diff options
Diffstat (limited to 'contrib/llvm/lib/Target/X86/X86InstrInfo.td')
| -rw-r--r-- | contrib/llvm/lib/Target/X86/X86InstrInfo.td | 4940 |
1 files changed, 4940 insertions, 0 deletions
diff --git a/contrib/llvm/lib/Target/X86/X86InstrInfo.td b/contrib/llvm/lib/Target/X86/X86InstrInfo.td new file mode 100644 index 0000000..1efef5a --- /dev/null +++ b/contrib/llvm/lib/Target/X86/X86InstrInfo.td @@ -0,0 +1,4940 @@ +//===----------------------------------------------------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file describes the X86 instruction set, defining the instructions, and +// properties of the instructions which are needed for code generation, machine +// code emission, and analysis. +// +//===----------------------------------------------------------------------===// + +//===----------------------------------------------------------------------===// +// X86 specific DAG Nodes. +// + +def SDTIntShiftDOp: SDTypeProfile<1, 3, + [SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, + SDTCisInt<0>, SDTCisInt<3>]>; + +def SDTX86CmpTest : SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisSameAs<1, 2>]>; + +def SDTX86Cmov : SDTypeProfile<1, 4, + [SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2>, + SDTCisVT<3, i8>, SDTCisVT<4, i32>]>; + +// Unary and binary operator instructions that set EFLAGS as a side-effect. +def SDTUnaryArithWithFlags : SDTypeProfile<2, 1, + [SDTCisInt<0>, SDTCisVT<1, i32>]>; + +def SDTBinaryArithWithFlags : SDTypeProfile<2, 2, + [SDTCisSameAs<0, 2>, + SDTCisSameAs<0, 3>, + SDTCisInt<0>, SDTCisVT<1, i32>]>; +def SDTX86BrCond : SDTypeProfile<0, 3, + [SDTCisVT<0, OtherVT>, + SDTCisVT<1, i8>, SDTCisVT<2, i32>]>; + +def SDTX86SetCC : SDTypeProfile<1, 2, + [SDTCisVT<0, i8>, + SDTCisVT<1, i8>, SDTCisVT<2, i32>]>; +def SDTX86SetCC_C : SDTypeProfile<1, 2, + [SDTCisInt<0>, + SDTCisVT<1, i8>, SDTCisVT<2, i32>]>; + +def SDTX86cas : SDTypeProfile<0, 3, [SDTCisPtrTy<0>, SDTCisInt<1>, + SDTCisVT<2, i8>]>; +def SDTX86cas8 : SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>; + +def SDTX86atomicBinary : SDTypeProfile<2, 3, [SDTCisInt<0>, SDTCisInt<1>, + SDTCisPtrTy<2>, SDTCisInt<3>,SDTCisInt<4>]>; +def SDTX86Ret : SDTypeProfile<0, -1, [SDTCisVT<0, i16>]>; + +def SDT_X86CallSeqStart : SDCallSeqStart<[SDTCisVT<0, i32>]>; +def SDT_X86CallSeqEnd : SDCallSeqEnd<[SDTCisVT<0, i32>, + SDTCisVT<1, i32>]>; + +def SDT_X86Call : SDTypeProfile<0, -1, [SDTCisVT<0, iPTR>]>; + +def SDT_X86VASTART_SAVE_XMM_REGS : SDTypeProfile<0, -1, [SDTCisVT<0, i8>, + SDTCisVT<1, iPTR>, + SDTCisVT<2, iPTR>]>; + +def SDTX86RepStr : SDTypeProfile<0, 1, [SDTCisVT<0, OtherVT>]>; + +def SDTX86Void : SDTypeProfile<0, 0, []>; + +def SDTX86Wrapper : SDTypeProfile<1, 1, [SDTCisSameAs<0, 1>, SDTCisPtrTy<0>]>; + +def SDT_X86TLSADDR : SDTypeProfile<0, 1, [SDTCisInt<0>]>; + +def SDT_X86TLSCALL : SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>; + +def SDT_X86SegmentBaseAddress : SDTypeProfile<1, 1, [SDTCisPtrTy<0>]>; + +def SDT_X86EHRET : SDTypeProfile<0, 1, [SDTCisInt<0>]>; + +def SDT_X86TCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>, SDTCisVT<1, i32>]>; + +def X86bsf : SDNode<"X86ISD::BSF", SDTUnaryArithWithFlags>; +def X86bsr : SDNode<"X86ISD::BSR", SDTUnaryArithWithFlags>; +def X86shld : SDNode<"X86ISD::SHLD", SDTIntShiftDOp>; +def X86shrd : SDNode<"X86ISD::SHRD", SDTIntShiftDOp>; + +def X86cmp : SDNode<"X86ISD::CMP" , SDTX86CmpTest>; +def X86bt : SDNode<"X86ISD::BT", SDTX86CmpTest>; + +def X86cmov : SDNode<"X86ISD::CMOV", SDTX86Cmov>; +def X86brcond : SDNode<"X86ISD::BRCOND", SDTX86BrCond, + [SDNPHasChain]>; +def X86setcc : SDNode<"X86ISD::SETCC", SDTX86SetCC>; +def X86setcc_c : SDNode<"X86ISD::SETCC_CARRY", SDTX86SetCC_C>; + +def X86cas : SDNode<"X86ISD::LCMPXCHG_DAG", SDTX86cas, + [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore, + SDNPMayLoad]>; +def X86cas8 : SDNode<"X86ISD::LCMPXCHG8_DAG", SDTX86cas8, + [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore, + SDNPMayLoad]>; +def X86AtomAdd64 : SDNode<"X86ISD::ATOMADD64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomSub64 : SDNode<"X86ISD::ATOMSUB64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomOr64 : SDNode<"X86ISD::ATOMOR64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomXor64 : SDNode<"X86ISD::ATOMXOR64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomAnd64 : SDNode<"X86ISD::ATOMAND64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomNand64 : SDNode<"X86ISD::ATOMNAND64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomSwap64 : SDNode<"X86ISD::ATOMSWAP64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86retflag : SDNode<"X86ISD::RET_FLAG", SDTX86Ret, + [SDNPHasChain, SDNPOptInFlag, SDNPVariadic]>; + +def X86vastart_save_xmm_regs : + SDNode<"X86ISD::VASTART_SAVE_XMM_REGS", + SDT_X86VASTART_SAVE_XMM_REGS, + [SDNPHasChain, SDNPVariadic]>; + +def X86callseq_start : + SDNode<"ISD::CALLSEQ_START", SDT_X86CallSeqStart, + [SDNPHasChain, SDNPOutFlag]>; +def X86callseq_end : + SDNode<"ISD::CALLSEQ_END", SDT_X86CallSeqEnd, + [SDNPHasChain, SDNPOptInFlag, SDNPOutFlag]>; + +def X86call : SDNode<"X86ISD::CALL", SDT_X86Call, + [SDNPHasChain, SDNPOutFlag, SDNPOptInFlag, + SDNPVariadic]>; + +def X86rep_stos: SDNode<"X86ISD::REP_STOS", SDTX86RepStr, + [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore]>; +def X86rep_movs: SDNode<"X86ISD::REP_MOVS", SDTX86RepStr, + [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore, + SDNPMayLoad]>; + +def X86rdtsc : SDNode<"X86ISD::RDTSC_DAG", SDTX86Void, + [SDNPHasChain, SDNPOutFlag, SDNPSideEffect]>; + +def X86Wrapper : SDNode<"X86ISD::Wrapper", SDTX86Wrapper>; +def X86WrapperRIP : SDNode<"X86ISD::WrapperRIP", SDTX86Wrapper>; + +def X86tlsaddr : SDNode<"X86ISD::TLSADDR", SDT_X86TLSADDR, + [SDNPHasChain, SDNPOptInFlag, SDNPOutFlag]>; +def X86SegmentBaseAddress : SDNode<"X86ISD::SegmentBaseAddress", + SDT_X86SegmentBaseAddress, []>; + +def X86ehret : SDNode<"X86ISD::EH_RETURN", SDT_X86EHRET, + [SDNPHasChain]>; + +def X86tcret : SDNode<"X86ISD::TC_RETURN", SDT_X86TCRET, + [SDNPHasChain, SDNPOptInFlag, SDNPVariadic]>; + +def X86add_flag : SDNode<"X86ISD::ADD", SDTBinaryArithWithFlags, + [SDNPCommutative]>; +def X86sub_flag : SDNode<"X86ISD::SUB", SDTBinaryArithWithFlags>; +def X86smul_flag : SDNode<"X86ISD::SMUL", SDTBinaryArithWithFlags, + [SDNPCommutative]>; +def X86umul_flag : SDNode<"X86ISD::UMUL", SDTUnaryArithWithFlags, + [SDNPCommutative]>; + +def X86inc_flag : SDNode<"X86ISD::INC", SDTUnaryArithWithFlags>; +def X86dec_flag : SDNode<"X86ISD::DEC", SDTUnaryArithWithFlags>; +def X86or_flag : SDNode<"X86ISD::OR", SDTBinaryArithWithFlags, + [SDNPCommutative]>; +def X86xor_flag : SDNode<"X86ISD::XOR", SDTBinaryArithWithFlags, + [SDNPCommutative]>; +def X86and_flag : SDNode<"X86ISD::AND", SDTBinaryArithWithFlags, + [SDNPCommutative]>; + +def X86mul_imm : SDNode<"X86ISD::MUL_IMM", SDTIntBinOp>; + +def X86MingwAlloca : SDNode<"X86ISD::MINGW_ALLOCA", SDTX86Void, + [SDNPHasChain, SDNPInFlag, SDNPOutFlag]>; + +def X86TLSCall : SDNode<"X86ISD::TLSCALL", SDT_X86TLSCALL, + []>; + +//===----------------------------------------------------------------------===// +// X86 Operand Definitions. +// + +// A version of ptr_rc which excludes SP, ESP, and RSP. This is used for +// the index operand of an address, to conform to x86 encoding restrictions. +def ptr_rc_nosp : PointerLikeRegClass<1>; + +// *mem - Operand definitions for the funky X86 addressing mode operands. +// +def X86MemAsmOperand : AsmOperandClass { + let Name = "Mem"; + let SuperClasses = []; +} +def X86AbsMemAsmOperand : AsmOperandClass { + let Name = "AbsMem"; + let SuperClasses = [X86MemAsmOperand]; +} +class X86MemOperand<string printMethod> : Operand<iPTR> { + let PrintMethod = printMethod; + let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm); + let ParserMatchClass = X86MemAsmOperand; +} + +def opaque32mem : X86MemOperand<"printopaquemem">; +def opaque48mem : X86MemOperand<"printopaquemem">; +def opaque80mem : X86MemOperand<"printopaquemem">; +def opaque512mem : X86MemOperand<"printopaquemem">; + +def i8mem : X86MemOperand<"printi8mem">; +def i16mem : X86MemOperand<"printi16mem">; +def i32mem : X86MemOperand<"printi32mem">; +def i64mem : X86MemOperand<"printi64mem">; +def i128mem : X86MemOperand<"printi128mem">; +//def i256mem : X86MemOperand<"printi256mem">; +def f32mem : X86MemOperand<"printf32mem">; +def f64mem : X86MemOperand<"printf64mem">; +def f80mem : X86MemOperand<"printf80mem">; +def f128mem : X86MemOperand<"printf128mem">; +def f256mem : X86MemOperand<"printf256mem">; + +// 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_NOSP, i32imm, i8imm); + let ParserMatchClass = X86MemAsmOperand; +} + +// Special i32mem for addresses of load folding tail calls. These are not +// allowed to use callee-saved registers since they must be scheduled +// after callee-saved register are popped. +def i32mem_TC : Operand<i32> { + let PrintMethod = "printi32mem"; + let MIOperandInfo = (ops GR32_TC, i8imm, GR32_TC, i32imm, i8imm); + let ParserMatchClass = X86MemAsmOperand; +} + + +let ParserMatchClass = X86AbsMemAsmOperand, + PrintMethod = "print_pcrel_imm" in { +def i32imm_pcrel : Operand<i32>; +def i16imm_pcrel : Operand<i16>; + +def offset8 : Operand<i64>; +def offset16 : Operand<i64>; +def offset32 : Operand<i64>; +def offset64 : Operand<i64>; + +// Branch targets have OtherVT type and print as pc-relative values. +def brtarget : Operand<OtherVT>; +def brtarget8 : Operand<OtherVT>; + +} + +def SSECC : Operand<i8> { + let PrintMethod = "printSSECC"; +} + +class ImmSExtAsmOperandClass : AsmOperandClass { + let SuperClasses = [ImmAsmOperand]; + let RenderMethod = "addImmOperands"; +} + +// Sign-extended immediate classes. We don't need to define the full lattice +// here because there is no instruction with an ambiguity between ImmSExti64i32 +// and ImmSExti32i8. +// +// The strange ranges come from the fact that the assembler always works with +// 64-bit immediates, but for a 16-bit target value we want to accept both "-1" +// (which will be a -1ULL), and "0xFF" (-1 in 16-bits). + +// [0, 0x7FFFFFFF] | +// [0xFFFFFFFF80000000, 0xFFFFFFFFFFFFFFFF] +def ImmSExti64i32AsmOperand : ImmSExtAsmOperandClass { + let Name = "ImmSExti64i32"; +} + +// [0, 0x0000007F] | [0x000000000000FF80, 0x000000000000FFFF] | +// [0xFFFFFFFFFFFFFF80, 0xFFFFFFFFFFFFFFFF] +def ImmSExti16i8AsmOperand : ImmSExtAsmOperandClass { + let Name = "ImmSExti16i8"; + let SuperClasses = [ImmSExti64i32AsmOperand]; +} + +// [0, 0x0000007F] | [0x00000000FFFFFF80, 0x00000000FFFFFFFF] | +// [0xFFFFFFFFFFFFFF80, 0xFFFFFFFFFFFFFFFF] +def ImmSExti32i8AsmOperand : ImmSExtAsmOperandClass { + let Name = "ImmSExti32i8"; +} + +// [0, 0x0000007F] | +// [0xFFFFFFFFFFFFFF80, 0xFFFFFFFFFFFFFFFF] +def ImmSExti64i8AsmOperand : ImmSExtAsmOperandClass { + let Name = "ImmSExti64i8"; + let SuperClasses = [ImmSExti16i8AsmOperand, ImmSExti32i8AsmOperand, + ImmSExti64i32AsmOperand]; +} + +// A couple of more descriptive operand definitions. +// 16-bits but only 8 bits are significant. +def i16i8imm : Operand<i16> { + let ParserMatchClass = ImmSExti16i8AsmOperand; +} +// 32-bits but only 8 bits are significant. +def i32i8imm : Operand<i32> { + let ParserMatchClass = ImmSExti32i8AsmOperand; +} + +//===----------------------------------------------------------------------===// +// X86 Complex Pattern Definitions. +// + +// Define X86 specific addressing mode. +def addr : ComplexPattern<iPTR, 