X86InstrInfo.td

                   [(store (sub (load addr:$dst), GR32:$src2), addr:$dst)]>;
  def SUB8mi   : Ii8<0x80, MRM5m, (outs), (ins i8mem :$dst, i8imm:$src2), 
                     "sub{b}\t{$src2, $dst|$dst, $src2}",
                   [(store (sub (loadi8 addr:$dst), imm:$src2), addr:$dst)]>;
  def SUB16mi  : Ii16<0x81, MRM5m, (outs), (ins i16mem:$dst, i16imm:$src2), 
                      "sub{w}\t{$src2, $dst|$dst, $src2}",
                  [(store (sub (loadi16 addr:$dst), imm:$src2), addr:$dst)]>,
                 OpSize;
  def SUB32mi  : Ii32<0x81, MRM5m, (outs), (ins i32mem:$dst, i32imm:$src2), 
                      "sub{l}\t{$src2, $dst|$dst, $src2}",
                  [(store (sub (loadi32 addr:$dst), imm:$src2), addr:$dst)]>;
  def SUB16mi8 : Ii8<0x83, MRM5m, (outs), (ins i16mem:$dst, i16i8imm :$src2), 
                     "sub{w}\t{$src2, $dst|$dst, $src2}",
                [(store (sub (load addr:$dst), i16immSExt8:$src2), addr:$dst)]>,
                 OpSize;
  def SUB32mi8 : Ii8<0x83, MRM5m, (outs), (ins i32mem:$dst, i32i8imm :$src2), 
                     "sub{l}\t{$src2, $dst|$dst, $src2}",
                [(store (sub (load addr:$dst), i32immSExt8:$src2), addr:$dst)]>;
}

let Uses = [EFLAGS] in {
def SBB32rr    : I<0x19, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                  "sbb{l}\t{$src2, $dst|$dst, $src2}",
                 [(set GR32:$dst, (sube GR32:$src1, GR32:$src2))]>;

let isTwoAddress = 0 in {
  def SBB32mr  : I<0x19, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2), 
                   "sbb{l}\t{$src2, $dst|$dst, $src2}",
                   [(store (sube (load addr:$dst), GR32:$src2), addr:$dst)]>;
  def SBB8mi  : Ii32<0x80, MRM3m, (outs), (ins i8mem:$dst, i8imm:$src2), 
                      "sbb{b}\t{$src2, $dst|$dst, $src2}",
                   [(store (sube (loadi8 addr:$dst), imm:$src2), addr:$dst)]>;
  def SBB32mi  : Ii32<0x81, MRM3m, (outs), (ins i32mem:$dst, i32imm:$src2), 
                      "sbb{l}\t{$src2, $dst|$dst, $src2}",
                  [(store (sube (loadi32 addr:$dst), imm:$src2), addr:$dst)]>;
  def SBB32mi8 : Ii8<0x83, MRM3m, (outs), (ins i32mem:$dst, i32i8imm :$src2), 
                     "sbb{l}\t{$src2, $dst|$dst, $src2}",
               [(store (sube (load addr:$dst), i32immSExt8:$src2), addr:$dst)]>;
}
def SBB32rm  : I<0x1B, MRMSrcMem, (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                    "sbb{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (sube GR32:$src1, (load addr:$src2)))]>;
def SBB32ri  : Ii32<0x81, MRM3r, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
                    "sbb{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (sube GR32:$src1, imm:$src2))]>;
def SBB32ri8 : Ii8<0x83, MRM3r, (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
                   "sbb{l}\t{$src2, $dst|$dst, $src2}",
                   [(set GR32:$dst, (sube GR32:$src1, i32immSExt8:$src2))]>;
} // Uses = [EFLAGS]
} // Defs = [EFLAGS]

let Defs = [EFLAGS] in {
let isCommutable = 1 in {  // X = IMUL Y, Z --> X = IMUL Z, Y
def IMUL16rr : I<0xAF, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
                 "imul{w}\t{$src2, $dst|$dst, $src2}",
                 [(set GR16:$dst, (mul GR16:$src1, GR16:$src2))]>, TB, OpSize;
def IMUL32rr : I<0xAF, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                 "imul{l}\t{$src2, $dst|$dst, $src2}",
                 [(set GR32:$dst, (mul GR32:$src1, GR32:$src2))]>, TB;
}
def IMUL16rm : I<0xAF, MRMSrcMem, (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
                 "imul{w}\t{$src2, $dst|$dst, $src2}",
                 [(set GR16:$dst, (mul GR16:$src1, (load addr:$src2)))]>,
                 TB, OpSize;
def IMUL32rm : I<0xAF, MRMSrcMem, (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
                 "imul{l}\t{$src2, $dst|$dst, $src2}",
                 [(set GR32:$dst, (mul GR32:$src1, (load addr:$src2)))]>, TB;
} // Defs = [EFLAGS]
} // end Two Address instructions

// Suprisingly enough, these are not two address instructions!
let Defs = [EFLAGS] in {
def IMUL16rri  : Ii16<0x69, MRMSrcReg,                      // GR16 = GR16*I16
                      (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2),
                      "imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                      [(set GR16:$dst, (mul GR16:$src1, imm:$src2))]>, OpSize;
def IMUL32rri  : Ii32<0x69, MRMSrcReg,                      // GR32 = GR32*I32
                      (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
                      "imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                      [(set GR32:$dst, (mul GR32:$src1, imm:$src2))]>;
def IMUL16rri8 : Ii8<0x6B, MRMSrcReg,                       // GR16 = GR16*I8
                     (outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2),
                     "imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                     [(set GR16:$dst, (mul GR16:$src1, i16immSExt8:$src2))]>,
                     OpSize;
def IMUL32rri8 : Ii8<0x6B, MRMSrcReg,                       // GR32 = GR32*I8
                     (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
                     "imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                     [(set GR32:$dst, (mul GR32:$src1, i32immSExt8:$src2))]>;

