[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>]>;
+// Unary and binary operator instructions that set EFLAGS as a side-effect.
+def SDTUnaryArithWithFlags : SDTypeProfile<1, 1,
+ [SDTCisInt<0>]>;
+def SDTBinaryArithWithFlags : SDTypeProfile<1, 2,
+ [SDTCisSameAs<0, 1>,
+ SDTCisSameAs<0, 2>,
+ SDTCisInt<0>]>;
def SDTX86BrCond : SDTypeProfile<0, 3,
[SDTCisVT<0, OtherVT>,
def SDTX86Wrapper : SDTypeProfile<1, 1, [SDTCisSameAs<0, 1>, SDTCisPtrTy<0>]>;
-def SDT_X86TLSADDR : SDTypeProfile<1, 1, [SDTCisPtrTy<0>, SDTCisInt<1>]>;
+def SDT_X86TLSADDR : SDTypeProfile<0, 1, [SDTCisInt<0>]>;
-def SDT_X86TLSTP : SDTypeProfile<1, 0, [SDTCisPtrTy<0>]>;
+def SDT_X86SegmentBaseAddress : SDTypeProfile<1, 1, [SDTCisPtrTy<0>]>;
def SDT_X86EHRET : SDTypeProfile<0, 1, [SDTCisInt<0>]>;
def X86tlsaddr : SDNode<"X86ISD::TLSADDR", SDT_X86TLSADDR,
[SDNPHasChain, SDNPOptInFlag, SDNPOutFlag]>;
-def X86TLStp : SDNode<"X86ISD::THREAD_POINTER", SDT_X86TLSTP, []>;
+def X86SegmentBaseAddress : SDNode<"X86ISD::SegmentBaseAddress",
+ SDT_X86SegmentBaseAddress, []>;
def X86ehret : SDNode<"X86ISD::EH_RETURN", SDT_X86EHRET,
[SDNPHasChain]>;
def X86tcret : SDNode<"X86ISD::TC_RETURN", SDT_X86TCRET,
[SDNPHasChain, SDNPOptInFlag]>;
-def X86add_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>;
+def X86add_flag : SDNode<"X86ISD::ADD", SDTBinaryArithWithFlags>;
+def X86sub_flag : SDNode<"X86ISD::SUB", SDTBinaryArithWithFlags>;
+def X86smul_flag : SDNode<"X86ISD::SMUL", SDTBinaryArithWithFlags>;
+def X86umul_flag : SDNode<"X86ISD::UMUL", SDTUnaryArithWithFlags>;
+def X86inc_flag : SDNode<"X86ISD::INC", SDTUnaryArithWithFlags>;
+def X86dec_flag : SDNode<"X86ISD::DEC", SDTUnaryArithWithFlags>;
+
+def X86mul_imm : SDNode<"X86ISD::MUL_IMM", SDTIntBinOp>;
//===----------------------------------------------------------------------===//
// X86 Operand Definitions.
//
class X86MemOperand<string printMethod> : Operand<iPTR> {
let PrintMethod = printMethod;
- let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc, i32imm);
+ let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc, i32imm, i8imm);
}
def i8mem : X86MemOperand<"printi8mem">;
def f80mem : X86MemOperand<"printf80mem">;
def f128mem : X86MemOperand<"printf128mem">;
+// A version of i8mem for use on x86-64 that uses GR64_NOREX instead of
+// plain GR64, so that it doesn't potentially require a REX prefix.
+def i8mem_NOREX : Operand<i64> {
+ let PrintMethod = "printi8mem";
+ let MIOperandInfo = (ops GR64_NOREX, i8imm, GR64_NOREX, i32imm, i8imm);
+}
+
def lea32mem : Operand<i32> {
- let PrintMethod = "printi32mem";
+ let PrintMethod = "printlea32mem";
let MIOperandInfo = (ops GR32, i8imm, GR32, i32imm);
}
//
// Define X86 specific addressing mode.
