[SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2>,
SDTCisVT<3, i8>, SDTCisVT<4, i32>]>;
+def SDTUnaryArithOvf : SDTypeProfile<1, 1,
+ [SDTCisInt<0>]>;
+def SDTBinaryArithOvf : SDTypeProfile<1, 2,
+ [SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>,
+ SDTCisInt<0>]>;
+
def SDTX86BrCond : SDTypeProfile<0, 3,
[SDTCisVT<0, OtherVT>,
SDTCisVT<1, i8>, SDTCisVT<2, i32>]>;
def X86cmp : SDNode<"X86ISD::CMP" , SDTX86CmpTest>;
+def X86bt : SDNode<"X86ISD::BT", SDTX86CmpTest>;
+
def X86cmov : SDNode<"X86ISD::CMOV", SDTX86Cmov>;
def X86brcond : SDNode<"X86ISD::BRCOND", SDTX86BrCond,
[SDNPHasChain]>;
def X86tcret : SDNode<"X86ISD::TC_RETURN", SDT_X86TCRET,
[SDNPHasChain, SDNPOptInFlag]>;
+def X86add_ovf : SDNode<"X86ISD::ADD", SDTBinaryArithOvf>;
+def X86sub_ovf : SDNode<"X86ISD::SUB", SDTBinaryArithOvf>;
+def X86smul_ovf : SDNode<"X86ISD::SMUL", SDTBinaryArithOvf>;
+def X86umul_ovf : SDNode<"X86ISD::UMUL", SDTUnaryArithOvf>;
+
//===----------------------------------------------------------------------===//
// X86 Operand Definitions.
//
def NotSmallCode : Predicate<"TM.getCodeModel() != CodeModel::Small">;
def IsStatic : Predicate<"TM.getRelocationModel() == Reloc::Static">;
def OptForSpeed : Predicate<"!OptForSize">;
+def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">;
//===----------------------------------------------------------------------===//
// X86 Instruction Format Definitions.
// 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_A : PatLeaf<(i8 0)>; // alt. COND_NBE
+def X86_COND_AE : PatLeaf<(i8 1)>; // alt. COND_NC
+def X86_COND_B : PatLeaf<(i8 2)>; // alt. COND_C
+def X86_COND_BE : PatLeaf<(i8 3)>; // alt. COND_NA
+def X86_COND_E : PatLeaf<(i8 4)>; // alt. COND_Z
+def X86_COND_G : PatLeaf<(i8 5)>; // alt. COND_NLE
+def X86_COND_GE : PatLeaf<(i8 6)>; // alt. COND_NL
+def X86_COND_L : PatLeaf<(i8 7)>; // alt. COND_NGE
+def X86_COND_LE : PatLeaf<(i8 8)>; // alt. COND_NG
+def X86_COND_NE : PatLeaf<(i8 9)>; // alt. COND_NZ
def X86_COND_NO : PatLeaf<(i8 10)>;
-def X86_COND_NP : PatLeaf<(i8 11)>;
+def X86_COND_NP : PatLeaf<(i8 11)>; // alt. COND_PO
def X86_COND_NS : PatLeaf<(i8 12)>;
-def X86_COND_NC : PatLeaf<(i8 13)>;
-def X86_COND_O : PatLeaf<(i8 14)>;
-def X86_COND_P : PatLeaf<(i8 15)>;
-def X86_COND_S : PatLeaf<(i8 16)>;
-def X86_COND_C : PatLeaf<(i8 17)>;
+def X86_COND_O : PatLeaf<(i8 13)>;
+def X86_COND_P : PatLeaf<(i8 14)>; // alt. COND_PE
+def X86_COND_S : PatLeaf<(i8 15)>;
def i16immSExt8 : PatLeaf<(i16 imm), [{
// i16immSExt8 predicate - True if the 16-bit immediate fits in a 8-bit
return false;
}]>;
+def gsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
+ LoadSDNode *LD = cast<LoadSDNode>(N);
+ const Value *Src = LD->getSrcValue();
+ if (!Src)
+ return false;
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ return PT->getAddressSpace() == 256;
+ return false;
+}]>;
+
def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr))>;
def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr))>;
[(X86brcond bb:$dst, X86_COND_O, EFLAGS)]>, TB;
def JNO : IBr<0x81, (ins brtarget:$dst), "jno\t$dst",
[(X86brcond bb:$dst, X86_COND_NO, EFLAGS)]>, TB;
-def JC : IBr<0x82, (ins brtarget:$dst), "jc\t$dst",
- [(X86brcond bb:$dst, X86_COND_C, EFLAGS)]>, TB;
-def JNC : IBr<0x83, (ins brtarget:$dst), "jnc\t$dst",
- [(X86brcond bb:$dst, X86_COND_NC, EFLAGS)]>, TB;
} // Uses = [EFLAGS]
//===----------------------------------------------------------------------===//
"mov{l}\t{$src, $dst|$dst, $src}",
[(store (i32 imm:$src), addr:$dst)]>;
-let isSimpleLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
+let canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
def MOV8rm : I<0x8A, MRMSrcMem, (outs GR8 :$dst), (ins i8mem :$src),
"mov{b}\t{$src, $dst|$dst, $src}",
[(set GR8:$dst, (load addr:$src))]>;
// FIXME: Used for 8-bit mul, ignore result upper 8 bits.
// This probably ought to be moved to a def : Pat<> if the
// syntax can be accepted.