def IMUL16rmi  : Ii16<0x69, MRMSrcMem,                      // GR16 = [mem16]*I16
                      (outs GR16:$dst), (ins i16mem:$src1, i16imm:$src2),
                      "imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                      [(set GR16:$dst, (mul (load addr:$src1), imm:$src2))]>,
                      OpSize;
def IMUL32rmi  : Ii32<0x69, MRMSrcMem,                      // GR32 = [mem32]*I32
                      (outs GR32:$dst), (ins i32mem:$src1, i32imm:$src2),
                      "imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                      [(set GR32:$dst, (mul (load addr:$src1), imm:$src2))]>;
def IMUL16rmi8 : Ii8<0x6B, MRMSrcMem,                       // GR16 = [mem16]*I8
                     (outs GR16:$dst), (ins i16mem:$src1, i16i8imm :$src2),
                     "imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                  [(set GR16:$dst, (mul (load addr:$src1), i16immSExt8:$src2))]>,
                     OpSize;
def IMUL32rmi8 : Ii8<0x6B, MRMSrcMem,                       // GR32 = [mem32]*I8
                     (outs GR32:$dst), (ins i32mem:$src1, i32i8imm: $src2),
                     "imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                  [(set GR32:$dst, (mul (load addr:$src1), i32immSExt8:$src2))]>;
} // Defs = [EFLAGS]

//===----------------------------------------------------------------------===//
// Test instructions are just like AND, except they don't generate a result.
//
let Defs = [EFLAGS] in {
let isCommutable = 1 in {   // TEST X, Y   --> TEST Y, X
def TEST8rr  : I<0x84, MRMDestReg, (outs),  (ins GR8:$src1, GR8:$src2),
                     "test{b}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and_su GR8:$src1, GR8:$src2), 0),
                      (implicit EFLAGS)]>;
def TEST16rr : I<0x85, MRMDestReg, (outs),  (ins GR16:$src1, GR16:$src2),
                     "test{w}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and_su GR16:$src1, GR16:$src2), 0),
                      (implicit EFLAGS)]>,
                 OpSize;
def TEST32rr : I<0x85, MRMDestReg, (outs),  (ins GR32:$src1, GR32:$src2),
                     "test{l}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and_su GR32:$src1, GR32:$src2), 0),
                      (implicit EFLAGS)]>;
}

def TEST8rm  : I<0x84, MRMSrcMem, (outs),  (ins GR8 :$src1, i8mem :$src2),
                     "test{b}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and GR8:$src1, (loadi8 addr:$src2)), 0),
                      (implicit EFLAGS)]>;
def TEST16rm : I<0x85, MRMSrcMem, (outs),  (ins GR16:$src1, i16mem:$src2),
                     "test{w}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and GR16:$src1, (loadi16 addr:$src2)), 0),
                      (implicit EFLAGS)]>, OpSize;
def TEST32rm : I<0x85, MRMSrcMem, (outs),  (ins GR32:$src1, i32mem:$src2),
                     "test{l}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and GR32:$src1, (loadi32 addr:$src2)), 0),
                      (implicit EFLAGS)]>;

def TEST8ri  : Ii8 <0xF6, MRM0r,                     // flags = GR8  & imm8
                    (outs),  (ins GR8:$src1, i8imm:$src2),
                    "test{b}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (and_su GR8:$src1, imm:$src2), 0),
                     (implicit EFLAGS)]>;
def TEST16ri : Ii16<0xF7, MRM0r,                     // flags = GR16 & imm16
                    (outs),  (ins GR16:$src1, i16imm:$src2),
                    "test{w}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (and_su GR16:$src1, imm:$src2), 0),
                     (implicit EFLAGS)]>, OpSize;
def TEST32ri : Ii32<0xF7, MRM0r,                     // flags = GR32 & imm32
                    (outs),  (ins GR32:$src1, i32imm:$src2),
                    "test{l}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (and_su GR32:$src1, imm:$src2), 0),
                     (implicit EFLAGS)]>;

def TEST8mi  : Ii8 <0xF6, MRM0m,                   // flags = [mem8]  & imm8
                    (outs), (ins i8mem:$src1, i8imm:$src2),
                    "test{b}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (and (loadi8 addr:$src1), imm:$src2), 0),
                     (implicit EFLAGS)]>;
def TEST16mi : Ii16<0xF7, MRM0m,                   // flags = [mem16] & imm16
                    (outs), (ins i16mem:$src1, i16imm:$src2),
                    "test{w}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (and (loadi16 addr:$src1), imm:$src2), 0),
                     (implicit EFLAGS)]>, OpSize;
def TEST32mi : Ii32<0xF7, MRM0m,                   // flags = [mem32] & imm32
                    (outs), (ins i32mem:$src1, i32imm:$src2),
                    "test{l}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (and (loadi32 addr:$src1), imm:$src2), 0),
                     (implicit EFLAGS)]>;
} // Defs = [EFLAGS]


// Condition code ops, incl. set if equal/not equal/...
let Defs = [EFLAGS], Uses = [AH], neverHasSideEffects = 1 in
def SAHF     : I<0x9E, RawFrm, (outs),  (ins), "sahf", []>;  // flags = AH
let Defs = [AH], Uses = [EFLAGS], neverHasSideEffects = 1 in
def LAHF     : I<0x9F, RawFrm, (outs),  (ins), "lahf", []>;  // AH = flags

let Uses = [EFLAGS] in {
def SETEr    : I<0x94, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "sete\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_E, EFLAGS))]>,
               TB;                        // GR8 = ==
def SETEm    : I<0x94, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "sete\t$dst",
                 [(store (X86setcc X86_COND_E, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = ==
def SETNEr   : I<0x95, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setne\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_NE, EFLAGS))]>,
               TB;                        // GR8 = !=
def SETNEm   : I<0x95, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setne\t$dst",
                 [(store (X86setcc X86_COND_NE, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = !=
def SETLr    : I<0x9C, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setl\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_L, EFLAGS))]>,
               TB;                        // GR8 = <  signed
def SETLm    : I<0x9C, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setl\t$dst",
                 [(store (X86setcc X86_COND_L, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = <  signed
def SETGEr   : I<0x9D, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setge\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_GE, EFLAGS))]>,
               TB;                        // GR8 = >= signed
def SETGEm   : I<0x9D, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setge\t$dst",
                 [(store (X86setcc X86_COND_GE, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = >= signed
def SETLEr   : I<0x9E, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setle\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_LE, EFLAGS))]>,
               TB;                        // GR8 = <= signed
def SETLEm   : I<0x9E, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setle\t$dst",
                 [(store (X86setcc X86_COND_LE, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = <= signed
def SETGr    : I<0x9F, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setg\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_G, EFLAGS))]>,
               TB;                        // GR8 = >  signed
def SETGm    : I<0x9F, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setg\t$dst",
                 [(store (X86setcc X86_COND_G, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = >  signed

