Implement Mips fast-isel signed and unsigned integer compare

[rkotler]

Summary

Implement the Mips fast-isel signed and unsigned integer compare
operations.

[rkotler]

SelectCmp and the corresponding lines in TargetSelectInstruction are the real parts of this patch.
There are other pieces which are previous but yet unapproved patches that are in here too.

The executable test case is uploaded here.

icmp.c1 KBDownload

[rkotler]

Superseded by D5566

lib/Target/Mips/MipsFastISel.cpp

 //===-- MipsastISel.cpp - Mips FastISel implementation
 //---------------------===//
 
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/FastISel.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/Target/TargetInstrInfo.h"
 #include "llvm/Target/TargetLibraryInfo.h"
 #include "MipsRegisterInfo.h"
 #include "MipsISelLowering.h"
 #include "MipsMachineFunction.h"
 #include "MipsSubtarget.h"
public:
   bool TargetSelectInstruction(const Instruction *I) override;
   unsigned TargetMaterializeConstant(const Constant *C) override;
 
   bool ComputeAddress(const Value *Obj, Address &Addr);
 
 private:
   bool EmitStore(MVT VT, unsigned SrcReg, Address &Addr,
                  unsigned Alignment = 0);
+
+  bool EmitLoad(MVT VT, unsigned &ResultReg, Address &Addr,
+                unsigned Alignment = 0, bool IsZExt = true);
+
+  bool SelectLoad(const Instruction *I);
   bool SelectRet(const Instruction *I);
   bool SelectStore(const Instruction *I);
+  bool SelectIntExt(const Instruction *I);
+  bool SelectTrunc(const Instruction *I);
+  bool SelectFPExt(const Instruction *I);
+  bool SelectFPTrunc(const Instruction *I);
+  bool SelectFPToI(const Instruction *I, bool IsSigned);
+  bool SelectCmp(const Instruction *I);
 
   bool isTypeLegal(Type *Ty, MVT &VT);
   bool isLoadTypeLegal(Type *Ty, MVT &VT);
 
   unsigned MaterializeFP(const ConstantFP *CFP, MVT VT);
   unsigned MaterializeGV(const GlobalValue *GV, MVT VT);
   unsigned MaterializeInt(const Constant *C, MVT VT);
   unsigned Materialize32BitInt(int64_t Imm, const TargetRegisterClass *RC);
 
+  bool EmitIntZExt(MVT SrcVT, unsigned SrcReg, MVT DestVT, unsigned DestReg);
+
+  bool EmitIntSExt(MVT SrcVT, unsigned SrcReg, MVT DestVT, unsigned DestReg);
+
   // for some reason, this default is not generated by tablegen
   // so we explicitly generate it here.
   //
   unsigned FastEmitInst_riir(uint64_t inst, const TargetRegisterClass *RC,
                              unsigned Op0, bool Op0IsKill, uint64_t imm1,
                              uint64_t imm2, unsigned Op3, bool Op3IsKill) {
     return 0;
   }
 
   MachineInstrBuilder EmitInst(unsigned Opc) {
     return BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc));
   }
 
   MachineInstrBuilder EmitInst(unsigned Opc, unsigned DstReg) {
     return BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc),
                    DstReg);
   }
 
   MachineInstrBuilder EmitInstStore(unsigned Opc, unsigned SrcReg,
                                     unsigned MemReg, int64_t MemOffset) {
     return EmitInst(Opc).addReg(SrcReg).addReg(MemReg).addImm(MemOffset);
   }
 
+  MachineInstrBuilder EmitInstLoadMem(unsigned Opc, unsigned DstReg,
+                                      unsigned MemReg, int64_t MemOffset) {
+    return EmitInst(Opc, DstReg).addReg(MemReg).addImm(MemOffset);
+  }
+
 #include "MipsGenFastISel.inc"
 };
 
 bool MipsFastISel::isTypeLegal(Type *Ty, MVT &VT) {
   EVT evt = TLI.getValueType(Ty, true);
   // Only handle simple types.
   if (evt == MVT::Other || !evt.isSimple())
     return false;
   VT = evt.getSimpleVT();
 
