LLVM API Documentation

FastISel.cpp

Go to the documentation of this file.
00001 ///===-- FastISel.cpp - Implementation of the FastISel class --------------===//
00002 //
00003 //                     The LLVM Compiler Infrastructure
00004 //
00005 // This file is distributed under the University of Illinois Open Source
00006 // License. See LICENSE.TXT for details.
00007 //
00008 //===----------------------------------------------------------------------===//
00009 //
00010 // This file contains the implementation of the FastISel class.
00011 //
00012 // "Fast" instruction selection is designed to emit very poor code quickly.
00013 // Also, it is not designed to be able to do much lowering, so most illegal
00014 // types (e.g. i64 on 32-bit targets) and operations are not supported.  It is
00015 // also not intended to be able to do much optimization, except in a few cases
00016 // where doing optimizations reduces overall compile time.  For example, folding
00017 // constants into immediate fields is often done, because it's cheap and it
00018 // reduces the number of instructions later phases have to examine.
00019 //
00020 // "Fast" instruction selection is able to fail gracefully and transfer
00021 // control to the SelectionDAG selector for operations that it doesn't
00022 // support.  In many cases, this allows us to avoid duplicating a lot of
00023 // the complicated lowering logic that SelectionDAG currently has.
00024 //
00025 // The intended use for "fast" instruction selection is "-O0" mode
00026 // compilation, where the quality of the generated code is irrelevant when
00027 // weighed against the speed at which the code can be generated.  Also,
00028 // at -O0, the LLVM optimizers are not running, and this makes the
00029 // compile time of codegen a much higher portion of the overall compile
00030 // time.  Despite its limitations, "fast" instruction selection is able to
00031 // handle enough code on its own to provide noticeable overall speedups
00032 // in -O0 compiles.
00033 //
00034 // Basic operations are supported in a target-independent way, by reading
00035 // the same instruction descriptions that the SelectionDAG selector reads,
00036 // and identifying simple arithmetic operations that can be directly selected
00037 // from simple operators.  More complicated operations currently require
00038 // target-specific code.
00039 //
00040 //===----------------------------------------------------------------------===//
00041 
00042 #include "llvm/Function.h"
00043 #include "llvm/GlobalVariable.h"
00044 #include "llvm/Instructions.h"
00045 #include "llvm/IntrinsicInst.h"
00046 #include "llvm/CodeGen/FastISel.h"
00047 #include "llvm/CodeGen/MachineInstrBuilder.h"
00048 #include "llvm/CodeGen/MachineModuleInfo.h"
00049 #include "llvm/CodeGen/MachineRegisterInfo.h"
00050 #include "llvm/CodeGen/DwarfWriter.h"
00051 #include "llvm/Analysis/DebugInfo.h"
00052 #include "llvm/Target/TargetData.h"
00053 #include "llvm/Target/TargetInstrInfo.h"
00054 #include "llvm/Target/TargetLowering.h"
00055 #include "llvm/Target/TargetMachine.h"
00056 #include "SelectionDAGBuild.h"
00057 using namespace llvm;
00058 
00059 unsigned FastISel::getRegForValue(Value *V) {
00060   EVT RealVT = TLI.getValueType(V->getType(), /*AllowUnknown=*/true);
00061   // Don't handle non-simple values in FastISel.
00062   if (!RealVT.isSimple())
00063     return 0;
00064 
00065   // Ignore illegal types. We must do this before looking up the value
00066   // in ValueMap because Arguments are given virtual registers regardless
00067   // of whether FastISel can handle them.
00068   MVT VT = RealVT.getSimpleVT();
00069   if (!TLI.isTypeLegal(VT)) {
00070     // Promote MVT::i1 to a legal type though, because it's common and easy.
00071     if (VT == MVT::i1)
00072       VT = TLI.getTypeToTransformTo(V->getContext(), VT).getSimpleVT();
00073     else
00074       return 0;
00075   }
00076 
00077   // Look up the value to see if we already have a register for it. We
00078   // cache values defined by Instructions across blocks, and other values
00079   // only locally. This is because Instructions already have the SSA
00080   // def-dominatess-use requirement enforced.
00081   if (ValueMap.count(V))
00082     return ValueMap[V];
00083   unsigned Reg = LocalValueMap[V];
00084   if (Reg != 0)
00085     return Reg;
00086 
00087   if (ConstantInt *CI = dyn_cast<ConstantInt>(V)) {
00088     if (CI->getValue().getActiveBits() <= 64)
00089       Reg = FastEmit_i(VT, VT, ISD::Constant, CI->getZExtValue());
00090   } else if (isa<AllocaInst>(V)) {
00091     Reg = TargetMaterializeAlloca(cast<AllocaInst>(V));
00092   } else if (isa<ConstantPointerNull>(V)) {
00093     // Translate this as an integer zero so that it can be
00094     // local-CSE'd with actual integer zeros.
00095     Reg =
00096       getRegForValue(Constant::getNullValue(TD.getIntPtrType(V->getContext())));
00097   } else if (ConstantFP *CF = dyn_cast<ConstantFP>(V)) {
00098     Reg = FastEmit_f(VT, VT, ISD::ConstantFP, CF);
00099 
00100     if (!Reg) {
00101       const APFloat &Flt = CF->getValueAPF();
00102       EVT IntVT = TLI.getPointerTy();
00103 
00104       uint64_t x[2];
00105       uint32_t IntBitWidth = IntVT.getSizeInBits();
00106       bool isExact;
00107       (void) Flt.convertToInteger(x, IntBitWidth, /*isSigned=*/true,
00108                                 APFloat::rmTowardZero, &isExact);
00109       if (isExact) {
00110         APInt IntVal(IntBitWidth, 2, x);
00111 
00112         unsigned IntegerReg =
00113           getRegForValue(ConstantInt::get(V->getContext(), IntVal));
00114         if (IntegerReg != 0)
00115           Reg = FastEmit_r(IntVT.getSimpleVT(), VT, ISD::SINT_TO_FP, IntegerReg);
00116       }
00117     }
00118   } else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(V)) {
00119     if (!SelectOperator(CE, CE->getOpcode())) return 0;
00120     Reg = LocalValueMap[CE];
00121   } else if (isa<UndefValue>(V)) {
00122     Reg = createResultReg(TLI.getRegClassFor(VT));
00123     BuildMI(MBB, DL, TII.get(TargetInstrInfo::IMPLICIT_DEF), Reg);
00124   }
00125   
00126   // If target-independent code couldn't handle the value, give target-specific
00127   // code a try.