def SETBr    : I<0x92, MRM0r,
                 (outs GR8   :$dst), (ins),
                 "setb\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_B, EFLAGS))]>,
               TB;                        // GR8 = <  unsign
def SETBm    : I<0x92, MRM0m,
                 (outs), (ins i8mem:$dst),
                 "setb\t$dst",
                 [(store (X86setcc X86_COND_B, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = <  unsign
def SETAEr   : I<0x93, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setae\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_AE, EFLAGS))]>,
               TB;                        // GR8 = >= unsign
def SETAEm   : I<0x93, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setae\t$dst",
                 [(store (X86setcc X86_COND_AE, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = >= unsign
def SETBEr   : I<0x96, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setbe\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_BE, EFLAGS))]>,
               TB;                        // GR8 = <= unsign
def SETBEm   : I<0x96, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setbe\t$dst",
                 [(store (X86setcc X86_COND_BE, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = <= unsign
def SETAr    : I<0x97, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "seta\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_A, EFLAGS))]>,
               TB;                        // GR8 = >  signed
def SETAm    : I<0x97, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "seta\t$dst",
                 [(store (X86setcc X86_COND_A, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = >  signed

def SETSr    : I<0x98, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "sets\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_S, EFLAGS))]>,
               TB;                        // GR8 = <sign bit>
def SETSm    : I<0x98, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "sets\t$dst",
                 [(store (X86setcc X86_COND_S, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = <sign bit>
def SETNSr   : I<0x99, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setns\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_NS, EFLAGS))]>,
               TB;                        // GR8 = !<sign bit>
def SETNSm   : I<0x99, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setns\t$dst",
                 [(store (X86setcc X86_COND_NS, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = !<sign bit>
def SETPr    : I<0x9A, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setp\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_P, EFLAGS))]>,
               TB;                        // GR8 = parity
def SETPm    : I<0x9A, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setp\t$dst",
                 [(store (X86setcc X86_COND_P, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = parity
def SETNPr   : I<0x9B, MRM0r, 
                 (outs GR8   :$dst), (ins),
                 "setnp\t$dst",
                 [(set GR8:$dst, (X86setcc X86_COND_NP, EFLAGS))]>,
               TB;                        // GR8 = not parity
def SETNPm   : I<0x9B, MRM0m, 
                 (outs), (ins i8mem:$dst),
                 "setnp\t$dst",
                 [(store (X86setcc X86_COND_NP, EFLAGS), addr:$dst)]>,
               TB;                        // [mem8] = not parity
} // Uses = [EFLAGS]


// Integer comparisons
let Defs = [EFLAGS] in {
def CMP8rr  : I<0x38, MRMDestReg,
                (outs), (ins GR8 :$src1, GR8 :$src2),
                "cmp{b}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp GR8:$src1, GR8:$src2), (implicit EFLAGS)]>;
def CMP16rr : I<0x39, MRMDestReg,
                (outs), (ins GR16:$src1, GR16:$src2),
                "cmp{w}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp GR16:$src1, GR16:$src2), (implicit EFLAGS)]>, OpSize;
def CMP32rr : I<0x39, MRMDestReg,
                (outs), (ins GR32:$src1, GR32:$src2),
                "cmp{l}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp GR32:$src1, GR32:$src2), (implicit EFLAGS)]>;
def CMP8mr  : I<0x38, MRMDestMem,
                (outs), (ins i8mem :$src1, GR8 :$src2),
                "cmp{b}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp (loadi8 addr:$src1), GR8:$src2),
                 (implicit EFLAGS)]>;
def CMP16mr : I<0x39, MRMDestMem,
                (outs), (ins i16mem:$src1, GR16:$src2),
                "cmp{w}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp (loadi16 addr:$src1), GR16:$src2),
                 (implicit EFLAGS)]>, OpSize;
def CMP32mr : I<0x39, MRMDestMem,
                (outs), (ins i32mem:$src1, GR32:$src2),
                "cmp{l}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp (loadi32 addr:$src1), GR32:$src2),
                 (implicit EFLAGS)]>;
def CMP8rm  : I<0x3A, MRMSrcMem,
                (outs), (ins GR8 :$src1, i8mem :$src2),
                "cmp{b}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp GR8:$src1, (loadi8 addr:$src2)),
                 (implicit EFLAGS)]>;
def CMP16rm : I<0x3B, MRMSrcMem,
                (outs), (ins GR16:$src1, i16mem:$src2),
                "cmp{w}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp GR16:$src1, (loadi16 addr:$src2)),
                 (implicit EFLAGS)]>, OpSize;
def CMP32rm : I<0x3B, MRMSrcMem,
                (outs), (ins GR32:$src1, i32mem:$src2),
                "cmp{l}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp GR32:$src1, (loadi32 addr:$src2)),
                 (implicit EFLAGS)]>;
def CMP8ri  : Ii8<0x80, MRM7r,
                  (outs), (ins GR8:$src1, i8imm:$src2),
                  "cmp{b}\t{$src2, $src1|$src1, $src2}",
                  [(X86cmp GR8:$src1, imm:$src2), (implicit EFLAGS)]>;
def CMP16ri : Ii16<0x81, MRM7r,
                   (outs), (ins GR16:$src1, i16imm:$src2),
                   "cmp{w}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp GR16:$src1, imm:$src2),
                    (implicit EFLAGS)]>, OpSize;
def CMP32ri : Ii32<0x81, MRM7r,
                   (outs), (ins GR32:$src1, i32imm:$src2),
                   "cmp{l}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp GR32:$src1, imm:$src2), (implicit EFLAGS)]>;
def CMP8mi  : Ii8 <0x80, MRM7m,
                   (outs), (ins i8mem :$src1, i8imm :$src2),
                   "cmp{b}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp (loadi8 addr:$src1), imm:$src2),
                    (implicit EFLAGS)]>;
def CMP16mi : Ii16<0x81, MRM7m,
                   (outs), (ins i16mem:$src1, i16imm:$src2),
                   "cmp{w}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp (loadi16 addr:$src1), imm:$src2),
                    (implicit EFLAGS)]>, OpSize;
def CMP32mi : Ii32<0x81, MRM7m,
                   (outs), (ins i32mem:$src1, i32imm:$src2),
                   "cmp{l}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp (loadi32 addr:$src1), imm:$src2),
                    (implicit EFLAGS)]>;
def CMP16ri8 : Ii8<0x83, MRM7r,
                   (outs), (ins GR16:$src1, i16i8imm:$src2),
                   "cmp{w}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp GR16:$src1, i16immSExt8:$src2),
                    (implicit EFLAGS)]>, OpSize;
def CMP16mi8 : Ii8<0x83, MRM7m,
                   (outs), (ins i16mem:$src1, i16i8imm:$src2),
                   "cmp{w}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp (loadi16 addr:$src1), i16immSExt8:$src2),
                    (implicit EFLAGS)]>, OpSize;
def CMP32mi8 : Ii8<0x83, MRM7m,
                   (outs), (ins i32mem:$src1, i32i8imm:$src2),
                   "cmp{l}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp (loadi32 addr:$src1), i32immSExt8:$src2),
                    (implicit EFLAGS)]>;
def CMP32ri8 : Ii8<0x83, MRM7r,
                   (outs), (ins GR32:$src1, i32i8imm:$src2),
                   "cmp{l}\t{$src2, $src1|$src1, $src2}",
                   [(X86cmp GR32:$src1, i32immSExt8:$src2),
                    (implicit EFLAGS)]>;
} // Defs = [EFLAGS]