-def addr : ComplexPattern<iPTR, 4, "SelectAddr", [], []>;
+def addr : ComplexPattern<iPTR, 5, "SelectAddr", [], []>;
def lea32addr : ComplexPattern<i32, 4, "SelectLEAAddr",
[add, mul, shl, or, frameindex], []>;
// known to be 32-bit aligned or better. Ditto for i8 to i16.
def loadi16 : PatFrag<(ops node:$ptr), (i16 (unindexedload node:$ptr)), [{
LoadSDNode *LD = cast<LoadSDNode>(N);
+ if (const Value *Src = LD->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
ISD::LoadExtType ExtType = LD->getExtensionType();
if (ExtType == ISD::NON_EXTLOAD)
return true;
def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
LoadSDNode *LD = cast<LoadSDNode>(N);
+ if (const Value *Src = LD->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
ISD::LoadExtType ExtType = LD->getExtensionType();
if (ExtType == ISD::EXTLOAD)
return LD->getAlignment() >= 2 && !LD->isVolatile();
def loadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
LoadSDNode *LD = cast<LoadSDNode>(N);
+ if (const Value *Src = LD->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
ISD::LoadExtType ExtType = LD->getExtensionType();
if (ExtType == ISD::NON_EXTLOAD)
return true;
def nvloadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
LoadSDNode *LD = cast<LoadSDNode>(N);
+ if (const Value *Src = LD->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
if (LD->isVolatile())
return false;
ISD::LoadExtType ExtType = LD->getExtensionType();
}]>;
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;
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ return PT->getAddressSpace() == 256;
return false;
}]>;
-def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr))>;
-def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr))>;
+def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr)), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
+ return true;
+}]>;
+def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr)), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
+ return true;
+}]>;
-def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr))>;
-def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr))>;
-def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr))>;
+def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr)), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
+ return true;
+}]>;
+def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr)), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
+ return true;
+}]>;
+def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr)), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() != 0)
+ return false;
+ return true;
+}]>;
def sextloadi16i8 : PatFrag<(ops node:$ptr), (i16 (sextloadi8 node:$ptr))>;
def sextloadi32i8 : PatFrag<(ops node:$ptr), (i32 (sextloadi8 node:$ptr))>;
def and_su : PatFrag<(ops node:$lhs, node:$rhs), (and node:$lhs, node:$rhs), [{
return N->hasOneUse();
}]>;
+// An 'srl' node with a single use.
+def srl_su : PatFrag<(ops node:$lhs, node:$rhs), (srl node:$lhs, node:$rhs), [{
+ return N->hasOneUse();
+}]>;
+// An 'trunc' node with a single use.
+def trunc_su : PatFrag<(ops node:$src), (trunc node:$src), [{
+ return N->hasOneUse();
+}]>;
// 'shld' and 'shrd' instruction patterns. Note that even though these have
// the srl and shl in their patterns, the C++ code must still check for them,
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
Uses = [ESP] in {
def CALLpcrel32 : Ii32<0xE8, RawFrm, (outs), (ins i32imm:$dst,variable_ops),
- "call\t${dst:call}", []>;
+ "call\t${dst:call}", [(X86call imm:$dst)]>,
+ Requires<[In32BitMode]>;
def CALL32r : I<0xFF, MRM2r, (outs), (ins GR32:$dst, variable_ops),
"call\t{*}$dst", [(X86call GR32:$dst)]>;
def CALL32m : I<0xFF, MRM2m, (outs), (ins i32mem:$dst, variable_ops),
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:$src))]>;
+ [(set GR8:$dst, (loadi8 addr:$src))]>;
def MOV16rm : I<0x8B, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src),
"mov{w}\t{$src, $dst|$dst, $src}",
- [(set GR16:$dst, (load addr:$src))]>, OpSize;
+ [(set GR16:$dst, (loadi16 addr:$src))]>, OpSize;
def MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
"mov{l}\t{$src, $dst|$dst, $src}",
- [(set GR32:$dst, (load addr:$src))]>;
+ [(set GR32:$dst, (loadi32 addr:$src))]>;
}
def MOV8mr : I<0x88, MRMDestMem, (outs), (ins i8mem :$dst, GR8 :$src),
def MOV32mr : I<0x89, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src),
"mov{l}\t{$src, $dst|$dst, $src}",
[(store GR32:$src, addr:$dst)]>;
-
+
+// Versions of MOV8rr and MOV8mr that use i8mem_NOREX and GR8_NOREX so that they
+// can be used for copying and storing h registers, which can't be encoded when
+// a REX prefix is present.