- [(set AL, (mul AL, GR8:$src))]>; // AL,AH = AL*GR8
+ [(set AL, (mul AL, GR8:$src)),
+ (implicit EFLAGS)]>; // AL,AH = AL*GR8
+
let Defs = [AX,DX,EFLAGS], Uses = [AX], neverHasSideEffects = 1 in
-def MUL16r : I<0xF7, MRM4r, (outs), (ins GR16:$src), "mul{w}\t$src", []>,
- OpSize; // AX,DX = AX*GR16
+def MUL16r : I<0xF7, MRM4r, (outs), (ins GR16:$src),
+ "mul{w}\t$src",
+ []>, OpSize; // AX,DX = AX*GR16
+
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX], neverHasSideEffects = 1 in
-def MUL32r : I<0xF7, MRM4r, (outs), (ins GR32:$src), "mul{l}\t$src", []>;
- // EAX,EDX = EAX*GR32
+def MUL32r : I<0xF7, MRM4r, (outs), (ins GR32:$src),
+ "mul{l}\t$src",
+ []>; // EAX,EDX = EAX*GR32
+
let Defs = [AL,AH,EFLAGS], Uses = [AL] in
def MUL8m : I<0xF6, MRM4m, (outs), (ins i8mem :$src),
"mul{b}\t$src",
// FIXME: Used for 8-bit mul, ignore result upper 8 bits.
// This probably ought to be moved to a def : Pat<> if the
// syntax can be accepted.
- [(set AL, (mul AL, (loadi8 addr:$src)))]>; // AL,AH = AL*[mem8]
+ [(set AL, (mul AL, (loadi8 addr:$src))),
+ (implicit EFLAGS)]>; // AL,AH = AL*[mem8]
+
let mayLoad = 1, neverHasSideEffects = 1 in {
let Defs = [AX,DX,EFLAGS], Uses = [AX] in
def MUL16m : I<0xF7, MRM4m, (outs), (ins i16mem:$src),
- "mul{w}\t$src", []>, OpSize; // AX,DX = AX*[mem16]
+ "mul{w}\t$src",
+ []>, OpSize; // AX,DX = AX*[mem16]
+
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX] in
def MUL32m : I<0xF7, MRM4m, (outs), (ins i32mem:$src),
- "mul{l}\t$src", []>; // EAX,EDX = EAX*[mem32]
+ "mul{l}\t$src",
+ []>; // EAX,EDX = EAX*[mem32]
}
let neverHasSideEffects = 1 in {
[(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
X86_COND_B, EFLAGS))]>,
TB;
-
def CMOVAE16rr: I<0x43, MRMSrcReg, // if >=u, GR16 = GR16
(outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
"cmovae\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
X86_COND_NP, EFLAGS))]>,
TB;
-} // isCommutable = 1
-
-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, EFLAGS))]>,
+def CMOVO16rr : I<0x40, MRMSrcReg, // if overflow, GR16 = GR16
+ (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
+ "cmovo\t{$src2, $dst|$dst, $src2}",
+ [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
+ X86_COND_O, EFLAGS))]>,
+ TB, OpSize;
+def CMOVO32rr : I<0x40, MRMSrcReg, // if overflow, GR32 = GR32
+ (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
+ "cmovo\t{$src2, $dst|$dst, $src2}",
+ [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
+ X86_COND_O, EFLAGS))]>,
+ TB;
+def CMOVNO16rr : I<0x41, MRMSrcReg, // if !overflow, GR16 = GR16
+ (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
+ "cmovno\t{$src2, $dst|$dst, $src2}",
+ [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2,
+ X86_COND_NO, EFLAGS))]>,
+ TB, OpSize;
+def CMOVNO32rr : I<0x41, MRMSrcReg, // if !overflow, GR32 = GR32
+ (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
+ "cmovno\t{$src2, $dst|$dst, $src2}",
+ [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
+ X86_COND_NO, EFLAGS))]>,
TB;
+} // isCommutable = 1
def CMOVB16rm : I<0x42, MRMSrcMem, // if <u, GR16 = [mem16]
(outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
[(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
X86_COND_NP, EFLAGS))]>,
TB, OpSize;
+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, EFLAGS))]>,
+ TB;
+def CMOVO16rm : I<0x40, MRMSrcMem, // if overflow, GR16 = [mem16]
+ (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
+ "cmovo\t{$src2, $dst|$dst, $src2}",
+ [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
+ X86_COND_O, EFLAGS))]>,
+ TB, OpSize;
+def CMOVO32rm : I<0x40, MRMSrcMem, // if overflow, GR32 = [mem32]
+ (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
+ "cmovo\t{$src2, $dst|$dst, $src2}",
+ [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
+ X86_COND_O, EFLAGS))]>,
+ TB;
+def CMOVNO16rm : I<0x41, MRMSrcMem, // if !overflow, GR16 = [mem16]
+ (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
+ "cmovno\t{$src2, $dst|$dst, $src2}",
+ [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2),
+ X86_COND_NO, EFLAGS))]>,
+ TB, OpSize;
+def CMOVNO32rm : I<0x41, MRMSrcMem, // if !overflow, GR32 = [mem32]
+ (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
+ "cmovno\t{$src2, $dst|$dst, $src2}",
+ [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
+ X86_COND_NO, EFLAGS))]>,
+ TB;
} // Uses = [EFLAGS]
}
} // Defs = [EFLAGS]
+// Match xor -1 to not. Favors these over a move imm + xor to save code size.
+let AddedComplexity = 15 in {
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$dst",
[(store (not (loadi8 addr:$dst)), addr:$dst)]>;
// Arithmetic.
let Defs = [EFLAGS] in {
let isCommutable = 1 in { // X = ADD Y, Z --> X = ADD Z, Y
-def ADD8rr : I<0x00, MRMDestReg, (outs GR8 :$dst),
- (ins GR8 :$src1, GR8 :$src2),
- "add{b}\t{$src2, $dst|$dst, $src2}",
- [(set GR8:$dst, (add GR8:$src1, GR8:$src2)),
- (implicit EFLAGS)]>;
+// Register-Register Addition
+def ADD8rr : I<0x00, MRMDestReg, (outs GR8 :$dst),
+ (ins GR8 :$src1, GR8 :$src2),
+ "add{b}\t{$src2, $dst|$dst, $src2}",
+ [(set GR8:$dst, (add GR8:$src1, GR8:$src2)),
+ (implicit EFLAGS)]>;
+
let isConvertibleToThreeAddress = 1 in { // Can transform into LEA.