5, "SelectAddr", [], []>; +def lea32addr : ComplexPattern<i32, 5, "SelectLEAAddr", + [add, sub, mul, X86mul_imm, shl, or, frameindex], + []>; +def tls32addr : ComplexPattern<i32, 5, "SelectTLSADDRAddr", + [tglobaltlsaddr], []>; + +//===----------------------------------------------------------------------===// +// X86 Instruction Predicate Definitions. +def HasCMov : Predicate<"Subtarget->hasCMov()">; +def NoCMov : Predicate<"!Subtarget->hasCMov()">; +def HasMMX : Predicate<"Subtarget->hasMMX()">; +def HasSSE1 : Predicate<"Subtarget->hasSSE1()">; +def HasSSE2 : Predicate<"Subtarget->hasSSE2()">; +def HasSSE3 : Predicate<"Subtarget->hasSSE3()">; +def HasSSSE3 : Predicate<"Subtarget->hasSSSE3()">; +def HasSSE41 : Predicate<"Subtarget->hasSSE41()">; +def HasSSE42 : Predicate<"Subtarget->hasSSE42()">; +def HasSSE4A : Predicate<"Subtarget->hasSSE4A()">; +def HasAVX : Predicate<"Subtarget->hasAVX()">; +def HasFMA3 : Predicate<"Subtarget->hasFMA3()">; +def HasFMA4 : Predicate<"Subtarget->hasFMA4()">; +def FPStackf32 : Predicate<"!Subtarget->hasSSE1()">; +def FPStackf64 : Predicate<"!Subtarget->hasSSE2()">; +def In32BitMode : Predicate<"!Subtarget->is64Bit()">; +def In64BitMode : Predicate<"Subtarget->is64Bit()">; +def IsWin64 : Predicate<"Subtarget->isTargetWin64()">; +def NotWin64 : Predicate<"!Subtarget->isTargetWin64()">; +def SmallCode : Predicate<"TM.getCodeModel() == CodeModel::Small">; +def KernelCode : Predicate<"TM.getCodeModel() == CodeModel::Kernel">; +def FarData : Predicate<"TM.getCodeModel() != CodeModel::Small &&" + "TM.getCodeModel() != CodeModel::Kernel">; +def NearData : Predicate<"TM.getCodeModel() == CodeModel::Small ||" + "TM.getCodeModel() == CodeModel::Kernel">; +def IsStatic : Predicate<"TM.getRelocationModel() == Reloc::Static">; +def IsNotPIC : Predicate<"TM.getRelocationModel() != Reloc::PIC_">; +def OptForSize : Predicate<"OptForSize">; +def OptForSpeed : Predicate<"!OptForSize">; +def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">; +def CallImmAddr : Predicate<"Subtarget->IsLegalToCallImmediateAddr(TM)">; +def HasAES : Predicate<"Subtarget->hasAES()">; + +//===----------------------------------------------------------------------===// +// X86 Instruction Format Definitions. +// + +include "X86InstrFormats.td" + +//===----------------------------------------------------------------------===// +// Pattern fragments... +// + +// X86 specific condition code. These correspond to CondCode in +// X86InstrInfo.h. They must be kept in synch. +def X86_COND_A : PatLeaf<(i8 0)>; // alt. COND_NBE +def X86_COND_AE : PatLeaf<(i8 1)>; // alt. COND_NC +def X86_COND_B : PatLeaf<(i8 2)>; // alt. COND_C +def X86_COND_BE : PatLeaf<(i8 3)>; // alt. COND_NA +def X86_COND_E : PatLeaf<(i8 4)>; // alt. COND_Z +def X86_COND_G : PatLeaf<(i8 5)>; // alt. COND_NLE +def X86_COND_GE : PatLeaf<(i8 6)>; // alt. COND_NL +def X86_COND_L : PatLeaf<(i8 7)>; // alt. COND_NGE +def X86_COND_LE : PatLeaf<(i8 8)>; // alt. COND_NG +def X86_COND_NE : PatLeaf<(i8 9)>; // alt. COND_NZ +def X86_COND_NO : PatLeaf<(i8 10)>; +def X86_COND_NP : PatLeaf<(i8 11)>; // alt. COND_PO +def X86_COND_NS : PatLeaf<(i8 12)>; +def X86_COND_O : PatLeaf<(i8 13)>; +def X86_COND_P : PatLeaf<(i8 14)>; // alt. COND_PE +def X86_COND_S : PatLeaf<(i8 15)>; + +def immSext8 : PatLeaf<(imm), [{ + return N->getSExtValue() == (int8_t)N->getSExtValue(); +}]>; + +def i16immSExt8 : PatLeaf<(i16 immSext8)>; +def i32immSExt8 : PatLeaf<(i32 immSext8)>; + +/// Load patterns: these constraint the match to the right address space. +def dsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{ + if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue()) + if (const PointerType *PT = dyn_cast<PointerType>(Src->getType())) + if (PT->getAddressSpace() > 255) + return false; + return true; +}]>; + +def gsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{ + if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue()) + if (const PointerType *PT = dyn_cast<PointerType>(Src->getType())) + return PT->getAddressSpace() == 256; + return false; +}]>; + +def fsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{ + if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue()) + if (const PointerType *PT = dyn_cast<PointerType>(Src->getType())) + return PT->getAddressSpace() == 257; + return false; +}]>; + + +// Helper fragments for loads. +// It's always safe to treat a anyext i16 load as a i32 load if the i16 is +// known to be 32-bit aligned or better. Ditto for i8 to i16. +def loadi16 : PatFrag<(ops node:$ptr), (i16 (unindexedload node:$ptr)), [{ + LoadSDNode *LD = cast<LoadSDNode>(N); + if (const Value *Src = LD->getSrcValue()) + if (const PointerType *PT = dyn_cast<PointerType>(Src->getType())) + if (PT->getAddressSpace() > 255) + return false; + ISD::LoadExtType ExtType = LD->getExtensionType(); + if (ExtType == ISD::NON_EXTLOAD) + return true; + if (ExtType == ISD::EXTLOAD) + return LD->getAlignment() >= 2 && !LD->isVolatile(); + return false; +}]>; + +def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)),[{ + LoadSDNode *LD = cast<LoadSDNode>(N); + if (const Value *Src = LD->getSrcValue()) + if (const PointerType *PT = dyn_cast<PointerType>(Src->getType())) + if (PT->getAddressSpace() > 255) + return false; + ISD::LoadExtType ExtType = LD->getExtensionType(); + if (ExtType == ISD::EXTLOAD) + return LD->getAlignment() >= 2 && !LD->isVolatile(); + return false; +}]>; + +def loadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{ + LoadSDNode *LD = cast<LoadSDNode>(N); + if (const Value *Src = LD->getSrcValue()) + if (const PointerType *PT = dyn_cast<PointerType>(Src->getType())) + if (PT->getAddressSpace() > 255) + return false; + ISD::LoadExtType ExtType = LD->getExtensionType(); + if (ExtType == ISD::NON_EXTLOAD) + return true; + if (ExtType == ISD::EXTLOAD) + return LD->getAlignment() >= 4 && !LD->isVolatile(); + return false; +}]>; + +def loadi8 : PatFrag<(ops node:$ptr), (i8 (dsload node:$ptr))>; +def loadi64 : PatFrag<(ops node:$ptr), (i64 (dsload node:$ptr))>; +def loadf32 : PatFrag<(ops node:$ptr), (f32 (dsload node:$ptr))>; +def loadf64 : PatFrag<(ops node:$ptr), (f64 (dsload node:$ptr))>; +def loadf80 : PatFrag<(ops node:$ptr), (f80 (dsload node:$ptr))>; + +def sextloadi16i8 : PatFrag<(ops node:$ptr), (i16 (sextloadi8 node:$ptr))>; +def sextloadi32i8 : PatFrag<(ops node:$ptr), (i32 (sextloadi8 node:$ptr))>; +def sextloadi32i16 : PatFrag<(ops node:$ptr), (i32 (sextloadi16 node:$ptr))>; + +def zextloadi8i1 : PatFrag<(ops node:$ptr), (i8 (zextloadi1 node:$ptr))>; +def zextloadi16i1 : PatFrag<(ops node:$ptr), (i16 (zextloadi1 node:$ptr))>; +def zextloadi32i1 : PatFrag<(ops node:$ptr), (i32 (zextloadi1 node:$ptr))>; +def zextloadi16i8 : PatFrag<(ops node:$ptr), (i16 (zextloadi8 node:$ptr))>; +def zextloadi32i8 : PatFrag<(ops node:$ptr), (i32 (zextloadi8 node:$ptr))>; +def zextloadi32i16 : PatFrag<(ops node:$ptr), (i32 (zextloadi16 node:$ptr))>; + +def extloadi8i1 : PatFrag<(ops node:$ptr), (i8 (extloadi1 node:$ptr))>; +def extloadi16i1 : PatFrag<(ops node:$ptr), (i16 (extloadi1 node:$ptr))>; +def extloadi32i1 : PatFrag<(ops node:$ptr), (i32 (extloadi1 node:$ptr))>; +def extloadi16i8 : PatFrag<(ops node:$ptr), (i16 (extloadi8 node:$ptr))>; +def extloadi32i8 : PatFrag<(ops node:$ptr), (i32 (extloadi8 node:$ptr))>; +def extloadi32i16 : PatFrag<(ops node:$ptr), (i32 (extloadi16 node:$ptr))>; + + +// An 'and' node with a single use. +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(); +}]>; + +// Treat an 'or' node is as an 'add' if the or'ed bits are known to be zero. +def or_is_add : PatFrag<(ops node:$lhs, node:$rhs), (or node:$lhs, node:$rhs),[{ + if (ConstantSDNode *CN = dyn_cast<ConstantSDNode>(N->getOperand(1))) + return CurDAG->MaskedValueIsZero(N->getOperand(0), CN->getAPIntValue()); + + unsigned BitWidth = N->getValueType(0).getScalarType().getSizeInBits(); + APInt Mask = APInt::getAllOnesValue(BitWidth); + APInt KnownZero0, KnownOne0; + CurDAG->ComputeMaskedBits(N->getOperand(0), Mask, KnownZero0, KnownOne0, 0); + APInt KnownZero1, KnownOne1; + CurDAG->ComputeMaskedBits(N->getOperand(1), Mask, KnownZero1, KnownOne1, 0); + return (~KnownZero0 & ~KnownZero1) == 0; +}]>; + +//===----------------------------------------------------------------------===// +// Instruction list... +// + +// ADJCALLSTACKDOWN/UP implicitly use/def ESP because they may be expanded into +// a stack adjustment and the codegen must know that they may modify the stack +// pointer before prolog-epilog rewriting occurs. +// Pessimistically assume ADJCALLSTACKDOWN / ADJCALLSTACKUP will become +// sub / add which can clobber EFLAGS. +let Defs = [ESP, EFLAGS], Uses = [ESP] in { +def ADJCALLSTACKDOWN32 : I<0, Pseudo, (outs), (ins i32imm:$amt), + "#ADJCALLSTACKDOWN", + [(X86callseq_start timm:$amt)]>, + Requires<[In32BitMode]>; +def ADJCALLSTACKUP32 : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2), + "#ADJCALLSTACKUP", + [(X86callseq_end timm:$amt1, timm:$amt2)]>, + Requires<[In32BitMode]>; +} + +// x86-64 va_start lowering magic. +let usesCustomInserter = 1 in { +def VASTART_SAVE_XMM_REGS : I<0, Pseudo, + (outs), + (ins GR8:$al, + i64imm:$regsavefi, i64imm:$offset, + variable_ops), + "#VASTART_SAVE_XMM_REGS $al, $regsavefi, $offset", + [(X86vastart_save_xmm_regs GR8:$al, + imm:$regsavefi, + imm:$offset)]>; + +// Dynamic stack allocation yields _alloca call for Cygwin/Mingw targets. Calls +// to _alloca is needed to probe the stack when allocating more than 4k bytes in +// one go. Touching the stack at 4K increments is necessary to ensure that the +// guard pages used by the OS virtual memory manager are allocated in correct +// sequence. +// The main point of having separate instruction are extra unmodelled effects +// (compared to ordinary calls) like stack pointer change. + +def MINGW_ALLOCA : I<0, Pseudo, (outs), (ins), + "# dynamic stack allocation", + [(X86MingwAlloca)]>; +} + +// Nop +let neverHasSideEffects = 1 in { + def NOOP : I<0x90, RawFrm, (outs), (ins), "nop", []>; + def NOOPW : I<0x1f, MRM0m, (outs), (ins i16mem:$zero), + "nop{w}\t$zero", []>, TB, OpSize; + def NOOPL : I<0x1f, MRM0m, (outs), (ins i32mem:$zero), + "nop{l}\t$zero", []>, TB; +} + +// Trap +def INTO : I<0xce, RawFrm, (outs), (ins), "into", []>; +def INT3 : I<0xcc, RawFrm, (outs), (ins), "int3", []>; +// FIXME: need to make sure that "int $3" matches int3 +def INT : Ii8<0xcd, RawFrm, (outs), (ins i8imm:$trap), "int\t$trap", []>; +def IRET16 : I<0xcf, RawFrm, (outs), (ins), "iret{w}", []>, OpSize; +def IRET32 : I<0xcf, RawFrm, (outs), (ins), "iret{l}", []>; + +// PIC base construction. This expands to code that looks like this: +// call $next_inst +// popl %destreg" +let neverHasSideEffects = 1, isNotDuplicable = 1, Uses = [ESP] in + def MOVPC32r : Ii32<0xE8, Pseudo, (outs GR32:$reg), (ins i32imm:$label), + "", []>; + +//===----------------------------------------------------------------------===// +// Control Flow Instructions. +// + +// Return instructions. +let isTerminator = 1, isReturn = 1, isBarrier = 1, + hasCtrlDep = 1, FPForm = SpecialFP in { + def RET : I <0xC3, RawFrm, (outs), (ins variable_ops), + "ret", + [(X86retflag 0)]>; + def RETI : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops), + "ret\t$amt", + [(X86retflag timm:$amt)]>; + def LRET : I <0xCB, RawFrm, (outs), (ins), + "lret", []>; + def LRETI : Ii16<0xCA, RawFrm, (outs), (ins i16imm:$amt), + "lret\t$amt", []>; +} + +// Unconditional branches. +let isBarrier = 1, isBranch = 1, isTerminator = 1 in { + def JMP_4 : Ii32PCRel<0xE9, RawFrm, (outs), (ins brtarget:$dst), + "jmp\t$dst", [(br bb:$dst)]>; + def JMP_1 : Ii8PCRel<0xEB, RawFrm, (outs), (ins brtarget8:$dst), + "jmp\t$dst", []>; +} + +// Conditional Branches. +let isBranch = 1, isTerminator = 1, Uses = [EFLAGS] in { + multiclass ICBr<bits<8> opc1, bits<8> opc4, string asm, PatFrag Cond> { + def _1 : Ii8PCRel <opc1, RawFrm, (outs), (ins brtarget8:$dst), asm, []>; + def _4 : Ii32PCRel<opc4, RawFrm, (outs), (ins brtarget:$dst), asm, + [(X86brcond bb:$dst, Cond, EFLAGS)]>, TB; + } +} + +defm JO : ICBr<0x70, 0x80, "jo\t$dst" , X86_COND_O>; +defm JNO : ICBr<0x71, 0x81, "jno\t$dst" , X86_COND_NO>; +defm JB : ICBr<0x72, 0x82, "jb\t$dst" , X86_COND_B>; +defm JAE : ICBr<0x73, 0x83, "jae\t$dst", X86_COND_AE>; +defm JE : ICBr<0x74, 0x84, "je\t$dst" , X86_COND_E>; +defm JNE : ICBr<0x75, 0x85, "jne\t$dst", X86_COND_NE>; +defm JBE : ICBr<0x76, 0x86, "jbe\t$dst", X86_COND_BE>; +defm JA : ICBr<0x77, 0x87, "ja\t$dst" , X86_COND_A>; +defm JS : ICBr<0x78, 0x88, "js\t$dst" , X86_COND_S>; +defm JNS : ICBr<0x79, 0x89, "jns\t$dst", X86_COND_NS>; +defm JP : ICBr<0x7A, 0x8A, "jp\t$dst" , X86_COND_P>; +defm JNP : ICBr<0x7B, 0x8B, "jnp\t$dst", X86_COND_NP>; +defm JL : ICBr<0x7C, 0x8C, "jl\t$dst" , X86_COND_L>; +defm JGE : ICBr<0x7D, 0x8D, "jge\t$dst", X86_COND_GE>; +defm JLE : ICBr<0x7E, 0x8E, "jle\t$dst", X86_COND_LE>; +defm JG : ICBr<0x7F, 0x8F, "jg\t$dst" , X86_COND_G>; + +// FIXME: What about the CX/RCX versions of this instruction? +let Uses = [ECX], isBranch = 1, isTerminator = 1 in + def JCXZ8 : Ii8PCRel<0xE3, RawFrm, (outs), (ins brtarget8:$dst), + "jcxz\t$dst", []>; + + +// Indirect branches +let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in { + def JMP32r : I<0xFF, MRM4r, (outs), (ins GR32:$dst), "jmp{l}\t{*}$dst", + [(brind GR32:$dst)]>; + def JMP32m : I<0xFF, MRM4m, (outs), (ins i32mem:$dst), "jmp{l}\t{*}$dst", + [(brind (loadi32 addr:$dst))]>; + + def FARJMP16i : Iseg16<0xEA, RawFrm, (outs), + (ins i16imm:$seg, i16imm:$off), + "ljmp{w}\t$seg, $off", []>, OpSize; + def FARJMP32i : Iseg32<0xEA, RawFrm, (outs), + (ins i16imm:$seg, i32imm:$off), + "ljmp{l}\t$seg, $off", []>; + + def FARJMP16m : I<0xFF, MRM5m, (outs), (ins opaque32mem:$dst), + "ljmp{w}\t{*}$dst", []>, OpSize; + def FARJMP32m : I<0xFF, MRM5m, (outs), (ins opaque48mem:$dst), + "ljmp{l}\t{*}$dst", []>; +} + + +// Loop instructions + +def LOOP : I<0xE2, RawFrm, (outs), (ins brtarget8:$dst), "loop\t$dst", []>; +def LOOPE : I<0xE1, RawFrm, (outs), (ins brtarget8:$dst), "loope\t$dst", []>; +def LOOPNE : I<0xE0, RawFrm, (outs), (ins brtarget8:$dst), "loopne\t$dst", []>; + +//===----------------------------------------------------------------------===// +// Call Instructions... +// +let isCall = 1 in + // All calls clobber the non-callee saved registers. ESP is marked as + // a use to prevent stack-pointer assignments that appear immediately + // before calls from potentially appearing dead. Uses for argument + // registers are added manually. + let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, + MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7, + XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, + XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS], + Uses = [ESP] in { + def CALLpcrel32 : Ii32PCRel<0xE8, RawFrm, + (outs), (ins i32imm_pcrel:$dst,variable_ops), + "call\t$dst", []>; + def CALL32r : I<0xFF, MRM2r, (outs), (ins GR32:$dst, variable_ops), + "call\t{*}$dst", [(X86call GR32:$dst)]>; + def CALL32m : I<0xFF, MRM2m, (outs), (ins i32mem:$dst, variable_ops), + "call\t{*}$dst", [(X86call (loadi32 addr:$dst))]>; + + def FARCALL16i : Iseg16<0x9A, RawFrm, (outs), + (ins i16imm:$seg, i16imm:$off), + "lcall{w}\t$seg, $off", []>, OpSize; + def FARCALL32i : Iseg32<0x9A, RawFrm, (outs), + (ins i16imm:$seg, i32imm:$off), + "lcall{l}\t$seg, $off", []>; + + def FARCALL16m : I<0xFF, MRM3m, (outs), (ins opaque32mem:$dst), + "lcall{w}\t{*}$dst", []>, OpSize; + def FARCALL32m : I<0xFF, MRM3m, (outs), (ins opaque48mem:$dst), + "lcall{l}\t{*}$dst", []>; + + // callw for 16 bit code for the assembler. + let isAsmParserOnly = 1 in + def CALLpcrel16 : Ii16PCRel<0xE8, RawFrm, + (outs), (ins i16imm_pcrel:$dst, variable_ops), + "callw\t$dst", []>, OpSize; + } + +// Constructing a stack frame. + +def ENTER : I<0xC8, RawFrm, (outs), (ins i16imm:$len, i8imm:$lvl), + "enter\t$len, $lvl", []>; + +// Tail call stuff. + +let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in + let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, + MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7, + XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, + XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS], + Uses = [ESP] in { + def TCRETURNdi : I<0, Pseudo, (outs), + (ins i32imm_pcrel:$dst, i32imm:$offset, variable_ops), + "#TC_RETURN $dst $offset", []>; + def TCRETURNri : I<0, Pseudo, (outs), + (ins GR32_TC:$dst, i32imm:$offset, variable_ops), + "#TC_RETURN $dst $offset", []>; + let mayLoad = 1 in + def TCRETURNmi : I<0, Pseudo, (outs), + (ins i32mem_TC:$dst, i32imm:$offset, variable_ops), + "#TC_RETURN $dst $offset", []>; + + // FIXME: The should be pseudo instructions that are lowered when going to + // mcinst. + def TAILJMPd : Ii32PCRel<0xE9, RawFrm, (outs), + (ins i32imm_pcrel:$dst, variable_ops), + "jmp\t$dst # TAILCALL", + []>; + def TAILJMPr : I<0xFF, MRM4r, (outs), (ins GR32_TC:$dst, variable_ops), + "", []>; // FIXME: Remove encoding when JIT is dead. + let mayLoad = 1 in + def TAILJMPm : I<0xFF, MRM4m, (outs), (ins i32mem_TC:$dst, variable_ops), + "jmp{l}\t{*}$dst # TAILCALL", []>; +} + +//===----------------------------------------------------------------------===// +// Miscellaneous Instructions... +// +let Defs = [EBP, ESP], Uses = [EBP, ESP], mayLoad = 1, neverHasSideEffects=1 in +def LEAVE : I<0xC9, RawFrm, + (outs), (ins), "leave", []>; + +def POPCNT16rr : I<0xB8, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src), + "popcnt{w}\t{$src, $dst|$dst, $src}", []>, OpSize, XS; +let mayLoad = 1 in +def POPCNT16rm : I<0xB8, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src), + "popcnt{w}\t{$src, $dst|$dst, $src}", []>, OpSize, XS; +def POPCNT32rr : I<0xB8, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "popcnt{l}\t{$src, $dst|$dst, $src}", []>, XS; +let mayLoad = 1 in +def POPCNT32rm : I<0xB8, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "popcnt{l}\t{$src, $dst|$dst, $src}", []>, XS; + +let Defs = [ESP], Uses = [ESP], neverHasSideEffects=1 in { +let mayLoad = 1 in { +def POP16r : I<0x58, AddRegFrm, (outs GR16:$reg), (ins), "pop{w}\t$reg", []>, + OpSize; +def POP32r : I<0x58, AddRegFrm, (outs GR32:$reg), (ins), "pop{l}\t$reg", []>; +def POP16rmr: I<0x8F, MRM0r, (outs GR16:$reg), (ins), "pop{w}\t$reg", []>, + OpSize; +def POP16rmm: I<0x8F, MRM0m, (outs i16mem:$dst), (ins), "pop{w}\t$dst", []>, + OpSize; +def POP32rmr: I<0x8F, MRM0r, (outs GR32:$reg), (ins), "pop{l}\t$reg", []>; +def POP32rmm: I<0x8F, MRM0m, (outs i32mem:$dst), (ins), "pop{l}\t$dst", []>; +} + +let mayStore = 1 in { +def PUSH16r : I<0x50, AddRegFrm, (outs), (ins GR16:$reg), "push{w}\t$reg",[]>, + OpSize; +def PUSH32r : I<0x50, AddRegFrm, (outs), (ins GR32:$reg), "push{l}\t$reg",[]>; +def PUSH16rmr: I<0xFF, MRM6r, (outs), (ins GR16:$reg), "push{w}\t$reg",[]>, + OpSize; +def PUSH16rmm: I<0xFF, MRM6m, (outs), (ins i16mem:$src), "push{w}\t$src",[]>, + OpSize; +def PUSH32rmr: I<0xFF, MRM6r, (outs), (ins GR32:$reg), "push{l}\t$reg",[]>; +def PUSH32rmm: I<0xFF, MRM6m, (outs), (ins i32mem:$src), "push{l}\t$src",[]>; +} +} + +let Defs = [ESP], Uses = [ESP], neverHasSideEffects = 1, mayStore = 1 in { +def PUSHi8 : Ii8<0x6a, RawFrm, (outs), (ins i32i8imm:$imm), + "push{l}\t$imm", []>; +def PUSHi16 : Ii16<0x68, RawFrm, (outs), (ins i16imm:$imm), + "push{w}\t$imm", []>, OpSize; +def PUSHi32 : Ii32<0x68, RawFrm, (outs), (ins i32imm:$imm), + "push{l}\t$imm", []>; +} + +let Defs = [ESP, EFLAGS], Uses = [ESP], mayLoad = 1, neverHasSideEffects=1 in { +def POPF16 : I<0x9D, RawFrm, (outs), (ins), "popf{w}", []>, OpSize; +def POPF32 : I<0x9D, RawFrm, (outs), (ins), "popf{l|d}", []>, + Requires<[In32BitMode]>; +} +let Defs = [ESP], Uses = [ESP, EFLAGS], mayStore = 1, neverHasSideEffects=1 in { +def PUSHF16 : I<0x9C, RawFrm, (outs), (ins), "pushf{w}", []>, OpSize; +def PUSHF32 : I<0x9C, RawFrm, (outs), (ins), "pushf{l|d}", []>, + Requires<[In32BitMode]>; +} + +let Defs = [EDI, ESI, EBP, EBX, EDX, ECX, EAX, ESP], Uses = [ESP], + mayLoad=1, neverHasSideEffects=1 in { +def POPA32 : I<0x61, RawFrm, (outs), (ins), "popa{l}", []>, + Requires<[In32BitMode]>; +} +let Defs = [ESP], Uses = [EDI, ESI, EBP, EBX, EDX, ECX, EAX, ESP], + mayStore=1, neverHasSideEffects=1 in { +def PUSHA32 : I<0x60, RawFrm, (outs), (ins), "pusha{l}", []>, + Requires<[In32BitMode]>; +} + +let Uses = [EFLAGS], Constraints = "$src = $dst" in // GR32 = bswap GR32 + def BSWAP32r : I<0xC8, AddRegFrm, + (outs GR32:$dst), (ins GR32:$src), + "bswap{l}\t$dst", + [(set GR32:$dst, (bswap GR32:$src))]>, TB; + + +// Bit scan instructions. +let Defs = [EFLAGS] in { +def BSF16rr : I<0xBC, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src), + "bsf{w}\t{$src, $dst|$dst, $src}", + [(set GR16:$dst, EFLAGS, (X86bsf GR16:$src))]>, TB, OpSize; +def BSF16rm : I<0xBC, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src), + "bsf{w}\t{$src, $dst|$dst, $src}", + [(set GR16:$dst, EFLAGS, (X86bsf (loadi16 addr:$src)))]>, TB, + OpSize; +def BSF32rr : I<0xBC, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "bsf{l}\t{$src, $dst|$dst, $src}", + [(set GR32:$dst, EFLAGS, (X86bsf GR32:$src))]>, TB; +def BSF32rm : I<0xBC, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "bsf{l}\t{$src, $dst|$dst, $src}", + [(set GR32:$dst, EFLAGS, (X86bsf (loadi32 addr:$src)))]>, TB; + +def BSR16rr : I<0xBD, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src), + "bsr{w}\t{$src, $dst|$dst, $src}", + [(set GR16:$dst, EFLAGS, (X86bsr GR16:$src))]>, TB, OpSize; +def BSR16rm : I<0xBD, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src), + "bsr{w}\t{$src, $dst|$dst, $src}", + [(set GR16:$dst, EFLAGS, (X86bsr (loadi16 addr:$src)))]>, TB, + OpSize; +def BSR32rr : I<0xBD, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "bsr{l}\t{$src, $dst|$dst, $src}", + [(set GR32:$dst, EFLAGS, (X86bsr GR32:$src))]>, TB; +def BSR32rm : I<0xBD, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "bsr{l}\t{$src, $dst|$dst, $src}", + [(set GR32:$dst, EFLAGS, (X86bsr (loadi32 addr:$src)))]>, TB; +} // Defs = [EFLAGS] + +let neverHasSideEffects = 1 in +def LEA16r : I<0x8D, MRMSrcMem, + (outs GR16:$dst), (ins i32mem:$src), + "lea{w}\t{$src|$dst}, {$dst|$src}", []>, OpSize; +let isReMaterializable = 1 in +def LEA32r : I<0x8D, MRMSrcMem, + (outs GR32:$dst), (ins i32mem:$src), + "lea{l}\t{$src|$dst}, {$dst|$src}", + [(set GR32:$dst, lea32addr:$src)]>, Requires<[In32BitMode]>; + +let Defs = [ECX,EDI,ESI], Uses = [ECX,EDI,ESI], isCodeGenOnly = 1 in { +def REP_MOVSB : I<0xA4, RawFrm, (outs), (ins), "{rep;movsb|rep movsb}", + [(X86rep_movs i8)]>, REP; +def REP_MOVSW : I<0xA5, RawFrm, (outs), (ins), "{rep;movsw|rep movsw}", + [(X86rep_movs i16)]>, REP, OpSize; +def REP_MOVSD : I<0xA5, RawFrm, (outs), (ins), "{rep;movsl|rep movsd}", + [(X86rep_movs i32)]>, REP; +} + +// These uses the DF flag in the EFLAGS register to inc or dec EDI and ESI +let Defs = [EDI,ESI], Uses = [EDI,ESI,EFLAGS] in { +def MOVSB : I<0xA4, RawFrm, (outs), (ins), "{movsb}", []>; +def