X86InstrInfo.td

//===- X86InstrInfo.td - Describe the X86 Instruction Set --*- tablegen -*-===//
// 
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
// 
//===----------------------------------------------------------------------===//
//
// This file describes the X86 instruction set, defining the instructions, and
// properties of the instructions which are needed for code generation, machine
// code emission, and analysis.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// X86 specific DAG Nodes.
//

def SDTIntShiftDOp: SDTypeProfile<1, 3,
                                  [SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>,
                                   SDTCisInt<0>, SDTCisInt<3>]>;

def SDTX86CmpTest : SDTypeProfile<0, 2, [SDTCisSameAs<0, 1>]>;

def SDTX86Cmov    : SDTypeProfile<1, 4,
                                  [SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2>,
                                   SDTCisVT<3, i8>, SDTCisVT<4, i32>]>;

// Unary and binary operator instructions that set EFLAGS as a side-effect.
def SDTUnaryArithWithFlags  : SDTypeProfile<1, 1,
                                            [SDTCisInt<0>]>;
def SDTBinaryArithWithFlags : SDTypeProfile<1, 2,
                                            [SDTCisSameAs<0, 1>,
                                             SDTCisSameAs<0, 2>,
                                             SDTCisInt<0>]>;

def SDTX86BrCond  : SDTypeProfile<0, 3,
                                  [SDTCisVT<0, OtherVT>,
                                   SDTCisVT<1, i8>, SDTCisVT<2, i32>]>;

def SDTX86SetCC   : SDTypeProfile<1, 2,
                                  [SDTCisVT<0, i8>,
                                   SDTCisVT<1, i8>, SDTCisVT<2, i32>]>;

def SDTX86cas : SDTypeProfile<0, 3, [SDTCisPtrTy<0>, SDTCisInt<1>, 
                                     SDTCisVT<2, i8>]>;
def SDTX86cas8 : SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>;

def SDTX86atomicBinary : SDTypeProfile<2, 3, [SDTCisInt<0>, SDTCisInt<1>,
                                SDTCisPtrTy<2>, SDTCisInt<3>,SDTCisInt<4>]>;
def SDTX86Ret     : SDTypeProfile<0, -1, [SDTCisVT<0, i16>]>;

def SDT_X86CallSeqStart : SDCallSeqStart<[ SDTCisVT<0, i32> ]>;
def SDT_X86CallSeqEnd   : SDCallSeqEnd<[ SDTCisVT<0, i32>,
                                         SDTCisVT<1, i32> ]>;

def SDT_X86Call   : SDTypeProfile<0, -1, [SDTCisVT<0, iPTR>]>;

def SDTX86RepStr  : SDTypeProfile<0, 1, [SDTCisVT<0, OtherVT>]>;

def SDTX86RdTsc   : SDTypeProfile<0, 0, []>;

def SDTX86Wrapper : SDTypeProfile<1, 1, [SDTCisSameAs<0, 1>, SDTCisPtrTy<0>]>;

def SDT_X86TLSADDR : SDTypeProfile<1, 1, [SDTCisPtrTy<0>, SDTCisInt<1>]>;

def SDT_X86SegmentBaseAddress : SDTypeProfile<1, 1, [SDTCisPtrTy<0>]>;

def SDT_X86EHRET : SDTypeProfile<0, 1, [SDTCisInt<0>]>;

def SDT_X86TCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>, SDTCisVT<1, i32>]>;

def X86bsf     : SDNode<"X86ISD::BSF",      SDTIntUnaryOp>;
def X86bsr     : SDNode<"X86ISD::BSR",      SDTIntUnaryOp>;
def X86shld    : SDNode<"X86ISD::SHLD",     SDTIntShiftDOp>;
def X86shrd    : SDNode<"X86ISD::SHRD",     SDTIntShiftDOp>;

def X86cmp     : SDNode<"X86ISD::CMP" ,     SDTX86CmpTest>;

def X86bt      : SDNode<"X86ISD::BT",       SDTX86CmpTest>;

def X86cmov    : SDNode<"X86ISD::CMOV",     SDTX86Cmov>;
def X86brcond  : SDNode<"X86ISD::BRCOND",   SDTX86BrCond,
                        [SDNPHasChain]>;
def X86setcc   : SDNode<"X86ISD::SETCC",    SDTX86SetCC>;

def X86cas : SDNode<"X86ISD::LCMPXCHG_DAG", SDTX86cas,
                        [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore,
                         SDNPMayLoad]>;
def X86cas8 : SDNode<"X86ISD::LCMPXCHG8_DAG", SDTX86cas8,
                        [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore,
                         SDNPMayLoad]>;
def X86AtomAdd64 : SDNode<"X86ISD::ATOMADD64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86AtomSub64 : SDNode<"X86ISD::ATOMSUB64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86AtomOr64 : SDNode<"X86ISD::ATOMOR64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86AtomXor64 : SDNode<"X86ISD::ATOMXOR64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86AtomAnd64 : SDNode<"X86ISD::ATOMAND64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86AtomNand64 : SDNode<"X86ISD::ATOMNAND64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86AtomSwap64 : SDNode<"X86ISD::ATOMSWAP64_DAG", SDTX86atomicBinary,
                        [SDNPHasChain, SDNPMayStore, 
                         SDNPMayLoad, SDNPMemOperand]>;
def X86retflag : SDNode<"X86ISD::RET_FLAG", SDTX86Ret,
                        [SDNPHasChain, SDNPOptInFlag]>;

def X86callseq_start :
                 SDNode<"ISD::CALLSEQ_START", SDT_X86CallSeqStart,
                        [SDNPHasChain, SDNPOutFlag]>;
def X86callseq_end :
                 SDNode<"ISD::CALLSEQ_END",   SDT_X86CallSeqEnd,
                        [SDNPHasChain, SDNPOptInFlag, SDNPOutFlag]>;       

def X86call    : SDNode<"X86ISD::CALL",     SDT_X86Call,
                        [SDNPHasChain, SDNPOutFlag, SDNPOptInFlag]>;