+// Register-Register Addition
def ADD16rr : I<0x01, MRMDestReg, (outs GR16:$dst),
(ins GR16:$src1, GR16:$src2),
"add{w}\t{$src2, $dst|$dst, $src2}",
(implicit EFLAGS)]>;
} // end isConvertibleToThreeAddress
} // end isCommutable
+
+// Register-Memory Addition
def ADD8rm : I<0x02, MRMSrcMem, (outs GR8 :$dst),
(ins GR8 :$src1, i8mem :$src2),
"add{b}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (add GR32:$src1, (load addr:$src2))),
(implicit EFLAGS)]>;
-def ADD8ri : Ii8<0x80, MRM0r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2),
- "add{b}\t{$src2, $dst|$dst, $src2}",
- [(set GR8:$dst, (add GR8:$src1, imm:$src2)),
- (implicit EFLAGS)]>;
+// Register-Integer Addition
+def ADD8ri : Ii8<0x80, MRM0r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2),
+ "add{b}\t{$src2, $dst|$dst, $src2}",
+ [(set GR8:$dst, (add GR8:$src1, imm:$src2)),
+ (implicit EFLAGS)]>;
let isConvertibleToThreeAddress = 1 in { // Can transform into LEA.
+// Register-Integer Addition
def ADD16ri : Ii16<0x81, MRM0r, (outs GR16:$dst),
(ins GR16:$src1, i16imm:$src2),
"add{w}\t{$src2, $dst|$dst, $src2}",
def ADD16ri8 : Ii8<0x83, MRM0r, (outs GR16:$dst),
(ins GR16:$src1, i16i8imm:$src2),
"add{w}\t{$src2, $dst|$dst, $src2}",
- [(set GR16:$dst, (add GR16:$src1, i16immSExt8:$src2)),
- (implicit EFLAGS)]>, OpSize;
+ [(set GR16:$dst, (add GR16:$src1, i16immSExt8:$src2)),
+ (implicit EFLAGS)]>, OpSize;
def ADD32ri8 : Ii8<0x83, MRM0r, (outs GR32:$dst),
(ins GR32:$src1, i32i8imm:$src2),
"add{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (add GR32:$src1, i32immSExt8:$src2)),
- (implicit EFLAGS)]>;
+ [(set GR32:$dst, (add GR32:$src1, i32immSExt8:$src2)),
+ (implicit EFLAGS)]>;
}
let isTwoAddress = 0 in {
- def ADD8mr : I<0x00, MRMDestMem, (outs), (ins i8mem :$dst, GR8 :$src2),
+ // Memory-Register Addition
+ def ADD8mr : I<0x00, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src2),
"add{b}\t{$src2, $dst|$dst, $src2}",
[(store (add (load addr:$dst), GR8:$src2), addr:$dst),
(implicit EFLAGS)]>;
def ADD16mr : I<0x01, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
"add{w}\t{$src2, $dst|$dst, $src2}",
[(store (add (load addr:$dst), GR16:$src2), addr:$dst),
- (implicit EFLAGS)]>,
- OpSize;
+ (implicit EFLAGS)]>, OpSize;
def ADD32mr : I<0x01, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2),
"add{l}\t{$src2, $dst|$dst, $src2}",
[(store (add (load addr:$dst), GR32:$src2), addr:$dst),
def ADD16mi : Ii16<0x81, MRM0m, (outs), (ins i16mem:$dst, i16imm:$src2),
"add{w}\t{$src2, $dst|$dst, $src2}",
[(store (add (loadi16 addr:$dst), imm:$src2), addr:$dst),
- (implicit EFLAGS)]>,
- OpSize;
+ (implicit EFLAGS)]>, OpSize;
def ADD32mi : Ii32<0x81, MRM0m, (outs), (ins i32mem:$dst, i32imm:$src2),
"add{l}\t{$src2, $dst|$dst, $src2}",
- [(store (add (loadi32 addr:$dst), imm:$src2), addr:$dst),
- (implicit EFLAGS)]>;
+ [(store (add (loadi32 addr:$dst), imm:$src2), addr:$dst),
+ (implicit EFLAGS)]>;
def ADD16mi8 : Ii8<0x83, MRM0m, (outs), (ins i16mem:$dst, i16i8imm :$src2),
"add{w}\t{$src2, $dst|$dst, $src2}",
- [(store (add (load addr:$dst), i16immSExt8:$src2), addr:$dst),
- (implicit EFLAGS)]>,
- OpSize;
+ [(store (add (load addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)]>, OpSize;
def ADD32mi8 : Ii8<0x83, MRM0m, (outs), (ins i32mem:$dst, i32i8imm :$src2),
"add{l}\t{$src2, $dst|$dst, $src2}",
- [(store (add (load addr:$dst), i32immSExt8:$src2), addr:$dst),
+ [(store (add (load addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
(implicit EFLAGS)]>;
}
let isCommutable = 1 in { // X = ADC Y, Z --> X = ADC Z, Y
def ADC32rr : I<0x11, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (adde GR32:$src1, GR32:$src2)),
- (implicit EFLAGS)]>;
+ [(set GR32:$dst, (adde GR32:$src1, GR32:$src2))]>;
}
def ADC32rm : I<0x13, MRMSrcMem , (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (adde GR32:$src1, (load addr:$src2))),
- (implicit EFLAGS)]>;
+ [(set GR32:$dst, (adde GR32:$src1, (load addr:$src2)))]>;
def ADC32ri : Ii32<0x81, MRM2r, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (adde GR32:$src1, imm:$src2)),
- (implicit EFLAGS)]>;
+ [(set GR32:$dst, (adde GR32:$src1, imm:$src2))]>;
def ADC32ri8 : Ii8<0x83, MRM2r, (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (adde GR32:$src1, i32immSExt8:$src2)),