+let neverHasSideEffects = 1 in
+def MOV8rr_NOREX : I<0x88, MRMDestReg,
+ (outs GR8_NOREX:$dst), (ins GR8_NOREX:$src),
+ "mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>;
+def MOV8mr_NOREX : I<0x88, MRMDestMem,
+ (outs), (ins i8mem_NOREX:$dst, GR8_NOREX:$src),
+ "mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>;
+
//===----------------------------------------------------------------------===//
// Fixed-Register Multiplication and Division Instructions...
//
def AND8rm : I<0x22, MRMSrcMem,
(outs GR8 :$dst), (ins GR8 :$src1, i8mem :$src2),
"and{b}\t{$src2, $dst|$dst, $src2}",
- [(set GR8:$dst, (and GR8:$src1, (load addr:$src2))),
+ [(set GR8:$dst, (and GR8:$src1, (loadi8 addr:$src2))),
(implicit EFLAGS)]>;
def AND16rm : I<0x23, MRMSrcMem,
(outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
"and{w}\t{$src2, $dst|$dst, $src2}",
- [(set GR16:$dst, (and GR16:$src1, (load addr:$src2))),
+ [(set GR16:$dst, (and GR16:$src1, (loadi16 addr:$src2))),
(implicit EFLAGS)]>, OpSize;
def AND32rm : I<0x23, MRMSrcMem,
(outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
"and{l}\t{$src2, $dst|$dst, $src2}",
- [(set GR32:$dst, (and GR32:$src1, (load addr:$src2))),
+ [(set GR32:$dst, (and GR32:$src1, (loadi32 addr:$src2))),
(implicit EFLAGS)]>;
def AND8ri : Ii8<0x80, MRM4r,
"movz{wl|x}\t{$src, $dst|$dst, $src}",
[(set GR32:$dst, (zextloadi32i16 addr:$src))]>, TB;
+// These are the same as the regular regular MOVZX32rr8 and MOVZX32rm8
+// except that they use GR32_NOREX for the output operand register class
+// instead of GR32. This allows them to operate on h registers on x86-64.
+def MOVZX32_NOREXrr8 : I<0xB6, MRMSrcReg,
+ (outs GR32_NOREX:$dst), (ins GR8:$src),
+ "movz{bl|x}\t{$src, $dst|$dst, $src} # NOREX",
+ []>, TB;
+def MOVZX32_NOREXrm8 : I<0xB6, MRMSrcMem,
+ (outs GR32_NOREX:$dst), (ins i8mem:$src),
+ "movz{bl|x}\t{$src, $dst|$dst, $src} # NOREX",
+ []>, TB;
+
let neverHasSideEffects = 1 in {
let Defs = [AX], Uses = [AL] in
def CBW : I<0x98, RawFrm, (outs), (ins),
[(set GR32:$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, 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, $src}", []>;
-
-def MOV16_rr : I<0x89, MRMDestReg, (outs GR16_:$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, $src}", []>;
-} // neverHasSideEffects
-
-let canFoldAsLoad = 1, mayLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
-def MOV16_rm : I<0x8B, MRMSrcMem, (outs GR16_:$dst), (ins i16mem:$src),
- "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize;
-def MOV32_rm : I<0x8B, MRMSrcMem, (outs GR32_:$dst), (ins i32mem:$src),
- "mov{l}\t{$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:$src)))]>;
-
-let AddedComplexity = 15 in
-def TLS_gs_ri : I<0x8B, Pseudo, (outs GR32:$dst), (ins i32imm:$src),
- "movl\t%gs:${src:mem}, $dst",
- [(set GR32:$dst,
- (load (add X86TLStp, (X86Wrapper tglobaltlsaddr:$src))))]>,
- SegGS;
-
-def TLS_tp : I<0x8B, Pseudo, (outs GR32:$dst), (ins),
- "movl\t%gs:0, $dst",
- [(set GR32:$dst, X86TLStp)]>, SegGS;
+// All calls clobber the non-callee saved registers. ESP is marked as
+// a use to prevent stack-pointer assignments that appear immediately
+// before calls from potentially appearing dead.