MOVSW : I<0xA5, RawFrm, (outs), (ins), "{movsw}", []>, OpSize; +def MOVSD : I<0xA5, RawFrm, (outs), (ins), "{movsl|movsd}", []>; +} + +let Defs = [ECX,EDI], Uses = [AL,ECX,EDI], isCodeGenOnly = 1 in +def REP_STOSB : I<0xAA, RawFrm, (outs), (ins), "{rep;stosb|rep stosb}", + [(X86rep_stos i8)]>, REP; +let Defs = [ECX,EDI], Uses = [AX,ECX,EDI], isCodeGenOnly = 1 in +def REP_STOSW : I<0xAB, RawFrm, (outs), (ins), "{rep;stosw|rep stosw}", + [(X86rep_stos i16)]>, REP, OpSize; +let Defs = [ECX,EDI], Uses = [EAX,ECX,EDI], isCodeGenOnly = 1 in +def REP_STOSD : I<0xAB, RawFrm, (outs), (ins), "{rep;stosl|rep stosd}", + [(X86rep_stos i32)]>, REP; + +// These uses the DF flag in the EFLAGS register to inc or dec EDI and ESI +let Defs = [EDI], Uses = [AL,EDI,EFLAGS] in +def STOSB : I<0xAA, RawFrm, (outs), (ins), "{stosb}", []>; +let Defs = [EDI], Uses = [AX,EDI,EFLAGS] in +def STOSW : I<0xAB, RawFrm, (outs), (ins), "{stosw}", []>, OpSize; +let Defs = [EDI], Uses = [EAX,EDI,EFLAGS] in +def STOSD : I<0xAB, RawFrm, (outs), (ins), "{stosl|stosd}", []>; + +def SCAS8 : I<0xAE, RawFrm, (outs), (ins), "scas{b}", []>; +def SCAS16 : I<0xAF, RawFrm, (outs), (ins), "scas{w}", []>, OpSize; +def SCAS32 : I<0xAF, RawFrm, (outs), (ins), "scas{l}", []>; + +def CMPS8 : I<0xA6, RawFrm, (outs), (ins), "cmps{b}", []>; +def CMPS16 : I<0xA7, RawFrm, (outs), (ins), "cmps{w}", []>, OpSize; +def CMPS32 : I<0xA7, RawFrm, (outs), (ins), "cmps{l}", []>; + +let Defs = [RAX, RDX] in +def RDTSC : I<0x31, RawFrm, (outs), (ins), "rdtsc", [(X86rdtsc)]>, + TB; + +let Defs = [RAX, RCX, RDX] in +def RDTSCP : I<0x01, MRM_F9, (outs), (ins), "rdtscp", []>, TB; + +let isTerminator = 1, isBarrier = 1, hasCtrlDep = 1 in { +def TRAP : I<0x0B, RawFrm, (outs), (ins), "ud2", [(trap)]>, TB; +} + +def SYSCALL : I<0x05, RawFrm, + (outs), (ins), "syscall", []>, TB; +def SYSRET : I<0x07, RawFrm, + (outs), (ins), "sysret", []>, TB; +def SYSENTER : I<0x34, RawFrm, + (outs), (ins), "sysenter", []>, TB; +def SYSEXIT : I<0x35, RawFrm, + (outs), (ins), "sysexit", []>, TB; + +def WAIT : I<0x9B, RawFrm, (outs), (ins), "wait", []>; + + +//===----------------------------------------------------------------------===// +// Input/Output Instructions... +// +let Defs = [AL], Uses = [DX] in +def IN8rr : I<0xEC, RawFrm, (outs), (ins), + "in{b}\t{%dx, %al|%AL, %DX}", []>; +let Defs = [AX], Uses = [DX] in +def IN16rr : I<0xED, RawFrm, (outs), (ins), + "in{w}\t{%dx, %ax|%AX, %DX}", []>, OpSize; +let Defs = [EAX], Uses = [DX] in +def IN32rr : I<0xED, RawFrm, (outs), (ins), + "in{l}\t{%dx, %eax|%EAX, %DX}", []>; + +let Defs = [AL] in +def IN8ri : Ii8<0xE4, RawFrm, (outs), (ins i16i8imm:$port), + "in{b}\t{$port, %al|%AL, $port}", []>; +let Defs = [AX] in +def IN16ri : Ii8<0xE5, RawFrm, (outs), (ins i16i8imm:$port), + "in{w}\t{$port, %ax|%AX, $port}", []>, OpSize; +let Defs = [EAX] in +def IN32ri : Ii8<0xE5, RawFrm, (outs), (ins i16i8imm:$port), + "in{l}\t{$port, %eax|%EAX, $port}", []>; + +let Uses = [DX, AL] in +def OUT8rr : I<0xEE, RawFrm, (outs), (ins), + "out{b}\t{%al, %dx|%DX, %AL}", []>; +let Uses = [DX, AX] in +def OUT16rr : I<0xEF, RawFrm, (outs), (ins), + "out{w}\t{%ax, %dx|%DX, %AX}", []>, OpSize; +let Uses = [DX, EAX] in +def OUT32rr : I<0xEF, RawFrm, (outs), (ins), + "out{l}\t{%eax, %dx|%DX, %EAX}", []>; + +let Uses = [AL] in +def OUT8ir : Ii8<0xE6, RawFrm, (outs), (ins i16i8imm:$port), + "out{b}\t{%al, $port|$port, %AL}", []>; +let Uses = [AX] in +def OUT16ir : Ii8<0xE7, RawFrm, (outs), (ins i16i8imm:$port), + "out{w}\t{%ax, $port|$port, %AX}", []>, OpSize; +let Uses = [EAX] in +def OUT32ir : Ii8<0xE7, RawFrm, (outs), (ins i16i8imm:$port), + "out{l}\t{%eax, $port|$port, %EAX}", []>; + +def IN8 : I<0x6C, RawFrm, (outs), (ins), + "ins{b}", []>; +def IN16 : I<0x6D, RawFrm, (outs), (ins), + "ins{w}", []>, OpSize; +def IN32 : I<0x6D, RawFrm, (outs), (ins), + "ins{l}", []>; + +//===----------------------------------------------------------------------===// +// Move Instructions... +// +let neverHasSideEffects = 1 in { +def MOV8rr : I<0x88, MRMDestReg, (outs GR8 :$dst), (ins GR8 :$src), + "mov{b}\t{$src, $dst|$dst, $src}", []>; +def MOV16rr : I<0x89, MRMDestReg, (outs GR16:$dst), (ins GR16:$src), + "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def MOV32rr : I<0x89, MRMDestReg, (outs GR32:$dst), (ins GR32:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; +} +let isReMaterializable = 1, isAsCheapAsAMove = 1 in { +def MOV8ri : Ii8 <0xB0, AddRegFrm, (outs GR8 :$dst), (ins i8imm :$src), + "mov{b}\t{$src, $dst|$dst, $src}", + [(set GR8:$dst, imm:$src)]>; +def MOV16ri : Ii16<0xB8, AddRegFrm, (outs GR16:$dst), (ins i16imm:$src), + "mov{w}\t{$src, $dst|$dst, $src}", + [(set GR16:$dst, imm:$src)]>, OpSize; +def MOV32ri : Ii32<0xB8, AddRegFrm, (outs GR32:$dst), (ins i32imm:$src), + "mov{l}\t{$src, $dst|$dst, $src}", + [(set GR32:$dst, imm:$src)]>; +} + +def MOV8mi : Ii8 <0xC6, MRM0m, (outs), (ins i8mem :$dst, i8imm :$src), + "mov{b}\t{$src, $dst|$dst, $src}", + [(store (i8 imm:$src), addr:$dst)]>; +def MOV16mi : Ii16<0xC7, MRM0m, (outs), (ins i16mem:$dst, i16imm:$src), + "mov{w}\t{$src, $dst|$dst, $src}", + [(store (i16 imm:$src), addr:$dst)]>, OpSize; +def MOV32mi : Ii32<0xC7, MRM0m, (outs), (ins i32mem:$dst, i32imm:$src), + "mov{l}\t{$src, $dst|$dst, $src}", + [(store (i32 imm:$src), addr:$dst)]>; + +/// moffs8, moffs16 and moffs32 versions of moves. The immediate is a +/// 32-bit offset from the PC. These are only valid in x86-32 mode. +def MOV8o8a : Ii32 <0xA0, RawFrm, (outs), (ins offset8:$src), + "mov{b}\t{$src, %al|%al, $src}", []>; +def MOV16o16a : Ii32 <0xA1, RawFrm, (outs), (ins offset16:$src), + "mov{w}\t{$src, %ax|%ax, $src}", []>, OpSize; +def MOV32o32a : Ii32 <0xA1, RawFrm, (outs), (ins offset32:$src), + "mov{l}\t{$src, %eax|%eax, $src}", []>; +def MOV8ao8 : Ii32 <0xA2, RawFrm, (outs offset8:$dst), (ins), + "mov{b}\t{%al, $dst|$dst, %al}", []>; +def MOV16ao16 : Ii32 <0xA3, RawFrm, (outs offset16:$dst), (ins), + "mov{w}\t{%ax, $dst|$dst, %ax}", []>, OpSize; +def MOV32ao32 : Ii32 <0xA3, RawFrm, (outs offset32:$dst), (ins), + "mov{l}\t{%eax, $dst|$dst, %eax}", []>; + +// Moves to and from segment registers +def MOV16rs : I<0x8C, MRMDestReg, (outs GR16:$dst), (ins SEGMENT_REG:$src), + "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def MOV32rs : I<0x8C, MRMDestReg, (outs GR32:$dst), (ins SEGMENT_REG:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; +def MOV16ms : I<0x8C, MRMDestMem, (outs i16mem:$dst), (ins SEGMENT_REG:$src), + "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def MOV32ms : I<0x8C, MRMDestMem, (outs i32mem:$dst), (ins SEGMENT_REG:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; +def MOV16sr : I<0x8E, MRMSrcReg, (outs SEGMENT_REG:$dst), (ins GR16:$src), + "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def MOV32sr : I<0x8E, MRMSrcReg, (outs SEGMENT_REG:$dst), (ins GR32:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; +def MOV16sm : I<0x8E, MRMSrcMem, (outs SEGMENT_REG:$dst), (ins i16mem:$src), + "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def MOV32sm : I<0x8E, MRMSrcMem, (outs SEGMENT_REG:$dst), (ins i32mem:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; + +let isCodeGenOnly = 1 in { +def MOV8rr_REV : I<0x8A, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src), + "mov{b}\t{$src, $dst|$dst, $src}", []>; +def MOV16rr_REV : I<0x8B, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src), + "mov{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def MOV32rr_REV : I<0x8B, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; +} + +let canFoldAsLoad = 1, isReMaterializable = 1 in { +def MOV8rm : I<0x8A, MRMSrcMem, (outs GR8 :$dst), (ins i8mem :$src), + "mov{b}\t{$src, $dst|$dst, $src}", + [(set GR8:$dst, (loadi8 addr:$src))]>; +def MOV16rm : I<0x8B, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src), + "mov{w}\t{$src, $dst|$dst, $src}", + [(set GR16:$dst, (loadi16 addr:$src))]>, OpSize; +def MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "mov{l}\t{$src, $dst|$dst, $src}", + [(set GR32:$dst, (loadi32 addr:$src))]>; +} + +def MOV8mr : I<0x88, MRMDestMem, (outs), (ins i8mem :$dst, GR8 :$src), + "mov{b}\t{$src, $dst|$dst, $src}", + [(store GR8:$src, addr:$dst)]>; +def MOV16mr : I<0x89, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src), + "mov{w}\t{$src, $dst|$dst, $src}", + [(store GR16:$src, addr:$dst)]>, OpSize; +def MOV32mr : I<0x89, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src), + "mov{l}\t{$src, $dst|$dst, $src}", + [(store GR32:$src, addr:$dst)]>; + +/// Versions of MOV32rr, MOV32rm, and MOV32mr for i32mem_TC and GR32_TC. +let neverHasSideEffects = 1 in +def MOV32rr_TC : I<0x89, MRMDestReg, (outs GR32_TC:$dst), (ins GR32_TC:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>; + +let mayLoad = 1, + canFoldAsLoad = 1, isReMaterializable = 1 in +def MOV32rm_TC : I<0x8B, MRMSrcMem, (outs GR32_TC:$dst), (ins i32mem_TC:$src), + "mov{l}\t{$src, $dst|$dst, $src}", + []>; + +let mayStore = 1 in +def MOV32mr_TC : I<0x89, MRMDestMem, (outs), (ins i32mem_TC:$dst, GR32_TC:$src), + "mov{l}\t{$src, $dst|$dst, $src}", + []>; + +// Versions of MOV8rr, MOV8mr, and MOV8rm that use i8mem_NOREX and GR8_NOREX so +// that they can be used for copying and storing h registers, which can't be +// encoded when a REX prefix is present. +let neverHasSideEffects = 1 in +def MOV8rr_NOREX : I<0x88, MRMDestReg, + (outs GR8_NOREX:$dst), (ins GR8_NOREX:$src), + "mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>; +let mayStore = 1 in +def MOV8mr_NOREX : I<0x88, MRMDestMem, + (outs), (ins i8mem_NOREX:$dst, GR8_NOREX:$src), + "mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>; +let mayLoad = 1, + canFoldAsLoad = 1, isReMaterializable = 1 in +def MOV8rm_NOREX : I<0x8A, MRMSrcMem, + (outs GR8_NOREX:$dst), (ins i8mem_NOREX:$src), + "mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>; + +// Moves to and from debug registers +def MOV32rd : I<0x21, MRMDestReg, (outs GR32:$dst), (ins DEBUG_REG:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>, TB; +def MOV32dr : I<0x23, MRMSrcReg, (outs DEBUG_REG:$dst), (ins GR32:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>, TB; + +// Moves to and from control registers +def MOV32rc : I<0x20, MRMDestReg, (outs GR32:$dst), (ins CONTROL_REG:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>, TB; +def MOV32cr : I<0x22, MRMSrcReg, (outs CONTROL_REG:$dst), (ins GR32:$src), + "mov{l}\t{$src, $dst|$dst, $src}", []>, TB; + +//===----------------------------------------------------------------------===// +// Fixed-Register Multiplication and Division Instructions... +// + +// Extra precision multiplication + +// AL is really implied by AX, by the registers in Defs must match the +// SDNode results (i8, i32). +let Defs = [AL,EFLAGS,AX], Uses = [AL] in +def MUL8r : I<0xF6, MRM4r, (outs), (ins GR8:$src), "mul{b}\t$src", + // FIXME: Used for 8-bit mul, ignore result upper 8 bits. + // This probably ought to be moved to a def : Pat<> if the + // syntax can be accepted. + [(set AL, (mul AL, GR8:$src)), + (implicit EFLAGS)]>; // AL,AH = AL*GR8 + +let Defs = [AX,DX,EFLAGS], Uses = [AX], neverHasSideEffects = 1 in +def MUL16r : I<0xF7, MRM4r, (outs), (ins GR16:$src), + "mul{w}\t$src", + []>, OpSize; // AX,DX = AX*GR16 + +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX], neverHasSideEffects = 1 in +def MUL32r : I<0xF7, MRM4r, (outs), (ins GR32:$src), + "mul{l}\t$src", + []>; // EAX,EDX = EAX*GR32 + +let Defs = [AL,EFLAGS,AX], Uses = [AL] in +def MUL8m : I<0xF6, MRM4m, (outs), (ins i8mem :$src), + "mul{b}\t$src", + // FIXME: Used for 8-bit mul, ignore result upper 8 bits. + // This probably ought to be moved to a def : Pat<> if the + // syntax can be accepted. + [(set AL, (mul AL, (loadi8 addr:$src))), + (implicit EFLAGS)]>; // AL,AH = AL*[mem8] + +let mayLoad = 1, neverHasSideEffects = 1 in { +let Defs = [AX,DX,EFLAGS], Uses = [AX] in +def MUL16m : I<0xF7, MRM4m, (outs), (ins i16mem:$src), + "mul{w}\t$src", + []>, OpSize; // AX,DX = AX*[mem16] + +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX] in +def MUL32m : I<0xF7, MRM4m, (outs), (ins i32mem:$src), + "mul{l}\t$src", + []>; // EAX,EDX = EAX*[mem32] +} + +let neverHasSideEffects = 1 in { +let Defs = [AL,EFLAGS,AX], Uses = [AL] in +def IMUL8r : I<0xF6, MRM5r, (outs), (ins GR8:$src), "imul{b}\t$src", []>; + // AL,AH = AL*GR8 +let Defs = [AX,DX,EFLAGS], Uses = [AX] in +def IMUL16r : I<0xF7, MRM5r, (outs), (ins GR16:$src), "imul{w}\t$src", []>, + OpSize; // AX,DX = AX*GR16 +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX] in +def IMUL32r : I<0xF7, MRM5r, (outs), (ins GR32:$src), "imul{l}\t$src", []>; + // EAX,EDX = EAX*GR32 +let mayLoad = 1 in { +let Defs = [AL,EFLAGS,AX], Uses = [AL] in +def IMUL8m : I<0xF6, MRM5m, (outs), (ins i8mem :$src), + "imul{b}\t$src", []>; // AL,AH = AL*[mem8] +let Defs = [AX,DX,EFLAGS], Uses = [AX] in +def IMUL16m : I<0xF7, MRM5m, (outs), (ins i16mem:$src), + "imul{w}\t$src", []>, OpSize; // AX,DX = AX*[mem16] +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX] in +def IMUL32m : I<0xF7, MRM5m, (outs), (ins i32mem:$src), + "imul{l}\t$src", []>; // EAX,EDX = EAX*[mem32] +} +} // neverHasSideEffects + +// unsigned division/remainder +let Defs = [AL,EFLAGS,AX], Uses = [AX] in +def DIV8r : I<0xF6, MRM6r, (outs), (ins GR8:$src), // AX/r8 = AL,AH + "div{b}\t$src", []>; +let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in +def DIV16r : I<0xF7, MRM6r, (outs), (ins GR16:$src), // DX:AX/r16 = AX,DX + "div{w}\t$src", []>, OpSize; +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in +def DIV32r : I<0xF7, MRM6r, (outs), (ins GR32:$src), // EDX:EAX/r32 = EAX,EDX + "div{l}\t$src", []>; +let mayLoad = 1 in { +let Defs = [AL,EFLAGS,AX], Uses = [AX] in +def DIV8m : I<0xF6, MRM6m, (outs), (ins i8mem:$src), // AX/[mem8] = AL,AH + "div{b}\t$src", []>; +let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in +def DIV16m : I<0xF7, MRM6m, (outs), (ins i16mem:$src), // DX:AX/[mem16] = AX,DX + "div{w}\t$src", []>, OpSize; +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in + // EDX:EAX/[mem32] = EAX,EDX +def DIV32m : I<0xF7, MRM6m, (outs), (ins i32mem:$src), + "div{l}\t$src", []>; +} + +// Signed division/remainder. +let Defs = [AL,EFLAGS,AX], Uses = [AX] in +def IDIV8r : I<0xF6, MRM7r, (outs), (ins GR8:$src), // AX/r8 = AL,AH + "idiv{b}\t$src", []>; +let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in +def IDIV16r: I<0xF7, MRM7r, (outs), (ins GR16:$src), // DX:AX/r16 = AX,DX + "idiv{w}\t$src", []>, OpSize; +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in +def IDIV32r: I<0xF7, MRM7r, (outs), (ins GR32:$src), // EDX:EAX/r32 = EAX,EDX + "idiv{l}\t$src", []>; +let mayLoad = 1, mayLoad = 1 in { +let Defs = [AL,EFLAGS,AX], Uses = [AX] in +def IDIV8m : I<0xF6, MRM7m, (outs), (ins i8mem:$src), // AX/[mem8] = AL,AH + "idiv{b}\t$src", []>; +let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in +def IDIV16m: I<0xF7, MRM7m, (outs), (ins i16mem:$src), // DX:AX/[mem16] = AX,DX + "idiv{w}\t$src", []>, OpSize; +let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in +def IDIV32m: I<0xF7, MRM7m, (outs), (ins i32mem:$src), + // EDX:EAX/[mem32] = EAX,EDX + "idiv{l}\t$src", []>; +} + +//===----------------------------------------------------------------------===// +// Two address Instructions. +// +let Constraints = "$src1 = $dst" in { + +// Conditional moves +let Uses = [EFLAGS] in { + +let Predicates = [HasCMov] in { +let isCommutable = 1 in { +def CMOVB16rr : I<0x42, MRMSrcReg, // if <u, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovb{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_B, EFLAGS))]>, + TB, OpSize; +def CMOVB32rr : I<0x42, MRMSrcReg, // if <u, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovb{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_B, EFLAGS))]>, + TB; +def CMOVAE16rr: I<0x43, MRMSrcReg, // if >=u, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovae{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_AE, EFLAGS))]>, + TB, OpSize; +def CMOVAE32rr: I<0x43, MRMSrcReg, // if >=u, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovae{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_AE, EFLAGS))]>, + TB; +def CMOVE16rr : I<0x44, MRMSrcReg, // if ==, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmove{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_E, EFLAGS))]>, + TB, OpSize; +def CMOVE32rr : I<0x44, MRMSrcReg, // if ==, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmove{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_E, EFLAGS))]>, + TB; +def CMOVNE16rr: I<0x45, MRMSrcReg, // if !=, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovne{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_NE, EFLAGS))]>, + TB, OpSize; +def CMOVNE32rr: I<0x45, MRMSrcReg, // if !=, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovne{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_NE, EFLAGS))]>, + TB; +def CMOVBE16rr: I<0x46, MRMSrcReg, // if <=u, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovbe{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_BE, EFLAGS))]>, + TB, OpSize; +def CMOVBE32rr: I<0x46, MRMSrcReg, // if <=u, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovbe{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_BE, EFLAGS))]>, + TB; +def CMOVA16rr : I<0x47, MRMSrcReg, // if >u, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmova{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_A, EFLAGS))]>, + TB, OpSize; +def CMOVA32rr : I<0x47, MRMSrcReg, // if >u, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmova{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_A, EFLAGS))]>, + TB; +def CMOVL16rr : I<0x4C, MRMSrcReg, // if <s, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovl{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_L, EFLAGS))]>, + TB, OpSize; +def CMOVL32rr : I<0x4C, MRMSrcReg, // if <s, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovl{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_L, EFLAGS))]>, + TB; +def CMOVGE16rr: I<0x4D, MRMSrcReg, // if >=s, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovge{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_GE, EFLAGS))]>, + TB, OpSize; +def CMOVGE32rr: I<0x4D, MRMSrcReg, // if >=s, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovge{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_GE, EFLAGS))]>, + TB; +def CMOVLE16rr: I<0x4E, MRMSrcReg, // if <=s, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovle{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_LE, EFLAGS))]>, + TB, OpSize; +def CMOVLE32rr: I<0x4E, MRMSrcReg, // if <=s, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovle{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_LE, EFLAGS))]>, + TB; +def CMOVG16rr : I<0x4F, MRMSrcReg, // if >s, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovg{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_G, EFLAGS))]>, + TB, OpSize; +def CMOVG32rr : I<0x4F, MRMSrcReg, // if >s, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovg{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_G, EFLAGS))]>, + TB; +def CMOVS16rr : I<0x48, MRMSrcReg, // if signed, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovs{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_S, EFLAGS))]>, + TB, OpSize; +def CMOVS32rr : I<0x48, MRMSrcReg, // if signed, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovs{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_S, EFLAGS))]>, + TB; +def CMOVNS16rr: I<0x49, MRMSrcReg, // if !signed, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovns{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_NS, EFLAGS))]>, + TB, OpSize; +def CMOVNS32rr: I<0x49, MRMSrcReg, // if !signed, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovns{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_NS, EFLAGS))]>, + TB; +def CMOVP16rr : I<0x4A, MRMSrcReg, // if parity, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovp{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_P, EFLAGS))]>, + TB, OpSize; +def CMOVP32rr : I<0x4A, MRMSrcReg, // if parity, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovp{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_P, EFLAGS))]>, + TB; +def CMOVNP16rr : I<0x4B, MRMSrcReg, // if !parity, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovnp{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, GR16:$src2, + X86_COND_NP, EFLAGS))]>, + TB, OpSize; +def CMOVNP32rr : I<0x4B, MRMSrcReg, // if !parity, GR32 = GR32 + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "cmovnp{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2, + X86_COND_NP, EFLAGS))]>, + TB; +def CMOVO16rr : I<0x40, MRMSrcReg, // if overflow, GR16 = GR16 + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "cmovo{w}\t{$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:$src2), + "cmovo{l}\t{$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:$src2), + "cmovno{w}\t{$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:$src2), + "cmovno{l}\t{$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:$src2), + "cmovb{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_B, EFLAGS))]>, + TB, OpSize; +def CMOVB32rm : I<0x42, MRMSrcMem, // if <u, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovb{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_B, EFLAGS))]>, + TB; +def CMOVAE16rm: I<0x43, MRMSrcMem, // if >=u, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovae{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_AE, EFLAGS))]>, + TB, OpSize; +def CMOVAE32rm: I<0x43, MRMSrcMem, // if >=u, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovae{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_AE, EFLAGS))]>, + TB; +def CMOVE16rm : I<0x44, MRMSrcMem, // if ==, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmove{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_E, EFLAGS))]>, + TB, OpSize; +def CMOVE32rm : I<0x44, MRMSrcMem, // if ==, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmove{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_E, EFLAGS))]>, + TB; +def CMOVNE16rm: I<0x45, MRMSrcMem, // if !=, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovne{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_NE, EFLAGS))]>, + TB, OpSize; +def CMOVNE32rm: I<0x45, MRMSrcMem, // if !=, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovne{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_NE, EFLAGS))]>, + TB; +def CMOVBE16rm: I<0x46, MRMSrcMem, // if <=u, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovbe{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_BE, EFLAGS))]>, + TB, OpSize; +def CMOVBE32rm: I<0x46, MRMSrcMem, // if <=u, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovbe{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_BE, EFLAGS))]>, + TB; +def CMOVA16rm : I<0x47, MRMSrcMem, // if >u, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmova{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_A, EFLAGS))]>, + TB, OpSize; +def CMOVA32rm : I<0x47, MRMSrcMem, // if >u, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmova{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_A, EFLAGS))]>, + TB; +def CMOVL16rm : I<0x4C, MRMSrcMem, // if <s, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovl{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_L, EFLAGS))]>, + TB, OpSize; +def CMOVL32rm : I<0x4C, MRMSrcMem, // if <s, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovl{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_L, EFLAGS))]>, + TB; +def CMOVGE16rm: I<0x4D, MRMSrcMem, // if >=s, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovge{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_GE, EFLAGS))]>, + TB, OpSize; +def CMOVGE32rm: I<0x4D, MRMSrcMem, // if >=s, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovge{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_GE, EFLAGS))]>, + TB; +def CMOVLE16rm: I<0x4E, MRMSrcMem, // if <=s, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovle{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_LE, EFLAGS))]>, + TB, OpSize; +def CMOVLE32rm: I<0x4E, MRMSrcMem, // if <=s, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovle{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_LE, EFLAGS))]>, + TB; +def CMOVG16rm : I<0x4F, MRMSrcMem, // if >s, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovg{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_G, EFLAGS))]>, + TB, OpSize; +def CMOVG32rm : I<0x4F, MRMSrcMem, // if >s, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovg{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_G, EFLAGS))]>, + TB; +def CMOVS16rm : I<0x48, MRMSrcMem, // if signed, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovs{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_S, EFLAGS))]>, + TB, OpSize; +def CMOVS32rm : I<0x48, MRMSrcMem, // if signed, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovs{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_S, EFLAGS))]>, + TB; +def CMOVNS16rm: I<0x49, MRMSrcMem, // if !signed, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovns{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_NS, EFLAGS))]>, + TB, OpSize; +def CMOVNS32rm: I<0x49, MRMSrcMem, // if !signed, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovns{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_NS, EFLAGS))]>, + TB; +def CMOVP16rm : I<0x4A, MRMSrcMem, // if parity, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovp{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (X86cmov GR16:$src1, (loadi16 addr:$src2), + X86_COND_P, EFLAGS))]>, + TB, OpSize; +def CMOVP32rm : I<0x4A, MRMSrcMem, // if parity, GR32 = [mem32] + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "cmovp{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_P, EFLAGS))]>, + TB; +def CMOVNP16rm : I<0x4B, MRMSrcMem, // if !parity, GR16 = [mem16] + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "cmovnp{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$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:$src2), + "cmovnp{l}\t{$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:$src2), + "cmovo{w}\t{$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:$src2), + "cmovo{l}\t{$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:$src2), + "cmovno{w}\t{$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:$src2), + "cmovno{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2), + X86_COND_NO, EFLAGS))]>, + TB; +} // Predicates = [HasCMov] + +// X86 doesn't have 8-bit conditional moves. Use a customInserter to +// emit control flow. An alternative to this is to mark i8 SELECT as Promote, +// however that requires promoting the operands, and can induce additional +// i8 register pressure. Note that CMOV_GR8 is conservatively considered to +// clobber EFLAGS, because if one of the operands is zero, the expansion +// could involve an xor. +let usesCustomInserter = 1, Constraints = "", Defs = [EFLAGS] in { +def CMOV_GR8 : I<0, Pseudo, + (outs GR8:$dst), (ins GR8:$src1, GR8:$src2, i8imm:$cond), + "#CMOV_GR8 PSEUDO!", + [(set GR8:$dst, (X86cmov GR8:$src1, GR8:$src2, + imm:$cond, EFLAGS))]>; + +let Predicates = [NoCMov] in { +def CMOV_GR32 : I<0, Pseudo, + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2, i8imm:$cond), + "#CMOV_GR32* PSEUDO!", + [(set GR32:$dst, + (X86cmov GR32:$src1, GR32:$src2, imm:$cond, EFLAGS))]>; +def CMOV_GR16 : I<0, Pseudo, + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2, i8imm:$cond), + "#CMOV_GR16* PSEUDO!", + [(set GR16:$dst, + (X86cmov GR16:$src1, GR16:$src2, imm:$cond, EFLAGS))]>; +def CMOV_RFP32 : I<0, Pseudo, + (outs RFP32:$dst), + (ins RFP32:$src1, RFP32:$src2, i8imm:$cond), + "#CMOV_RFP32 PSEUDO!", + [(set RFP32:$dst, + (X86cmov RFP32:$src1, RFP32:$src2, imm:$cond, + EFLAGS))]>; +def CMOV_RFP64 : I<0, Pseudo, + (outs RFP64:$dst), + (ins RFP64:$src1, RFP64:$src2, i8imm:$cond), + "#CMOV_RFP64 PSEUDO!", + [(set RFP64:$dst, + (X86cmov RFP64:$src1, RFP64:$src2, imm:$cond, + EFLAGS))]>; +def CMOV_RFP80 : I<0, Pseudo, + (outs RFP80:$dst), + (ins RFP80:$src1, RFP80:$src2, i8imm:$cond), + "#CMOV_RFP80 PSEUDO!", + [(set RFP80:$dst, + (X86cmov RFP80:$src1, RFP80:$src2, imm:$cond, + EFLAGS))]>; +} // Predicates = [NoCMov] +} // UsesCustomInserter = 1, Constraints = "", Defs = [EFLAGS] +} // Uses = [EFLAGS] + + +// unary instructions +let CodeSize = 2 in { +let Defs = [EFLAGS] in { +def NEG8r : I<0xF6, MRM3r, (outs GR8 :$dst), (ins GR8 :$src1), + "neg{b}\t$dst", + [(set GR8:$dst, (ineg GR8:$src1)), + (implicit EFLAGS)]>; +def NEG16r : I<0xF7, MRM3r, (outs GR16:$dst), (ins GR16:$src1), + "neg{w}\t$dst", + [(set GR16:$dst, (ineg GR16:$src1)), + (implicit EFLAGS)]>, OpSize; +def NEG32r : I<0xF7, MRM3r, (outs GR32:$dst), (ins GR32:$src1), + "neg{l}\t$dst", + [(set GR32:$dst, (ineg GR32:$src1)), + (implicit EFLAGS)]>; + +let Constraints = "" in { + def NEG8m : I<0xF6, MRM3m, (outs), (ins i8mem :$dst), + "neg{b}\t$dst", + [(store (ineg (loadi8 addr:$dst)), addr:$dst), + (implicit EFLAGS)]>; + def NEG16m : I<0xF7, MRM3m, (outs), (ins i16mem:$dst), + "neg{w}\t$dst", + [(store (ineg (loadi16 addr:$dst)), addr:$dst), + (implicit EFLAGS)]>, OpSize; + def NEG32m : I<0xF7, MRM3m, (outs), (ins i32mem:$dst), + "neg{l}\t$dst", + [(store (ineg (loadi32 addr:$dst)), addr:$dst), + (implicit EFLAGS)]>; +} // Constraints = "" +} // Defs = [EFLAGS] + +// Match xor -1 to not. Favors these over a move imm + xor to save code size. +let AddedComplexity = 15 in { +def NOT8r : I<0xF6, MRM2r, (outs GR8 :$dst), (ins GR8 :$src1), + "not{b}\t$dst", + [(set GR8:$dst, (not GR8:$src1))]>; +def NOT16r : I<0xF7, MRM2r, (outs GR16:$dst), (ins GR16:$src1), + "not{w}\t$dst", + [(set GR16:$dst, (not GR16:$src1))]>, OpSize; +def NOT32r : I<0xF7, MRM2r, (outs GR32:$dst), (ins GR32:$src1), + "not{l}\t$dst", + [(set GR32:$dst, (not GR32:$src1))]>; +} +let Constraints = "" in { + def NOT8m : I<0xF6, MRM2m, (outs), (ins i8mem :$dst), + "not{b}\t$dst", + [(store (not (loadi8 addr:$dst)), addr:$dst)]>; + def NOT16m : I<0xF7, MRM2m, (outs), (ins i16mem:$dst), + "not{w}\t$dst", + [(store (not (loadi16 addr:$dst)), addr:$dst)]>, OpSize; + def NOT32m : I<0xF7, MRM2m, (outs), (ins i32mem:$dst), + "not{l}\t$dst", + [(store (not (loadi32 addr:$dst)), addr:$dst)]>; +} // Constraints = "" +} // CodeSize + +// TODO: inc/dec is slow for P4, but fast for Pentium-M. +let Defs = [EFLAGS] in { +let CodeSize = 2 in +def INC8r : I<0xFE, MRM0r, (outs GR8 :$dst), (ins GR8 :$src1), + "inc{b}\t$dst", + [(set GR8:$dst, EFLAGS, (X86inc_flag GR8:$src1))]>; + +let isConvertibleToThreeAddress = 1, CodeSize = 1 in { // Can xform into LEA. +def INC16r : I<0x40, AddRegFrm, (outs GR16:$dst), (ins GR16:$src1), + "inc{w}\t$dst", + [(set GR16:$dst, EFLAGS, (X86inc_flag GR16:$src1))]>, + OpSize, Requires<[In32BitMode]>; +def INC32r : I<0x40, AddRegFrm, (outs GR32:$dst), (ins GR32:$src1), + "inc{l}\t$dst", + [(set GR32:$dst, EFLAGS, (X86inc_flag GR32:$src1))]>, + Requires<[In32BitMode]>; +} +let Constraints = "", CodeSize = 2 in { + def INC8m : I<0xFE, MRM0m, (outs), (ins i8mem :$dst), "inc{b}\t$dst", + [(store (add (loadi8 addr:$dst), 1), addr:$dst), + (implicit EFLAGS)]>; + def INC16m : I<0xFF, MRM0m, (outs), (ins i16mem:$dst), "inc{w}\t$dst", + [(store (add (loadi16 addr:$dst), 1), addr:$dst), + (implicit EFLAGS)]>, + OpSize, Requires<[In32BitMode]>; + def INC32m : I<0xFF, MRM0m, (outs), (ins i32mem:$dst), "inc{l}\t$dst", + [(store (add (loadi32 addr:$dst), 1), addr:$dst), + (implicit EFLAGS)]>, + Requires<[In32BitMode]>; +} // Constraints = "", CodeSize = 2 + +let CodeSize = 2 in +def DEC8r : I<0xFE, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1), + "dec{b}\t$dst", + [(set GR8:$dst, EFLAGS, (X86dec_flag GR8:$src1))]>; +let isConvertibleToThreeAddress = 1, CodeSize = 1 in { // Can xform into LEA. +def DEC16r : I<0x48, AddRegFrm, (outs GR16:$dst), (ins GR16:$src1), + "dec{w}\t$dst", + [(set GR16:$dst, EFLAGS, (X86dec_flag GR16:$src1))]>, + OpSize, Requires<[In32BitMode]>; +def DEC32r : I<0x48, AddRegFrm, (outs GR32:$dst), (ins GR32:$src1), + "dec{l}\t$dst", + [(set GR32:$dst, EFLAGS, (X86dec_flag GR32:$src1))]>, + Requires<[In32BitMode]>; +} // CodeSize = 2 + +let Constraints = "", CodeSize = 2 in { + def DEC8m : I<0xFE, MRM1m, (outs), (ins i8mem :$dst), "dec{b}\t$dst", + [(store (add (loadi8 addr:$dst), -1), addr:$dst), + (implicit EFLAGS)]>; + def DEC16m : I<0xFF, MRM1m, (outs), (ins i16mem:$dst), "dec{w}\t$dst", + [(store (add (loadi16 addr:$dst), -1), addr:$dst), + (implicit EFLAGS)]>, + OpSize, Requires<[In32BitMode]>; + def DEC32m : I<0xFF, MRM1m, (outs), (ins i32mem:$dst), "dec{l}\t$dst", + [(store (add (loadi32 addr:$dst), -1), addr:$dst), + (implicit EFLAGS)]>, + Requires<[In32BitMode]>; +} // Constraints = "", CodeSize = 2 +} // Defs = [EFLAGS] + +// Logical operators... +let Defs = [EFLAGS] in { +let isCommutable = 1 in { // X = AND Y, Z --> X = AND Z, Y +def AND8rr : I<0x20, MRMDestReg, + (outs GR8 :$dst), (ins GR8 :$src1, GR8 :$src2), + "and{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86and_flag GR8:$src1, GR8:$src2))]>; +def AND16rr : I<0x21, MRMDestReg, + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "and{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86and_flag GR16:$src1, + GR16:$src2))]>, OpSize; +def AND32rr : I<0x21, MRMDestReg, + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "and{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86and_flag GR32:$src1, + GR32:$src2))]>; +} + +// AND instructions with the destination register in REG and the source register +// in R/M. Included for the disassembler. +let isCodeGenOnly = 1 in { +def AND8rr_REV : I<0x22, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "and{b}\t{$src2, $dst|$dst, $src2}", []>; +def AND16rr_REV : I<0x23, MRMSrcReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "and{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; +def AND32rr_REV : I<0x23, MRMSrcReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "and{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +def AND8rm : I<0x22, MRMSrcMem, + (outs GR8 :$dst), (ins GR8 :$src1, i8mem :$src2), + "and{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86and_flag GR8:$src1, + (loadi8 addr:$src2)))]>; +def AND16rm : I<0x23, MRMSrcMem, + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "and{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86and_flag