def X86tailcall: SDNode<"X86ISD::TAILCALL",     SDT_X86Call,
                        [SDNPHasChain, SDNPOutFlag, SDNPOptInFlag]>;

def X86rep_stos: SDNode<"X86ISD::REP_STOS", SDTX86RepStr,
                        [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore]>;
def X86rep_movs: SDNode<"X86ISD::REP_MOVS", SDTX86RepStr,
                        [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore,
                         SDNPMayLoad]>;

def X86rdtsc   : SDNode<"X86ISD::RDTSC_DAG",SDTX86RdTsc,
                        [SDNPHasChain, SDNPOutFlag, SDNPSideEffect]>;

def X86Wrapper    : SDNode<"X86ISD::Wrapper",     SDTX86Wrapper>;
def X86WrapperRIP : SDNode<"X86ISD::WrapperRIP",  SDTX86Wrapper>;

def X86tlsaddr : SDNode<"X86ISD::TLSADDR", SDT_X86TLSADDR,
                        [SDNPHasChain, SDNPOptInFlag, SDNPOutFlag]>;
def X86SegmentBaseAddress : SDNode<"X86ISD::SegmentBaseAddress",
                                 SDT_X86SegmentBaseAddress, []>;

def X86ehret : SDNode<"X86ISD::EH_RETURN", SDT_X86EHRET,
                        [SDNPHasChain]>;

def X86tcret : SDNode<"X86ISD::TC_RETURN", SDT_X86TCRET, 
                        [SDNPHasChain,  SDNPOptInFlag]>;

def X86add_flag  : SDNode<"X86ISD::ADD",  SDTBinaryArithWithFlags>;
def X86sub_flag  : SDNode<"X86ISD::SUB",  SDTBinaryArithWithFlags>;
def X86smul_flag : SDNode<"X86ISD::SMUL", SDTBinaryArithWithFlags>;
def X86umul_flag : SDNode<"X86ISD::UMUL", SDTUnaryArithWithFlags>;
def X86inc_flag  : SDNode<"X86ISD::INC",  SDTUnaryArithWithFlags>;
def X86dec_flag  : SDNode<"X86ISD::DEC",  SDTUnaryArithWithFlags>;

def X86mul_imm : SDNode<"X86ISD::MUL_IMM", SDTIntBinOp>;

//===----------------------------------------------------------------------===//
// X86 Operand Definitions.
//

// *mem - Operand definitions for the funky X86 addressing mode operands.
//
class X86MemOperand<string printMethod> : Operand<iPTR> {
  let PrintMethod = printMethod;
  let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc, i32imm, i8imm);
}

def i8mem   : X86MemOperand<"printi8mem">;
def i16mem  : X86MemOperand<"printi16mem">;
def i32mem  : X86MemOperand<"printi32mem">;
def i64mem  : X86MemOperand<"printi64mem">;
def i128mem : X86MemOperand<"printi128mem">;
def f32mem  : X86MemOperand<"printf32mem">;
def f64mem  : X86MemOperand<"printf64mem">;
def f80mem  : X86MemOperand<"printf80mem">;
def f128mem : X86MemOperand<"printf128mem">;

def lea32mem : Operand<i32> {
  let PrintMethod = "printlea32mem";
  let MIOperandInfo = (ops GR32, i8imm, GR32, i32imm);
}

def SSECC : Operand<i8> {
  let PrintMethod = "printSSECC";
}

def piclabel: Operand<i32> {
  let PrintMethod = "printPICLabel";
}

// A couple of more descriptive operand definitions.
// 16-bits but only 8 bits are significant.
def i16i8imm  : Operand<i16>;
// 32-bits but only 8 bits are significant.
def i32i8imm  : Operand<i32>;

// Branch targets have OtherVT type.
def brtarget : Operand<OtherVT>;

//===----------------------------------------------------------------------===//
// X86 Complex Pattern Definitions.
//

// Define X86 specific addressing mode.
def addr      : ComplexPattern<iPTR, 5, "SelectAddr", [], []>;
def lea32addr : ComplexPattern<i32, 4, "SelectLEAAddr",
                               [add, mul, shl, or, frameindex], []>;

//===----------------------------------------------------------------------===//
// X86 Instruction Predicate Definitions.
def HasMMX       : Predicate<"Subtarget->hasMMX()">;
def HasSSE1      : Predicate<"Subtarget->hasSSE1()">;
def HasSSE2      : Predicate<"Subtarget->hasSSE2()">;
def HasSSE3      : Predicate<"Subtarget->hasSSE3()">;
def HasSSSE3     : Predicate<"Subtarget->hasSSSE3()">;
def HasSSE41     : Predicate<"Subtarget->hasSSE41()">;
def HasSSE42     : Predicate<"Subtarget->hasSSE42()">;
def FPStackf32   : Predicate<"!Subtarget->hasSSE1()">;
def FPStackf64   : Predicate<"!Subtarget->hasSSE2()">;
def In32BitMode  : Predicate<"!Subtarget->is64Bit()">;
def In64BitMode  : Predicate<"Subtarget->is64Bit()">;
def SmallCode    : Predicate<"TM.getCodeModel() == CodeModel::Small">;
def NotSmallCode : Predicate<"TM.getCodeModel() != CodeModel::Small">;
def IsStatic     : Predicate<"TM.getRelocationModel() == Reloc::Static">;
def OptForSpeed  : Predicate<"!OptForSize">;
def FastBTMem    : Predicate<"!Subtarget->isBTMemSlow()">;

//===----------------------------------------------------------------------===//
// X86 Instruction Format Definitions.
//

include "X86InstrFormats.td"

//===----------------------------------------------------------------------===//
// Pattern fragments...
//

