X86InstrInfo.td

//===- X86InstrInfo.td - Describe the X86 Instruction Set -------*- C++ -*-===//
// 
//                     The LLVM Compiler Infrastructure
//
// This file was developed by the LLVM research group and 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, 3,
                                  [SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2>,
                                   SDTCisVT<3, i8>]>;

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

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

def SDTX86Ret     : SDTypeProfile<0, 1, [SDTCisVT<0, i16>]>;

def SDT_X86CallSeqStart : SDTypeProfile<0, 1, [ SDTCisVT<0, i32> ]>;
def SDT_X86CallSeqEnd   : SDTypeProfile<0, 2, [ 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_X86TLSTP : SDTypeProfile<1, 0, [SDTCisPtrTy<0>]>;

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

def X86shld    : SDNode<"X86ISD::SHLD",     SDTIntShiftDOp>;
def X86shrd    : SDNode<"X86ISD::SHRD",     SDTIntShiftDOp>;

def X86cmp     : SDNode<"X86ISD::CMP" ,     SDTX86CmpTest,
                        [SDNPHasChain, SDNPOutFlag]>;

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

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

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

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

def X86tlsaddr : SDNode<"X86ISD::TLSADDR", SDT_X86TLSADDR,
                        [SDNPHasChain, SDNPInFlag, SDNPOutFlag]>;
def X86TLStp : SDNode<"X86ISD::THREAD_POINTER", SDT_X86TLSTP, []>;

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


//===----------------------------------------------------------------------===//
// 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);
}

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 = "printi32mem";
  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, 4, "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 FPStack      : Predicate<"!Subtarget->hasSSE2()">;
def In32BitMode  : Predicate<"!Subtarget->is64Bit()">;
def In64BitMode  : Predicate<"Subtarget->is64Bit()">;
def HasLow4G     : Predicate<"Subtarget->hasLow4GUserSpaceAddress()">;
def SmallCode    : Predicate<"TM.getCodeModel() == CodeModel::Small">;
def NotSmallCode : Predicate<"TM.getCodeModel() != CodeModel::Small">;
def IsStatic     : Predicate<"TM.getRelocationModel() == Reloc::Static">;

//===----------------------------------------------------------------------===//
// 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)>;
def X86_COND_AE  : PatLeaf<(i8 1)>;
def X86_COND_B   : PatLeaf<(i8 2)>;
def X86_COND_BE  : PatLeaf<(i8 3)>;
def X86_COND_E   : PatLeaf<(i8 4)>;
def X86_COND_G   : PatLeaf<(i8 5)>;
def X86_COND_GE  : PatLeaf<(i8 6)>;
def X86_COND_L   : PatLeaf<(i8 7)>;
def X86_COND_LE  : PatLeaf<(i8 8)>;
def X86_COND_NE  : PatLeaf<(i8 9)>;
def X86_COND_NO  : PatLeaf<(i8 10)>;
def X86_COND_NP  : PatLeaf<(i8 11)>;
def X86_COND_NS  : PatLeaf<(i8 12)>;
def X86_COND_O   : PatLeaf<(i8 13)>;
def X86_COND_P   : PatLeaf<(i8 14)>;
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->getValue() == (int8_t)N->getValue();
}]>;

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->getValue() == (int8_t)N->getValue();
}]>;

// Helper fragments for loads.
def loadi8  : PatFrag<(ops node:$ptr), (i8  (load node:$ptr))>;
def loadi16 : PatFrag<(ops node:$ptr), (i16 (load node:$ptr))>;
def loadi32 : PatFrag<(ops node:$ptr), (i32 (load node:$ptr))>;
def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr))>;

def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr))>;
def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr))>;
def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr))>;

def sextloadi16i1  : PatFrag<(ops node:$ptr), (i16 (sextloadi1 node:$ptr))>;
def sextloadi32i1  : PatFrag<(ops node:$ptr), (i32 (sextloadi1 node:$ptr))>;
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))>;