// Sign/Zero extenders
// Use movsbl intead of movsbw; we don't care about the high 16 bits
// of the register here. This has a smaller encoding and avoids a
// partial-register update.
def MOVSX16rr8 : I<0xBE, MRMSrcReg, (outs GR16:$dst), (ins GR8 :$src),
                   "movs{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR16:$dst, (sext GR8:$src))]>, TB;
def MOVSX16rm8 : I<0xBE, MRMSrcMem, (outs GR16:$dst), (ins i8mem :$src),
                   "movs{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR16:$dst, (sextloadi16i8 addr:$src))]>, TB;
def MOVSX32rr8 : I<0xBE, MRMSrcReg, (outs GR32:$dst), (ins GR8 :$src),
                   "movs{bl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (sext GR8:$src))]>, TB;
def MOVSX32rm8 : I<0xBE, MRMSrcMem, (outs GR32:$dst), (ins i8mem :$src),
                   "movs{bl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (sextloadi32i8 addr:$src))]>, TB;
def MOVSX32rr16: I<0xBF, MRMSrcReg, (outs GR32:$dst), (ins GR16:$src),
                   "movs{wl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (sext GR16:$src))]>, TB;
def MOVSX32rm16: I<0xBF, MRMSrcMem, (outs GR32:$dst), (ins i16mem:$src),
                   "movs{wl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (sextloadi32i16 addr:$src))]>, TB;

// Use movzbl intead of movzbw; we don't care about the high 16 bits
// of the register here. This has a smaller encoding and avoids a
// partial-register update.
def MOVZX16rr8 : I<0xB6, MRMSrcReg, (outs GR16:$dst), (ins GR8 :$src),
                   "movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR16:$dst, (zext GR8:$src))]>, TB;
def MOVZX16rm8 : I<0xB6, MRMSrcMem, (outs GR16:$dst), (ins i8mem :$src),
                   "movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR16:$dst, (zextloadi16i8 addr:$src))]>, TB;
def MOVZX32rr8 : I<0xB6, MRMSrcReg, (outs GR32:$dst), (ins GR8 :$src),
                   "movz{bl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (zext GR8:$src))]>, TB;
def MOVZX32rm8 : I<0xB6, MRMSrcMem, (outs GR32:$dst), (ins i8mem :$src),
                   "movz{bl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (zextloadi32i8 addr:$src))]>, TB;
def MOVZX32rr16: I<0xB7, MRMSrcReg, (outs GR32:$dst), (ins GR16:$src),
                   "movz{wl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (zext GR16:$src))]>, TB;
def MOVZX32rm16: I<0xB7, MRMSrcMem, (outs GR32:$dst), (ins i16mem:$src),
                   "movz{wl|x}\t{$src, $dst|$dst, $src}",
                   [(set GR32:$dst, (zextloadi32i16 addr:$src))]>, TB;

let neverHasSideEffects = 1 in {
  let Defs = [AX], Uses = [AL] in
  def CBW : I<0x98, RawFrm, (outs), (ins),
              "{cbtw|cbw}", []>, OpSize;   // AX = signext(AL)
  let Defs = [EAX], Uses = [AX] in
  def CWDE : I<0x98, RawFrm, (outs), (ins),
              "{cwtl|cwde}", []>;   // EAX = signext(AX)

  let Defs = [AX,DX], Uses = [AX] in
  def CWD : I<0x99, RawFrm, (outs), (ins),
              "{cwtd|cwd}", []>, OpSize; // DX:AX = signext(AX)
  let Defs = [EAX,EDX], Uses = [EAX] in
  def CDQ : I<0x99, RawFrm, (outs), (ins),
              "{cltd|cdq}", []>; // EDX:EAX = signext(EAX)
}

//===----------------------------------------------------------------------===//
// Alias Instructions
//===----------------------------------------------------------------------===//

// Alias instructions that map movr0 to xor.
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
let Defs = [EFLAGS], isReMaterializable = 1, isAsCheapAsAMove = 1 in {
def MOV8r0   : I<0x30, MRMInitReg, (outs GR8 :$dst), (ins),
                 "xor{b}\t$dst, $dst",
                 [(set GR8:$dst, 0)]>;
// Use xorl instead of xorw since we don't care about the high 16 bits,
// it's smaller, and it avoids a partial-register update.
def MOV16r0  : I<0x31, MRMInitReg,  (outs GR16:$dst), (ins),
                 "xor{l}\t${dst:subreg32}, ${dst:subreg32}",
                 [(set GR16:$dst, 0)]>;
def MOV32r0  : I<0x31, MRMInitReg,  (outs GR32:$dst), (ins),
                 "xor{l}\t$dst, $dst",
                 [(set GR32:$dst, 0)]>;
}