// X86 specific condition code. These correspond to CondCode in
// X86InstrInfo.h. They must be kept in synch.
def X86_COND_A   : PatLeaf<(i8 0)>;  // alt. COND_NBE
def X86_COND_AE  : PatLeaf<(i8 1)>;  // alt. COND_NC
def X86_COND_B   : PatLeaf<(i8 2)>;  // alt. COND_C
def X86_COND_BE  : PatLeaf<(i8 3)>;  // alt. COND_NA
def X86_COND_E   : PatLeaf<(i8 4)>;  // alt. COND_Z
def X86_COND_G   : PatLeaf<(i8 5)>;  // alt. COND_NLE
def X86_COND_GE  : PatLeaf<(i8 6)>;  // alt. COND_NL
def X86_COND_L   : PatLeaf<(i8 7)>;  // alt. COND_NGE
def X86_COND_LE  : PatLeaf<(i8 8)>;  // alt. COND_NG
def X86_COND_NE  : PatLeaf<(i8 9)>;  // alt. COND_NZ
def X86_COND_NO  : PatLeaf<(i8 10)>;
def X86_COND_NP  : PatLeaf<(i8 11)>; // alt. COND_PO
def X86_COND_NS  : PatLeaf<(i8 12)>;
def X86_COND_O   : PatLeaf<(i8 13)>;
def X86_COND_P   : PatLeaf<(i8 14)>; // alt. COND_PE
def X86_COND_S   : PatLeaf<(i8 15)>;

def i16immSExt8  : PatLeaf<(i16 imm), [{
  // i16immSExt8 predicate - True if the 16-bit immediate fits in a 8-bit
  // sign extended field.
  return (int16_t)N->getZExtValue() == (int8_t)N->getZExtValue();
}]>;

def i32immSExt8  : PatLeaf<(i32 imm), [{
  // i32immSExt8 predicate - True if the 32-bit immediate fits in a 8-bit
  // sign extended field.
  return (int32_t)N->getZExtValue() == (int8_t)N->getZExtValue();
}]>;

// Helper fragments for loads.
// It's always safe to treat a anyext i16 load as a i32 load if the i16 is
// known to be 32-bit aligned or better. Ditto for i8 to i16.
def loadi16 : PatFrag<(ops node:$ptr), (i16 (unindexedload node:$ptr)), [{
  LoadSDNode *LD = cast<LoadSDNode>(N);
  if (const Value *Src = LD->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  ISD::LoadExtType ExtType = LD->getExtensionType();
  if (ExtType == ISD::NON_EXTLOAD)
    return true;
  if (ExtType == ISD::EXTLOAD)
    return LD->getAlignment() >= 2 && !LD->isVolatile();
  return false;
}]>;

def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
  LoadSDNode *LD = cast<LoadSDNode>(N);
  if (const Value *Src = LD->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  ISD::LoadExtType ExtType = LD->getExtensionType();
  if (ExtType == ISD::EXTLOAD)
    return LD->getAlignment() >= 2 && !LD->isVolatile();
  return false;
}]>;

def loadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
  LoadSDNode *LD = cast<LoadSDNode>(N);
  if (const Value *Src = LD->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  ISD::LoadExtType ExtType = LD->getExtensionType();
  if (ExtType == ISD::NON_EXTLOAD)
    return true;
  if (ExtType == ISD::EXTLOAD)
    return LD->getAlignment() >= 4 && !LD->isVolatile();
  return false;
}]>;

def nvloadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
  LoadSDNode *LD = cast<LoadSDNode>(N);
  if (const Value *Src = LD->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  if (LD->isVolatile())
    return false;
  ISD::LoadExtType ExtType = LD->getExtensionType();
  if (ExtType == ISD::NON_EXTLOAD)
    return true;
  if (ExtType == ISD::EXTLOAD)
    return LD->getAlignment() >= 4;
  return false;
}]>;

def gsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      return PT->getAddressSpace() == 256;
  return false;
}]>;

def loadi8  : PatFrag<(ops node:$ptr), (i8  (load node:$ptr)), [{
  if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  return true;
}]>;
def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr)), [{
  if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  return true;
}]>;

def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr)), [{
  if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  return true;
}]>;
def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr)), [{
  if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  return true;
}]>;
def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr)), [{
  if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
    if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
      if (PT->getAddressSpace() != 0)
        return false;
  return true;
}]>;

def sextloadi16i8  : PatFrag<(ops node:$ptr), (i16 (sextloadi8 node:$ptr))>;
def sextloadi32i8  : PatFrag<(ops node:$ptr), (i32 (sextloadi8 node:$ptr))>;
def sextloadi32i16 : PatFrag<(ops node:$ptr), (i32 (sextloadi16 node:$ptr))>;

def zextloadi8i1   : PatFrag<(ops node:$ptr), (i8  (zextloadi1 node:$ptr))>;
def zextloadi16i1  : PatFrag<(ops node:$ptr), (i16 (zextloadi1 node:$ptr))>;
def zextloadi32i1  : PatFrag<(ops node:$ptr), (i32 (zextloadi1 node:$ptr))>;
def zextloadi16i8  : PatFrag<(ops node:$ptr), (i16 (zextloadi8 node:$ptr))>;
def zextloadi32i8  : PatFrag<(ops node:$ptr), (i32 (zextloadi8 node:$ptr))>;
def zextloadi32i16 : PatFrag<(ops node:$ptr), (i32 (zextloadi16 node:$ptr))>;

def extloadi8i1    : PatFrag<(ops node:$ptr), (i8  (extloadi1 node:$ptr))>;
def extloadi16i1   : PatFrag<(ops node:$ptr), (i16 (extloadi1 node:$ptr))>;
def extloadi32i1   : PatFrag<(ops node:$ptr), (i32 (extloadi1 node:$ptr))>;
def extloadi16i8   : PatFrag<(ops node:$ptr), (i16 (extloadi8 node:$ptr))>;
def extloadi32i8   : PatFrag<(ops node:$ptr), (i32 (extloadi8 node:$ptr))>;
def extloadi32i16  : PatFrag<(ops node:$ptr), (i32 (extloadi16 node:$ptr))>;


// An 'and' node with a single use.
def and_su : PatFrag<(ops node:$lhs, node:$rhs), (and node:$lhs, node:$rhs), [{
  return N->hasOneUse();
}]>;

// 'shld' and 'shrd' instruction patterns. Note that even though these have
// the srl and shl in their patterns, the C++ code must still check for them,
// because predicates are tested before children nodes are explored.

