLowering interface
class X86TargetLowering : public TargetLowering {
int VarArgsFrameIndex; // FrameIndex for start of varargs area.
int ReturnAddrIndex; // FrameIndex for return slot.
int BytesToPopOnReturn; // Number of arg bytes ret should pop.
int BytesCallerReserves; // Number of arg bytes caller makes.
public:
X86TargetLowering(TargetMachine &TM);
// Return the number of bytes that a function should pop when it returns (in
// addition to the space used by the return address).
//
unsigned getBytesToPopOnReturn() const { return BytesToPopOnReturn; }
// Return the number of bytes that the caller reserves for arguments passed
// to this function.
unsigned getBytesCallerReserves() const { return BytesCallerReserves; }
/// LowerOperation - Provide custom lowering hooks for some operations.
///
virtual SDOperand LowerOperation(SDOperand Op, SelectionDAG &DAG);
/// LowerArguments - This hook must be implemented to indicate how we should
/// lower the arguments for the specified function, into the specified DAG.
virtual std::vector<SDOperand>
LowerArguments(Function &F, SelectionDAG &DAG);
/// LowerCallTo - This hook lowers an abstract call to a function into an
/// actual call.
virtual std::pair<SDOperand, SDOperand>
LowerCallTo(SDOperand Chain, const Type *RetTy, bool isVarArg, unsigned CC,
bool isTailCall, SDOperand Callee, ArgListTy &Args,
SelectionDAG &DAG);
virtual SDOperand LowerVAStart(SDOperand Chain, SDOperand VAListP,
Value *VAListV, SelectionDAG &DAG);
virtual std::pair<SDOperand,SDOperand>
LowerVAArg(SDOperand Chain, SDOperand VAListP, Value *VAListV,
const Type *ArgTy, SelectionDAG &DAG);
virtual std::pair<SDOperand, SDOperand>
LowerFrameReturnAddress(bool isFrameAddr, SDOperand Chain, unsigned Depth,
SelectionDAG &DAG);
SDOperand getReturnAddressFrameIndex(SelectionDAG &DAG);
private:
// C Calling Convention implementation.
std::vector<SDOperand> LowerCCCArguments(Function &F, SelectionDAG &DAG);
std::pair<SDOperand, SDOperand>
LowerCCCCallTo(SDOperand Chain, const Type *RetTy, bool isVarArg,
bool isTailCall,
SDOperand Callee, ArgListTy &Args, SelectionDAG &DAG);
// Fast Calling Convention implementation.
std::vector<SDOperand> LowerFastCCArguments(Function &F, SelectionDAG &DAG);
std::pair<SDOperand, SDOperand>
LowerFastCCCallTo(SDOperand Chain, const Type *RetTy, bool isTailCall,
SDOperand Callee, ArgListTy &Args, SelectionDAG &DAG);
};
}
#endif // X86ISELLOWERING_H

File diff suppressed because it is too large Load Diff

View File

@ -124,7 +124,7 @@ bool X86TargetMachine::addPassesToEmitFile(PassManager &PM, std::ostream &Out,
PM.add(createUnreachableBlockEliminationPass());
// Install an instruction selector.
PM.add(createX86PatternInstructionSelector(*this));
PM.add(createX86ISelPattern(*this));
// Run optional SSA-based machine code optimizations next...
if (!NoSSAPeephole)
@ -192,7 +192,7 @@ void X86JITInfo::addPassesToJITCompile(FunctionPassManager &PM) {
PM.add(createUnreachableBlockEliminationPass());
// Install an instruction selector.
PM.add(createX86PatternInstructionSelector(TM));
PM.add(createX86ISelPattern(TM));
// Run optional SSA-based machine code optimizations next...
if (!NoSSAPeephole)