// Basic operations on GR16 / GR32 subclasses GR16_ and GR32_ which contains only
// those registers that have GR8 sub-registers (i.e. AX - DX, EAX - EDX).
let neverHasSideEffects = 1 in {
def MOV16to16_ : I<0x89, MRMDestReg, (outs GR16_:$dst), (ins GR16:$src),
                "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
def MOV32to32_ : I<0x89, MRMDestReg, (outs GR32_:$dst), (ins GR32:$src),
                "mov{l}\t{$src, $dst|$dst, $src}", []>;
                
def MOV16_rr : I<0x89, MRMDestReg, (outs GR16_:$dst), (ins GR16_:$src),
                "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
def MOV32_rr : I<0x89, MRMDestReg, (outs GR32_:$dst), (ins GR32_:$src),
                "mov{l}\t{$src, $dst|$dst, $src}", []>;
} // neverHasSideEffects

let isSimpleLoad = 1, mayLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
def MOV16_rm : I<0x8B, MRMSrcMem, (outs GR16_:$dst), (ins i16mem:$src),
                "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
def MOV32_rm : I<0x8B, MRMSrcMem, (outs GR32_:$dst), (ins i32mem:$src),
                "mov{l}\t{$src, $dst|$dst, $src}", []>;
}
let mayStore = 1, neverHasSideEffects = 1 in {
def MOV16_mr : I<0x89, MRMDestMem, (outs), (ins i16mem:$dst, GR16_:$src),
                "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
def MOV32_mr : I<0x89, MRMDestMem, (outs), (ins i32mem:$dst, GR32_:$src),
                "mov{l}\t{$src, $dst|$dst, $src}", []>;
}

//===----------------------------------------------------------------------===//
// Thread Local Storage Instructions
//

let Uses = [EBX] in
def TLS_addr32 : I<0, Pseudo, (outs GR32:$dst), (ins i32imm:$sym),
                  "leal\t${sym:mem}(,%ebx,1), $dst",
                  [(set GR32:$dst, (X86tlsaddr tglobaltlsaddr:$sym))]>;

let AddedComplexity = 10 in
def TLS_gs_rr  : I<0, Pseudo, (outs GR32:$dst), (ins GR32:$src),
                  "movl\t%gs:($src), $dst",
                  [(set GR32:$dst, (load (add X86TLStp, GR32:$src)))]>;

let AddedComplexity = 15 in
def TLS_gs_ri : I<0, Pseudo, (outs GR32:$dst), (ins i32imm:$src),
                  "movl\t%gs:${src:mem}, $dst",
                  [(set GR32:$dst,
                    (load (add X86TLStp, (X86Wrapper tglobaltlsaddr:$src))))]>;

def TLS_tp : I<0, Pseudo, (outs GR32:$dst), (ins),
               "movl\t%gs:0, $dst",
               [(set GR32:$dst, X86TLStp)]>;

//===----------------------------------------------------------------------===//
// DWARF Pseudo Instructions
//

def DWARF_LOC   : I<0, Pseudo, (outs),
                    (ins i32imm:$line, i32imm:$col, i32imm:$file),
                    ".loc\t${file:debug} ${line:debug} ${col:debug}",
                    [(dwarf_loc (i32 imm:$line), (i32 imm:$col),
                      (i32 imm:$file))]>;

//===----------------------------------------------------------------------===//
// EH Pseudo Instructions
//
let isTerminator = 1, isReturn = 1, isBarrier = 1,
    hasCtrlDep = 1 in {
def EH_RETURN   : I<0xC3, RawFrm, (outs), (ins GR32:$addr),
                    "ret\t#eh_return, addr: $addr",
                    [(X86ehret GR32:$addr)]>;

}

//===----------------------------------------------------------------------===//
// Atomic support
//

// Atomic swap. These are just normal xchg instructions. But since a memory
// operand is referenced, the atomicity is ensured.
let Constraints = "$val = $dst" in {
def XCHG32rm : I<0x87, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$ptr, GR32:$val),
               "xchg{l}\t{$val, $ptr|$ptr, $val}", 
               [(set GR32:$dst, (atomic_swap_32 addr:$ptr, GR32:$val))]>;
def XCHG16rm : I<0x87, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$ptr, GR16:$val),
               "xchg{w}\t{$val, $ptr|$ptr, $val}", 
               [(set GR16:$dst, (atomic_swap_16 addr:$ptr, GR16:$val))]>, 
                OpSize;
def XCHG8rm  : I<0x86, MRMSrcMem, (outs GR8:$dst), (ins i8mem:$ptr, GR8:$val),
               "xchg{b}\t{$val, $ptr|$ptr, $val}", 
               [(set GR8:$dst, (atomic_swap_8 addr:$ptr, GR8:$val))]>;
}

// Atomic compare and swap.
let Defs = [EAX, EFLAGS], Uses = [EAX] in {
def LCMPXCHG32 : I<0xB1, MRMDestMem, (outs), (ins i32mem:$ptr, GR32:$swap),
               "lock\n\tcmpxchg{l}\t{$swap, $ptr|$ptr, $swap}",
               [(X86cas addr:$ptr, GR32:$swap, 4)]>, TB, LOCK;
}
let Defs = [EAX, EBX, ECX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX] in {
def LCMPXCHG8B : I<0xC7, MRM1m, (outs), (ins i32mem:$ptr),
               "lock\n\tcmpxchg8b\t$ptr",
               [(X86cas8 addr:$ptr)]>, TB, LOCK;
}

let Defs = [AX, EFLAGS], Uses = [AX] in {
def LCMPXCHG16 : I<0xB1, MRMDestMem, (outs), (ins i16mem:$ptr, GR16:$swap),
               "lock\n\tcmpxchg{w}\t{$swap, $ptr|$ptr, $swap}",
               [(X86cas addr:$ptr, GR16:$swap, 2)]>, TB, OpSize, LOCK;
}
let Defs = [AL, EFLAGS], Uses = [AL] in {
def LCMPXCHG8 : I<0xB0, MRMDestMem, (outs), (ins i8mem:$ptr, GR8:$swap),
               "lock\n\tcmpxchg{b}\t{$swap, $ptr|$ptr, $swap}",
               [(X86cas addr:$ptr, GR8:$swap, 1)]>, TB, LOCK;
}