- (implicit EFLAGS)]>;
+ [(set GR32:$dst, (adde GR32:$src1, i32immSExt8:$src2))]>;
let isTwoAddress = 0 in {
def ADC32mr : I<0x11, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(store (adde (load addr:$dst), GR32:$src2), addr:$dst),
- (implicit EFLAGS)]>;
+ [(store (adde (load addr:$dst), GR32:$src2), addr:$dst)]>;
def ADC32mi : Ii32<0x81, MRM2m, (outs), (ins i32mem:$dst, i32imm:$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(store (adde (loadi32 addr:$dst), imm:$src2), addr:$dst),
- (implicit EFLAGS)]>;
+ [(store (adde (loadi32 addr:$dst), imm:$src2), addr:$dst)]>;
def ADC32mi8 : Ii8<0x83, MRM2m, (outs), (ins i32mem:$dst, i32i8imm :$src2),
"adc{l}\t{$src2, $dst|$dst, $src2}",
- [(store (adde (load addr:$dst), i32immSExt8:$src2), addr:$dst),
- (implicit EFLAGS)]>;
+ [(store (adde (load addr:$dst), i32immSExt8:$src2), addr:$dst)]>;
}
} // Uses = [EFLAGS]
-def SUB8rr : I<0x28, MRMDestReg, (outs GR8 :$dst), (ins GR8 :$src1, GR8 :$src2),
- "sub{b}\t{$src2, $dst|$dst, $src2}",
- [(set GR8:$dst, (sub GR8:$src1, GR8:$src2))]>;
-def SUB16rr : I<0x29, MRMDestReg, (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
- "sub{w}\t{$src2, $dst|$dst, $src2}",
- [(set GR16:$dst, (sub GR16:$src1, GR16:$src2))]>, OpSize;
-def SUB32rr : I<0x29, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
- "sub{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (sub GR32:$src1, GR32:$src2))]>;
-def SUB8rm : I<0x2A, MRMSrcMem, (outs GR8 :$dst), (ins GR8 :$src1, i8mem :$src2),
- "sub{b}\t{$src2, $dst|$dst, $src2}",
- [(set GR8:$dst, (sub GR8:$src1, (load addr:$src2)))]>;
-def SUB16rm : I<0x2B, MRMSrcMem, (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
- "sub{w}\t{$src2, $dst|$dst, $src2}",
- [(set GR16:$dst, (sub GR16:$src1, (load addr:$src2)))]>, OpSize;
-def SUB32rm : I<0x2B, MRMSrcMem, (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
- "sub{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (sub GR32:$src1, (load addr:$src2)))]>;
-
-def SUB8ri : Ii8 <0x80, MRM5r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2),
+// Register-Register Subtraction
+def SUB8rr : I<0x28, MRMDestReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2),
+ "sub{b}\t{$src2, $dst|$dst, $src2}",
+ [(set GR8:$dst, (sub GR8:$src1, GR8:$src2)),
+ (implicit EFLAGS)]>;
+def SUB16rr : I<0x29, MRMDestReg, (outs GR16:$dst), (ins GR16:$src1,GR16:$src2),
+ "sub{w}\t{$src2, $dst|$dst, $src2}",
+ [(set GR16:$dst, (sub GR16:$src1, GR16:$src2)),
+ (implicit EFLAGS)]>, OpSize;
+def SUB32rr : I<0x29, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1,GR32:$src2),
+ "sub{l}\t{$src2, $dst|$dst, $src2}",
+ [(set GR32:$dst, (sub GR32:$src1, GR32:$src2)),
+ (implicit EFLAGS)]>;
+
+// Register-Memory Subtraction
+def SUB8rm : I<0x2A, MRMSrcMem, (outs GR8 :$dst),
+ (ins GR8 :$src1, i8mem :$src2),
+ "sub{b}\t{$src2, $dst|$dst, $src2}",
+ [(set GR8:$dst, (sub GR8:$src1, (load addr:$src2))),
+ (implicit EFLAGS)]>;
+def SUB16rm : I<0x2B, MRMSrcMem, (outs GR16:$dst),
+ (ins GR16:$src1, i16mem:$src2),
+ "sub{w}\t{$src2, $dst|$dst, $src2}",
+ [(set GR16:$dst, (sub GR16:$src1, (load addr:$src2))),
+ (implicit EFLAGS)]>, OpSize;
+def SUB32rm : I<0x2B, MRMSrcMem, (outs GR32:$dst),
+ (ins GR32:$src1, i32mem:$src2),
+ "sub{l}\t{$src2, $dst|$dst, $src2}",
+ [(set GR32:$dst, (sub GR32:$src1, (load addr:$src2))),
+ (implicit EFLAGS)]>;
+
+// Register-Integer Subtraction
+def SUB8ri : Ii8 <0x80, MRM5r, (outs GR8:$dst),
+ (ins GR8:$src1, i8imm:$src2),
"sub{b}\t{$src2, $dst|$dst, $src2}",
- [(set GR8:$dst, (sub GR8:$src1, imm:$src2))]>;
-def SUB16ri : Ii16<0x81, MRM5r, (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2),
+ [(set GR8:$dst, (sub GR8:$src1, imm:$src2)),
+ (implicit EFLAGS)]>;
+def SUB16ri : Ii16<0x81, MRM5r, (outs GR16:$dst),
+ (ins GR16:$src1, i16imm:$src2),
"sub{w}\t{$src2, $dst|$dst, $src2}",
- [(set GR16:$dst, (sub GR16:$src1, imm:$src2))]>, OpSize;
-def SUB32ri : Ii32<0x81, MRM5r, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
+ [(set GR16:$dst, (sub GR16:$src1, imm:$src2)),
+ (implicit EFLAGS)]>, OpSize;
+def SUB32ri : Ii32<0x81, MRM5r, (outs GR32:$dst),
+ (ins GR32:$src1, i32imm:$src2),