+let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0,
+ MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
+ XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
+ XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
+ Uses = [ESP, EBX] in
+def TLS_addr32 : I<0, Pseudo, (outs), (ins i32imm:$sym),
+ "leal\t${sym:mem}(,%ebx,1), %eax; call\t___tls_get_addr@PLT",
+ [(X86tlsaddr tglobaltlsaddr:$sym)]>,
+ Requires<[In32BitMode]>;
let AddedComplexity = 5 in
def GS_MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
// r & (2^16-1) ==> movz
def : Pat<(and GR32:$src1, 0xffff),
- (MOVZX32rr16 (i16 (EXTRACT_SUBREG GR32:$src1, x86_subreg_16bit)))>;
+ (MOVZX32rr16 (EXTRACT_SUBREG GR32:$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)))>,
+ (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src1, GR32_),
+ x86_subreg_8bit))>,
Requires<[In32BitMode]>;
// r & (2^8-1) ==> movz
def : Pat<(and GR16:$src1, 0xff),
- (MOVZX16rr8 (i8 (EXTRACT_SUBREG (MOV16to16_ GR16:$src1),
- x86_subreg_8bit)))>,
+ (MOVZX16rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src1, GR16_),
+ x86_subreg_8bit))>,
Requires<[In32BitMode]>;
// sext_inreg patterns
def : Pat<(sext_inreg GR32:$src, i16),
- (MOVSX32rr16 (i16 (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit)))>;
+ (MOVSX32rr16 (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit))>;
def : Pat<(sext_inreg GR32:$src, i8),
- (MOVSX32rr8 (i8 (EXTRACT_SUBREG (MOV32to32_ GR32:$src),
- x86_subreg_8bit)))>,
+ (MOVSX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_),
+ x86_subreg_8bit))>,
Requires<[In32BitMode]>;
def : Pat<(sext_inreg GR16:$src, i8),
- (MOVSX16rr8 (i8 (EXTRACT_SUBREG (MOV16to16_ GR16:$src),
- x86_subreg_8bit)))>,
+ (MOVSX16rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_),
+ x86_subreg_8bit))>,
Requires<[In32BitMode]>;
// trunc patterns
def : Pat<(i16 (trunc GR32:$src)),
- (i16 (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit))>;
+ (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit)>;
def : Pat<(i8 (trunc GR32:$src)),
- (i8 (EXTRACT_SUBREG (MOV32to32_ GR32:$src), x86_subreg_8bit))>,
+ (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_),
+ x86_subreg_8bit)>,
Requires<[In32BitMode]>;
def : Pat<(i8 (trunc GR16:$src)),
- (i8 (EXTRACT_SUBREG (MOV16to16_ GR16:$src), x86_subreg_8bit))>,
+ (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_),
+ x86_subreg_8bit)>,
+ Requires<[In32BitMode]>;
+
+// h-register tricks
+def : Pat<(i8 (trunc (srl_su GR16:$src, (i8 8)))),
+ (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_),
+ x86_subreg_8bit_hi)>,
+ Requires<[In32BitMode]>;
+def : Pat<(i8 (trunc (srl_su GR32:$src, (i8 8)))),
+ (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_),
+ x86_subreg_8bit_hi)>,
+ Requires<[In32BitMode]>;
+def : Pat<(srl_su GR16:$src, (i8 8)),
+ (EXTRACT_SUBREG
+ (MOVZX32rr8
+ (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_),
+ x86_subreg_8bit_hi)),
+ x86_subreg_16bit)>,
+ Requires<[In32BitMode]>;
+def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)),
+ (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_),
+ x86_subreg_8bit_hi))>,
Requires<[In32BitMode]>;
// (shl x, 1) ==> (add x, x)
(SHLD16mri8 addr:$dst, GR16:$src2, (i8 imm:$amt1))>;
//===----------------------------------------------------------------------===//
-// Overflow Patterns
+// EFLAGS-defining Patterns
//===----------------------------------------------------------------------===//