   // Handle all legal types, i.e. a register that will directly hold this
   // value.
   return TLI.isTypeLegal(VT);
 }
 
 bool MipsFastISel::isLoadTypeLegal(Type *Ty, MVT &VT) {
   if (isTypeLegal(Ty, VT))
     return true;
   // We will extend this in a later patch:
   //   If this is a type than can be sign or zero-extended to a basic operation
   //   go ahead and accept it now.
+  if (VT == MVT::i8 || VT == MVT::i16)
+    return true;
   return false;
 }
 
 bool MipsFastISel::ComputeAddress(const Value *Obj, Address &Addr) {
   // This construct looks a big awkward but it is how other ports handle this
   // and as this function is more fully completed, these cases which
   // return false will have additional code in them.
   //
unsigned MipsFastISel::TargetMaterializeConstant(const Constant *C) {
   else if (const GlobalValue *GV = dyn_cast<GlobalValue>(C))
     return MaterializeGV(GV, VT);
   else if (isa<ConstantInt>(C))
     return MaterializeInt(C, VT);
 
   return 0;
 }
 
+bool MipsFastISel::EmitLoad(MVT VT, unsigned &ResultReg, Address &Addr,
+                            unsigned Alignment, bool IsZExt) {
+  //
+  // more cases will be handled here in following patches.
+  //
+  if (!IsZExt)
+    return false; // this is not needed yet.
+  unsigned Opc;
+  switch (VT.SimpleTy) {
+  case MVT::i32: {
+    ResultReg = createResultReg(&Mips::GPR32RegClass);
+    Opc = Mips::LW;
+    break;
+  }
+  case MVT::i16: {
+    ResultReg = createResultReg(&Mips::GPR32RegClass);
+    Opc = Mips::LH;
+    break;
+  }
+  case MVT::i8: {
+    ResultReg = createResultReg(&Mips::GPR32RegClass);
+    Opc = Mips::LB;
+    break;
+  }
+  case MVT::f32: {
+    ResultReg = createResultReg(&Mips::FGR32RegClass);
+    Opc = Mips::LWC1;
+    break;
+  }
+  case MVT::f64: {
+    ResultReg = createResultReg(&Mips::FGR32RegClass);
+    Opc = Mips::LDC1;
+    break;
+  }
+  default:
+    return false;
+  }
+  EmitInstLoadMem(Opc, ResultReg, Addr.Base.Reg, Addr.Offset);
+  return true;
+}
+
 bool MipsFastISel::EmitStore(MVT VT, unsigned SrcReg, Address &Addr,
                              unsigned Alignment) {
   //
   // more cases will be handled here in following patches.
   //
-  if (VT == MVT::i32)
-    EmitInstStore(Mips::SW, SrcReg, Addr.Base.Reg, Addr.Offset);
-  else if (VT == MVT::f32)
-    EmitInstStore(Mips::SWC1, SrcReg, Addr.Base.Reg, Addr.Offset);
-  else if (VT == MVT::f64)
-    EmitInstStore(Mips::SDC1, SrcReg, Addr.Base.Reg, Addr.Offset);
-  else
+  unsigned Opc;
+  switch (VT.SimpleTy) {
+  case MVT::i8:
+    Opc = Mips::SB;
+    break;
+  case MVT::i16:
+    Opc = Mips::SH;
+    break;
+  case MVT::i32:
+    Opc = Mips::SW;
+    break;
+  case MVT::f32:
+    Opc = Mips::SWC1;
+    break;
+  case MVT::f64:
+    Opc = Mips::SDC1;
+    break;
+  default:
+    return false;
+  }
+  EmitInstStore(Opc, SrcReg, Addr.Base.Reg, Addr.Offset);
+  return true;
+}
+
+// Attempt to emit an integer extend of SrcReg into DestReg.  Both
+// signed and zero extensions are supported.  Return false if we
+// can't handle it.
+bool MipsFastISel::EmitIntSExt(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                               unsigned DestReg) {
+  if ((DestVT != MVT::i32) && (DestVT != MVT::i16))
+    return false;
+  switch (SrcVT.SimpleTy) {
+  default:
+    return false;
+  case MVT::i8:
+    EmitInst(Mips::SEB, DestReg).addReg(SrcReg);
+    break;
+  case MVT::i16:
+    EmitInst(Mips::SEH, DestReg).addReg(SrcReg);
+    break;
+  }
+  return true;
+}
+
+bool MipsFastISel::EmitIntZExt(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                               unsigned DestReg) {
+  switch (SrcVT.SimpleTy) {
+  default:
+    return false;
+  case MVT::i1:
+    EmitInst(Mips::ANDi, DestReg).addReg(SrcReg).addImm(1);
+    break;
+  case MVT::i8:
+    EmitInst(Mips::ANDi, DestReg).addReg(SrcReg).addImm(0xff);
+    break;
+  case MVT::i16:
+    EmitInst(Mips::ANDi, DestReg).addReg(SrcReg).addImm(0xffff);
+    break;
+  }
+  return true;
+}
+
+bool MipsFastISel::SelectLoad(const Instruction *I) {
+  // Atomic loads need special handling.
+  if (cast<LoadInst>(I)->isAtomic())
     return false;
+
+  // Verify we have a legal type before going any further.
+  MVT VT;
+  if (!isLoadTypeLegal(I->getType(), VT))
+    return false;
+
+  // See if we can handle this address.
+  Address Addr;
+  if (!ComputeAddress(I->getOperand(0), Addr))
+    return false;
+
+  unsigned ResultReg;
+  if (!EmitLoad(VT, ResultReg, Addr, cast<LoadInst>(I)->getAlignment()))
+    return false;
+  UpdateValueMap(I, ResultReg);
   return true;
 }
 