00128   if (!Reg && isa<Constant>(V))
00129     Reg = TargetMaterializeConstant(cast<Constant>(V));
00130   
00131   // Don't cache constant materializations in the general ValueMap.
00132   // To do so would require tracking what uses they dominate.
00133   if (Reg != 0)
00134     LocalValueMap[V] = Reg;
00135   return Reg;
00136 }
00137 
00138 unsigned FastISel::lookUpRegForValue(Value *V) {
00139   // Look up the value to see if we already have a register for it. We
00140   // cache values defined by Instructions across blocks, and other values
00141   // only locally. This is because Instructions already have the SSA
00142   // def-dominatess-use requirement enforced.
00143   if (ValueMap.count(V))
00144     return ValueMap[V];
00145   return LocalValueMap[V];
00146 }
00147 
00148 /// UpdateValueMap - Update the value map to include the new mapping for this
00149 /// instruction, or insert an extra copy to get the result in a previous
00150 /// determined register.
00151 /// NOTE: This is only necessary because we might select a block that uses
00152 /// a value before we select the block that defines the value.  It might be
00153 /// possible to fix this by selecting blocks in reverse postorder.
00154 unsigned FastISel::UpdateValueMap(Value* I, unsigned Reg) {
00155   if (!isa<Instruction>(I)) {
00156     LocalValueMap[I] = Reg;
00157     return Reg;
00158   }
00159   
00160   unsigned &AssignedReg = ValueMap[I];
00161   if (AssignedReg == 0)
00162     AssignedReg = Reg;
00163   else if (Reg != AssignedReg) {
00164     const TargetRegisterClass *RegClass = MRI.getRegClass(Reg);
00165     TII.copyRegToReg(*MBB, MBB->end(), AssignedReg,
00166                      Reg, RegClass, RegClass);
00167   }
00168   return AssignedReg;
00169 }
00170 
00171 unsigned FastISel::getRegForGEPIndex(Value *Idx) {
00172   unsigned IdxN = getRegForValue(Idx);
00173   if (IdxN == 0)
00174     // Unhandled operand. Halt "fast" selection and bail.
00175     return 0;
00176 
00177   // If the index is smaller or larger than intptr_t, truncate or extend it.
00178   MVT PtrVT = TLI.getPointerTy();
00179   EVT IdxVT = EVT::getEVT(Idx->getType(), /*HandleUnknown=*/false);
00180   if (IdxVT.bitsLT(PtrVT))
00181     IdxN = FastEmit_r(IdxVT.getSimpleVT(), PtrVT, ISD::SIGN_EXTEND, IdxN);
00182   else if (IdxVT.bitsGT(PtrVT))
00183     IdxN = FastEmit_r(IdxVT.getSimpleVT(), PtrVT, ISD::TRUNCATE, IdxN);
00184   return IdxN;
00185 }
00186 
00187 /// SelectBinaryOp - Select and emit code for a binary operator instruction,
00188 /// which has an opcode which directly corresponds to the given ISD opcode.
00189 ///
00190 bool FastISel::SelectBinaryOp(User *I, ISD::NodeType ISDOpcode) {
00191   EVT VT = EVT::getEVT(I->getType(), /*HandleUnknown=*/true);
00192   if (VT == MVT::Other || !VT.isSimple())
00193     // Unhandled type. Halt "fast" selection and bail.
00194     return false;
00195 
00196   // We only handle legal types. For example, on x86-32 the instruction
00197   // selector contains all of the 64-bit instructions from x86-64,
00198   // under the assumption that i64 won't be used if the target doesn't
00199   // support it.
00200   if (!TLI.isTypeLegal(VT)) {
00201     // MVT::i1 is special. Allow AND, OR, or XOR because they
00202     // don't require additional zeroing, which makes them easy.
00203     if (VT == MVT::i1 &&
00204         (ISDOpcode == ISD::AND || ISDOpcode == ISD::OR ||
00205          ISDOpcode == ISD::XOR))
00206       VT = TLI.getTypeToTransformTo(I->getContext(), VT);
00207     else
00208       return false;
00209   }
00210 
00211   unsigned Op0 = getRegForValue(I->getOperand(0));
00212   if (Op0 == 0)
00213     // Unhandled operand. Halt "fast" selection and bail.
00214     return false;
00215 
00216   // Check if the second operand is a constant and handle it appropriately.
00217   if (ConstantInt *CI = dyn_cast<ConstantInt>(I->getOperand(1))) {
00218     unsigned ResultReg = FastEmit_ri(VT.getSimpleVT(), VT.getSimpleVT(),
00219                                      ISDOpcode, Op0, CI->getZExtValue());
00220     if (ResultReg != 0) {
00221       // We successfully emitted code for the given LLVM Instruction.
00222       UpdateValueMap(I, ResultReg);
00223       return true;
00224     }
00225   }
00226 
00227   // Check if the second operand is a constant float.
00228   if (ConstantFP *CF = dyn_cast<ConstantFP>(I->getOperand(1))) {
00229     unsigned ResultReg = FastEmit_rf(VT.getSimpleVT(), VT.getSimpleVT(),
00230                                      ISDOpcode, Op0, CF);
00231     if (ResultReg != 0) {
00232       // We successfully emitted code for the given LLVM Instruction.