//===----------------------------------------------------------------------===//
// 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.
def ADJCALLSTACKDOWN : I<0, Pseudo, (outs), (ins i32imm:$amt), "#ADJCALLSTACKDOWN",
                         [(X86callseq_start imm:$amt)]>, Imp<[ESP],[ESP]>;
def ADJCALLSTACKUP   : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
                         "#ADJCALLSTACKUP",
                         [(X86callseq_end imm:$amt1, imm:$amt2)]>,
                         Imp<[ESP],[ESP]>;
def IMPLICIT_USE     : I<0, Pseudo, (outs), (ins variable_ops),
                         "#IMPLICIT_USE", []>;
def IMPLICIT_DEF     : I<0, Pseudo, (outs variable_ops), (ins),
                          "#IMPLICIT_DEF", []>;
def IMPLICIT_DEF_GR8  : I<0, Pseudo, (outs GR8:$dst), (ins),
                         "#IMPLICIT_DEF $dst",
                         [(set GR8:$dst, (undef))]>;
def IMPLICIT_DEF_GR16  : I<0, Pseudo, (outs GR16:$dst), (ins),
                         "#IMPLICIT_DEF $dst",
                         [(set GR16:$dst, (undef))]>;
def IMPLICIT_DEF_GR32  : I<0, Pseudo, (outs GR32:$dst), (ins),
                         "#IMPLICIT_DEF $dst",
                         [(set GR32:$dst, (undef))]>;

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


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

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

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

let isBranch = 1, isTerminator = 1, isBarrier = 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
def JE  : IBr<0x84, (ins brtarget:$dst), "je\t$dst",
              [(X86brcond bb:$dst, X86_COND_E)]>, TB;
def JNE : IBr<0x85, (ins brtarget:$dst), "jne\t$dst",
              [(X86brcond bb:$dst, X86_COND_NE)]>, TB;
def JL  : IBr<0x8C, (ins brtarget:$dst), "jl\t$dst",
              [(X86brcond bb:$dst, X86_COND_L)]>, TB;
def JLE : IBr<0x8E, (ins brtarget:$dst), "jle\t$dst",
              [(X86brcond bb:$dst, X86_COND_LE)]>, TB;
def JG  : IBr<0x8F, (ins brtarget:$dst), "jg\t$dst",
              [(X86brcond bb:$dst, X86_COND_G)]>, TB;
def JGE : IBr<0x8D, (ins brtarget:$dst), "jge\t$dst",
              [(X86brcond bb:$dst, X86_COND_GE)]>, TB;

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

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

//===----------------------------------------------------------------------===//
//  Call Instructions...
//
let isCall = 1 in
  // All calls clobber the non-callee saved registers...
  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] in {
    def CALLpcrel32 : I<0xE8, RawFrm, (outs), (ins i32imm:$dst, variable_ops),
                        "call\t${dst:call}", []>;
    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", []>;
  }

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

//===----------------------------------------------------------------------===//
//  Miscellaneous Instructions...
//
def LEAVE    : I<0xC9, RawFrm,
                 (outs), (ins), "leave", []>, Imp<[EBP,ESP],[EBP,ESP]>;
def POP32r   : I<0x58, AddRegFrm,
                 (outs GR32:$reg), (ins), "pop{l}\t$reg", []>, Imp<[ESP],[ESP]>;

def PUSH32r  : I<0x50, AddRegFrm,
                 (outs), (ins GR32:$reg), "push{l}\t$reg", []>, Imp<[ESP],[ESP]>;

def MovePCtoStack : I<0, Pseudo, (outs), (ins piclabel:$label),
                      "call\t$label", []>;

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;