// Atomic exchange and add
let Constraints = "$val = $dst", Defs = [EFLAGS] in {
def LXADD32 : I<0xC1, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$ptr, GR32:$val),
               "lock\n\txadd{l}\t{$val, $ptr|$ptr, $val}", 
               [(set GR32:$dst, (atomic_load_add_32 addr:$ptr, GR32:$val))]>,
                TB, LOCK;
def LXADD16 : I<0xC1, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$ptr, GR16:$val),
               "lock\n\txadd{w}\t{$val, $ptr|$ptr, $val}", 
               [(set GR16:$dst, (atomic_load_add_16 addr:$ptr, GR16:$val))]>,
                TB, OpSize, LOCK;
def LXADD8  : I<0xC0, MRMSrcMem, (outs GR8:$dst), (ins i8mem:$ptr, GR8:$val),
               "lock\n\txadd{b}\t{$val, $ptr|$ptr, $val}", 
               [(set GR8:$dst, (atomic_load_add_8 addr:$ptr, GR8:$val))]>,
                TB, LOCK;
}

// Atomic exchange, and, or, xor
let Constraints = "$val = $dst", Defs = [EFLAGS],
                  usesCustomDAGSchedInserter = 1 in {
def ATOMAND32 : I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMAND32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_and_32 addr:$ptr, GR32:$val))]>;
def ATOMOR32 : I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMOR32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_or_32 addr:$ptr, GR32:$val))]>;
def ATOMXOR32 : I<0, Pseudo,(outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMXOR32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_xor_32 addr:$ptr, GR32:$val))]>;
def ATOMNAND32 : I<0, Pseudo,(outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMNAND32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_nand_32 addr:$ptr, GR32:$val))]>;
def ATOMMIN32: I<0, Pseudo, (outs GR32:$dst), (ins i32mem:$ptr, GR32:$val),
               "#ATOMMIN32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_min_32 addr:$ptr, GR32:$val))]>;
def ATOMMAX32: I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMMAX32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_max_32 addr:$ptr, GR32:$val))]>;
def ATOMUMIN32: I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMUMIN32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_umin_32 addr:$ptr, GR32:$val))]>;
def ATOMUMAX32: I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
               "#ATOMUMAX32 PSUEDO!", 
               [(set GR32:$dst, (atomic_load_umax_32 addr:$ptr, GR32:$val))]>;

def ATOMAND16 : I<0, Pseudo, (outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMAND16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_and_16 addr:$ptr, GR16:$val))]>;
def ATOMOR16 : I<0, Pseudo, (outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMOR16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_or_16 addr:$ptr, GR16:$val))]>;
def ATOMXOR16 : I<0, Pseudo,(outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMXOR16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_xor_16 addr:$ptr, GR16:$val))]>;
def ATOMNAND16 : I<0, Pseudo,(outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMNAND16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_nand_16 addr:$ptr, GR16:$val))]>;
def ATOMMIN16: I<0, Pseudo, (outs GR16:$dst), (ins i16mem:$ptr, GR16:$val),
               "#ATOMMIN16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_min_16 addr:$ptr, GR16:$val))]>;
def ATOMMAX16: I<0, Pseudo, (outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMMAX16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_max_16 addr:$ptr, GR16:$val))]>;
def ATOMUMIN16: I<0, Pseudo, (outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMUMIN16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_umin_16 addr:$ptr, GR16:$val))]>;
def ATOMUMAX16: I<0, Pseudo, (outs GR16:$dst),(ins i16mem:$ptr, GR16:$val),
               "#ATOMUMAX16 PSUEDO!", 
               [(set GR16:$dst, (atomic_load_umax_16 addr:$ptr, GR16:$val))]>;

def ATOMAND8 : I<0, Pseudo, (outs GR8:$dst),(ins i8mem:$ptr, GR8:$val),
               "#ATOMAND8 PSUEDO!", 
               [(set GR8:$dst, (atomic_load_and_8 addr:$ptr, GR8:$val))]>;
def ATOMOR8 : I<0, Pseudo, (outs GR8:$dst),(ins i8mem:$ptr, GR8:$val),
               "#ATOMOR8 PSUEDO!", 
               [(set GR8:$dst, (atomic_load_or_8 addr:$ptr, GR8:$val))]>;
def ATOMXOR8 : I<0, Pseudo,(outs GR8:$dst),(ins i8mem:$ptr, GR8:$val),
               "#ATOMXOR8 PSUEDO!", 
               [(set GR8:$dst, (atomic_load_xor_8 addr:$ptr, GR8:$val))]>;
def ATOMNAND8 : I<0, Pseudo,(outs GR8:$dst),(ins i8mem:$ptr, GR8:$val),
               "#ATOMNAND8 PSUEDO!", 
               [(set GR8:$dst, (atomic_load_nand_8 addr:$ptr, GR8:$val))]>;
}

//===----------------------------------------------------------------------===//
// Non-Instruction Patterns
//===----------------------------------------------------------------------===//

// ConstantPool GlobalAddress, Symbol, and JumpTable
def : Pat<(i32 (X86Wrapper tconstpool  :$dst)), (MOV32ri tconstpool  :$dst)>;
def : Pat<(i32 (X86Wrapper tjumptable  :$dst)), (MOV32ri tjumptable  :$dst)>;
def : Pat<(i32 (X86Wrapper tglobaltlsaddr:$dst)),(MOV32ri tglobaltlsaddr:$dst)>;
def : Pat<(i32 (X86Wrapper tglobaladdr :$dst)), (MOV32ri tglobaladdr :$dst)>;
def : Pat<(i32 (X86Wrapper texternalsym:$dst)), (MOV32ri texternalsym:$dst)>;

def : Pat<(add GR32:$src1, (X86Wrapper tconstpool:$src2)),
          (ADD32ri GR32:$src1, tconstpool:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper tjumptable:$src2)),
          (ADD32ri GR32:$src1, tjumptable:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper tglobaladdr :$src2)),
          (ADD32ri GR32:$src1, tglobaladdr:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper texternalsym:$src2)),
          (ADD32ri GR32:$src1, texternalsym:$src2)>;

def : Pat<(store (i32 (X86Wrapper tglobaladdr:$src)), addr:$dst),
          (MOV32mi addr:$dst, tglobaladdr:$src)>;
def : Pat<(store (i32 (X86Wrapper texternalsym:$src)), addr:$dst),
          (MOV32mi addr:$dst, texternalsym:$src)>;