def shrd : PatFrag<(ops node:$src1, node:$amt1, node:$src2, node:$amt2),
                   (or (srl node:$src1, node:$amt1),
                       (shl node:$src2, node:$amt2)), [{
  assert(N->getOpcode() == ISD::OR);
  return N->getOperand(0).getOpcode() == ISD::SRL &&
         N->getOperand(1).getOpcode() == ISD::SHL &&
         isa<ConstantSDNode>(N->getOperand(0).getOperand(1)) &&
         isa<ConstantSDNode>(N->getOperand(1).getOperand(1)) &&
         N->getOperand(0).getConstantOperandVal(1) ==
         N->getValueSizeInBits(0) - N->getOperand(1).getConstantOperandVal(1);
}]>;

def shld : PatFrag<(ops node:$src1, node:$amt1, node:$src2, node:$amt2),
                   (or (shl node:$src1, node:$amt1),
                       (srl node:$src2, node:$amt2)), [{
  assert(N->getOpcode() == ISD::OR);
  return N->getOperand(0).getOpcode() == ISD::SHL &&
         N->getOperand(1).getOpcode() == ISD::SRL &&
         isa<ConstantSDNode>(N->getOperand(0).getOperand(1)) &&
         isa<ConstantSDNode>(N->getOperand(1).getOperand(1)) &&
         N->getOperand(0).getConstantOperandVal(1) ==
         N->getValueSizeInBits(0) - N->getOperand(1).getConstantOperandVal(1);
}]>;

//===----------------------------------------------------------------------===//
// Instruction list...
//

// ADJCALLSTACKDOWN/UP implicitly use/def ESP because they may be expanded into
// a stack adjustment and the codegen must know that they may modify the stack
// pointer before prolog-epilog rewriting occurs.
// Pessimistically assume ADJCALLSTACKDOWN / ADJCALLSTACKUP will become
// sub / add which can clobber EFLAGS.
let Defs = [ESP, EFLAGS], Uses = [ESP] in {
def ADJCALLSTACKDOWN32 : I<0, Pseudo, (outs), (ins i32imm:$amt),
                           "#ADJCALLSTACKDOWN",
                           [(X86callseq_start timm:$amt)]>,
                          Requires<[In32BitMode]>;
def ADJCALLSTACKUP32   : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
                           "#ADJCALLSTACKUP",
                           [(X86callseq_end timm:$amt1, timm:$amt2)]>,
                          Requires<[In32BitMode]>;
}

// Nop
let neverHasSideEffects = 1 in
  def NOOP : I<0x90, RawFrm, (outs), (ins), "nop", []>;

// PIC base
let neverHasSideEffects = 1, isNotDuplicable = 1, Uses = [ESP] in
  def MOVPC32r : Ii32<0xE8, Pseudo, (outs GR32:$reg), (ins piclabel:$label),
                      "call\t$label\n\tpop{l}\t$reg", []>;

//===----------------------------------------------------------------------===//
//  Control Flow Instructions...
//

// Return instructions.
let isTerminator = 1, isReturn = 1, isBarrier = 1,
    hasCtrlDep = 1, FPForm = SpecialFP, FPFormBits = SpecialFP.Value in {
  def RET    : I   <0xC3, RawFrm, (outs), (ins variable_ops),
                    "ret",
                    [(X86retflag 0)]>;
  def RETI   : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops),
                    "ret\t$amt",
                    [(X86retflag imm:$amt)]>;
}

// All branches are RawFrm, Void, Branch, and Terminators
let isBranch = 1, isTerminator = 1 in
  class IBr<bits<8> opcode, dag ins, string asm, list<dag> pattern> :
        I<opcode, RawFrm, (outs), ins, asm, pattern>;

let isBranch = 1, isBarrier = 1 in
  def JMP : IBr<0xE9, (ins brtarget:$dst), "jmp\t$dst", [(br bb:$dst)]>;

// Indirect branches
let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in {
  def JMP32r     : I<0xFF, MRM4r, (outs), (ins GR32:$dst), "jmp{l}\t{*}$dst",
                     [(brind GR32:$dst)]>;
  def JMP32m     : I<0xFF, MRM4m, (outs), (ins i32mem:$dst), "jmp{l}\t{*}$dst",
                     [(brind (loadi32 addr:$dst))]>;
}

// Conditional branches
let Uses = [EFLAGS] in {
def JE  : IBr<0x84, (ins brtarget:$dst), "je\t$dst",
              [(X86brcond bb:$dst, X86_COND_E, EFLAGS)]>, TB;
def JNE : IBr<0x85, (ins brtarget:$dst), "jne\t$dst",
              [(X86brcond bb:$dst, X86_COND_NE, EFLAGS)]>, TB;
def JL  : IBr<0x8C, (ins brtarget:$dst), "jl\t$dst",
              [(X86brcond bb:$dst, X86_COND_L, EFLAGS)]>, TB;
def JLE : IBr<0x8E, (ins brtarget:$dst), "jle\t$dst",
              [(X86brcond bb:$dst, X86_COND_LE, EFLAGS)]>, TB;
def JG  : IBr<0x8F, (ins brtarget:$dst), "jg\t$dst",
              [(X86brcond bb:$dst, X86_COND_G, EFLAGS)]>, TB;
def JGE : IBr<0x8D, (ins brtarget:$dst), "jge\t$dst",
              [(X86brcond bb:$dst, X86_COND_GE, EFLAGS)]>, TB;

def JB  : IBr<0x82, (ins brtarget:$dst), "jb\t$dst",
              [(X86brcond bb:$dst, X86_COND_B, EFLAGS)]>, TB;
def JBE : IBr<0x86, (ins brtarget:$dst), "jbe\t$dst",
              [(X86brcond bb:$dst, X86_COND_BE, EFLAGS)]>, TB;
def JA  : IBr<0x87, (ins brtarget:$dst), "ja\t$dst",
              [(X86brcond bb:$dst, X86_COND_A, EFLAGS)]>, TB;
def JAE : IBr<0x83, (ins brtarget:$dst), "jae\t$dst",
              [(X86brcond bb:$dst, X86_COND_AE, EFLAGS)]>, TB;