GR16:$src1, + (loadi16 addr:$src2)))]>, + OpSize; +def AND32rm : I<0x23, MRMSrcMem, + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "and{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86and_flag GR32:$src1, + (loadi32 addr:$src2)))]>; + +def AND8ri : Ii8<0x80, MRM4r, + (outs GR8 :$dst), (ins GR8 :$src1, i8imm :$src2), + "and{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86and_flag GR8:$src1, + imm:$src2))]>; +def AND16ri : Ii16<0x81, MRM4r, + (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2), + "and{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86and_flag GR16:$src1, + imm:$src2))]>, OpSize; +def AND32ri : Ii32<0x81, MRM4r, + (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2), + "and{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86and_flag GR32:$src1, + imm:$src2))]>; +def AND16ri8 : Ii8<0x83, MRM4r, + (outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2), + "and{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86and_flag GR16:$src1, + i16immSExt8:$src2))]>, + OpSize; +def AND32ri8 : Ii8<0x83, MRM4r, + (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2), + "and{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86and_flag GR32:$src1, + i32immSExt8:$src2))]>; + +let Constraints = "" in { + def AND8mr : I<0x20, MRMDestMem, + (outs), (ins i8mem :$dst, GR8 :$src), + "and{b}\t{$src, $dst|$dst, $src}", + [(store (and (load addr:$dst), GR8:$src), addr:$dst), + (implicit EFLAGS)]>; + def AND16mr : I<0x21, MRMDestMem, + (outs), (ins i16mem:$dst, GR16:$src), + "and{w}\t{$src, $dst|$dst, $src}", + [(store (and (load addr:$dst), GR16:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def AND32mr : I<0x21, MRMDestMem, + (outs), (ins i32mem:$dst, GR32:$src), + "and{l}\t{$src, $dst|$dst, $src}", + [(store (and (load addr:$dst), GR32:$src), addr:$dst), + (implicit EFLAGS)]>; + def AND8mi : Ii8<0x80, MRM4m, + (outs), (ins i8mem :$dst, i8imm :$src), + "and{b}\t{$src, $dst|$dst, $src}", + [(store (and (loadi8 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>; + def AND16mi : Ii16<0x81, MRM4m, + (outs), (ins i16mem:$dst, i16imm:$src), + "and{w}\t{$src, $dst|$dst, $src}", + [(store (and (loadi16 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def AND32mi : Ii32<0x81, MRM4m, + (outs), (ins i32mem:$dst, i32imm:$src), + "and{l}\t{$src, $dst|$dst, $src}", + [(store (and (loadi32 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>; + def AND16mi8 : Ii8<0x83, MRM4m, + (outs), (ins i16mem:$dst, i16i8imm :$src), + "and{w}\t{$src, $dst|$dst, $src}", + [(store (and (load addr:$dst), i16immSExt8:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def AND32mi8 : Ii8<0x83, MRM4m, + (outs), (ins i32mem:$dst, i32i8imm :$src), + "and{l}\t{$src, $dst|$dst, $src}", + [(store (and (load addr:$dst), i32immSExt8:$src), addr:$dst), + (implicit EFLAGS)]>; + + def AND8i8 : Ii8<0x24, RawFrm, (outs), (ins i8imm:$src), + "and{b}\t{$src, %al|%al, $src}", []>; + def AND16i16 : Ii16<0x25, RawFrm, (outs), (ins i16imm:$src), + "and{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def AND32i32 : Ii32<0x25, RawFrm, (outs), (ins i32imm:$src), + "and{l}\t{$src, %eax|%eax, $src}", []>; + +} // Constraints = "" + + +let isCommutable = 1 in { // X = OR Y, Z --> X = OR Z, Y +def OR8rr : I<0x08, MRMDestReg, (outs GR8 :$dst), + (ins GR8 :$src1, GR8 :$src2), + "or{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86or_flag GR8:$src1, GR8:$src2))]>; +def OR16rr : I<0x09, MRMDestReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "or{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86or_flag GR16:$src1,GR16:$src2))]>, + OpSize; +def OR32rr : I<0x09, MRMDestReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "or{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86or_flag GR32:$src1,GR32:$src2))]>; +} + +// OR instructions with the destination register in REG and the source register +// in R/M. Included for the disassembler. +let isCodeGenOnly = 1 in { +def OR8rr_REV : I<0x0A, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "or{b}\t{$src2, $dst|$dst, $src2}", []>; +def OR16rr_REV : I<0x0B, MRMSrcReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "or{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; +def OR32rr_REV : I<0x0B, MRMSrcReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "or{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +def OR8rm : I<0x0A, MRMSrcMem, (outs GR8 :$dst), + (ins GR8 :$src1, i8mem :$src2), + "or{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86or_flag GR8:$src1, + (load addr:$src2)))]>; +def OR16rm : I<0x0B, MRMSrcMem, (outs GR16:$dst), + (ins GR16:$src1, i16mem:$src2), + "or{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86or_flag GR16:$src1, + (load addr:$src2)))]>, + OpSize; +def OR32rm : I<0x0B, MRMSrcMem, (outs GR32:$dst), + (ins GR32:$src1, i32mem:$src2), + "or{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86or_flag GR32:$src1, + (load addr:$src2)))]>; + +def OR8ri : Ii8 <0x80, MRM1r, (outs GR8 :$dst), + (ins GR8 :$src1, i8imm:$src2), + "or{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst,EFLAGS, (X86or_flag GR8:$src1, imm:$src2))]>; +def OR16ri : Ii16<0x81, MRM1r, (outs GR16:$dst), + (ins GR16:$src1, i16imm:$src2), + "or{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86or_flag GR16:$src1, + imm:$src2))]>, OpSize; +def OR32ri : Ii32<0x81, MRM1r, (outs GR32:$dst), + (ins GR32:$src1, i32imm:$src2), + "or{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86or_flag GR32:$src1, + imm:$src2))]>; + +def OR16ri8 : Ii8<0x83, MRM1r, (outs GR16:$dst), + (ins GR16:$src1, i16i8imm:$src2), + "or{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86or_flag GR16:$src1, + i16immSExt8:$src2))]>, OpSize; +def OR32ri8 : Ii8<0x83, MRM1r, (outs GR32:$dst), + (ins GR32:$src1, i32i8imm:$src2), + "or{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86or_flag GR32:$src1, + i32immSExt8:$src2))]>; +let Constraints = "" in { + def OR8mr : I<0x08, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src), + "or{b}\t{$src, $dst|$dst, $src}", + [(store (or (load addr:$dst), GR8:$src), addr:$dst), + (implicit EFLAGS)]>; + def OR16mr : I<0x09, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src), + "or{w}\t{$src, $dst|$dst, $src}", + [(store (or (load addr:$dst), GR16:$src), addr:$dst), + (implicit EFLAGS)]>, OpSize; + def OR32mr : I<0x09, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src), + "or{l}\t{$src, $dst|$dst, $src}", + [(store (or (load addr:$dst), GR32:$src), addr:$dst), + (implicit EFLAGS)]>; + def OR8mi : Ii8<0x80, MRM1m, (outs), (ins i8mem :$dst, i8imm:$src), + "or{b}\t{$src, $dst|$dst, $src}", + [(store (or (loadi8 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>; + def OR16mi : Ii16<0x81, MRM1m, (outs), (ins i16mem:$dst, i16imm:$src), + "or{w}\t{$src, $dst|$dst, $src}", + [(store (or (loadi16 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def OR32mi : Ii32<0x81, MRM1m, (outs), (ins i32mem:$dst, i32imm:$src), + "or{l}\t{$src, $dst|$dst, $src}", + [(store (or (loadi32 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>; + def OR16mi8 : Ii8<0x83, MRM1m, (outs), (ins i16mem:$dst, i16i8imm:$src), + "or{w}\t{$src, $dst|$dst, $src}", + [(store (or (load addr:$dst), i16immSExt8:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def OR32mi8 : Ii8<0x83, MRM1m, (outs), (ins i32mem:$dst, i32i8imm:$src), + "or{l}\t{$src, $dst|$dst, $src}", + [(store (or (load addr:$dst), i32immSExt8:$src), addr:$dst), + (implicit EFLAGS)]>; + + def OR8i8 : Ii8 <0x0C, RawFrm, (outs), (ins i8imm:$src), + "or{b}\t{$src, %al|%al, $src}", []>; + def OR16i16 : Ii16 <0x0D, RawFrm, (outs), (ins i16imm:$src), + "or{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def OR32i32 : Ii32 <0x0D, RawFrm, (outs), (ins i32imm:$src), + "or{l}\t{$src, %eax|%eax, $src}", []>; +} // Constraints = "" + + +let isCommutable = 1 in { // X = XOR Y, Z --> X = XOR Z, Y + def XOR8rr : I<0x30, MRMDestReg, + (outs GR8 :$dst), (ins GR8 :$src1, GR8 :$src2), + "xor{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86xor_flag GR8:$src1, + GR8:$src2))]>; + def XOR16rr : I<0x31, MRMDestReg, + (outs GR16:$dst), (ins GR16:$src1, GR16:$src2), + "xor{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86xor_flag GR16:$src1, + GR16:$src2))]>, OpSize; + def XOR32rr : I<0x31, MRMDestReg, + (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), + "xor{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86xor_flag GR32:$src1, + GR32:$src2))]>; +} // isCommutable = 1 + +// XOR instructions with the destination register in REG and the source register +// in R/M. Included for the disassembler. +let isCodeGenOnly = 1 in { +def XOR8rr_REV : I<0x32, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "xor{b}\t{$src2, $dst|$dst, $src2}", []>; +def XOR16rr_REV : I<0x33, MRMSrcReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "xor{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; +def XOR32rr_REV : I<0x33, MRMSrcReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "xor{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +def XOR8rm : I<0x32, MRMSrcMem, + (outs GR8 :$dst), (ins GR8:$src1, i8mem :$src2), + "xor{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86xor_flag GR8:$src1, + (load addr:$src2)))]>; +def XOR16rm : I<0x33, MRMSrcMem, + (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2), + "xor{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86xor_flag GR16:$src1, + (load addr:$src2)))]>, + OpSize; +def XOR32rm : I<0x33, MRMSrcMem, + (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), + "xor{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86xor_flag GR32:$src1, + (load addr:$src2)))]>; + +def XOR8ri : Ii8<0x80, MRM6r, + (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2), + "xor{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86xor_flag GR8:$src1, imm:$src2))]>; +def XOR16ri : Ii16<0x81, MRM6r, + (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2), + "xor{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86xor_flag GR16:$src1, + imm:$src2))]>, OpSize; +def XOR32ri : Ii32<0x81, MRM6r, + (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2), + "xor{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86xor_flag GR32:$src1, + imm:$src2))]>; +def XOR16ri8 : Ii8<0x83, MRM6r, + (outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2), + "xor{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86xor_flag GR16:$src1, + i16immSExt8:$src2))]>, + OpSize; +def XOR32ri8 : Ii8<0x83, MRM6r, + (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2), + "xor{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86xor_flag GR32:$src1, + i32immSExt8:$src2))]>; + +let Constraints = "" in { + def XOR8mr : I<0x30, MRMDestMem, + (outs), (ins i8mem :$dst, GR8 :$src), + "xor{b}\t{$src, $dst|$dst, $src}", + [(store (xor (load addr:$dst), GR8:$src), addr:$dst), + (implicit EFLAGS)]>; + def XOR16mr : I<0x31, MRMDestMem, + (outs), (ins i16mem:$dst, GR16:$src), + "xor{w}\t{$src, $dst|$dst, $src}", + [(store (xor (load addr:$dst), GR16:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def XOR32mr : I<0x31, MRMDestMem, + (outs), (ins i32mem:$dst, GR32:$src), + "xor{l}\t{$src, $dst|$dst, $src}", + [(store (xor (load addr:$dst), GR32:$src), addr:$dst), + (implicit EFLAGS)]>; + def XOR8mi : Ii8<0x80, MRM6m, + (outs), (ins i8mem :$dst, i8imm :$src), + "xor{b}\t{$src, $dst|$dst, $src}", + [(store (xor (loadi8 