 bool MipsFastISel::SelectStore(const Instruction *I) {
   Value *Op0 = I->getOperand(0);
   unsigned SrcReg = 0;
 
   // Atomic stores need special handling.
if (!FuncInfo.CanLowerReturn)
     return false;
   if (Ret->getNumOperands() > 0) {
     return false;
   }
   EmitInst(Mips::RetRA);
   return true;
 }
 
+// Attempt to fast-select a floating-point extend instruction.
+bool MipsFastISel::SelectFPExt(const Instruction *I) {
+  Value *Src = I->getOperand(0);
+  EVT SrcVT = TLI.getValueType(Src->getType(), true);
+  EVT DestVT = TLI.getValueType(I->getType(), true);
+
+  if (SrcVT != MVT::f32 || DestVT != MVT::f64)
+    return false;
+
+  unsigned SrcReg =
+      getRegForValue(Src); // his must be a 32 bit floating point register class
+                           // maybe we should handle this differently
+  if (!SrcReg)
+    return false;
+
+  unsigned DestReg = createResultReg(&Mips::AFGR64RegClass);
+  EmitInst(Mips::CVT_D_S_MM, DestReg).addReg(SrcReg);
+  UpdateValueMap(I, DestReg);
+  return true;
+}
+
+// Attempt to fast-select a floating-point truncate instruction.
+bool MipsFastISel::SelectFPTrunc(const Instruction *I) {
+  Value *Src = I->getOperand(0);
+  EVT SrcVT = TLI.getValueType(Src->getType(), true);
+  EVT DestVT = TLI.getValueType(I->getType(), true);
+
+  if (SrcVT != MVT::f64 || DestVT != MVT::f32)
+    return false;
+
+  unsigned SrcReg =
+      getRegForValue(Src); // his must be a 32 bit floating point register class
+                           // maybe we should handle this differently
+  if (!SrcReg)
+    return false;
+
+  unsigned DestReg = createResultReg(&Mips::FGR32RegClass);
+  EmitInst(Mips::CVT_S_D32, DestReg).addReg(SrcReg);
+  UpdateValueMap(I, DestReg);
+  return true;
+}
+
+bool MipsFastISel::SelectIntExt(const Instruction *I) {
+  // On ARM, in general, integer casts don't involve legal types; this code
+  // handles promotable integers.
+  Type *DestTy = I->getType();
+  Value *Src = I->getOperand(0);
+  Type *SrcTy = Src->getType();
+
+  bool isZExt = isa<ZExtInst>(I);
+  unsigned SrcReg = getRegForValue(Src);
+  if (!SrcReg)
+    return false;
+
+  EVT SrcEVT, DestEVT;
+  SrcEVT = TLI.getValueType(SrcTy, true);
+  DestEVT = TLI.getValueType(DestTy, true);
+  if (!SrcEVT.isSimple())
+    return false;
+  if (!DestEVT.isSimple())
+    return false;
+
+  MVT SrcVT = SrcEVT.getSimpleVT();
+  MVT DestVT = DestEVT.getSimpleVT();
+  unsigned ResultReg = createResultReg(&Mips::GPR32RegClass);
+
+  if (isZExt) {
+    if (!EmitIntZExt(SrcVT, SrcReg, DestVT, ResultReg))
+      return false;
+  } else {
+    if (!EmitIntSExt(SrcVT, SrcReg, DestVT, ResultReg))
+      return false;
+  }
+  UpdateValueMap(I, ResultReg);
+  return true;
+}
+
+bool MipsFastISel::SelectTrunc(const Instruction *I) {
+  // The high bits for a type smaller than the register size are assumed to be
+  // undefined.
+  Value *Op = I->getOperand(0);
+
+  EVT SrcVT, DestVT;
+  SrcVT = TLI.getValueType(Op->getType(), true);