// FIXME: Model xchg* as two address instructions?
def XCHG8rr  : I<0x86, MRMDestReg,                    // xchg GR8, GR8
                 (outs), (ins GR8:$src1, GR8:$src2),
                 "xchg{b}\t{$src2|$src1}, {$src1|$src2}", []>;
def XCHG16rr : I<0x87, MRMDestReg,                    // xchg GR16, GR16
                 (outs), (ins GR16:$src1, GR16:$src2),
                 "xchg{w}\t{$src2|$src1}, {$src1|$src2}", []>, OpSize;
def XCHG32rr : I<0x87, MRMDestReg,                    // xchg GR32, GR32
                 (outs), (ins GR32:$src1, GR32:$src2),
                 "xchg{l}\t{$src2|$src1}, {$src1|$src2}", []>;

def XCHG8mr  : I<0x86, MRMDestMem,
                 (outs), (ins i8mem:$src1, GR8:$src2),
                 "xchg{b}\t{$src2|$src1}, {$src1|$src2}", []>;
def XCHG16mr : I<0x87, MRMDestMem,
                 (outs), (ins i16mem:$src1, GR16:$src2),
                 "xchg{w}\t{$src2|$src1}, {$src1|$src2}", []>, OpSize;
def XCHG32mr : I<0x87, MRMDestMem,
                 (outs), (ins i32mem:$src1, GR32:$src2),
                 "xchg{l}\t{$src2|$src1}, {$src1|$src2}", []>;
def XCHG8rm  : I<0x86, MRMSrcMem,
                 (outs), (ins GR8:$src1, i8mem:$src2),
                 "xchg{b}\t{$src2|$src1}, {$src1|$src2}", []>;
def XCHG16rm : I<0x87, MRMSrcMem,
                 (outs), (ins GR16:$src1, i16mem:$src2),
                 "xchg{w}\t{$src2|$src1}, {$src1|$src2}", []>, OpSize;
def XCHG32rm : I<0x87, MRMSrcMem,
                 (outs), (ins GR32:$src1, i32mem:$src2),
                 "xchg{l}\t{$src2|$src1}, {$src1|$src2}", []>;

def LEA16r   : I<0x8D, MRMSrcMem,
                 (outs GR16:$dst), (ins i32mem:$src),
                 "lea{w}\t{$src|$dst}, {$dst|$src}", []>, OpSize;
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]>;

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

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

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

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

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

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

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

//===----------------------------------------------------------------------===//
//  Move Instructions...
//
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, $src}", []>;
let isReMaterializable = 1 in {
def MOV8ri  : Ii8 <0xB0, AddRegFrm, (outs GR8 :$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 isLoad = 1 in {
def MOV8rm  : I<0x8A, MRMSrcMem, (outs GR8 :$dst), (ins i8mem :$src),
                "mov{b}\t{$src, $dst|$dst, $src}",
                [(set GR8:$dst, (load addr:$src))]>;
def MOV16rm : I<0x8B, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src),
                "mov{w}\t{$src, $dst|$dst, $src}",
                [(set GR16:$dst, (load addr:$src))]>, OpSize;
def MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
                "mov{l}\t{$src, $dst|$dst, $src}",
                [(set GR32:$dst, (load 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
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:$src))]>,
             Imp<[AL],[AL,AH]>;               // AL,AH = AL*GR8
def MUL16r : I<0xF7, MRM4r, (outs),  (ins GR16:$src), "mul{w}\t$src", []>,
             Imp<[AX],[AX,DX]>, OpSize;    // AX,DX = AX*GR16
def MUL32r : I<0xF7, MRM4r, (outs),  (ins GR32:$src), "mul{l}\t$src", []>,
             Imp<[EAX],[EAX,EDX]>;         // EAX,EDX = EAX*GR32
def MUL8m  : I<0xF6, MRM4m, (outs), (ins i8mem :$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)))]>,
             Imp<[AL],[AL,AH]>;          // AL,AH = AL*[mem8]
def MUL16m : I<0xF7, MRM4m, (outs), (ins i16mem:$src),
               "mul{w}\t$src", []>, Imp<[AX],[AX,DX]>,
               OpSize; // AX,DX = AX*[mem16]
def MUL32m : I<0xF7, MRM4m, (outs), (ins i32mem:$src),
              "mul{l}\t$src", []>, Imp<[EAX],[EAX,EDX]>;// EAX,EDX = EAX*[mem32]