"sub{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (sub GR32:$src1, imm:$src2))]>;
-def SUB16ri8 : Ii8<0x83, MRM5r, (outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2),
+ [(set GR32:$dst, (sub GR32:$src1, imm:$src2)),
+ (implicit EFLAGS)]>;
+def SUB16ri8 : Ii8<0x83, MRM5r, (outs GR16:$dst),
+ (ins GR16:$src1, i16i8imm:$src2),
"sub{w}\t{$src2, $dst|$dst, $src2}",
- [(set GR16:$dst, (sub GR16:$src1, i16immSExt8:$src2))]>,
- OpSize;
-def SUB32ri8 : Ii8<0x83, MRM5r, (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
+ [(set GR16:$dst, (sub GR16:$src1, i16immSExt8:$src2)),
+ (implicit EFLAGS)]>, OpSize;
+def SUB32ri8 : Ii8<0x83, MRM5r, (outs GR32:$dst),
+ (ins GR32:$src1, i32i8imm:$src2),
"sub{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (sub GR32:$src1, i32immSExt8:$src2))]>;
+ [(set GR32:$dst, (sub GR32:$src1, i32immSExt8:$src2)),
+ (implicit EFLAGS)]>;
+
let isTwoAddress = 0 in {
+ // Memory-Register Subtraction
def SUB8mr : I<0x28, MRMDestMem, (outs), (ins i8mem :$dst, GR8 :$src2),
"sub{b}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (load addr:$dst), GR8:$src2), addr:$dst)]>;
+ [(store (sub (load addr:$dst), GR8:$src2), addr:$dst),
+ (implicit EFLAGS)]>;
def SUB16mr : I<0x29, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
"sub{w}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (load addr:$dst), GR16:$src2), addr:$dst)]>,
- OpSize;
+ [(store (sub (load addr:$dst), GR16:$src2), addr:$dst),
+ (implicit EFLAGS)]>, OpSize;
def SUB32mr : I<0x29, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2),
"sub{l}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (load addr:$dst), GR32:$src2), addr:$dst)]>;
+ [(store (sub (load addr:$dst), GR32:$src2), addr:$dst),
+ (implicit EFLAGS)]>;
+
+ // Memory-Integer Subtraction
def SUB8mi : Ii8<0x80, MRM5m, (outs), (ins i8mem :$dst, i8imm:$src2),
"sub{b}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (loadi8 addr:$dst), imm:$src2), addr:$dst)]>;
+ [(store (sub (loadi8 addr:$dst), imm:$src2), addr:$dst),
+ (implicit EFLAGS)]>;
def SUB16mi : Ii16<0x81, MRM5m, (outs), (ins i16mem:$dst, i16imm:$src2),
"sub{w}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (loadi16 addr:$dst), imm:$src2), addr:$dst)]>,
- OpSize;
+ [(store (sub (loadi16 addr:$dst), imm:$src2),addr:$dst),
+ (implicit EFLAGS)]>, OpSize;
def SUB32mi : Ii32<0x81, MRM5m, (outs), (ins i32mem:$dst, i32imm:$src2),
"sub{l}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (loadi32 addr:$dst), imm:$src2), addr:$dst)]>;
+ [(store (sub (loadi32 addr:$dst), imm:$src2),addr:$dst),
+ (implicit EFLAGS)]>;
def SUB16mi8 : Ii8<0x83, MRM5m, (outs), (ins i16mem:$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),
+ [(store (sub (load addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)]>, OpSize;
+ def SUB32mi8 : Ii8<0x83, MRM5m, (outs), (ins i32mem:$dst, i32i8imm :$src2),
"sub{l}\t{$src2, $dst|$dst, $src2}",
- [(store (sub (load addr:$dst), i32immSExt8:$src2), addr:$dst)]>;
+ [(store (sub (load addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)]>;
}
let Uses = [EFLAGS] in {
let Defs = [EFLAGS] in {
let isCommutable = 1 in { // X = IMUL Y, Z --> X = IMUL Z, Y
-def IMUL16rr : I<0xAF, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
+// Register-Register Signed Integer Multiply
+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:$src2),
+ [(set GR16:$dst, (mul GR16:$src1, GR16:$src2)),
+ (implicit EFLAGS)]>, 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;
+ [(set GR32:$dst, (mul GR32:$src1, GR32:$src2)),
+ (implicit EFLAGS)]>, TB;
}
-def IMUL16rm : I<0xAF, MRMSrcMem, (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
+
+// Register-Memory Signed Integer Multiply
+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;
+ [(set GR16:$dst, (mul GR16:$src1, (load addr:$src2))),
+ (implicit EFLAGS)]>, TB, OpSize;
def IMUL32rm : I<0xAF, MRMSrcMem, (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
"imul{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (mul GR32:$src1, (load addr:$src2)))]>, TB;
+ [(set GR32:$dst, (mul GR32:$src1, (load addr:$src2))),
+ (implicit EFLAGS)]>, TB;
} // Defs = [EFLAGS]
} // end Two Address instructions
// Suprisingly enough, these are not two address instructions!