+  DestVT = TLI.getValueType(I->getType(), true);
+
+  if (SrcVT != MVT::i32 && SrcVT != MVT::i16 && SrcVT != MVT::i8)
+    return false;
+  if (DestVT != MVT::i16 && DestVT != MVT::i8 && DestVT != MVT::i1)
+    return false;
+
+  unsigned SrcReg = getRegForValue(Op);
+  if (!SrcReg)
+    return false;
+
+  // Because the high bits are undefined, a truncate doesn't generate
+  // any code.
+  UpdateValueMap(I, SrcReg);
+  return true;
+}
+
+// Attempt to fast-select a floating-point-to-integer conversion.
+bool MipsFastISel::SelectFPToI(const Instruction *I, bool IsSigned) {
+  MVT DstVT, SrcVT;
+  if (!IsSigned)
+    return false; // we don't handle this case yet. there is no native
+                  // instruction for this but it can be synthesized.
+  Type *DstTy = I->getType();
+  if (!isTypeLegal(DstTy, DstVT))
+    return false;
+
+  if (DstVT != MVT::i32)
+    return false;
+
+  Value *Src = I->getOperand(0);
+  Type *SrcTy = Src->getType();
+  if (!isTypeLegal(SrcTy, SrcVT))
+    return false;
+
+  if (SrcVT != MVT::f32 && SrcVT != MVT::f64)
+    return false;
+
+  unsigned SrcReg = getRegForValue(Src);
+  if (SrcReg == 0)
+    return false;
+
+  // Determine the opcode for the conversion, which takes place
+  // entirely within FPRs.
+  unsigned DestReg = createResultReg(&Mips::GPR32RegClass);
+  unsigned TempReg = createResultReg(&Mips::FGR32RegClass);
+  unsigned Opc;
+
+  if (SrcVT == MVT::f32)
+    Opc = Mips::TRUNC_W_S;
+  else
+    Opc = Mips::TRUNC_W_D32;
+
+  // Generate the convert.
+  EmitInst(Opc, TempReg).addReg(SrcReg);
+
+  EmitInst(Mips::MFC1, DestReg).addReg(TempReg);
+
+  UpdateValueMap(I, DestReg);
+  return true;
+}
+
+bool MipsFastISel::SelectCmp(const Instruction *I) {
+  const CmpInst *CI = cast<CmpInst>(I);
+  const Value *Left = I->getOperand(0), *Right = I->getOperand(1);
+  unsigned LeftReg = getRegForValue(Left);
+  unsigned RightReg = getRegForValue(Right);
+  unsigned ResultReg = createResultReg(&Mips::GPR32RegClass);
+  switch (CI->getPredicate()) {
+  default:
+    return false;
+  case CmpInst::ICMP_EQ: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::XOR, TempReg).addReg(LeftReg).addReg(RightReg);
+    EmitInst(Mips::SLTu, ResultReg).addReg(TempReg).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_NE: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::XOR, TempReg).addReg(LeftReg).addReg(RightReg);
+    EmitInst(Mips::SLTu, ResultReg).addReg(Mips::ZERO).addReg(TempReg);
+    break;
+  }
+  case CmpInst::ICMP_UGT: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLTu, TempReg).addReg(RightReg).addReg(LeftReg);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_ULT: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLTu, TempReg).addReg(LeftReg).addReg(RightReg);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_UGE: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    unsigned TempReg2 = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLTu, TempReg).addReg(LeftReg).addReg(RightReg);