// Calls
// tailcall stuff
def : Pat<(X86tailcall GR32:$dst),
          (TAILCALL)>;

def : Pat<(X86tailcall (i32 tglobaladdr:$dst)),
          (TAILCALL)>;
def : Pat<(X86tailcall (i32 texternalsym:$dst)),
          (TAILCALL)>;

def : Pat<(X86tcret GR32:$dst, imm:$off),
          (TCRETURNri GR32:$dst, imm:$off)>;

def : Pat<(X86tcret (i32 tglobaladdr:$dst), imm:$off),
          (TCRETURNdi texternalsym:$dst, imm:$off)>;

def : Pat<(X86tcret (i32 texternalsym:$dst), imm:$off),
          (TCRETURNdi texternalsym:$dst, imm:$off)>;

def : Pat<(X86call (i32 tglobaladdr:$dst)),
          (CALLpcrel32 tglobaladdr:$dst)>;
def : Pat<(X86call (i32 texternalsym:$dst)),
          (CALLpcrel32 texternalsym:$dst)>;

// X86 specific add which produces a flag.
def : Pat<(addc GR32:$src1, GR32:$src2),
          (ADD32rr GR32:$src1, GR32:$src2)>;
def : Pat<(addc GR32:$src1, (load addr:$src2)),
          (ADD32rm GR32:$src1, addr:$src2)>;
def : Pat<(addc GR32:$src1, imm:$src2),
          (ADD32ri GR32:$src1, imm:$src2)>;
def : Pat<(addc GR32:$src1, i32immSExt8:$src2),
          (ADD32ri8 GR32:$src1, i32immSExt8:$src2)>;

def : Pat<(subc GR32:$src1, GR32:$src2),
          (SUB32rr GR32:$src1, GR32:$src2)>;
def : Pat<(subc GR32:$src1, (load addr:$src2)),
          (SUB32rm GR32:$src1, addr:$src2)>;
def : Pat<(subc GR32:$src1, imm:$src2),
          (SUB32ri GR32:$src1, imm:$src2)>;
def : Pat<(subc GR32:$src1, i32immSExt8:$src2),
          (SUB32ri8 GR32:$src1, i32immSExt8:$src2)>;

// Comparisons.

// TEST R,R is smaller than CMP R,0
def : Pat<(parallel (X86cmp GR8:$src1, 0), (implicit EFLAGS)),
          (TEST8rr GR8:$src1, GR8:$src1)>;
def : Pat<(parallel (X86cmp GR16:$src1, 0), (implicit EFLAGS)),
          (TEST16rr GR16:$src1, GR16:$src1)>;
def : Pat<(parallel (X86cmp GR32:$src1, 0), (implicit EFLAGS)),
          (TEST32rr GR32:$src1, GR32:$src1)>;

// zextload bool -> zextload byte
def : Pat<(zextloadi8i1  addr:$src), (MOV8rm     addr:$src)>;
def : Pat<(zextloadi16i1 addr:$src), (MOVZX16rm8 addr:$src)>;
def : Pat<(zextloadi32i1 addr:$src), (MOVZX32rm8 addr:$src)>;

// extload bool -> extload byte
def : Pat<(extloadi8i1 addr:$src),   (MOV8rm      addr:$src)>;
def : Pat<(extloadi16i1 addr:$src),  (MOVZX16rm8  addr:$src)>,
         Requires<[In32BitMode]>;
def : Pat<(extloadi32i1 addr:$src),  (MOVZX32rm8  addr:$src)>;
def : Pat<(extloadi16i8 addr:$src),  (MOVZX16rm8  addr:$src)>,
         Requires<[In32BitMode]>;
def : Pat<(extloadi32i8 addr:$src),  (MOVZX32rm8  addr:$src)>;
def : Pat<(extloadi32i16 addr:$src), (MOVZX32rm16 addr:$src)>;

// anyext
def : Pat<(i16 (anyext GR8 :$src)), (MOVZX16rr8  GR8 :$src)>,
         Requires<[In32BitMode]>;
def : Pat<(i32 (anyext GR8 :$src)), (MOVZX32rr8  GR8 :$src)>,
         Requires<[In32BitMode]>;
def : Pat<(i32 (anyext GR16:$src)),
          (INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR16:$src, x86_subreg_16bit)>;

// (and (i32 load), 255) -> (zextload i8)
def : Pat<(i32 (and (loadi32 addr:$src), (i32 255))), (MOVZX32rm8 addr:$src)>;
def : Pat<(i32 (and (loadi32 addr:$src), (i32 65535))),(MOVZX32rm16 addr:$src)>;

//===----------------------------------------------------------------------===//
// Some peepholes
//===----------------------------------------------------------------------===//

// r & (2^16-1) ==> movz
def : Pat<(and GR32:$src1, 0xffff),
          (MOVZX32rr16 (i16 (EXTRACT_SUBREG GR32:$src1, x86_subreg_16bit)))>;
// r & (2^8-1) ==> movz
def : Pat<(and GR32:$src1, 0xff),
          (MOVZX32rr8 (i8 (EXTRACT_SUBREG (MOV32to32_ GR32:$src1),
                                          x86_subreg_8bit)))>,
      Requires<[In32BitMode]>;
// r & (2^8-1) ==> movz
def : Pat<(and GR16:$src1, 0xff),
          (MOVZX16rr8 (i8 (EXTRACT_SUBREG (MOV16to16_ GR16:$src1),
                                          x86_subreg_8bit)))>,
      Requires<[In32BitMode]>;