def JS  : IBr<0x88, (ins brtarget:$dst), "js\t$dst",
              [(X86brcond bb:$dst, X86_COND_S, EFLAGS)]>, TB;
def JNS : IBr<0x89, (ins brtarget:$dst), "jns\t$dst",
              [(X86brcond bb:$dst, X86_COND_NS, EFLAGS)]>, TB;
def JP  : IBr<0x8A, (ins brtarget:$dst), "jp\t$dst",
              [(X86brcond bb:$dst, X86_COND_P, EFLAGS)]>, TB;
def JNP : IBr<0x8B, (ins brtarget:$dst), "jnp\t$dst",
              [(X86brcond bb:$dst, X86_COND_NP, EFLAGS)]>, TB;
def JO  : IBr<0x80, (ins brtarget:$dst), "jo\t$dst",
              [(X86brcond bb:$dst, X86_COND_O, EFLAGS)]>, TB;
def JNO : IBr<0x81, (ins brtarget:$dst), "jno\t$dst",
              [(X86brcond bb:$dst, X86_COND_NO, EFLAGS)]>, TB;
} // Uses = [EFLAGS]

//===----------------------------------------------------------------------===//
//  Call Instructions...
//
let isCall = 1 in
  // All calls clobber the non-callee saved registers. ESP is marked as
  // a use to prevent stack-pointer assignments that appear immediately
  // before calls from potentially appearing dead. Uses for argument
  // registers are added manually.
  let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0,
              MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
              XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
              XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
      Uses = [ESP] in {
    def CALLpcrel32 : Ii32<0xE8, RawFrm, (outs), (ins i32imm:$dst,variable_ops),
                           "call\t${dst:call}", [(X86call imm:$dst)]>,
                      Requires<[In32BitMode]>;
    def CALL32r     : I<0xFF, MRM2r, (outs), (ins GR32:$dst, variable_ops),
                        "call\t{*}$dst", [(X86call GR32:$dst)]>;
    def CALL32m     : I<0xFF, MRM2m, (outs), (ins i32mem:$dst, variable_ops),
                        "call\t{*}$dst", [(X86call (loadi32 addr:$dst))]>;
  }

// Tail call stuff.

def TAILCALL : I<0, Pseudo, (outs), (ins),
                         "#TAILCALL",
                         []>;

let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
def TCRETURNdi : I<0, Pseudo, (outs), (ins i32imm:$dst, i32imm:$offset, variable_ops),
                 "#TC_RETURN $dst $offset",
                 []>;

let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
def TCRETURNri : I<0, Pseudo, (outs), (ins GR32:$dst, i32imm:$offset, variable_ops),
                 "#TC_RETURN $dst $offset",
                 []>;

let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in

  def TAILJMPd : IBr<0xE9, (ins i32imm:$dst), "jmp\t${dst:call}  # TAILCALL",
                 []>;
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
  def TAILJMPr : I<0xFF, MRM4r, (outs), (ins GR32:$dst), "jmp{l}\t{*}$dst  # TAILCALL",
                 []>;     
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
  def TAILJMPm : I<0xFF, MRM4m, (outs), (ins i32mem:$dst),
                   "jmp\t{*}$dst  # TAILCALL", []>;

//===----------------------------------------------------------------------===//
//  Miscellaneous Instructions...
//
let Defs = [EBP, ESP], Uses = [EBP, ESP], mayLoad = 1, neverHasSideEffects=1 in
def LEAVE    : I<0xC9, RawFrm,
                 (outs), (ins), "leave", []>;

let Defs = [ESP], Uses = [ESP], neverHasSideEffects=1 in {
let mayLoad = 1 in
def POP32r   : I<0x58, AddRegFrm, (outs GR32:$reg), (ins), "pop{l}\t$reg", []>;

let mayStore = 1 in
def PUSH32r  : I<0x50, AddRegFrm, (outs), (ins GR32:$reg), "push{l}\t$reg",[]>;
}

let Defs = [ESP, EFLAGS], Uses = [ESP], mayLoad = 1, neverHasSideEffects=1 in
def POPFD    : I<0x9D, RawFrm, (outs), (ins), "popf", []>;
let Defs = [ESP], Uses = [ESP, EFLAGS], mayStore = 1, neverHasSideEffects=1 in
def PUSHFD   : I<0x9C, RawFrm, (outs), (ins), "pushf", []>;

let isTwoAddress = 1 in                               // GR32 = bswap GR32
  def BSWAP32r : I<0xC8, AddRegFrm,
                   (outs GR32:$dst), (ins GR32:$src),
                   "bswap{l}\t$dst", 
                   [(set GR32:$dst, (bswap GR32:$src))]>, TB;


// Bit scan instructions.
let Defs = [EFLAGS] in {
def BSF16rr  : I<0xBC, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src),
                 "bsf{w}\t{$src, $dst|$dst, $src}",
                 [(set GR16:$dst, (X86bsf GR16:$src)), (implicit EFLAGS)]>, TB;
def BSF16rm  : I<0xBC, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src),
                 "bsf{w}\t{$src, $dst|$dst, $src}",
                 [(set GR16:$dst, (X86bsf (loadi16 addr:$src))),
                  (implicit EFLAGS)]>, TB;
def BSF32rr  : I<0xBC, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src),
                 "bsf{l}\t{$src, $dst|$dst, $src}",
                 [(set GR32:$dst, (X86bsf GR32:$src)), (implicit EFLAGS)]>, TB;
def BSF32rm  : I<0xBC, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
                 "bsf{l}\t{$src, $dst|$dst, $src}",
                 [(set GR32:$dst, (X86bsf (loadi32 addr:$src))),
                  (implicit EFLAGS)]>, TB;