-// Register-Register Addition with Overflow
-def : Pat<(parallel (X86add_ovf GR8:$src1, GR8:$src2),
+// Register-Register Addition with EFLAGS result
+def : Pat<(parallel (X86add_flag GR8:$src1, GR8:$src2),
(implicit EFLAGS)),
(ADD8rr GR8:$src1, GR8:$src2)>;
-// Register-Register Addition with Overflow
-def : Pat<(parallel (X86add_ovf GR16:$src1, GR16:$src2),
+// Register-Register Addition with EFLAGS result
+def : Pat<(parallel (X86add_flag GR16:$src1, GR16:$src2),
(implicit EFLAGS)),
(ADD16rr GR16:$src1, GR16:$src2)>;
-def : Pat<(parallel (X86add_ovf GR32:$src1, GR32:$src2),
+def : Pat<(parallel (X86add_flag GR32:$src1, GR32:$src2),
(implicit EFLAGS)),
(ADD32rr GR32:$src1, GR32:$src2)>;
-// Register-Memory Addition with Overflow
-def : Pat<(parallel (X86add_ovf GR8:$src1, (load addr:$src2)),
+// Register-Memory Addition with EFLAGS result
+def : Pat<(parallel (X86add_flag GR8:$src1, (loadi8 addr:$src2)),
(implicit EFLAGS)),
(ADD8rm GR8:$src1, addr:$src2)>;
-def : Pat<(parallel (X86add_ovf GR16:$src1, (load addr:$src2)),
+def : Pat<(parallel (X86add_flag GR16:$src1, (loadi16 addr:$src2)),
(implicit EFLAGS)),
(ADD16rm GR16:$src1, addr:$src2)>;
-def : Pat<(parallel (X86add_ovf GR32:$src1, (load addr:$src2)),
+def : Pat<(parallel (X86add_flag GR32:$src1, (loadi32 addr:$src2)),
(implicit EFLAGS)),
(ADD32rm GR32:$src1, addr:$src2)>;
-// Register-Integer Addition with Overflow
-def : Pat<(parallel (X86add_ovf GR8:$src1, imm:$src2),
+// Register-Integer Addition with EFLAGS result
+def : Pat<(parallel (X86add_flag GR8:$src1, imm:$src2),
(implicit EFLAGS)),
(ADD8ri GR8:$src1, imm:$src2)>;
-// Register-Integer Addition with Overflow
-def : Pat<(parallel (X86add_ovf GR16:$src1, imm:$src2),
+// Register-Integer Addition with EFLAGS result
+def : Pat<(parallel (X86add_flag GR16:$src1, imm:$src2),
(implicit EFLAGS)),
(ADD16ri GR16:$src1, imm:$src2)>;
-def : Pat<(parallel (X86add_ovf GR32:$src1, imm:$src2),
+def : Pat<(parallel (X86add_flag GR32:$src1, imm:$src2),
(implicit EFLAGS)),
(ADD32ri GR32:$src1, imm:$src2)>;
-def : Pat<(parallel (X86add_ovf GR16:$src1, i16immSExt8:$src2),
+def : Pat<(parallel (X86add_flag GR16:$src1, i16immSExt8:$src2),
(implicit EFLAGS)),
(ADD16ri8 GR16:$src1, i16immSExt8:$src2)>;
-def : Pat<(parallel (X86add_ovf GR32:$src1, i32immSExt8:$src2),
+def : Pat<(parallel (X86add_flag GR32:$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:$src2),
+// Memory-Register Addition with EFLAGS result
+def : Pat<(parallel (store (X86add_flag (loadi8 addr:$dst), GR8:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD8mr addr:$dst, GR8:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (load addr:$dst), GR16:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi16 addr:$dst), GR16:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD16mr addr:$dst, GR16:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (load addr:$dst), GR32:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi32 addr:$dst), GR32:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD32mr addr:$dst, GR32:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (loadi8 addr:$dst), imm:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi8 addr:$dst), imm:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD8mi addr:$dst, imm:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (loadi16 addr:$dst), imm:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi16 addr:$dst), imm:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD16mi addr:$dst, imm:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (loadi32 addr:$dst), imm:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi32 addr:$dst), imm:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD32mi addr:$dst, imm:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (load addr:$dst), i16immSExt8:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi16 addr:$dst), i16immSExt8:$src2),