let Defs = [EFLAGS] in {
+// Register-Integer Signed Integer Multiply
def IMUL16rri : Ii16<0x69, MRMSrcReg, // GR16 = GR16*I16
(outs GR16:$dst), (ins GR16:$src1, i16imm:$src2),
"imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
- [(set GR16:$dst, (mul GR16:$src1, imm:$src2))]>, OpSize;
+ [(set GR16:$dst, (mul GR16:$src1, imm:$src2)),
+ (implicit EFLAGS)]>, OpSize;
def IMUL32rri : Ii32<0x69, MRMSrcReg, // GR32 = GR32*I32
(outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
"imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
- [(set GR32:$dst, (mul GR32:$src1, imm:$src2))]>;
+ [(set GR32:$dst, (mul GR32:$src1, imm:$src2)),
+ (implicit EFLAGS)]>;
def IMUL16rri8 : Ii8<0x6B, MRMSrcReg, // GR16 = GR16*I8
(outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2),
"imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
- [(set GR16:$dst, (mul GR16:$src1, i16immSExt8:$src2))]>,
- OpSize;
+ [(set GR16:$dst, (mul GR16:$src1, i16immSExt8:$src2)),
+ (implicit EFLAGS)]>, OpSize;
def IMUL32rri8 : Ii8<0x6B, MRMSrcReg, // GR32 = GR32*I8
(outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
"imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
- [(set GR32:$dst, (mul GR32:$src1, i32immSExt8:$src2))]>;
+ [(set GR32:$dst, (mul GR32:$src1, i32immSExt8:$src2)),
+ (implicit EFLAGS)]>;
+// Memory-Integer Signed Integer Multiply
def IMUL16rmi : Ii16<0x69, MRMSrcMem, // GR16 = [mem16]*I16
(outs GR16:$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;
+ [(set GR16:$dst, (mul (load addr:$src1), imm:$src2)),
+ (implicit EFLAGS)]>, OpSize;
def IMUL32rmi : Ii32<0x69, MRMSrcMem, // GR32 = [mem32]*I32
(outs GR32:$dst), (ins i32mem:$src1, i32imm:$src2),
"imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
- [(set GR32:$dst, (mul (load addr:$src1), imm:$src2))]>;
+ [(set GR32:$dst, (mul (load addr:$src1), imm:$src2)),
+ (implicit EFLAGS)]>;
def IMUL16rmi8 : Ii8<0x6B, MRMSrcMem, // GR16 = [mem16]*I8
(outs GR16:$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;
+ [(set GR16:$dst, (mul (load addr:$src1),
+ i16immSExt8:$src2)),
+ (implicit EFLAGS)]>, OpSize;
def IMUL32rmi8 : Ii8<0x6B, MRMSrcMem, // GR32 = [mem32]*I8
(outs GR32:$dst), (ins i32mem:$src1, i32i8imm: $src2),
"imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
- [(set GR32:$dst, (mul (load addr:$src1), i32immSExt8:$src2))]>;
+ [(set GR32:$dst, (mul (load addr:$src1),
+ i32immSExt8:$src2)),
+ (implicit EFLAGS)]>;
} // Defs = [EFLAGS]
//===----------------------------------------------------------------------===//
"setno\t$dst",
[(store (X86setcc X86_COND_NO, EFLAGS), addr:$dst)]>,
TB; // [mem8] = not overflow
-
-def SETCr : I<0x92, MRM0r,
- (outs GR8 :$dst), (ins),
- "setc\t$dst",
- [(set GR8:$dst, (X86setcc X86_COND_C, EFLAGS))]>,
- TB; // GR8 = carry
-def SETCm : I<0x92, MRM0m,
- (outs), (ins i8mem:$dst),
- "setc\t$dst",
- [(store (X86setcc X86_COND_C, EFLAGS), addr:$dst)]>,
- TB; // [mem8] = carry
-def SETNCr : I<0x93, MRM0r,
- (outs GR8 :$dst), (ins),
- "setnc\t$dst",
- [(set GR8:$dst, (X86setcc X86_COND_NC, EFLAGS))]>,
- TB; // GR8 = not carry
-def SETNCm : I<0x93, MRM0m,
- (outs), (ins i8mem:$dst),
- "setnc\t$dst",
- [(store (X86setcc X86_COND_NC, EFLAGS), addr:$dst)]>,
- TB; // [mem8] = not carry
} // Uses = [EFLAGS]
(implicit EFLAGS)]>;
} // Defs = [EFLAGS]
+// Bit tests.
+// TODO: BTC, BTR, and BTS
+let Defs = [EFLAGS] in {
+def BT16rr : I<0xA3, MRMDestReg, (outs), (ins GR16:$src1, GR16:$src2),
+ "bt{w}\t{$src2, $src1|$src1, $src2}",
+ [(X86bt GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)]>, OpSize, TB;
+def BT32rr : I<0xA3, MRMDestReg, (outs), (ins GR32:$src1, GR32:$src2),
+ "bt{l}\t{$src2, $src1|$src1, $src2}",
+ [(X86bt GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)]>, TB;
+
+// Unlike with the register+register form, the memory+register form of the
+// bt instruction does not ignore the high bits of the index. From ISel's
+// perspective, this is pretty bizarre. Disable these instructions for now.
+//def BT16mr : I<0xA3, MRMDestMem, (outs), (ins i16mem:$src1, GR16:$src2),
+// "bt{w}\t{$src2, $src1|$src1, $src2}",
+// [(X86bt (loadi16 addr:$src1), GR16:$src2),
+// (implicit EFLAGS)]>, OpSize, TB, Requires<[FastBTMem]>;
+//def BT32mr : I<0xA3, MRMDestMem, (outs), (ins i32mem:$src1, GR32:$src2),
+// "bt{l}\t{$src2, $src1|$src1, $src2}",
+// [(X86bt (loadi32 addr:$src1), GR32:$src2),
+// (implicit EFLAGS)]>, TB, Requires<[FastBTMem]>;
+
+def BT16ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR16:$src1, i16i8imm:$src2),
+ "bt{w}\t{$src2, $src1|$src1, $src2}",
+ [(X86bt GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)]>, OpSize, TB;
+def BT32ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR32:$src1, i32i8imm:$src2),
+ "bt{l}\t{$src2, $src1|$src1, $src2}",
+ [(X86bt GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)]>, TB;
+// Note that these instructions don't need FastBTMem because that
+// only applies when the other operand is in a register. When it's
+// an immediate, bt is still fast.
+def BT16mi8 : Ii8<0xBA, MRM4m, (outs), (ins i16mem:$src1, i16i8imm:$src2),
+ "bt{w}\t{$src2, $src1|$src1, $src2}",
+ [(X86bt (loadi16 addr:$src1), i16immSExt8:$src2),
+ (implicit EFLAGS)]>, OpSize, TB;
+def BT32mi8 : Ii8<0xBA, MRM4m, (outs), (ins i32mem:$src1, i32i8imm:$src2),
+ "bt{l}\t{$src2, $src1|$src1, $src2}",
+ [(X86bt (loadi32 addr:$src1), i32immSExt8:$src2),
+ (implicit EFLAGS)]>, TB;
+} // Defs = [EFLAGS]
+
// Sign/Zero extenders
// Use movsbl intead of movsbw; we don't care about the high 16 bits
// of the register here. This has a smaller encoding and avoids a
// Basic operations on GR16 / GR32 subclasses GR16_ and GR32_ which contains only
// those registers that have GR8 sub-registers (i.e. AX - DX, EAX - EDX).