00233       UpdateValueMap(I, ResultReg);
00234       return true;
00235     }
00236   }
00237 
00238   unsigned Op1 = getRegForValue(I->getOperand(1));
00239   if (Op1 == 0)
00240     // Unhandled operand. Halt "fast" selection and bail.
00241     return false;
00242 
00243   // Now we have both operands in registers. Emit the instruction.
00244   unsigned ResultReg = FastEmit_rr(VT.getSimpleVT(), VT.getSimpleVT(),
00245                                    ISDOpcode, Op0, Op1);
00246   if (ResultReg == 0)
00247     // Target-specific code wasn't able to find a machine opcode for
00248     // the given ISD opcode and type. Halt "fast" selection and bail.
00249     return false;
00250 
00251   // We successfully emitted code for the given LLVM Instruction.
00252   UpdateValueMap(I, ResultReg);
00253   return true;
00254 }
00255 
00256 bool FastISel::SelectGetElementPtr(User *I) {
00257   unsigned N = getRegForValue(I->getOperand(0));
00258   if (N == 0)
00259     // Unhandled operand. Halt "fast" selection and bail.
00260     return false;
00261 
00262   const Type *Ty = I->getOperand(0)->getType();
00263   MVT VT = TLI.getPointerTy();
00264   for (GetElementPtrInst::op_iterator OI = I->op_begin()+1, E = I->op_end();
00265        OI != E; ++OI) {
00266     Value *Idx = *OI;
00267     if (const StructType *StTy = dyn_cast<StructType>(Ty)) {
00268       unsigned Field = cast<ConstantInt>(Idx)->getZExtValue();
00269       if (Field) {
00270         // N = N + Offset
00271         uint64_t Offs = TD.getStructLayout(StTy)->getElementOffset(Field);
00272         // FIXME: This can be optimized by combining the add with a
00273         // subsequent one.
00274         N = FastEmit_ri_(VT, ISD::ADD, N, Offs, VT);
00275         if (N == 0)
00276           // Unhandled operand. Halt "fast" selection and bail.
00277           return false;
00278       }
00279       Ty = StTy->getElementType(Field);
00280     } else {
00281       Ty = cast<SequentialType>(Ty)->getElementType();
00282 
00283       // If this is a constant subscript, handle it quickly.
00284       if (ConstantInt *CI = dyn_cast<ConstantInt>(Idx)) {
00285         if (CI->getZExtValue() == 0) continue;
00286         uint64_t Offs = 
00287           TD.getTypeAllocSize(Ty)*cast<ConstantInt>(CI)->getSExtValue();
00288         N = FastEmit_ri_(VT, ISD::ADD, N, Offs, VT);
00289         if (N == 0)
00290           // Unhandled operand. Halt "fast" selection and bail.
00291           return false;
00292         continue;
00293       }
00294       
00295       // N = N + Idx * ElementSize;
00296       uint64_t ElementSize = TD.getTypeAllocSize(Ty);
00297       unsigned IdxN = getRegForGEPIndex(Idx);
00298       if (IdxN == 0)
00299         // Unhandled operand. Halt "fast" selection and bail.
00300         return false;
00301 
00302       if (ElementSize != 1) {
00303         IdxN = FastEmit_ri_(VT, ISD::MUL, IdxN, ElementSize, VT);
00304         if (IdxN == 0)
00305           // Unhandled operand. Halt "fast" selection and bail.
00306           return false;
00307       }
00308       N = FastEmit_rr(VT, VT, ISD::ADD, N, IdxN);
00309       if (N == 0)
00310         // Unhandled operand. Halt "fast" selection and bail.
00311         return false;
00312     }
00313   }
00314 
00315   // We successfully emitted code for the given LLVM Instruction.
00316   UpdateValueMap(I, N);
00317   return true;
00318 }
00319 
00320 bool FastISel::SelectCall(User *I) {
00321   Function *F = cast<CallInst>(I)->getCalledFunction();
00322   if (!F) return false;
00323 
00324   unsigned IID = F->getIntrinsicID();
00325   switch (IID) {
00326   default: break;
00327   case Intrinsic::dbg_stoppoint: {
00328     DbgStopPointInst *SPI = cast<DbgStopPointInst>(I);
00329     if (isValidDebugInfoIntrinsic(*SPI, CodeGenOpt::None))
00330       setCurDebugLoc(ExtractDebugLocation(*SPI, MF.getDebugLocInfo()));
00331     return true;
00332   }
00333   case Intrinsic::dbg_region_start: {
00334     DbgRegionStartInst *RSI = cast<DbgRegionStartInst>(I);
00335     if (isValidDebugInfoIntrinsic(*RSI, CodeGenOpt::None) && DW
00336         && DW->ShouldEmitDwarfDebug()) {
00337       unsigned ID = 
00338         DW->RecordRegionStart(cast<GlobalVariable>(RSI->getContext()));
00339       const TargetInstrDesc &II = TII.get(TargetInstrInfo::DBG_LABEL);
00340       BuildMI(MBB, DL, II).addImm(ID);
00341     }
00342     return true;
00343   }
00344   case Intrinsic::dbg_region_end: {
00345     DbgRegionEndInst *REI = cast<DbgRegionEndInst>(I);
00346     if (isValidDebugInfoIntrinsic(*REI, CodeGenOpt::None) && DW
00347         && DW->ShouldEmitDwarfDebug()) {
00348      unsigned ID = 0;
00349      DISubprogram Subprogram(cast<GlobalVariable>(REI->getContext()));
00350      if (isInlinedFnEnd(*REI, MF.getFunction())) {
00351         // This is end of an inlined function.
00352         const TargetInstrDesc &II = TII.get(TargetInstrInfo::DBG_LABEL);
00353         ID = DW->RecordInlinedFnEnd(Subprogram);
00354         if (ID)
00355           // Returned ID is 0 if this is unbalanced "end of inlined
00356           // scope". This could happen if optimizer eats dbg intrinsics
00357           // or "beginning of inlined scope" is not recoginized due to
00358           // missing location info. In such cases, ignore this region.end.