+    EmitInst(Mips::XORi, TempReg2).addReg(TempReg).addImm(1);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg2).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_ULE: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    unsigned TempReg2 = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLTu, TempReg).addReg(RightReg).addReg(LeftReg);
+    EmitInst(Mips::XORi, TempReg2).addReg(TempReg).addImm(1);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg2).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_SGT: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLT, TempReg).addReg(RightReg).addReg(LeftReg);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg).addImm(1);
+    break;
+  } break;
+  case CmpInst::ICMP_SLT: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLT, TempReg).addReg(LeftReg).addReg(RightReg);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_SGE: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    unsigned TempReg2 = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLT, TempReg).addReg(LeftReg).addReg(RightReg);
+    EmitInst(Mips::XORi, TempReg2).addReg(TempReg).addImm(1);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg2).addImm(1);
+    break;
+  }
+  case CmpInst::ICMP_SLE: {
+    unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+    unsigned TempReg2 = createResultReg(&Mips::GPR32RegClass);
+    EmitInst(Mips::SLT, TempReg).addReg(RightReg).addReg(LeftReg);
+    EmitInst(Mips::XORi, TempReg2).addReg(TempReg).addImm(1);
+    EmitInst(Mips::ANDi, ResultReg).addReg(TempReg2).addImm(1);
+    break;
+  }
+  case CmpInst::FCMP_OEQ:
+  case CmpInst::FCMP_ONE:
+  case CmpInst::FCMP_OGT:
+  case CmpInst::FCMP_OLT:
+  case CmpInst::FCMP_OLE:
+  case CmpInst::FCMP_UEQ:
+  case CmpInst::FCMP_UNE:
+  case CmpInst::FCMP_UGT:
+  case CmpInst::FCMP_ULT:
+  case CmpInst::FCMP_UGE:
+  case CmpInst::FCMP_ULE:
+  case CmpInst::FCMP_ORD:
+  case CmpInst::FCMP_UNO:
+  case CmpInst::FCMP_TRUE:
+  case CmpInst::FCMP_FALSE:
+    return false;
+  }
+  UpdateValueMap(I, ResultReg);
+  return true;
+}
+
 bool MipsFastISel::TargetSelectInstruction(const Instruction *I) {
   if (!TargetSupported)
     return false;
   switch (I->getOpcode()) {
   default:
     break;
+  case Instruction::Load:
+    return SelectLoad(I);
   case Instruction::Store:
     return SelectStore(I);
   case Instruction::Ret:
     return SelectRet(I);
+  case Instruction::Trunc:
+    return SelectTrunc(I);
+  case Instruction::ZExt:
+  case Instruction::SExt:
+    return SelectIntExt(I);
+  case Instruction::FPTrunc:
+    return SelectFPTrunc(I);
+  case Instruction::FPExt:
+    return SelectFPExt(I);
+  case Instruction::FPToSI:
+    return SelectFPToI(I, /*isSigned*/ true);
+  case Instruction::FPToUI:
+    return SelectFPToI(I, /*isSigned*/ false);
+  case Instruction::ICmp:
+  case Instruction::FCmp:
+    return SelectCmp(I);
   }
   return false;
 }
 }
 