addr:$dst),
(implicit EFLAGS)),
(ADD16mi8 addr:$dst, i16immSExt8:$src2)>;
-def : Pat<(parallel (store (X86add_ovf (load addr:$dst), i32immSExt8:$src2),
+def : Pat<(parallel (store (X86add_flag (loadi32 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:$src2),
+// Register-Register Subtraction with EFLAGS result
+def : Pat<(parallel (X86sub_flag GR8:$src1, GR8:$src2),
(implicit EFLAGS)),
(SUB8rr GR8:$src1, GR8:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR16:$src1, GR16:$src2),
+def : Pat<(parallel (X86sub_flag GR16:$src1, GR16:$src2),
(implicit EFLAGS)),
(SUB16rr GR16:$src1, GR16:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR32:$src1, GR32:$src2),
+def : Pat<(parallel (X86sub_flag GR32:$src1, GR32:$src2),
(implicit EFLAGS)),
(SUB32rr GR32:$src1, GR32:$src2)>;
-// Register-Memory Subtraction with Overflow
-def : Pat<(parallel (X86sub_ovf GR8:$src1, (load addr:$src2)),
+// Register-Memory Subtraction with EFLAGS result
+def : Pat<(parallel (X86sub_flag GR8:$src1, (loadi8 addr:$src2)),
(implicit EFLAGS)),
(SUB8rm GR8:$src1, addr:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR16:$src1, (load addr:$src2)),
+def : Pat<(parallel (X86sub_flag GR16:$src1, (loadi16 addr:$src2)),
(implicit EFLAGS)),
(SUB16rm GR16:$src1, addr:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR32:$src1, (load addr:$src2)),
+def : Pat<(parallel (X86sub_flag GR32:$src1, (loadi32 addr:$src2)),
(implicit EFLAGS)),
(SUB32rm GR32:$src1, addr:$src2)>;
-// Register-Integer Subtraction with Overflow
-def : Pat<(parallel (X86sub_ovf GR8:$src1, imm:$src2),
+// Register-Integer Subtraction with EFLAGS result
+def : Pat<(parallel (X86sub_flag GR8:$src1, imm:$src2),
(implicit EFLAGS)),
(SUB8ri GR8:$src1, imm:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR16:$src1, imm:$src2),
+def : Pat<(parallel (X86sub_flag GR16:$src1, imm:$src2),
(implicit EFLAGS)),
(SUB16ri GR16:$src1, imm:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR32:$src1, imm:$src2),
+def : Pat<(parallel (X86sub_flag GR32:$src1, imm:$src2),
(implicit EFLAGS)),
(SUB32ri GR32:$src1, imm:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR16:$src1, i16immSExt8:$src2),
+def : Pat<(parallel (X86sub_flag GR16:$src1, i16immSExt8:$src2),
(implicit EFLAGS)),
(SUB16ri8 GR16:$src1, i16immSExt8:$src2)>;
-def : Pat<(parallel (X86sub_ovf GR32:$src1, i32immSExt8:$src2),
+def : Pat<(parallel (X86sub_flag GR32:$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:$src2),
+// Memory-Register Subtraction with EFLAGS result
+def : Pat<(parallel (store (X86sub_flag (loadi8 addr:$dst), GR8:$src2),
addr:$dst),
(implicit EFLAGS)),
(SUB8mr addr:$dst, GR8:$src2)>;
-def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), GR16:$src2),
+def : Pat<(parallel (store (X86sub_flag (loadi16 addr:$dst), GR16:$src2),
addr:$dst),
(implicit EFLAGS)),
(SUB16mr addr:$dst, GR16:$src2)>;
-def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), GR32:$src2),
+def : Pat<(parallel (store (X86sub_flag (loadi32 addr:$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),