// sext_inreg patterns
def : Pat<(sext_inreg GR32:$src, i16),
          (MOVSX32rr16 (i16 (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit)))>;
def : Pat<(sext_inreg GR32:$src, i8),
          (MOVSX32rr8 (i8 (EXTRACT_SUBREG (MOV32to32_ GR32:$src),
                                          x86_subreg_8bit)))>,
      Requires<[In32BitMode]>;
def : Pat<(sext_inreg GR16:$src, i8),
          (MOVSX16rr8 (i8 (EXTRACT_SUBREG (MOV16to16_ GR16:$src),
                                          x86_subreg_8bit)))>,
      Requires<[In32BitMode]>;

// trunc patterns
def : Pat<(i16 (trunc GR32:$src)),
          (i16 (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit))>;
def : Pat<(i8 (trunc GR32:$src)),
          (i8 (EXTRACT_SUBREG (MOV32to32_ GR32:$src), x86_subreg_8bit))>,
      Requires<[In32BitMode]>;
def : Pat<(i8 (trunc GR16:$src)),
          (i8 (EXTRACT_SUBREG (MOV16to16_ GR16:$src), x86_subreg_8bit))>,
      Requires<[In32BitMode]>;

// (shl x, 1) ==> (add x, x)
def : Pat<(shl GR8 :$src1, (i8 1)), (ADD8rr  GR8 :$src1, GR8 :$src1)>;
def : Pat<(shl GR16:$src1, (i8 1)), (ADD16rr GR16:$src1, GR16:$src1)>;
def : Pat<(shl GR32:$src1, (i8 1)), (ADD32rr GR32:$src1, GR32:$src1)>;

// (shl x (and y, 31)) ==> (shl x, y)
def : Pat<(shl GR8:$src1, (and CL:$amt, 31)),
          (SHL8rCL GR8:$src1)>;
def : Pat<(shl GR16:$src1, (and CL:$amt, 31)),
          (SHL16rCL GR16:$src1)>;
def : Pat<(shl GR32:$src1, (and CL:$amt, 31)),
          (SHL32rCL GR32:$src1)>;
def : Pat<(store (shl (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SHL8mCL addr:$dst)>;
def : Pat<(store (shl (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SHL16mCL addr:$dst)>;
def : Pat<(store (shl (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SHL32mCL addr:$dst)>;

def : Pat<(srl GR8:$src1, (and CL:$amt, 31)),
          (SHR8rCL GR8:$src1)>;
def : Pat<(srl GR16:$src1, (and CL:$amt, 31)),
          (SHR16rCL GR16:$src1)>;
def : Pat<(srl GR32:$src1, (and CL:$amt, 31)),
          (SHR32rCL GR32:$src1)>;
def : Pat<(store (srl (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SHR8mCL addr:$dst)>;
def : Pat<(store (srl (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SHR16mCL addr:$dst)>;
def : Pat<(store (srl (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SHR32mCL addr:$dst)>;

def : Pat<(sra GR8:$src1, (and CL:$amt, 31)),
          (SAR8rCL GR8:$src1)>;
def : Pat<(sra GR16:$src1, (and CL:$amt, 31)),
          (SAR16rCL GR16:$src1)>;
def : Pat<(sra GR32:$src1, (and CL:$amt, 31)),
          (SAR32rCL GR32:$src1)>;
def : Pat<(store (sra (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SAR8mCL addr:$dst)>;
def : Pat<(store (sra (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SAR16mCL addr:$dst)>;
def : Pat<(store (sra (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
          (SAR32mCL addr:$dst)>;

// (or (x >> c) | (y << (32 - c))) ==> (shrd32 x, y, c)
def : Pat<(or (srl GR32:$src1, CL:$amt),
              (shl GR32:$src2, (sub 32, CL:$amt))),
          (SHRD32rrCL GR32:$src1, GR32:$src2)>;

def : Pat<(store (or (srl (loadi32 addr:$dst), CL:$amt),
                     (shl GR32:$src2, (sub 32, CL:$amt))), addr:$dst),
          (SHRD32mrCL addr:$dst, GR32:$src2)>;

// (or (x << c) | (y >> (32 - c))) ==> (shld32 x, y, c)
def : Pat<(or (shl GR32:$src1, CL:$amt),
              (srl GR32:$src2, (sub 32, CL:$amt))),
          (SHLD32rrCL GR32:$src1, GR32:$src2)>;

def : Pat<(store (or (shl (loadi32 addr:$dst), CL:$amt),
                     (srl GR32:$src2, (sub 32, CL:$amt))), addr:$dst),
          (SHLD32mrCL addr:$dst, GR32:$src2)>;

// (or (x >> c) | (y << (16 - c))) ==> (shrd16 x, y, c)
def : Pat<(or (srl GR16:$src1, CL:$amt),
              (shl GR16:$src2, (sub 16, CL:$amt))),
          (SHRD16rrCL GR16:$src1, GR16:$src2)>;

def : Pat<(store (or (srl (loadi16 addr:$dst), CL:$amt),
                     (shl GR16:$src2, (sub 16, CL:$amt))), addr:$dst),
          (SHRD16mrCL addr:$dst, GR16:$src2)>;

// (or (x << c) | (y >> (16 - c))) ==> (shld16 x, y, c)
def : Pat<(or (shl GR16:$src1, CL:$amt),
              (srl GR16:$src2, (sub 16, CL:$amt))),
          (SHLD16rrCL GR16:$src1, GR16:$src2)>;

def : Pat<(store (or (shl (loadi16 addr:$dst), CL:$amt),
                     (srl GR16:$src2, (sub 16, CL:$amt))), addr:$dst),
          (SHLD16mrCL addr:$dst, GR16:$src2)>;

//===----------------------------------------------------------------------===//
// Floating Point Stack Support
//===----------------------------------------------------------------------===//

include "X86InstrFPStack.td"

//===----------------------------------------------------------------------===//
// X86-64 Support
//===----------------------------------------------------------------------===//

include "X86Instr64bit.td"

//===----------------------------------------------------------------------===//
// XMM Floating point support (requires SSE / SSE2)
//===----------------------------------------------------------------------===//

include "X86InstrSSE.td"

//===----------------------------------------------------------------------===//
// MMX and XMM Packed Integer support (requires MMX, SSE, and SSE2)
//===----------------------------------------------------------------------===//

include "X86InstrMMX.td"