 unsigned MipsFastISel::MaterializeFP(const ConstantFP *CFP, MVT VT) {
   int64_t Imm = CFP->getValueAPF().bitcastToAPInt().getZExtValue();
   if (VT == MVT::f32) {

test/CodeGen/Mips/Fast-ISel/fpext.ll

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@f = global float 0x40147E6B80000000, align 4
+@d_f = common global double 0.000000e+00, align 8
+@.str = private unnamed_addr constant [6 x i8] c"%f  \0A\00", align 1
+
+; Function Attrs: nounwind
+define void @dv() #0 {
+entry:
+  %0 = load float* @f, align 4
+  %conv = fpext float %0 to double
+; CHECK: cvt.d.s  $f{{[0-9]+}}, $f{{[0-9]+}}
+  store double %conv, double* @d_f, align 8
+  ret void
+}
+
+
+attributes #1 = { nounwind }
+
+

test/CodeGen/Mips/Fast-ISel/fpintconv.ll

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+
+@f = global float 0x40D6E83280000000, align 4
+@d = global double 0x4132D68780000000, align 8
+@i_f = common global i32 0, align 4
+@i_d = common global i32 0, align 4
+@.str = private unnamed_addr constant [5 x i8] c"%i \0A\00", align 1
+
+; Function Attrs: nounwind
+define void @ifv() #0 {
+entry:
+; CHECK:  .ent  ifv
+  %0 = load float* @f, align 4, !tbaa !1
+  %conv = fptosi float %0 to i32
+; CHECK:  trunc.w.s $f{{[0-9]+}}, $f{{[0-9]+}}
+  store i32 %conv, i32* @i_f, align 4, !tbaa !5
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @idv() #0 {
+entry:
+; CHECK:  .ent  idv
+  %0 = load double* @d, align 8, !tbaa !7
+  %conv = fptosi double %0 to i32
+; CHECK:  trunc.w.d $f{{[0-9]+}}, $f{{[0-9]+}}
+  store i32 %conv, i32* @i_d, align 4, !tbaa !5
+  ret void
+}
+
+; Function Attrs: nounwind
+define i32 @main() #0 {
+entry:
+  %0 = load float* @f, align 4, !tbaa !1
+  %conv.i = fptosi float %0 to i32
+  store i32 %conv.i, i32* @i_f, align 4, !tbaa !5
+  %call = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), i32 %conv.i) #1
+  %1 = load double* @d, align 8, !tbaa !7
+  %conv.i2 = fptosi double %1 to i32
+  store i32 %conv.i2, i32* @i_d, align 4, !tbaa !5
+  %call1 = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), i32 %conv.i2) #1
+  ret i32 0
+}
+
+; Function Attrs: nounwind
+declare i32 @printf(i8* nocapture readonly, ...) #0
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind }
+
+!llvm.ident = !{!0}
+
+!0 = metadata !{metadata !"clang version 3.5.0 ([e-mail]:clang.git f4545688eab4ddb6fb4dabe43d9d00f9d7db9602) ([e-mail]:llvm.git fe236d3fc6882ea8f4bfebdfee82766b0356506c)"}
+!1 = metadata !{metadata !2, metadata !2, i64 0}
+!2 = metadata !{metadata !"float", metadata !3, i64 0}
+!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
+!4 = metadata !{metadata !"Simple C/C++ TBAA"}
+!5 = metadata !{metadata !6, metadata !6, i64 0}
+!6 = metadata !{metadata !"int", metadata !3, i64 0}
+!7 = metadata !{metadata !8, metadata !8, i64 0}
+!8 = metadata !{metadata !"double", metadata !3, i64 0}

test/CodeGen/Mips/Fast-ISel/fptrunc.ll

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@d = global double 0x40147E6B74DF0446, align 8
+@f = common global float 0.000000e+00, align 4
+@.str = private unnamed_addr constant [6 x i8] c"%f  \0A\00", align 1
+
+; Function Attrs: nounwind
+define void @fv() #0 {
+entry:
+  %0 = load double* @d, align 8
+  %conv = fptrunc double %0 to float
+; CHECK: cvt.s.d  $f{{[0-9]+}}, $f{{[0-9]+}}
+  store float %conv, float* @f, align 4
+  ret void
+}
+
+attributes #1 = { nounwind }
+
+