00359           BuildMI(MBB, DL, II).addImm(ID);
00360       } else {
00361         const TargetInstrDesc &II = TII.get(TargetInstrInfo::DBG_LABEL);
00362         ID =  DW->RecordRegionEnd(cast<GlobalVariable>(REI->getContext()));
00363         BuildMI(MBB, DL, II).addImm(ID);
00364       }
00365     }
00366     return true;
00367   }
00368   case Intrinsic::dbg_func_start: {
00369     DbgFuncStartInst *FSI = cast<DbgFuncStartInst>(I);
00370     if (!isValidDebugInfoIntrinsic(*FSI, CodeGenOpt::None) || !DW
00371         || !DW->ShouldEmitDwarfDebug()) 
00372       return true;
00373 
00374     if (isInlinedFnStart(*FSI, MF.getFunction())) {
00375       // This is a beginning of an inlined function.
00376       
00377       // If llvm.dbg.func.start is seen in a new block before any
00378       // llvm.dbg.stoppoint intrinsic then the location info is unknown.
00379       // FIXME : Why DebugLoc is reset at the beginning of each block ?
00380       DebugLoc PrevLoc = DL;
00381       if (PrevLoc.isUnknown())
00382         return true;
00383       // Record the source line.
00384       setCurDebugLoc(ExtractDebugLocation(*FSI, MF.getDebugLocInfo()));
00385       
00386       DebugLocTuple PrevLocTpl = MF.getDebugLocTuple(PrevLoc);
00387       DISubprogram SP(cast<GlobalVariable>(FSI->getSubprogram()));
00388       unsigned LabelID = DW->RecordInlinedFnStart(SP,
00389                                                   DICompileUnit(PrevLocTpl.CompileUnit),
00390                                                   PrevLocTpl.Line,
00391                                                   PrevLocTpl.Col);
00392       const TargetInstrDesc &II = TII.get(TargetInstrInfo::DBG_LABEL);
00393       BuildMI(MBB, DL, II).addImm(LabelID);
00394       return true;
00395     }
00396     
00397     // This is a beginning of a new function.
00398     MF.setDefaultDebugLoc(ExtractDebugLocation(*FSI, MF.getDebugLocInfo()));
00399     
00400     // llvm.dbg.func_start also defines beginning of function scope.
00401     DW->RecordRegionStart(cast<GlobalVariable>(FSI->getSubprogram()));
00402     return true;
00403   }
00404   case Intrinsic::dbg_declare: {
00405     DbgDeclareInst *DI = cast<DbgDeclareInst>(I);
00406     if (!isValidDebugInfoIntrinsic(*DI, CodeGenOpt::None) || !DW
00407         || !DW->ShouldEmitDwarfDebug())
00408       return true;
00409 
00410     Value *Variable = DI->getVariable();
00411     Value *Address = DI->getAddress();
00412     if (BitCastInst *BCI = dyn_cast<BitCastInst>(Address))
00413       Address = BCI->getOperand(0);
00414     AllocaInst *AI = dyn_cast<AllocaInst>(Address);
00415     // Don't handle byval struct arguments or VLAs, for example.
00416     if (!AI) break;
00417     DenseMap<const AllocaInst*, int>::iterator SI =
00418       StaticAllocaMap.find(AI);
00419     if (SI == StaticAllocaMap.end()) break; // VLAs.
00420     int FI = SI->second;
00421     
00422     // Determine the debug globalvariable.
00423     GlobalValue *GV = cast<GlobalVariable>(Variable);
00424     
00425     // Build the DECLARE instruction.
00426     const TargetInstrDesc &II = TII.get(TargetInstrInfo::DECLARE);
00427     MachineInstr *DeclareMI 
00428       = BuildMI(MBB, DL, II).addFrameIndex(FI).addGlobalAddress(GV);
00429     DIVariable DV(cast<GlobalVariable>(GV));
00430     DW->RecordVariableScope(DV, DeclareMI);
00431     return true;
00432   }
00433   case Intrinsic::eh_exception: {
00434     EVT VT = TLI.getValueType(I->getType());
00435     switch (TLI.getOperationAction(ISD::EXCEPTIONADDR, VT)) {
00436     default: break;
00437     case TargetLowering::Expand: {
00438       assert(MBB->isLandingPad() && "Call to eh.exception not in landing pad!");
00439       unsigned Reg = TLI.getExceptionAddressRegister();
00440       const TargetRegisterClass *RC = TLI.getRegClassFor(VT);
00441       unsigned ResultReg = createResultReg(RC);
00442       bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00443                                            Reg, RC, RC);
00444       assert(InsertedCopy && "Can't copy address registers!");
00445       InsertedCopy = InsertedCopy;
00446       UpdateValueMap(I, ResultReg);
00447       return true;
00448     }
00449     }
00450     break;
00451   }
00452   case Intrinsic::eh_selector_i32:
00453   case Intrinsic::eh_selector_i64: {
00454     EVT VT = TLI.getValueType(I->getType());
00455     switch (TLI.getOperationAction(ISD::EHSELECTION, VT)) {
00456     default: break;
00457     case TargetLowering::Expand: {
00458       EVT VT = (IID == Intrinsic::eh_selector_i32 ?
00459                            MVT::i32 : MVT::i64);
00460 
00461       if (MMI) {
00462         if (MBB->isLandingPad())
00463           AddCatchInfo(*cast<CallInst>(I), MMI, MBB);
00464         else {
00465 #ifndef NDEBUG
00466           CatchInfoLost.insert(cast<CallInst>(I));
00467 #endif
00468           // FIXME: Mark exception selector register as live in.  Hack for PR1508.