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

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

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


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

// Conditional moves
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))]>,
                  TB, OpSize;
def CMOVB16rm : I<0x42, MRMSrcMem,       // if <u, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovb\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_B))]>,
                  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))]>,
                   TB;
def CMOVB32rm : I<0x42, MRMSrcMem,       // if <u, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovb\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_B))]>,
                   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))]>,
                   TB, OpSize;
def CMOVAE16rm: I<0x43, MRMSrcMem,       // if >=u, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovae\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_AE))]>,
                   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))]>,
                   TB;
def CMOVAE32rm: I<0x43, MRMSrcMem,       // if >=u, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovae\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_AE))]>,
                   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))]>,
                   TB, OpSize;
def CMOVE16rm : I<0x44, MRMSrcMem,       // if ==, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmove\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_E))]>,
                   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))]>,
                   TB;
def CMOVE32rm : I<0x44, MRMSrcMem,       // if ==, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmove\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_E))]>,
                   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))]>,
                   TB, OpSize;
def CMOVNE16rm: I<0x45, MRMSrcMem,       // if !=, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovne\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_NE))]>,
                   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))]>,
                   TB;
def CMOVNE32rm: I<0x45, MRMSrcMem,       // if !=, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovne\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_NE))]>,
                   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))]>,
                   TB, OpSize;
def CMOVBE16rm: I<0x46, MRMSrcMem,       // if <=u, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovbe\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_BE))]>,
                   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))]>,
                   TB;
def CMOVBE32rm: I<0x46, MRMSrcMem,       // if <=u, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovbe\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_BE))]>,
                   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))]>,
                   TB, OpSize;
def CMOVA16rm : I<0x47, MRMSrcMem,       // if >u, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmova\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_A))]>,
                   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))]>,
                   TB;
def CMOVA32rm : I<0x47, MRMSrcMem,       // if >u, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmova\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_A))]>,
                   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))]>,
                   TB, OpSize;
def CMOVL16rm : I<0x4C, MRMSrcMem,       // if <s, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovl\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_L))]>,
                   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))]>,
                   TB;
def CMOVL32rm : I<0x4C, MRMSrcMem,       // if <s, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovl\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_L))]>,
                   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))]>,
                   TB, OpSize;
def CMOVGE16rm: I<0x4D, MRMSrcMem,       // if >=s, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovge\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_GE))]>,
                   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))]>,
                   TB;
def CMOVGE32rm: I<0x4D, MRMSrcMem,       // if >=s, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovge\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_GE))]>,
                   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))]>,
                   TB, OpSize;
def CMOVLE16rm: I<0x4E, MRMSrcMem,       // if <=s, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovle\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_LE))]>,
                   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))]>,
                   TB;
def CMOVLE32rm: I<0x4E, MRMSrcMem,       // if <=s, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovle\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_LE))]>,
                   TB;

def CMOVG16rr : I<0x4F, MRMSrcReg,       // if >s, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovg\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_G))]>,
                   TB, OpSize;
def CMOVG16rm : I<0x4F, MRMSrcMem,       // if >s, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovg\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_G))]>,
                   TB, OpSize;
def CMOVG32rr : I<0x4F, MRMSrcReg,       // if >s, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovg\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_G))]>,
                   TB;
def CMOVG32rm : I<0x4F, MRMSrcMem,       // if >s, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovg\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_G))]>,
                   TB;

def CMOVS16rr : I<0x48, MRMSrcReg,       // if signed, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovs\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_S))]>,
                  TB, OpSize;
def CMOVS16rm : I<0x48, MRMSrcMem,       // if signed, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovs\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_S))]>,
                  TB, OpSize;
def CMOVS32rr : I<0x48, MRMSrcReg,       // if signed, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovs\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_S))]>,
                  TB;
def CMOVS32rm : I<0x48, MRMSrcMem,       // if signed, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovs\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_S))]>,
                  TB;

def CMOVNS16rr: I<0x49, MRMSrcReg,       // if !signed, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovns\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_NS))]>,
                  TB, OpSize;
def CMOVNS16rm: I<0x49, MRMSrcMem,       // if !signed, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovns\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_NS))]>,
                  TB, OpSize;
def CMOVNS32rr: I<0x49, MRMSrcReg,       // if !signed, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovns\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_NS))]>,
                  TB;
def CMOVNS32rm: I<0x49, MRMSrcMem,       // if !signed, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovns\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_NS))]>,
                  TB;