test/CodeGen/Mips/Fast-ISel/icmpa.ll

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@c = global i32 4, align 4
+@d = global i32 9, align 4
+@uc = global i32 4, align 4
+@ud = global i32 9, align 4
+@b1 = common global i32 0, align 4
+
+; Function Attrs: nounwind
+define void @eq() #0 {
+entry:
+; CHECK:  .ent  eq
+
+  %0 = load i32* @c, align 4
+  %1 = load i32* @d, align 4
+  %cmp = icmp eq i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  xor ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  sltu  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ne() #0 {
+entry:
+; CHECK:  .ent  ne
+  %0 = load i32* @c, align 4
+  %1 = load i32* @d, align 4
+  %cmp = icmp ne i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  xor ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  sltu  ${{[0-9]+}}, $zero, ${{[0-9]+}}
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ugt() #0 {
+entry:
+; CHECK:  .ent  ugt
+  %0 = load i32* @uc, align 4
+  %1 = load i32* @ud, align 4
+  %cmp = icmp ugt i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  sltu  ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ult() #0 {
+entry:
+; CHECK:  .ent  ult
+  %0 = load i32* @uc, align 4
+  %1 = load i32* @ud, align 4
+  %cmp = icmp ult i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  sltu  ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @uge() #0 {
+entry:
+; CHECK:  .ent  uge
+  %0 = load i32* @uc, align 4
+  %1 = load i32* @ud, align 4
+  %cmp = icmp uge i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  sltu  ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  xori  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ule() #0 {
+entry:
+; CHECK:  .ent  ule
+  %0 = load i32* @uc, align 4
+  %1 = load i32* @ud, align 4
+  %cmp = icmp ule i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  sltu  ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  xori  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @sgt() #0 {
+entry:
+; CHECK:  .ent sgt
+  %0 = load i32* @c, align 4
+  %1 = load i32* @d, align 4
+  %cmp = icmp sgt i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  slt ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @slt() #0 {
+entry:
+; CHECK:  .ent slt
+  %0 = load i32* @c, align 4
+  %1 = load i32* @d, align 4
+  %cmp = icmp slt i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:  slt ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @sge() #0 {
+entry:
+; CHECK:  .ent sge
+  %0 = load i32* @c, align 4
+  %1 = load i32* @d, align 4
+  %cmp = icmp sge i32 %0, %1
+  %conv = zext i1 %cmp to i32
+  store i32 %conv, i32* @b1, align 4
+; CHECK:  slt ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:  xori  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @sle() #0 {
+entry:
+; CHECK:  .ent sle
+  %0 = load i32* @c, align 4
+  %1 = load i32* @d, align 4
+  %cmp = icmp sle i32 %0, %1
+  %conv = zext i1 %cmp to i32
+; CHECK:        slt     ${{[0-9]+}}, ${{[0-9]+}}, ${{[0-9]+}}
+; CHECK:        xori    ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:        andi    ${{[0-9]+}}, ${{[0-9]+}}, 1
+  store i32 %conv, i32* @b1, align 4
+  ret void
+}
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+

test/CodeGen/Mips/Fast-ISel/loadstore2.ll

+; ModuleID = 'loadstore2.c'
+target datalayout = "E-m:m-p:32:32-i8:8:32-i16:16:32-i64:64-n32-S64"
+target triple = "mips--linux-gnu"
+
+@c2 = common global i8 0, align 1
+@c1 = common global i8 0, align 1
+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@s2 = common global i16 0, align 2
+@s1 = common global i16 0, align 2
+@i2 = common global i32 0, align 4
+@i1 = common global i32 0, align 4
+@f2 = common global float 0.000000e+00, align 4
+@f1 = common global float 0.000000e+00, align 4
+@d2 = common global double 0.000000e+00, align 8
+@d1 = common global double 0.000000e+00, align 8
+
+; Function Attrs: nounwind
+define void @cfoo() #0 {
+entry:
+  %0 = load i8* @c2, align 1
+  store i8 %0, i8* @c1, align 1
+; CHECK:  .ent  cfoo
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  sb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  .end  cfoo
+
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @sfoo() #0 {
+entry:
+  %0 = load i16* @s2, align 2
+  store i16 %0, i16* @s1, align 2
+; CHECK:  .ent  sfoo
+; CHECK:  lh  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  sh  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  .end  sfoo
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ifoo() #0 {
+entry:
+  %0 = load i32* @i2, align 4
+  store i32 %0, i32* @i1, align 4
+; CHECK:  .ent  ifoo
+; CHECK:  lw  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  sw  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  .end  ifoo
+
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ffoo() #0 {
+entry:
+  %0 = load float* @f2, align 4
+  store float %0, float* @f1, align 4
+; CHECK:  .ent  ffoo
+; CHECK:  lwc1  $f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  swc1  $f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  .end  ffoo
+
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @dfoo() #0 {
+entry:
+  %0 = load double* @d2, align 8
+  store double %0, double* @d1, align 8
+; CHECK:        .ent    dfoo
+; CHECK:        ldc1    $f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:        sdc1    $f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:        .end    dfoo
+  ret void
+}
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+