00469           unsigned Reg = TLI.getExceptionSelectorRegister();
00470           if (Reg) MBB->addLiveIn(Reg);
00471         }
00472 
00473         unsigned Reg = TLI.getExceptionSelectorRegister();
00474         const TargetRegisterClass *RC = TLI.getRegClassFor(VT);
00475         unsigned ResultReg = createResultReg(RC);
00476         bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00477                                              Reg, RC, RC);
00478         assert(InsertedCopy && "Can't copy address registers!");
00479         InsertedCopy = InsertedCopy;
00480         UpdateValueMap(I, ResultReg);
00481       } else {
00482         unsigned ResultReg =
00483           getRegForValue(Constant::getNullValue(I->getType()));
00484         UpdateValueMap(I, ResultReg);
00485       }
00486       return true;
00487     }
00488     }
00489     break;
00490   }
00491   }
00492   return false;
00493 }
00494 
00495 bool FastISel::SelectCast(User *I, ISD::NodeType Opcode) {
00496   EVT SrcVT = TLI.getValueType(I->getOperand(0)->getType());
00497   EVT DstVT = TLI.getValueType(I->getType());
00498     
00499   if (SrcVT == MVT::Other || !SrcVT.isSimple() ||
00500       DstVT == MVT::Other || !DstVT.isSimple())
00501     // Unhandled type. Halt "fast" selection and bail.
00502     return false;
00503     
00504   // Check if the destination type is legal. Or as a special case,
00505   // it may be i1 if we're doing a truncate because that's
00506   // easy and somewhat common.
00507   if (!TLI.isTypeLegal(DstVT))
00508     if (DstVT != MVT::i1 || Opcode != ISD::TRUNCATE)
00509       // Unhandled type. Halt "fast" selection and bail.
00510       return false;
00511 
00512   // Check if the source operand is legal. Or as a special case,
00513   // it may be i1 if we're doing zero-extension because that's
00514   // easy and somewhat common.
00515   if (!TLI.isTypeLegal(SrcVT))
00516     if (SrcVT != MVT::i1 || Opcode != ISD::ZERO_EXTEND)
00517       // Unhandled type. Halt "fast" selection and bail.
00518       return false;
00519 
00520   unsigned InputReg = getRegForValue(I->getOperand(0));
00521   if (!InputReg)
00522     // Unhandled operand.  Halt "fast" selection and bail.
00523     return false;
00524 
00525   // If the operand is i1, arrange for the high bits in the register to be zero.
00526   if (SrcVT == MVT::i1) {
00527    SrcVT = TLI.getTypeToTransformTo(I->getContext(), SrcVT);
00528    InputReg = FastEmitZExtFromI1(SrcVT.getSimpleVT(), InputReg);
00529    if (!InputReg)
00530      return false;
00531   }
00532   // If the result is i1, truncate to the target's type for i1 first.
00533   if (DstVT == MVT::i1)
00534     DstVT = TLI.getTypeToTransformTo(I->getContext(), DstVT);
00535 
00536   unsigned ResultReg = FastEmit_r(SrcVT.getSimpleVT(),
00537                                   DstVT.getSimpleVT(),
00538                                   Opcode,
00539                                   InputReg);
00540   if (!ResultReg)
00541     return false;
00542     
00543   UpdateValueMap(I, ResultReg);
00544   return true;
00545 }
00546 
00547 bool FastISel::SelectBitCast(User *I) {
00548   // If the bitcast doesn't change the type, just use the operand value.
00549   if (I->getType() == I->getOperand(0)->getType()) {
00550     unsigned Reg = getRegForValue(I->getOperand(0));
00551     if (Reg == 0)
00552       return false;
00553     UpdateValueMap(I, Reg);
00554     return true;
00555   }
00556 
00557   // Bitcasts of other values become reg-reg copies or BIT_CONVERT operators.
00558   EVT SrcVT = TLI.getValueType(I->getOperand(0)->getType());
00559   EVT DstVT = TLI.getValueType(I->getType());
00560   
00561   if (SrcVT == MVT::Other || !SrcVT.isSimple() ||
00562       DstVT == MVT::Other || !DstVT.isSimple() ||
00563       !TLI.isTypeLegal(SrcVT) || !TLI.isTypeLegal(DstVT))
00564     // Unhandled type. Halt "fast" selection and bail.
00565     return false;
00566   
00567   unsigned Op0 = getRegForValue(I->getOperand(0));
00568   if (Op0 == 0)
00569     // Unhandled operand. Halt "fast" selection and bail.
00570     return false;
00571   
00572   // First, try to perform the bitcast by inserting a reg-reg copy.
00573   unsigned ResultReg = 0;
00574   if (SrcVT.getSimpleVT() == DstVT.getSimpleVT()) {
00575     TargetRegisterClass* SrcClass = TLI.getRegClassFor(SrcVT);
00576     TargetRegisterClass* DstClass = TLI.getRegClassFor(DstVT);
00577     ResultReg = createResultReg(DstClass);
00578     
00579     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00580                                          Op0, DstClass, SrcClass);
00581     if (!InsertedCopy)
00582       ResultReg = 0;
00583   }
00584   
00585   // If the reg-reg copy failed, select a BIT_CONVERT opcode.
00586   if (!ResultReg)
00587     ResultReg = FastEmit_r(SrcVT.getSimpleVT(), DstVT.getSimpleVT(),
00588                            ISD::BIT_CONVERT, Op0);
00589   
00590   if (!ResultReg)
00591     return false;
00592   
00593   UpdateValueMap(I, ResultReg);
00594   return true;
00595 }
00596 
00597 bool
00598 FastISel::SelectInstruction(Instruction *I) {
00599   return SelectOperator(I, I->getOpcode());
00600 }
00601 
00602 /// FastEmitBranch - Emit an unconditional branch to the given block,
00603 /// unless it is the immediate (fall-through) successor, and update
00604 /// the CFG.