-let neverHasSideEffects = 1 in {
+let neverHasSideEffects = 1, isAsCheapAsAMove = 1 in {
def MOV16to16_ : I<0x89, MRMDestReg, (outs GR16_:$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, $src}", []>;
} // neverHasSideEffects
-let isSimpleLoad = 1, mayLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
+let canFoldAsLoad = 1, mayLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
def MOV16_rm : I<0x8B, MRMSrcMem, (outs GR16_:$dst), (ins i16mem:$src),
"mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
def MOV32_rm : I<0x8B, MRMSrcMem, (outs GR32_:$dst), (ins i32mem:$src),
"movl\t%gs:0, $dst",
[(set GR32:$dst, X86TLStp)]>, SegGS;
+let AddedComplexity = 5 in
+def GS_MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
+ "movl\t%gs:$src, $dst",
+ [(set GR32:$dst, (gsload addr:$src))]>, SegGS;
+
//===----------------------------------------------------------------------===//
// DWARF Pseudo Instructions
//
let Constraints = "$val = $dst", Defs = [EFLAGS],
usesCustomDAGSchedInserter = 1 in {
def ATOMAND32 : I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
- "#ATOMAND32 PSUEDO!",
+ "#ATOMAND32 PSEUDO!",
[(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!",
+ "#ATOMOR32 PSEUDO!",
[(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!",
+ "#ATOMXOR32 PSEUDO!",
[(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!",
+ "#ATOMNAND32 PSEUDO!",
[(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!",
+ "#ATOMMIN32 PSEUDO!",
[(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!",
+ "#ATOMMAX32 PSEUDO!",
[(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!",
+ "#ATOMUMIN32 PSEUDO!",
[(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!",
+ "#ATOMUMAX32 PSEUDO!",
[(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!",
+ "#ATOMAND16 PSEUDO!",
[(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!",
+ "#ATOMOR16 PSEUDO!",
[(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!",
+ "#ATOMXOR16 PSEUDO!",
[(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!",
+ "#ATOMNAND16 PSEUDO!",
[(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!",
+ "#ATOMMIN16 PSEUDO!",
[(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!",
+ "#ATOMMAX16 PSEUDO!",
[(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!",
+ "#ATOMUMIN16 PSEUDO!",
[(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!",
+ "#ATOMUMAX16 PSEUDO!",
[(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!",
+ "#ATOMAND8 PSEUDO!",
[(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!",
+ "#ATOMOR8 PSEUDO!",
[(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!",
+ "#ATOMXOR8 PSEUDO!",
[(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!",
+ "#ATOMNAND8 PSEUDO!",
[(set GR8:$dst, (atomic_load_nand_8 addr:$ptr, GR8:$val))]>;
}
usesCustomDAGSchedInserter = 1 in {
def ATOMAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMAND6432 PSUEDO!", []>;
+ "#ATOMAND6432 PSEUDO!", []>;
def ATOMOR6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMOR6432 PSUEDO!", []>;
+ "#ATOMOR6432 PSEUDO!", []>;
def ATOMXOR6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMXOR6432 PSUEDO!", []>;
+ "#ATOMXOR6432 PSEUDO!", []>;
def ATOMNAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMNAND6432 PSUEDO!", []>;
+ "#ATOMNAND6432 PSEUDO!", []>;
def ATOMADD6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMADD6432 PSUEDO!", []>;
+ "#ATOMADD6432 PSEUDO!", []>;
def ATOMSUB6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMSUB6432 PSUEDO!", []>;
+ "#ATOMSUB6432 PSEUDO!", []>;
def ATOMSWAP6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
- "#ATOMSWAP6432 PSUEDO!", []>;
+ "#ATOMSWAP6432 PSEUDO!", []>;
}
//===----------------------------------------------------------------------===//
def : Pat<(parallel (X86cmp GR32:$src1, 0), (implicit EFLAGS)),
(TEST32rr GR32:$src1, GR32:$src1)>;
+// Conditional moves with folded loads with operands swapped and conditions
+// inverted.
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_B, EFLAGS),
+ (CMOVAE16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_B, EFLAGS),
+ (CMOVAE32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_AE, EFLAGS),
+ (CMOVB16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_AE, EFLAGS),
+ (CMOVB32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_E, EFLAGS),
+ (CMOVNE16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_E, EFLAGS),
+ (CMOVNE32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_NE, EFLAGS),
+ (CMOVE16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_NE, EFLAGS),
+ (CMOVE32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_BE, EFLAGS),
+ (CMOVA16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_BE, EFLAGS),
+ (CMOVA32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_A, EFLAGS),
+ (CMOVBE16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_A, EFLAGS),
+ (CMOVBE32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_L, EFLAGS),
+ (CMOVGE16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_L, EFLAGS),
+ (CMOVGE32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_GE, EFLAGS),
+ (CMOVL16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_GE, EFLAGS),
+ (CMOVL32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_LE, EFLAGS),
+ (CMOVG16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_LE, EFLAGS),
+ (CMOVG32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_G, EFLAGS),
+ (CMOVLE16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_G, EFLAGS),
+ (CMOVLE32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_P, EFLAGS),
+ (CMOVNP16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_P, EFLAGS),
+ (CMOVNP32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_NP, EFLAGS),
+ (CMOVP16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_NP, EFLAGS),
+ (CMOVP32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_S, EFLAGS),
+ (CMOVNS16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_S, EFLAGS),
+ (CMOVNS32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_NS, EFLAGS),
+ (CMOVS16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_NS, EFLAGS),
+ (CMOVS32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_O, EFLAGS),
+ (CMOVNO16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_O, EFLAGS),
+ (CMOVNO32rm GR32:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, X86_COND_NO, EFLAGS),
+ (CMOVO16rm GR16:$src2, addr:$src1)>;
+def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, X86_COND_NO, EFLAGS),
+ (CMOVO32rm GR32:$src2, addr:$src1)>;
+
// zextload bool -> zextload byte
def : Pat<(zextloadi8i1 addr:$src), (MOV8rm addr:$src)>;
def : Pat<(zextloadi16i1 addr:$src), (MOVZX16rm8 addr:$src)>;
GR16:$src2, (i8 imm:$amt2)), addr:$dst),
(SHLD16mri8 addr:$dst, GR16:$src2, (i8 imm:$amt1))>;
+//===----------------------------------------------------------------------===//
+// Overflow Patterns
+//===----------------------------------------------------------------------===//
+
+// Register-Register Addition with Overflow
+def : Pat<(parallel (X86add_ovf GR8:$src1, GR8:$src2),
+ (implicit EFLAGS)),
+ (ADD8rr GR8:$src1, GR8:$src2)>;
+
+// Register-Register Addition with Overflow