test/CodeGen/Mips/Fast-ISel/loadstoreconv.ll

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@b2 = global i8 0, align 1
+@b1 = global i8 1, align 1
+@uc1 = global i8 0, align 1
+@uc2 = global i8 -1, align 1
+@sc1 = global i8 -128, align 1
+@sc2 = global i8 127, align 1
+@ss1 = global i16 -32768, align 2
+@ss2 = global i16 32767, align 2
+@us1 = global i16 0, align 2
+@us2 = global i16 -1, align 2
+@ssi = global i16 0, align 2
+@ssj = global i16 0, align 2
+@i = global i32 0, align 4
+@j = global i32 0, align 4
+@.str = private unnamed_addr constant [4 x i8] c"%i\0A\00", align 1
+@.str1 = private unnamed_addr constant [7 x i8] c"%i %i\0A\00", align 1
+
+; Function Attrs: nounwind
+define void @_Z3b_iv() #0 {
+entry:
+; CHECK:  .ent  _Z3b_iv
+  %0 = load i8* @b1, align 1
+  %tobool = trunc i8 %0 to i1
+  %frombool = zext i1 %tobool to i8
+  store i8 %frombool, i8* @b2, align 1
+  %1 = load i8* @b2, align 1
+  %tobool1 = trunc i8 %1 to i1
+  %conv = zext i1 %tobool1 to i32
+  store i32 %conv, i32* @i, align 4
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  sb  ${{[0-9]+}}, 0(${{[0-9]+}})
+
+
+
+  ret void
+; CHECK:  .end  _Z3b_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4uc_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4uc_iv
+
+  %0 = load i8* @uc1, align 1
+  %conv = zext i8 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i8* @uc2, align 1
+  %conv1 = zext i8 %1 to i32
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 255
+
+  store i32 %conv1, i32* @j, align 4
+  ret void
+; CHECK:  .end  _Z4uc_iv
+
+}
+
+; Function Attrs: nounwind
+define void @_Z4sc_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4sc_iv
+
+  %0 = load i8* @sc1, align 1
+  %conv = sext i8 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i8* @sc2, align 1
+  %conv1 = sext i8 %1 to i32
+  store i32 %conv1, i32* @j, align 4
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  seb ${{[0-9]+}}, ${{[0-9]+}}
+
+  ret void
+; CHECK:  .end  _Z4sc_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4us_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4us_iv
+  %0 = load i16* @us1, align 2
+  %conv = zext i16 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i16* @us2, align 2
+  %conv1 = zext i16 %1 to i32
+  store i32 %conv1, i32* @j, align 4
+  ret void
+; CHECK:  lh  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 65535
+; CHECK:  .end  _Z4us_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4ss_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4ss_iv
+
+  %0 = load i16* @ss1, align 2
+  %conv = sext i16 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i16* @ss2, align 2
+  %conv1 = sext i16 %1 to i32
+  store i32 %conv1, i32* @j, align 4
+; CHECK:  lh  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  seh ${{[0-9]+}}, ${{[0-9]+}}
+
+  ret void
+; CHECK:  .end  _Z4ss_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4b_ssv() #0 {
+entry:
+; CHECK:  .ent  _Z4b_ssv
+  %0 = load i8* @b2, align 1
+  %tobool = trunc i8 %0 to i1
+  %conv = zext i1 %tobool to i16
+  store i16 %conv, i16* @ssi, align 2
+  ret void
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  .end  _Z4b_ssv
+}
+
+; Function Attrs: nounwind
+define void @_Z5uc_ssv() #0 {
+entry:
+; CHECK:  .ent  _Z5uc_ssv
+  %0 = load i8* @uc1, align 1
+  %conv = zext i8 %0 to i16
+  store i16 %conv, i16* @ssi, align 2
+  %1 = load i8* @uc2, align 1
+  %conv1 = zext i8 %1 to i16
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 255
+
+  store i16 %conv1, i16* @ssj, align 2
+  ret void
+; CHECK:  .end  _Z5uc_ssv
+}
+
+; Function Attrs: nounwind
+define void @_Z5sc_ssv() #0 {
+entry:
+; CHECK:  .ent  _Z5sc_ssv
+  %0 = load i8* @sc1, align 1
+  %conv = sext i8 %0 to i16
+  store i16 %conv, i16* @ssi, align 2
+  %1 = load i8* @sc2, align 1
+  %conv1 = sext i8 %1 to i16
+  store i16 %conv1, i16* @ssj, align 2
+; CHECK:  lb  ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  seb ${{[0-9]+}}, ${{[0-9]+}}
+
+  ret void
+; CHECK:  .end  _Z5sc_ssv
+}
+
+declare i32 @printf(i8*, ...) #1
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+