00605 void
00606 FastISel::FastEmitBranch(MachineBasicBlock *MSucc) {
00607   MachineFunction::iterator NextMBB =
00608      next(MachineFunction::iterator(MBB));
00609 
00610   if (MBB->isLayoutSuccessor(MSucc)) {
00611     // The unconditional fall-through case, which needs no instructions.
00612   } else {
00613     // The unconditional branch case.
00614     TII.InsertBranch(*MBB, MSucc, NULL, SmallVector<MachineOperand, 0>());
00615   }
00616   MBB->addSuccessor(MSucc);
00617 }
00618 
00619 bool
00620 FastISel::SelectOperator(User *I, unsigned Opcode) {
00621   switch (Opcode) {
00622   case Instruction::Add:
00623     return SelectBinaryOp(I, ISD::ADD);
00624   case Instruction::FAdd:
00625     return SelectBinaryOp(I, ISD::FADD);
00626   case Instruction::Sub:
00627     return SelectBinaryOp(I, ISD::SUB);
00628   case Instruction::FSub:
00629     return SelectBinaryOp(I, ISD::FSUB);
00630   case Instruction::Mul:
00631     return SelectBinaryOp(I, ISD::MUL);
00632   case Instruction::FMul:
00633     return SelectBinaryOp(I, ISD::FMUL);
00634   case Instruction::SDiv:
00635     return SelectBinaryOp(I, ISD::SDIV);
00636   case Instruction::UDiv:
00637     return SelectBinaryOp(I, ISD::UDIV);
00638   case Instruction::FDiv:
00639     return SelectBinaryOp(I, ISD::FDIV);
00640   case Instruction::SRem:
00641     return SelectBinaryOp(I, ISD::SREM);
00642   case Instruction::URem:
00643     return SelectBinaryOp(I, ISD::UREM);
00644   case Instruction::FRem:
00645     return SelectBinaryOp(I, ISD::FREM);
00646   case Instruction::Shl:
00647     return SelectBinaryOp(I, ISD::SHL);
00648   case Instruction::LShr:
00649     return SelectBinaryOp(I, ISD::SRL);
00650   case Instruction::AShr:
00651     return SelectBinaryOp(I, ISD::SRA);
00652   case Instruction::And:
00653     return SelectBinaryOp(I, ISD::AND);
00654   case Instruction::Or:
00655     return SelectBinaryOp(I, ISD::OR);
00656   case Instruction::Xor:
00657     return SelectBinaryOp(I, ISD::XOR);
00658 
00659   case Instruction::GetElementPtr:
00660     return SelectGetElementPtr(I);
00661 
00662   case Instruction::Br: {
00663     BranchInst *BI = cast<BranchInst>(I);
00664 
00665     if (BI->isUnconditional()) {
00666       BasicBlock *LLVMSucc = BI->getSuccessor(0);
00667       MachineBasicBlock *MSucc = MBBMap[LLVMSucc];
00668       FastEmitBranch(MSucc);
00669       return true;
00670     }
00671 
00672     // Conditional branches are not handed yet.
00673     // Halt "fast" selection and bail.
00674     return false;
00675   }
00676 
00677   case Instruction::Unreachable:
00678     // Nothing to emit.
00679     return true;
00680 
00681   case Instruction::PHI:
00682     // PHI nodes are already emitted.
00683     return true;
00684 
00685   case Instruction::Alloca:
00686     // FunctionLowering has the static-sized case covered.
00687     if (StaticAllocaMap.count(cast<AllocaInst>(I)))
00688       return true;
00689 
00690     // Dynamic-sized alloca is not handled yet.
00691     return false;
00692     
00693   case Instruction::Call:
00694     return SelectCall(I);
00695   
00696   case Instruction::BitCast:
00697     return SelectBitCast(I);
00698 
00699   case Instruction::FPToSI:
00700     return SelectCast(I, ISD::FP_TO_SINT);
00701   case Instruction::ZExt:
00702     return SelectCast(I, ISD::ZERO_EXTEND);
00703   case Instruction::SExt:
00704     return SelectCast(I, ISD::SIGN_EXTEND);
00705   case Instruction::Trunc:
00706     return SelectCast(I, ISD::TRUNCATE);
00707   case Instruction::SIToFP:
00708     return SelectCast(I, ISD::SINT_TO_FP);
00709 
00710   case Instruction::IntToPtr: // Deliberate fall-through.
00711   case Instruction::PtrToInt: {
00712     EVT SrcVT = TLI.getValueType(I->getOperand(0)->getType());
00713     EVT DstVT = TLI.getValueType(I->getType());
00714     if (DstVT.bitsGT(SrcVT))
00715       return SelectCast(I, ISD::ZERO_EXTEND);
00716     if (DstVT.bitsLT(SrcVT))
00717       return SelectCast(I, ISD::TRUNCATE);
00718     unsigned Reg = getRegForValue(I->getOperand(0));
00719     if (Reg == 0) return false;
00720     UpdateValueMap(I, Reg);
00721     return true;
00722   }
00723 
00724   default:
00725     // Unhandled instruction. Halt "fast" selection and bail.