def BSR16rr  : I<0xBD, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src),
                 "bsr{w}\t{$src, $dst|$dst, $src}",
                 [(set GR16:$dst, (X86bsr GR16:$src)), (implicit EFLAGS)]>, TB;
def BSR16rm  : I<0xBD, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src),
                 "bsr{w}\t{$src, $dst|$dst, $src}",
                 [(set GR16:$dst, (X86bsr (loadi16 addr:$src))),
                  (implicit EFLAGS)]>, TB;
def BSR32rr  : I<0xBD, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src),
                 "bsr{l}\t{$src, $dst|$dst, $src}",
                 [(set GR32:$dst, (X86bsr GR32:$src)), (implicit EFLAGS)]>, TB;
def BSR32rm  : I<0xBD, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
                 "bsr{l}\t{$src, $dst|$dst, $src}",
                 [(set GR32:$dst, (X86bsr (loadi32 addr:$src))),
                  (implicit EFLAGS)]>, TB;
} // Defs = [EFLAGS]

let neverHasSideEffects = 1 in
def LEA16r   : I<0x8D, MRMSrcMem,
                 (outs GR16:$dst), (ins i32mem:$src),
                 "lea{w}\t{$src|$dst}, {$dst|$src}", []>, OpSize;
let isReMaterializable = 1 in
def LEA32r   : I<0x8D, MRMSrcMem,
                 (outs GR32:$dst), (ins lea32mem:$src),
                 "lea{l}\t{$src|$dst}, {$dst|$src}",
                 [(set GR32:$dst, lea32addr:$src)]>, Requires<[In32BitMode]>;

let Defs = [ECX,EDI,ESI], Uses = [ECX,EDI,ESI] in {
def REP_MOVSB : I<0xA4, RawFrm, (outs), (ins), "{rep;movsb|rep movsb}",
                  [(X86rep_movs i8)]>, REP;
def REP_MOVSW : I<0xA5, RawFrm, (outs), (ins), "{rep;movsw|rep movsw}",
                  [(X86rep_movs i16)]>, REP, OpSize;
def REP_MOVSD : I<0xA5, RawFrm, (outs), (ins), "{rep;movsl|rep movsd}",
                  [(X86rep_movs i32)]>, REP;
}

let Defs = [ECX,EDI], Uses = [AL,ECX,EDI] in
def REP_STOSB : I<0xAA, RawFrm, (outs), (ins), "{rep;stosb|rep stosb}",
                  [(X86rep_stos i8)]>, REP;
let Defs = [ECX,EDI], Uses = [AX,ECX,EDI] in
def REP_STOSW : I<0xAB, RawFrm, (outs), (ins), "{rep;stosw|rep stosw}",
                  [(X86rep_stos i16)]>, REP, OpSize;
let Defs = [ECX,EDI], Uses = [EAX,ECX,EDI] in
def REP_STOSD : I<0xAB, RawFrm, (outs), (ins), "{rep;stosl|rep stosd}",
                  [(X86rep_stos i32)]>, REP;

let Defs = [RAX, RDX] in
def RDTSC : I<0x31, RawFrm, (outs), (ins), "rdtsc", [(X86rdtsc)]>,
            TB;

let isBarrier = 1, hasCtrlDep = 1 in {
def TRAP    : I<0x0B, RawFrm, (outs), (ins), "ud2", [(trap)]>, TB;
}

//===----------------------------------------------------------------------===//
//  Input/Output Instructions...
//
let Defs = [AL], Uses = [DX] in
def IN8rr  : I<0xEC, RawFrm, (outs), (ins),
               "in{b}\t{%dx, %al|%AL, %DX}", []>;
let Defs = [AX], Uses = [DX] in
def IN16rr : I<0xED, RawFrm, (outs), (ins),
               "in{w}\t{%dx, %ax|%AX, %DX}", []>,  OpSize;
let Defs = [EAX], Uses = [DX] in
def IN32rr : I<0xED, RawFrm, (outs), (ins),
               "in{l}\t{%dx, %eax|%EAX, %DX}", []>;

let Defs = [AL] in
def IN8ri  : Ii8<0xE4, RawFrm, (outs), (ins i16i8imm:$port),
                  "in{b}\t{$port, %al|%AL, $port}", []>;
let Defs = [AX] in
def IN16ri : Ii8<0xE5, RawFrm, (outs), (ins i16i8imm:$port),
                  "in{w}\t{$port, %ax|%AX, $port}", []>, OpSize;
let Defs = [EAX] in
def IN32ri : Ii8<0xE5, RawFrm, (outs), (ins i16i8imm:$port),
                  "in{l}\t{$port, %eax|%EAX, $port}", []>;

let Uses = [DX, AL] in
def OUT8rr  : I<0xEE, RawFrm, (outs), (ins),
                "out{b}\t{%al, %dx|%DX, %AL}", []>;
let Uses = [DX, AX] in
def OUT16rr : I<0xEF, RawFrm, (outs), (ins),
                "out{w}\t{%ax, %dx|%DX, %AX}", []>, OpSize;
let Uses = [DX, EAX] in
def OUT32rr : I<0xEF, RawFrm, (outs), (ins),
                "out{l}\t{%eax, %dx|%DX, %EAX}", []>;

let Uses = [AL] in
def OUT8ir  : Ii8<0xE6, RawFrm, (outs), (ins i16i8imm:$port),
                   "out{b}\t{%al, $port|$port, %AL}", []>;
let Uses = [AX] in
def OUT16ir : Ii8<0xE7, RawFrm, (outs), (ins i16i8imm:$port),
                   "out{w}\t{%ax, $port|$port, %AX}", []>, OpSize;
let Uses = [EAX] in
def OUT32ir : Ii8<0xE7, RawFrm, (outs), (ins i16i8imm:$port),
                   "out{l}\t{%eax, $port|$port, %EAX}", []>;