+def : Pat<(parallel (X86add_ovf GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (ADD16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (X86add_ovf GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (ADD32rr GR32:$src1, GR32:$src2)>;
+
+// Register-Memory Addition with Overflow
+def : Pat<(parallel (X86add_ovf GR8:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (ADD8rm GR8:$src1, addr:$src2)>;
+def : Pat<(parallel (X86add_ovf GR16:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (ADD16rm GR16:$src1, addr:$src2)>;
+def : Pat<(parallel (X86add_ovf GR32:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (ADD32rm GR32:$src1, addr:$src2)>;
+
+// Register-Integer Addition with Overflow
+def : Pat<(parallel (X86add_ovf GR8:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (ADD8ri GR8:$src1, imm:$src2)>;
+
+// Register-Integer Addition with Overflow
+def : Pat<(parallel (X86add_ovf GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (ADD16ri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (X86add_ovf GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (ADD32ri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (X86add_ovf GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (ADD16ri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86add_ovf GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (ADD32ri8 GR32:$src1, i32immSExt8:$src2)>;
+
+// Memory-Register Addition with Overflow
+def : Pat<(parallel (store (X86add_ovf (load addr:$dst), GR8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD8mr addr:$dst, GR8:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (load addr:$dst), GR16:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD16mr addr:$dst, GR16:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (load addr:$dst), GR32:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD32mr addr:$dst, GR32:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (loadi8 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD8mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (loadi16 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD16mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (loadi32 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD32mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (load addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD16mi8 addr:$dst, i16immSExt8:$src2)>;
+def : Pat<(parallel (store (X86add_ovf (load addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (ADD32mi8 addr:$dst, i32immSExt8:$src2)>;
+
+// Register-Register Subtraction with Overflow
+def : Pat<(parallel (X86sub_ovf GR8:$src1, GR8:$src2),
+ (implicit EFLAGS)),
+ (SUB8rr GR8:$src1, GR8:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (SUB16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (SUB32rr GR32:$src1, GR32:$src2)>;
+
+// Register-Memory Subtraction with Overflow
+def : Pat<(parallel (X86sub_ovf GR8:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (SUB8rm GR8:$src1, addr:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR16:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (SUB16rm GR16:$src1, addr:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR32:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (SUB32rm GR32:$src1, addr:$src2)>;
+
+// Register-Integer Subtraction with Overflow
+def : Pat<(parallel (X86sub_ovf GR8:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (SUB8ri GR8:$src1, imm:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (SUB16ri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (SUB32ri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (SUB16ri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86sub_ovf GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (SUB32ri8 GR32:$src1, i32immSExt8:$src2)>;
+
+// Memory-Register Subtraction with Overflow
+def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), GR8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB8mr addr:$dst, GR8:$src2)>;
+def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), GR16:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB16mr addr:$dst, GR16:$src2)>;
+def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), GR32:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB32mr addr:$dst, GR32:$src2)>;
+
+// Memory-Integer Subtraction with Overflow
+def : Pat<(parallel (store (X86sub_ovf (loadi8 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB8mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86sub_ovf (loadi16 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB16mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86sub_ovf (loadi32 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB32mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB16mi8 addr:$dst, i16immSExt8:$src2)>;
+def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (SUB32mi8 addr:$dst, i32immSExt8:$src2)>;
+
+
+// Register-Register Signed Integer Multiply with Overflow
+def : Pat<(parallel (X86smul_ovf GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (IMUL16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (X86smul_ovf GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (IMUL32rr GR32:$src1, GR32:$src2)>;
+
+// Register-Memory Signed Integer Multiply with Overflow
+def : Pat<(parallel (X86smul_ovf GR16:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (IMUL16rm GR16:$src1, addr:$src2)>;
+def : Pat<(parallel (X86smul_ovf GR32:$src1, (load addr:$src2)),
+ (implicit EFLAGS)),
+ (IMUL32rm GR32:$src1, addr:$src2)>;
+
+// Register-Integer Signed Integer Multiply with Overflow
+def : Pat<(parallel (X86smul_ovf GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (IMUL16rri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (X86smul_ovf GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (IMUL32rri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (X86smul_ovf GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (IMUL16rri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86smul_ovf GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (IMUL32rri8 GR32:$src1, i32immSExt8:$src2)>;
+
+// Memory-Integer Signed Integer Multiply with Overflow
+def : Pat<(parallel (X86smul_ovf (load addr:$src1), imm:$src2),
+ (implicit EFLAGS)),
+ (IMUL16rmi addr:$src1, imm:$src2)>;
+def : Pat<(parallel (X86smul_ovf (load addr:$src1), imm:$src2),
+ (implicit EFLAGS)),
+ (IMUL32rmi addr:$src1, imm:$src2)>;
+def : Pat<(parallel (X86smul_ovf (load addr:$src1), i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (IMUL16rmi8 addr:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86smul_ovf (load addr:$src1), i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (IMUL32rmi8 addr:$src1, i32immSExt8:$src2)>;
+
+// Optimize multiple with overflow by 2.
+let AddedComplexity = 2 in {
+def : Pat<(parallel (X86smul_ovf GR16:$src1, 2),
+ (implicit EFLAGS)),
+ (ADD16rr GR16:$src1, GR16:$src1)>;
+
+def : Pat<(parallel (X86smul_ovf GR32:$src1, 2),
+ (implicit EFLAGS)),
+ (ADD32rr GR32:$src1, GR32:$src1)>;
+}
+
//===----------------------------------------------------------------------===//
// Floating Point Stack Support
//===----------------------------------------------------------------------===//
projects / oota-llvm.git / blobdiff