00726     return false;
00727   }
00728 }
00729 
00730 FastISel::FastISel(MachineFunction &mf,
00731                    MachineModuleInfo *mmi,
00732                    DwarfWriter *dw,
00733                    DenseMap<const Value *, unsigned> &vm,
00734                    DenseMap<const BasicBlock *, MachineBasicBlock *> &bm,
00735                    DenseMap<const AllocaInst *, int> &am
00736 #ifndef NDEBUG
00737                    , SmallSet<Instruction*, 8> &cil
00738 #endif
00739                    )
00740   : MBB(0),
00741     ValueMap(vm),
00742     MBBMap(bm),
00743     StaticAllocaMap(am),
00744 #ifndef NDEBUG
00745     CatchInfoLost(cil),
00746 #endif
00747     MF(mf),
00748     MMI(mmi),
00749     DW(dw),
00750     MRI(MF.getRegInfo()),
00751     MFI(*MF.getFrameInfo()),
00752     MCP(*MF.getConstantPool()),
00753     TM(MF.getTarget()),
00754     TD(*TM.getTargetData()),
00755     TII(*TM.getInstrInfo()),
00756     TLI(*TM.getTargetLowering()) {
00757 }
00758 
00759 FastISel::~FastISel() {}
00760 
00761 unsigned FastISel::FastEmit_(MVT, MVT,
00762                              ISD::NodeType) {
00763   return 0;
00764 }
00765 
00766 unsigned FastISel::FastEmit_r(MVT, MVT,
00767                               ISD::NodeType, unsigned /*Op0*/) {
00768   return 0;
00769 }
00770 
00771 unsigned FastISel::FastEmit_rr(MVT, MVT, 
00772                                ISD::NodeType, unsigned /*Op0*/,
00773                                unsigned /*Op0*/) {
00774   return 0;
00775 }
00776 
00777 unsigned FastISel::FastEmit_i(MVT, MVT, ISD::NodeType, uint64_t /*Imm*/) {
00778   return 0;
00779 }
00780 
00781 unsigned FastISel::FastEmit_f(MVT, MVT,
00782                               ISD::NodeType, ConstantFP * /*FPImm*/) {
00783   return 0;
00784 }
00785 
00786 unsigned FastISel::FastEmit_ri(MVT, MVT,
00787                                ISD::NodeType, unsigned /*Op0*/,
00788                                uint64_t /*Imm*/) {
00789   return 0;
00790 }
00791 
00792 unsigned FastISel::FastEmit_rf(MVT, MVT,
00793                                ISD::NodeType, unsigned /*Op0*/,
00794                                ConstantFP * /*FPImm*/) {
00795   return 0;
00796 }
00797 
00798 unsigned FastISel::FastEmit_rri(MVT, MVT,
00799                                 ISD::NodeType,
00800                                 unsigned /*Op0*/, unsigned /*Op1*/,
00801                                 uint64_t /*Imm*/) {
00802   return 0;
00803 }
00804 
00805 /// FastEmit_ri_ - This method is a wrapper of FastEmit_ri. It first tries
00806 /// to emit an instruction with an immediate operand using FastEmit_ri.
00807 /// If that fails, it materializes the immediate into a register and try
00808 /// FastEmit_rr instead.
00809 unsigned FastISel::FastEmit_ri_(MVT VT, ISD::NodeType Opcode,
00810                                 unsigned Op0, uint64_t Imm,
00811                                 MVT ImmType) {
00812   // First check if immediate type is legal. If not, we can't use the ri form.
00813   unsigned ResultReg = FastEmit_ri(VT, VT, Opcode, Op0, Imm);
00814   if (ResultReg != 0)
00815     return ResultReg;
00816   unsigned MaterialReg = FastEmit_i(ImmType, ImmType, ISD::Constant, Imm);
00817   if (MaterialReg == 0)
00818     return 0;
00819   return FastEmit_rr(VT, VT, Opcode, Op0, MaterialReg);
00820 }
00821 
00822 /// FastEmit_rf_ - This method is a wrapper of FastEmit_ri. It first tries
00823 /// to emit an instruction with a floating-point immediate operand using
00824 /// FastEmit_rf. If that fails, it materializes the immediate into a register
00825 /// and try FastEmit_rr instead.
00826 unsigned FastISel::FastEmit_rf_(MVT VT, ISD::NodeType Opcode,
00827                                 unsigned Op0, ConstantFP *FPImm,
00828                                 MVT ImmType) {
00829   // First check if immediate type is legal. If not, we can't use the rf form.
00830   unsigned ResultReg = FastEmit_rf(VT, VT, Opcode, Op0, FPImm);
00831   if (ResultReg != 0)
00832     return ResultReg;
00833 
00834   // Materialize the constant in a register.
00835   unsigned MaterialReg = FastEmit_f(ImmType, ImmType, ISD::ConstantFP, FPImm);
00836   if (MaterialReg == 0) {
00837     // If the target doesn't have a way to directly enter a floating-point
00838     // value into a register, use an alternate approach.
00839     // TODO: The current approach only supports floating-point constants
00840     // that can be constructed by conversion from integer values. This should
00841     // be replaced by code that creates a load from a constant-pool entry,
00842     // which will require some target-specific work.