//===----------------------------------------------------------------------===//
//  Move Instructions...
//
let neverHasSideEffects = 1 in {
def MOV8rr  : I<0x88, MRMDestReg, (outs GR8 :$dst), (ins GR8 :$src),
                "mov{b}\t{$src, $dst|$dst, $src}", []>;
def MOV16rr : I<0x89, MRMDestReg, (outs GR16:$dst), (ins GR16:$src),
                "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
def MOV32rr : I<0x89, MRMDestReg, (outs GR32:$dst), (ins GR32:$src),
                "mov{l}\t{$src, $dst|$dst, $src}", []>;
}
let isReMaterializable = 1, isAsCheapAsAMove = 1 in {
def MOV8ri  : Ii8 <0xB0, AddRegFrm, (outs GR8 :$dst), (ins i8imm :$src),
                   "mov{b}\t{$src, $dst|$dst, $src}",
                   [(set GR8:$dst, imm:$src)]>;
def MOV16ri : Ii16<0xB8, AddRegFrm, (outs GR16:$dst), (ins i16imm:$src),
                   "mov{w}\t{$src, $dst|$dst, $src}",
                   [(set GR16:$dst, imm:$src)]>, OpSize;
def MOV32ri : Ii32<0xB8, AddRegFrm, (outs GR32:$dst), (ins i32imm:$src),
                   "mov{l}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, imm:$src)]>;
}
def MOV8mi  : Ii8 <0xC6, MRM0m, (outs), (ins i8mem :$dst, i8imm :$src),
                   "mov{b}\t{$src, $dst|$dst, $src}",
                   [(store (i8 imm:$src), addr:$dst)]>;
def MOV16mi : Ii16<0xC7, MRM0m, (outs), (ins i16mem:$dst, i16imm:$src),
                   "mov{w}\t{$src, $dst|$dst, $src}",
                   [(store (i16 imm:$src), addr:$dst)]>, OpSize;
def MOV32mi : Ii32<0xC7, MRM0m, (outs), (ins i32mem:$dst, i32imm:$src),
                   "mov{l}\t{$src, $dst|$dst, $src}",
                   [(store (i32 imm:$src), addr:$dst)]>;

let canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
def MOV8rm  : I<0x8A, MRMSrcMem, (outs GR8 :$dst), (ins i8mem :$src),
                "mov{b}\t{$src, $dst|$dst, $src}",
                [(set GR8:$dst, (loadi8 addr:$src))]>;
def MOV16rm : I<0x8B, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src),
                "mov{w}\t{$src, $dst|$dst, $src}",
                [(set GR16:$dst, (loadi16 addr:$src))]>, OpSize;
def MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
                "mov{l}\t{$src, $dst|$dst, $src}",
                [(set GR32:$dst, (loadi32 addr:$src))]>;
}

def MOV8mr  : I<0x88, MRMDestMem, (outs), (ins i8mem :$dst, GR8 :$src),
                "mov{b}\t{$src, $dst|$dst, $src}",
                [(store GR8:$src, addr:$dst)]>;
def MOV16mr : I<0x89, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src),
                "mov{w}\t{$src, $dst|$dst, $src}",
                [(store GR16:$src, addr:$dst)]>, OpSize;
def MOV32mr : I<0x89, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src),
                "mov{l}\t{$src, $dst|$dst, $src}",
                [(store GR32:$src, addr:$dst)]>;
                
//===----------------------------------------------------------------------===//
//  Fixed-Register Multiplication and Division Instructions...
//

// Extra precision multiplication
let Defs = [AL,AH,EFLAGS], Uses = [AL] in
def MUL8r  : I<0xF6, MRM4r, (outs),  (ins GR8:$src), "mul{b}\t$src",
               // FIXME: Used for 8-bit mul, ignore result upper 8 bits.
               // This probably ought to be moved to a def : Pat<> if the
               // syntax can be accepted.
               [(set AL, (mul AL, GR8:$src)),
                (implicit EFLAGS)]>;     // AL,AH = AL*GR8

let Defs = [AX,DX,EFLAGS], Uses = [AX], neverHasSideEffects = 1 in
def MUL16r : I<0xF7, MRM4r, (outs),  (ins GR16:$src),
               "mul{w}\t$src", 
               []>, OpSize;    // AX,DX = AX*GR16

let Defs = [EAX,EDX,EFLAGS], Uses = [EAX], neverHasSideEffects = 1 in
def MUL32r : I<0xF7, MRM4r, (outs),  (ins GR32:$src),
               "mul{l}\t$src",
               []>; // EAX,EDX = EAX*GR32

let Defs = [AL,AH,EFLAGS], Uses = [AL] in
def MUL8m  : I<0xF6, MRM4m, (outs), (ins i8mem :$src),
               "mul{b}\t$src",
               // FIXME: Used for 8-bit mul, ignore result upper 8 bits.
               // This probably ought to be moved to a def : Pat<> if the
               // syntax can be accepted.
               [(set AL, (mul AL, (loadi8 addr:$src))),
                (implicit EFLAGS)]>;   // AL,AH = AL*[mem8]

let mayLoad = 1, neverHasSideEffects = 1 in {
let Defs = [AX,DX,EFLAGS], Uses = [AX] in
def MUL16m : I<0xF7, MRM4m, (outs), (ins i16mem:$src),
               "mul{w}\t$src",
               []>, OpSize; // AX,DX = AX*[mem16]

let Defs = [EAX,EDX,EFLAGS], Uses = [EAX] in
def MUL32m : I<0xF7, MRM4m, (outs), (ins i32mem:$src),
              "mul{l}\t$src",
              []>;          // EAX,EDX = EAX*[mem32]
}

let neverHasSideEffects = 1 in {
let Defs = [AL,AH,EFLAGS], Uses = [AL] in
def IMUL8r  : I<0xF6, MRM5r, (outs),  (ins GR8:$src), "imul{b}\t$src", []>;
              // AL,AH = AL*GR8
let Defs = [AX,DX,EFLAGS], Uses = [AX] in
def IMUL16r : I<0xF7, MRM5r, (outs),  (ins GR16:$src), "imul{w}\t$src", []>,
              OpSize;    // AX,DX = AX*GR16
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX] in
def IMUL32r : I<0xF7, MRM5r, (outs),  (ins GR32:$src), "imul{l}\t$src", []>;
              // EAX,EDX = EAX*GR32
let mayLoad = 1 in {
let Defs = [AL,AH,EFLAGS], Uses = [AL] in
def IMUL8m  : I<0xF6, MRM5m, (outs), (ins i8mem :$src),
                "imul{b}\t$src", []>;    // AL,AH = AL*[mem8]
let Defs = [AX,DX,EFLAGS], Uses = [AX] in
def IMUL16m : I<0xF7, MRM5m, (outs), (ins i16mem:$src),
                "imul{w}\t$src", []>, OpSize; // AX,DX = AX*[mem16]
let Defs = [EAX,EDX], Uses = [EAX] in
def IMUL32m : I<0xF7, MRM5m, (outs), (ins i32mem:$src),
                "imul{l}\t$src", []>;  // EAX,EDX = EAX*[mem32]
}
} // neverHasSideEffects