+// Memory-Integer Subtraction with EFLAGS result
+def : Pat<(parallel (store (X86sub_flag (loadi8 addr:$dst), imm:$src2),
addr:$dst),
(implicit EFLAGS)),
(SUB8mi addr:$dst, imm:$src2)>;
-def : Pat<(parallel (store (X86sub_ovf (loadi16 addr:$dst), imm:$src2),
+def : Pat<(parallel (store (X86sub_flag (loadi16 addr:$dst), imm:$src2),
addr:$dst),
(implicit EFLAGS)),
(SUB16mi addr:$dst, imm:$src2)>;
-def : Pat<(parallel (store (X86sub_ovf (loadi32 addr:$dst), imm:$src2),
+def : Pat<(parallel (store (X86sub_flag (loadi32 addr:$dst), imm:$src2),
addr:$dst),
(implicit EFLAGS)),
(SUB32mi addr:$dst, imm:$src2)>;
-def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), i16immSExt8:$src2),
+def : Pat<(parallel (store (X86sub_flag (loadi16 addr:$dst), i16immSExt8:$src2),
addr:$dst),
(implicit EFLAGS)),
(SUB16mi8 addr:$dst, i16immSExt8:$src2)>;
-def : Pat<(parallel (store (X86sub_ovf (load addr:$dst), i32immSExt8:$src2),
+def : Pat<(parallel (store (X86sub_flag (loadi32 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:$src2),
+// Register-Register Signed Integer Multiply with EFLAGS result
+def : Pat<(parallel (X86smul_flag GR16:$src1, GR16:$src2),
(implicit EFLAGS)),
(IMUL16rr GR16:$src1, GR16:$src2)>;
-def : Pat<(parallel (X86smul_ovf GR32:$src1, GR32:$src2),
+def : Pat<(parallel (X86smul_flag GR32:$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:$src2)),
+// Register-Memory Signed Integer Multiply with EFLAGS result
+def : Pat<(parallel (X86smul_flag GR16:$src1, (loadi16 addr:$src2)),
(implicit EFLAGS)),
(IMUL16rm GR16:$src1, addr:$src2)>;
-def : Pat<(parallel (X86smul_ovf GR32:$src1, (load addr:$src2)),
+def : Pat<(parallel (X86smul_flag GR32:$src1, (loadi32 addr:$src2)),
(implicit EFLAGS)),
(IMUL32rm GR32:$src1, addr:$src2)>;
-// Register-Integer Signed Integer Multiply with Overflow
-def : Pat<(parallel (X86smul_ovf GR16:$src1, imm:$src2),
+// Register-Integer Signed Integer Multiply with EFLAGS result
+def : Pat<(parallel (X86smul_flag GR16:$src1, imm:$src2),
(implicit EFLAGS)),
(IMUL16rri GR16:$src1, imm:$src2)>;
-def : Pat<(parallel (X86smul_ovf GR32:$src1, imm:$src2),
+def : Pat<(parallel (X86smul_flag GR32:$src1, imm:$src2),
(implicit EFLAGS)),
(IMUL32rri GR32:$src1, imm:$src2)>;
-def : Pat<(parallel (X86smul_ovf GR16:$src1, i16immSExt8:$src2),
+def : Pat<(parallel (X86smul_flag GR16:$src1, i16immSExt8:$src2),
(implicit EFLAGS)),
(IMUL16rri8 GR16:$src1, i16immSExt8:$src2)>;
-def : Pat<(parallel (X86smul_ovf GR32:$src1, i32immSExt8:$src2),
+def : Pat<(parallel (X86smul_flag GR32:$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:$src2),
+// Memory-Integer Signed Integer Multiply with EFLAGS result
+def : Pat<(parallel (X86smul_flag (loadi16 addr:$src1), imm:$src2),
(implicit EFLAGS)),
(IMUL16rmi addr:$src1, imm:$src2)>;
-def : Pat<(parallel (X86smul_ovf (load addr:$src1), imm:$src2),
+def : Pat<(parallel (X86smul_flag (loadi32 addr:$src1), imm:$src2),
(implicit EFLAGS)),
(IMUL32rmi addr:$src1, imm:$src2)>;
-def : Pat<(parallel (X86smul_ovf (load addr:$src1), i16immSExt8:$src2),
+def : Pat<(parallel (X86smul_flag (loadi16 addr:$src1), i16immSExt8:$src2),
(implicit EFLAGS)),
(IMUL16rmi8 addr:$src1, i16immSExt8:$src2)>;
-def : Pat<(parallel (X86smul_ovf (load addr:$src1), i32immSExt8:$src2),
+def : Pat<(parallel (X86smul_flag (loadi32 addr:$src1), i32immSExt8:$src2),
(implicit EFLAGS)),
(IMUL32rmi8 addr:$src1, i32immSExt8:$src2)>;
-// Optimize multiple with overflow by 2.