00843     const APFloat &Flt = FPImm->getValueAPF();
00844     EVT IntVT = TLI.getPointerTy();
00845 
00846     uint64_t x[2];
00847     uint32_t IntBitWidth = IntVT.getSizeInBits();
00848     bool isExact;
00849     (void) Flt.convertToInteger(x, IntBitWidth, /*isSigned=*/true,
00850                              APFloat::rmTowardZero, &isExact);
00851     if (!isExact)
00852       return 0;
00853     APInt IntVal(IntBitWidth, 2, x);
00854 
00855     unsigned IntegerReg = FastEmit_i(IntVT.getSimpleVT(), IntVT.getSimpleVT(),
00856                                      ISD::Constant, IntVal.getZExtValue());
00857     if (IntegerReg == 0)
00858       return 0;
00859     MaterialReg = FastEmit_r(IntVT.getSimpleVT(), VT,
00860                              ISD::SINT_TO_FP, IntegerReg);
00861     if (MaterialReg == 0)
00862       return 0;
00863   }
00864   return FastEmit_rr(VT, VT, Opcode, Op0, MaterialReg);
00865 }
00866 
00867 unsigned FastISel::createResultReg(const TargetRegisterClass* RC) {
00868   return MRI.createVirtualRegister(RC);
00869 }
00870 
00871 unsigned FastISel::FastEmitInst_(unsigned MachineInstOpcode,
00872                                  const TargetRegisterClass* RC) {
00873   unsigned ResultReg = createResultReg(RC);
00874   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00875 
00876   BuildMI(MBB, DL, II, ResultReg);
00877   return ResultReg;
00878 }
00879 
00880 unsigned FastISel::FastEmitInst_r(unsigned MachineInstOpcode,
00881                                   const TargetRegisterClass *RC,
00882                                   unsigned Op0) {
00883   unsigned ResultReg = createResultReg(RC);
00884   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00885 
00886   if (II.getNumDefs() >= 1)
00887     BuildMI(MBB, DL, II, ResultReg).addReg(Op0);
00888   else {
00889     BuildMI(MBB, DL, II).addReg(Op0);
00890     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00891                                          II.ImplicitDefs[0], RC, RC);
00892     if (!InsertedCopy)
00893       ResultReg = 0;
00894   }
00895 
00896   return ResultReg;
00897 }
00898 
00899 unsigned FastISel::FastEmitInst_rr(unsigned MachineInstOpcode,
00900                                    const TargetRegisterClass *RC,
00901                                    unsigned Op0, unsigned Op1) {
00902   unsigned ResultReg = createResultReg(RC);
00903   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00904 
00905   if (II.getNumDefs() >= 1)
00906     BuildMI(MBB, DL, II, ResultReg).addReg(Op0).addReg(Op1);
00907   else {
00908     BuildMI(MBB, DL, II).addReg(Op0).addReg(Op1);
00909     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00910                                          II.ImplicitDefs[0], RC, RC);
00911     if (!InsertedCopy)
00912       ResultReg = 0;
00913   }
00914   return ResultReg;
00915 }
00916 
00917 unsigned FastISel::FastEmitInst_ri(unsigned MachineInstOpcode,
00918                                    const TargetRegisterClass *RC,
00919                                    unsigned Op0, uint64_t Imm) {
00920   unsigned ResultReg = createResultReg(RC);
00921   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00922 
00923   if (II.getNumDefs() >= 1)
00924     BuildMI(MBB, DL, II, ResultReg).addReg(Op0).addImm(Imm);
00925   else {
00926     BuildMI(MBB, DL, II).addReg(Op0).addImm(Imm);
00927     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00928                                          II.ImplicitDefs[0], RC, RC);
00929     if (!InsertedCopy)
00930       ResultReg = 0;
00931   }
00932   return ResultReg;
00933 }
00934 
00935 unsigned FastISel::FastEmitInst_rf(unsigned MachineInstOpcode,
00936                                    const TargetRegisterClass *RC,
00937                                    unsigned Op0, ConstantFP *FPImm) {
00938   unsigned ResultReg = createResultReg(RC);
00939   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00940 
00941   if (II.getNumDefs() >= 1)
00942     BuildMI(MBB, DL, II, ResultReg).addReg(Op0).addFPImm(FPImm);
00943   else {
00944     BuildMI(MBB, DL, II).addReg(Op0).addFPImm(FPImm);
00945     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00946                                          II.ImplicitDefs[0], RC, RC);
00947     if (!InsertedCopy)
00948       ResultReg = 0;
00949   }
00950   return ResultReg;
00951 }
00952 
00953 unsigned FastISel::FastEmitInst_rri(unsigned MachineInstOpcode,
00954                                     const TargetRegisterClass *RC,
00955                                     unsigned Op0, unsigned Op1, uint64_t Imm) {
00956   unsigned ResultReg = createResultReg(RC);
00957   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00958 
00959   if (II.getNumDefs() >= 1)
00960     BuildMI(MBB, DL, II, ResultReg).addReg(Op0).addReg(Op1).addImm(Imm);
00961   else {
00962     BuildMI(MBB, DL, II).addReg(Op0).addReg(Op1).addImm(Imm);
00963     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00964                                          II.ImplicitDefs[0], RC, RC);
00965     if (!InsertedCopy)
00966       ResultReg = 0;
00967   }
00968   return ResultReg;
00969 }
00970 
00971 unsigned FastISel::FastEmitInst_i(unsigned MachineInstOpcode,
00972                                   const TargetRegisterClass *RC,
00973                                   uint64_t Imm) {
00974   unsigned ResultReg = createResultReg(RC);
00975   const TargetInstrDesc &II = TII.get(MachineInstOpcode);
00976   
00977   if (II.getNumDefs() >= 1)
00978     BuildMI(MBB, DL, II, ResultReg).addImm(Imm);
00979   else {
00980     BuildMI(MBB, DL, II).addImm(Imm);
00981     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
00982                                          II.ImplicitDefs[0], RC, RC);
00983     if (!InsertedCopy)
00984       ResultReg = 0;
00985   }
00986   return ResultReg;
00987 }
00988 
00989 unsigned FastISel::FastEmitInst_extractsubreg(MVT RetVT,
00990                                               unsigned Op0, uint32_t Idx) {
00991   const TargetRegisterClass* RC = MRI.getRegClass(Op0);
00992   
00993   unsigned ResultReg = createResultReg(TLI.getRegClassFor(RetVT));
00994   const TargetInstrDesc &II = TII.get(TargetInstrInfo::EXTRACT_SUBREG);
00995   
00996   if (II.getNumDefs() >= 1)
00997     BuildMI(MBB, DL, II, ResultReg).addReg(Op0).addImm(Idx);
00998   else {
00999     BuildMI(MBB, DL, II).addReg(Op0).addImm(Idx);
01000     bool InsertedCopy = TII.copyRegToReg(*MBB, MBB->end(), ResultReg,
01001                                          II.ImplicitDefs[0], RC, RC);
01002     if (!InsertedCopy)
01003       ResultReg = 0;
01004   }
01005   return ResultReg;
01006 }
01007 
01008 /// FastEmitZExtFromI1 - Emit MachineInstrs to compute the value of Op
01009 /// with all but the least significant bit set to zero.
01010 unsigned FastISel::FastEmitZExtFromI1(MVT VT, unsigned Op) {
01011   return FastEmit_ri(VT, VT, ISD::AND, Op, 1);
01012 }