// unsigned division/remainder
let Defs = [AL,AH,EFLAGS], Uses = [AX] in
def DIV8r  : I<0xF6, MRM6r, (outs),  (ins GR8:$src),          // AX/r8 = AL,AH
               "div{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def DIV16r : I<0xF7, MRM6r, (outs),  (ins GR16:$src),         // DX:AX/r16 = AX,DX
               "div{w}\t$src", []>, OpSize;
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in
def DIV32r : I<0xF7, MRM6r, (outs),  (ins GR32:$src),         // EDX:EAX/r32 = EAX,EDX
               "div{l}\t$src", []>;
let mayLoad = 1 in {
let Defs = [AL,AH,EFLAGS], Uses = [AX] in
def DIV8m  : I<0xF6, MRM6m, (outs), (ins i8mem:$src),       // AX/[mem8] = AL,AH
               "div{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def DIV16m : I<0xF7, MRM6m, (outs), (ins i16mem:$src),      // DX:AX/[mem16] = AX,DX
               "div{w}\t$src", []>, OpSize;
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in
def DIV32m : I<0xF7, MRM6m, (outs), (ins i32mem:$src),      // EDX:EAX/[mem32] = EAX,EDX
               "div{l}\t$src", []>;
}

// Signed division/remainder.
let Defs = [AL,AH,EFLAGS], Uses = [AX] in
def IDIV8r : I<0xF6, MRM7r, (outs),  (ins GR8:$src),          // AX/r8 = AL,AH
               "idiv{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def IDIV16r: I<0xF7, MRM7r, (outs),  (ins GR16:$src),         // DX:AX/r16 = AX,DX
               "idiv{w}\t$src", []>, OpSize;
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in
def IDIV32r: I<0xF7, MRM7r, (outs),  (ins GR32:$src),         // EDX:EAX/r32 = EAX,EDX
               "idiv{l}\t$src", []>;
let mayLoad = 1, mayLoad = 1 in {
let Defs = [AL,AH,EFLAGS], Uses = [AX] in
def IDIV8m : I<0xF6, MRM7m, (outs), (ins i8mem:$src),      // AX/[mem8] = AL,AH
               "idiv{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def IDIV16m: I<0xF7, MRM7m, (outs), (ins i16mem:$src),     // DX:AX/[mem16] = AX,DX
               "idiv{w}\t$src", []>, OpSize;
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in
def IDIV32m: I<0xF7, MRM7m, (outs), (ins i32mem:$src),     // EDX:EAX/[mem32] = EAX,EDX
               "idiv{l}\t$src", []>;
}

//===----------------------------------------------------------------------===//
//  Two address Instructions.
//
let isTwoAddress = 1 in {

// Conditional moves
let Uses = [EFLAGS] in {
let isCommutable = 1 in {
def CMOVB16rr : I<0x42, MRMSrcReg,       // if <u, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovb\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_B, EFLAGS))]>,
                  TB, OpSize;
def CMOVB32rr : I<0x42, MRMSrcReg,       // if <u, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovb\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_B, EFLAGS))]>,
                   TB;
def CMOVAE16rr: I<0x43, MRMSrcReg,       // if >=u, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovae\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_AE, EFLAGS))]>,
                   TB, OpSize;
def CMOVAE32rr: I<0x43, MRMSrcReg,       // if >=u, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovae\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_AE, EFLAGS))]>,
                   TB;
def CMOVE16rr : I<0x44, MRMSrcReg,       // if ==, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmove\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_E, EFLAGS))]>,
                   TB, OpSize;
def CMOVE32rr : I<0x44, MRMSrcReg,       // if ==, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmove\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_E, EFLAGS))]>,
                   TB;
def CMOVNE16rr: I<0x45, MRMSrcReg,       // if !=, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovne\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_NE, EFLAGS))]>,
                   TB, OpSize;
def CMOVNE32rr: I<0x45, MRMSrcReg,       // if !=, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovne\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_NE, EFLAGS))]>,
                   TB;
def CMOVBE16rr: I<0x46, MRMSrcReg,       // if <=u, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovbe\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_BE, EFLAGS))]>,
                   TB, OpSize;
def CMOVBE32rr: I<0x46, MRMSrcReg,       // if <=u, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovbe\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_BE, EFLAGS))]>,
                   TB;
def CMOVA16rr : I<0x47, MRMSrcReg,       // if >u, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmova\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_A, EFLAGS))]>,
                   TB, OpSize;
def CMOVA32rr : I<0x47, MRMSrcReg,       // if >u, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmova\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_A, EFLAGS))]>,
                   TB;
def CMOVL16rr : I<0x4C, MRMSrcReg,       // if <s, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovl\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_L, EFLAGS))]>,
                   TB, OpSize;
def CMOVL32rr : I<0x4C, MRMSrcReg,       // if <s, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovl\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_L, EFLAGS))]>,
                   TB;
def CMOVGE16rr: I<0x4D, MRMSrcReg,       // if >=s, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovge\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_GE, EFLAGS))]>,
                   TB, OpSize;
def CMOVGE32rr: I<0x4D, MRMSrcReg,       // if >=s, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovge\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_GE, EFLAGS))]>,
                   TB;
def CMOVLE16rr: I<0x4E, MRMSrcReg,       // if <=s, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovle\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_LE, EFLAGS))]>,
                   TB, OpSize;
def CMOVLE32rr: I<0x4E, MRMSrcReg,       // if <=s, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovle\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_LE, EFLAGS))]>,
                   TB;
def CMOVG16rr : I<0x4F, MRMSrcReg,       // if >s, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovg\t{$src2, $dst|$dst, $src2}",