def CMOVP16rr : I<0x4A, MRMSrcReg,       // if parity, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovp\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                   X86_COND_P))]>,
                  TB, OpSize;
def CMOVP16rm : I<0x4A, MRMSrcMem,       // if parity, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovp\t{$src2, $dst|$dst, $src2}",
                  [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                   X86_COND_P))]>,
                  TB, OpSize;
def CMOVP32rr : I<0x4A, MRMSrcReg,       // if parity, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovp\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                   X86_COND_P))]>,
                  TB;
def CMOVP32rm : I<0x4A, MRMSrcMem,       // if parity, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovp\t{$src2, $dst|$dst, $src2}",
                  [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                   X86_COND_P))]>,
                  TB;

def CMOVNP16rr : I<0x4B, MRMSrcReg,       // if !parity, GR16 = GR16
                  (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                  "cmovnp\t{$src2, $dst|$dst, $src2}",
                   [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
                                    X86_COND_NP))]>,
                  TB, OpSize;
def CMOVNP16rm : I<0x4B, MRMSrcMem,       // if !parity, GR16 = [mem16]
                  (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                  "cmovnp\t{$src2, $dst|$dst, $src2}",
                   [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
                                    X86_COND_NP))]>,
                  TB, OpSize;
def CMOVNP32rr : I<0x4B, MRMSrcReg,       // if !parity, GR32 = GR32
                  (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "cmovnp\t{$src2, $dst|$dst, $src2}",
                   [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
                                    X86_COND_NP))]>,
                  TB;
def CMOVNP32rm : I<0x4B, MRMSrcMem,       // if !parity, GR32 = [mem32]
                  (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                  "cmovnp\t{$src2, $dst|$dst, $src2}",
                   [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
                                    X86_COND_NP))]>,
                  TB;


// unary instructions
let CodeSize = 2 in {
def NEG8r  : I<0xF6, MRM3r, (outs GR8 :$dst), (ins GR8 :$src), "neg{b}\t$dst",
               [(set GR8:$dst, (ineg GR8:$src))]>;
def NEG16r : I<0xF7, MRM3r, (outs GR16:$dst), (ins GR16:$src), "neg{w}\t$dst",
               [(set GR16:$dst, (ineg GR16:$src))]>, OpSize;
def NEG32r : I<0xF7, MRM3r, (outs GR32:$dst), (ins GR32:$src), "neg{l}\t$dst",
               [(set GR32:$dst, (ineg GR32:$src))]>;
let isTwoAddress = 0 in {
  def NEG8m  : I<0xF6, MRM3m, (outs), (ins i8mem :$dst), "neg{b}\t$dst",
                 [(store (ineg (loadi8 addr:$dst)), addr:$dst)]>;
  def NEG16m : I<0xF7, MRM3m, (outs), (ins i16mem:$dst), "neg{w}\t$dst",
                 [(store (ineg (loadi16 addr:$dst)), addr:$dst)]>, OpSize;
  def NEG32m : I<0xF7, MRM3m, (outs), (ins i32mem:$dst), "neg{l}\t$dst",
                 [(store (ineg (loadi32 addr:$dst)), addr:$dst)]>;

}

def NOT8r  : I<0xF6, MRM2r, (outs GR8 :$dst), (ins GR8 :$src), "not{b}\t$dst",
               [(set GR8:$dst, (not GR8:$src))]>;
def NOT16r : I<0xF7, MRM2r, (outs GR16:$dst), (ins GR16:$src), "not{w}\t$dst",
               [(set GR16:$dst, (not GR16:$src))]>, OpSize;
def NOT32r : I<0xF7, MRM2r, (outs GR32:$dst), (ins GR32:$src), "not{l}\t$dst",
               [(set GR32:$dst, (not GR32:$src))]>;
let isTwoAddress = 0 in {
  def NOT8m  : I<0xF6, MRM2m, (outs), (ins i8mem :$dst), "not{b}\t$dst",