+// Optimize multiply by 2 with EFLAGS result.
let AddedComplexity = 2 in {
-def : Pat<(parallel (X86smul_ovf GR16:$src1, 2),
+def : Pat<(parallel (X86smul_flag GR16:$src1, 2),
(implicit EFLAGS)),
(ADD16rr GR16:$src1, GR16:$src1)>;
-def : Pat<(parallel (X86smul_ovf GR32:$src1, 2),
+def : Pat<(parallel (X86smul_flag GR32:$src1, 2),
(implicit EFLAGS)),
(ADD32rr GR32:$src1, GR32:$src1)>;
}
+// INC and DEC with EFLAGS result. Note that these do not set CF.
+def : Pat<(parallel (X86inc_flag GR8:$src), (implicit EFLAGS)),
+ (INC8r GR8:$src)>;
+def : Pat<(parallel (store (i8 (X86inc_flag (loadi8 addr:$dst))), addr:$dst),
+ (implicit EFLAGS)),
+ (INC8m addr:$dst)>;
+def : Pat<(parallel (X86dec_flag GR8:$src), (implicit EFLAGS)),
+ (DEC8r GR8:$src)>;
+def : Pat<(parallel (store (i8 (X86dec_flag (loadi8 addr:$dst))), addr:$dst),
+ (implicit EFLAGS)),
+ (DEC8m addr:$dst)>;
+
+def : Pat<(parallel (X86inc_flag GR16:$src), (implicit EFLAGS)),
+ (INC16r GR16:$src)>, Requires<[In32BitMode]>;
+def : Pat<(parallel (store (i16 (X86inc_flag (loadi16 addr:$dst))), addr:$dst),
+ (implicit EFLAGS)),
+ (INC16m addr:$dst)>, Requires<[In32BitMode]>;
+def : Pat<(parallel (X86dec_flag GR16:$src), (implicit EFLAGS)),
+ (DEC16r GR16:$src)>, Requires<[In32BitMode]>;
+def : Pat<(parallel (store (i16 (X86dec_flag (loadi16 addr:$dst))), addr:$dst),
+ (implicit EFLAGS)),
+ (DEC16m addr:$dst)>, Requires<[In32BitMode]>;
+
+def : Pat<(parallel (X86inc_flag GR32:$src), (implicit EFLAGS)),
+ (INC32r GR32:$src)>, Requires<[In32BitMode]>;
+def : Pat<(parallel (store (i32 (X86inc_flag (loadi32 addr:$dst))), addr:$dst),
+ (implicit EFLAGS)),
+ (INC32m addr:$dst)>, Requires<[In32BitMode]>;
+def : Pat<(parallel (X86dec_flag GR32:$src), (implicit EFLAGS)),
+ (DEC32r GR32:$src)>, Requires<[In32BitMode]>;
+def : Pat<(parallel (store (i32 (X86dec_flag (loadi32 addr:$dst))), addr:$dst),
+ (implicit EFLAGS)),
+ (DEC32m addr:$dst)>, Requires<[In32BitMode]>;
+
//===----------------------------------------------------------------------===//
// Floating Point Stack Support
//===----------------------------------------------------------------------===//
projects / oota-llvm.git / blobdiff