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>; + def XOR16mi : Ii16<0x81, MRM6m, + (outs), (ins i16mem:$dst, i16imm:$src), + "xor{w}\t{$src, $dst|$dst, $src}", + [(store (xor (loadi16 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def XOR32mi : Ii32<0x81, MRM6m, + (outs), (ins i32mem:$dst, i32imm:$src), + "xor{l}\t{$src, $dst|$dst, $src}", + [(store (xor (loadi32 addr:$dst), imm:$src), addr:$dst), + (implicit EFLAGS)]>; + def XOR16mi8 : Ii8<0x83, MRM6m, + (outs), (ins i16mem:$dst, i16i8imm :$src), + "xor{w}\t{$src, $dst|$dst, $src}", + [(store (xor (load addr:$dst), i16immSExt8:$src), addr:$dst), + (implicit EFLAGS)]>, + OpSize; + def XOR32mi8 : Ii8<0x83, MRM6m, + (outs), (ins i32mem:$dst, i32i8imm :$src), + "xor{l}\t{$src, $dst|$dst, $src}", + [(store (xor (load addr:$dst), i32immSExt8:$src), addr:$dst), + (implicit EFLAGS)]>; + + def XOR8i8 : Ii8 <0x34, RawFrm, (outs), (ins i8imm:$src), + "xor{b}\t{$src, %al|%al, $src}", []>; + def XOR16i16 : Ii16<0x35, RawFrm, (outs), (ins i16imm:$src), + "xor{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def XOR32i32 : Ii32<0x35, RawFrm, (outs), (ins i32imm:$src), + "xor{l}\t{$src, %eax|%eax, $src}", []>; +} // Constraints = "" +} // Defs = [EFLAGS] + +// Shift instructions +let Defs = [EFLAGS] in { +let Uses = [CL] in { +def SHL8rCL : I<0xD2, MRM4r, (outs GR8 :$dst), (ins GR8 :$src1), + "shl{b}\t{%cl, $dst|$dst, CL}", + [(set GR8:$dst, (shl GR8:$src1, CL))]>; +def SHL16rCL : I<0xD3, MRM4r, (outs GR16:$dst), (ins GR16:$src1), + "shl{w}\t{%cl, $dst|$dst, CL}", + [(set GR16:$dst, (shl GR16:$src1, CL))]>, OpSize; +def SHL32rCL : I<0xD3, MRM4r, (outs GR32:$dst), (ins GR32:$src1), + "shl{l}\t{%cl, $dst|$dst, CL}", + [(set GR32:$dst, (shl GR32:$src1, CL))]>; +} // Uses = [CL] + +def SHL8ri : Ii8<0xC0, MRM4r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2), + "shl{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (shl GR8:$src1, (i8 imm:$src2)))]>; + +let isConvertibleToThreeAddress = 1 in { // Can transform into LEA. +def SHL16ri : Ii8<0xC1, MRM4r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2), + "shl{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (shl GR16:$src1, (i8 imm:$src2)))]>, OpSize; +def SHL32ri : Ii8<0xC1, MRM4r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2), + "shl{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (shl GR32:$src1, (i8 imm:$src2)))]>; + +// NOTE: We don't include patterns for shifts of a register by one, because +// 'add reg,reg' is cheaper. + +def SHL8r1 : I<0xD0, MRM4r, (outs GR8:$dst), (ins GR8:$src1), + "shl{b}\t$dst", []>; +def SHL16r1 : I<0xD1, MRM4r, (outs GR16:$dst), (ins GR16:$src1), + "shl{w}\t$dst", []>, OpSize; +def SHL32r1 : I<0xD1, MRM4r, (outs GR32:$dst), (ins GR32:$src1), + "shl{l}\t$dst", []>; + +} // isConvertibleToThreeAddress = 1 + +let Constraints = "" in { + let Uses = [CL] in { + def SHL8mCL : I<0xD2, MRM4m, (outs), (ins i8mem :$dst), + "shl{b}\t{%cl, $dst|$dst, CL}", + [(store (shl (loadi8 addr:$dst), CL), addr:$dst)]>; + def SHL16mCL : I<0xD3, MRM4m, (outs), (ins i16mem:$dst), + "shl{w}\t{%cl, $dst|$dst, CL}", + [(store (shl (loadi16 addr:$dst), CL), addr:$dst)]>, OpSize; + def SHL32mCL : I<0xD3, MRM4m, (outs), (ins i32mem:$dst), + "shl{l}\t{%cl, $dst|$dst, CL}", + [(store (shl (loadi32 addr:$dst), CL), addr:$dst)]>; + } + def SHL8mi : Ii8<0xC0, MRM4m, (outs), (ins i8mem :$dst, i8imm:$src), + "shl{b}\t{$src, $dst|$dst, $src}", + [(store (shl (loadi8 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + def SHL16mi : Ii8<0xC1, MRM4m, (outs), (ins i16mem:$dst, i8imm:$src), + "shl{w}\t{$src, $dst|$dst, $src}", + [(store (shl (loadi16 addr:$dst), (i8 imm:$src)), addr:$dst)]>, + OpSize; + def SHL32mi : Ii8<0xC1, MRM4m, (outs), (ins i32mem:$dst, i8imm:$src), + "shl{l}\t{$src, $dst|$dst, $src}", + [(store (shl (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + + // Shift by 1 + def SHL8m1 : I<0xD0, MRM4m, (outs), (ins i8mem :$dst), + "shl{b}\t$dst", + [(store (shl (loadi8 addr:$dst), (i8 1)), addr:$dst)]>; + def SHL16m1 : I<0xD1, MRM4m, (outs), (ins i16mem:$dst), + "shl{w}\t$dst", + [(store (shl (loadi16 addr:$dst), (i8 1)), addr:$dst)]>, + OpSize; + def SHL32m1 : I<0xD1, MRM4m, (outs), (ins i32mem:$dst), + "shl{l}\t$dst", + [(store (shl (loadi32 addr:$dst), (i8 1)), addr:$dst)]>; +} // Constraints = "" + +let Uses = [CL] in { +def SHR8rCL : I<0xD2, MRM5r, (outs GR8 :$dst), (ins GR8 :$src1), + "shr{b}\t{%cl, $dst|$dst, CL}", + [(set GR8:$dst, (srl GR8:$src1, CL))]>; +def SHR16rCL : I<0xD3, MRM5r, (outs GR16:$dst), (ins GR16:$src1), + "shr{w}\t{%cl, $dst|$dst, CL}", + [(set GR16:$dst, (srl GR16:$src1, CL))]>, OpSize; +def SHR32rCL : I<0xD3, MRM5r, (outs GR32:$dst), (ins GR32:$src1), + "shr{l}\t{%cl, $dst|$dst, CL}", + [(set GR32:$dst, (srl GR32:$src1, CL))]>; +} + +def SHR8ri : Ii8<0xC0, MRM5r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2), + "shr{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (srl GR8:$src1, (i8 imm:$src2)))]>; +def SHR16ri : Ii8<0xC1, MRM5r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2), + "shr{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (srl GR16:$src1, (i8 imm:$src2)))]>, OpSize; +def SHR32ri : Ii8<0xC1, MRM5r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2), + "shr{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (srl GR32:$src1, (i8 imm:$src2)))]>; + +// Shift by 1 +def SHR8r1 : I<0xD0, MRM5r, (outs GR8:$dst), (ins GR8:$src1), + "shr{b}\t$dst", + [(set GR8:$dst, (srl GR8:$src1, (i8 1)))]>; +def SHR16r1 : I<0xD1, MRM5r, (outs GR16:$dst), (ins GR16:$src1), + "shr{w}\t$dst", + [(set GR16:$dst, (srl GR16:$src1, (i8 1)))]>, OpSize; +def SHR32r1 : I<0xD1, MRM5r, (outs GR32:$dst), (ins GR32:$src1), + "shr{l}\t$dst", + [(set GR32:$dst, (srl GR32:$src1, (i8 1)))]>; + +let Constraints = "" in { + let Uses = [CL] in { + def SHR8mCL : I<0xD2, MRM5m, (outs), (ins i8mem :$dst), + "shr{b}\t{%cl, $dst|$dst, CL}", + [(store (srl (loadi8 addr:$dst), CL), addr:$dst)]>; + def SHR16mCL : I<0xD3, MRM5m, (outs), (ins i16mem:$dst), + "shr{w}\t{%cl, $dst|$dst, CL}", + [(store (srl (loadi16 addr:$dst), CL), addr:$dst)]>, + OpSize; + def SHR32mCL : I<0xD3, MRM5m, (outs), (ins i32mem:$dst), + "shr{l}\t{%cl, $dst|$dst, CL}", + [(store (srl (loadi32 addr:$dst), CL), addr:$dst)]>; + } + def SHR8mi : Ii8<0xC0, MRM5m, (outs), (ins i8mem :$dst, i8imm:$src), + "shr{b}\t{$src, $dst|$dst, $src}", + [(store (srl (loadi8 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + def SHR16mi : Ii8<0xC1, MRM5m, (outs), (ins i16mem:$dst, i8imm:$src), + "shr{w}\t{$src, $dst|$dst, $src}", + [(store (srl (loadi16 addr:$dst), (i8 imm:$src)), addr:$dst)]>, + OpSize; + def SHR32mi : Ii8<0xC1, MRM5m, (outs), (ins i32mem:$dst, i8imm:$src), + "shr{l}\t{$src, $dst|$dst, $src}", + [(store (srl (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + + // Shift by 1 + def SHR8m1 : I<0xD0, MRM5m, (outs), (ins i8mem :$dst), + "shr{b}\t$dst", + [(store (srl (loadi8 addr:$dst), (i8 1)), addr:$dst)]>; + def SHR16m1 : I<0xD1, MRM5m, (outs), (ins i16mem:$dst), + "shr{w}\t$dst", + [(store (srl (loadi16 addr:$dst), (i8 1)), addr:$dst)]>,OpSize; + def SHR32m1 : I<0xD1, MRM5m, (outs), (ins i32mem:$dst), + "shr{l}\t$dst", + [(store (srl (loadi32 addr:$dst), (i8 1)), addr:$dst)]>; +} // Constraints = "" + +let Uses = [CL] in { +def SAR8rCL : I<0xD2, MRM7r, (outs GR8 :$dst), (ins GR8 :$src1), + "sar{b}\t{%cl, $dst|$dst, CL}", + [(set GR8:$dst, (sra GR8:$src1, CL))]>; +def SAR16rCL : I<0xD3, MRM7r, (outs GR16:$dst), (ins GR16:$src1), + "sar{w}\t{%cl, $dst|$dst, CL}", + [(set GR16:$dst, (sra GR16:$src1, CL))]>, OpSize; +def SAR32rCL : I<0xD3, MRM7r, (outs GR32:$dst), (ins GR32:$src1), + "sar{l}\t{%cl, $dst|$dst, CL}", + [(set GR32:$dst, (sra GR32:$src1, CL))]>; +} + +def SAR8ri : Ii8<0xC0, MRM7r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2), + "sar{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (sra GR8:$src1, (i8 imm:$src2)))]>; +def SAR16ri : Ii8<0xC1, MRM7r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2), + "sar{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (sra GR16:$src1, (i8 imm:$src2)))]>, + OpSize; +def SAR32ri : Ii8<0xC1, MRM7r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2), + "sar{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (sra GR32:$src1, (i8 imm:$src2)))]>; + +// Shift by 1 +def SAR8r1 : I<0xD0, MRM7r, (outs GR8 :$dst), (ins GR8 :$src1), + "sar{b}\t$dst", + [(set GR8:$dst, (sra GR8:$src1, (i8 1)))]>; +def SAR16r1 : I<0xD1, MRM7r, (outs GR16:$dst), (ins GR16:$src1), + "sar{w}\t$dst", + [(set GR16:$dst, (sra GR16:$src1, (i8 1)))]>, OpSize; +def SAR32r1 : I<0xD1, MRM7r, (outs GR32:$dst), (ins GR32:$src1), + "sar{l}\t$dst", + [(set GR32:$dst, (sra GR32:$src1, (i8 1)))]>; + +let Constraints = "" in { + let Uses = [CL] in { + def SAR8mCL : I<0xD2, MRM7m, (outs), (ins i8mem :$dst), + "sar{b}\t{%cl, $dst|$dst, CL}", + [(store (sra (loadi8 addr:$dst), CL), addr:$dst)]>; + def SAR16mCL : I<0xD3, MRM7m, (outs), (ins i16mem:$dst), + "sar{w}\t{%cl, $dst|$dst, CL}", + [(store (sra (loadi16 addr:$dst), CL), addr:$dst)]>, OpSize; + def SAR32mCL : I<0xD3, MRM7m, (outs), (ins i32mem:$dst), + "sar{l}\t{%cl, $dst|$dst, CL}", + [(store (sra (loadi32 addr:$dst), CL), addr:$dst)]>; + } + def SAR8mi : Ii8<0xC0, MRM7m, (outs), (ins i8mem :$dst, i8imm:$src), + "sar{b}\t{$src, $dst|$dst, $src}", + [(store (sra (loadi8 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + def SAR16mi : Ii8<0xC1, MRM7m, (outs), (ins i16mem:$dst, i8imm:$src), + "sar{w}\t{$src, $dst|$dst, $src}", + [(store (sra (loadi16 addr:$dst), (i8 imm:$src)), addr:$dst)]>, + OpSize; + def SAR32mi : Ii8<0xC1, MRM7m, (outs), (ins i32mem:$dst, i8imm:$src), + "sar{l}\t{$src, $dst|$dst, $src}", + [(store (sra (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + + // Shift by 1 + def SAR8m1 : I<0xD0, MRM7m, (outs), (ins i8mem :$dst), + "sar{b}\t$dst", + [(store (sra (loadi8 addr:$dst), (i8 1)), addr:$dst)]>; + def SAR16m1 : I<0xD1, MRM7m, (outs), (ins i16mem:$dst), + "sar{w}\t$dst", + [(store (sra (loadi16 addr:$dst), (i8 1)), addr:$dst)]>, + OpSize; + def SAR32m1 : I<0xD1, MRM7m, (outs), (ins i32mem:$dst), + "sar{l}\t$dst", + [(store (sra (loadi32 addr:$dst), (i8 1)), addr:$dst)]>; +} // Constraints = "" + +// Rotate instructions + +def RCL8r1 : I<0xD0, MRM2r, (outs GR8:$dst), (ins GR8:$src1), + "rcl{b}\t{1, $dst|$dst, 1}", []>; +let Uses = [CL] in { +def RCL8rCL : I<0xD2, MRM2r, (outs GR8:$dst), (ins GR8:$src1), + "rcl{b}\t{%cl, $dst|$dst, CL}", []>; +} +def RCL8ri : Ii8<0xC0, MRM2r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$cnt), + "rcl{b}\t{$cnt, $dst|$dst, $cnt}", []>; + +def RCL16r1 : I<0xD1, MRM2r, (outs GR16:$dst), (ins GR16:$src1), + "rcl{w}\t{1, $dst|$dst, 1}", []>, OpSize; +let Uses = [CL] in { +def RCL16rCL : I<0xD3, MRM2r, (outs GR16:$dst), (ins GR16:$src1), + "rcl{w}\t{%cl, $dst|$dst, CL}", []>, OpSize; +} +def RCL16ri : Ii8<0xC1, MRM2r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$cnt), + "rcl{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize; + +def RCL32r1 : I<0xD1, MRM2r, (outs GR32:$dst), (ins GR32:$src1), + "rcl{l}\t{1, $dst|$dst, 1}", []>; +let Uses = [CL] in { +def RCL32rCL : I<0xD3, MRM2r, (outs GR32:$dst), (ins GR32:$src1), + "rcl{l}\t{%cl, $dst|$dst, CL}", []>; +} +def RCL32ri : Ii8<0xC1, MRM2r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$cnt), + "rcl{l}\t{$cnt, $dst|$dst, $cnt}", []>; + +def RCR8r1 : I<0xD0, MRM3r, (outs GR8:$dst), (ins GR8:$src1), + "rcr{b}\t{1, $dst|$dst, 1}", []>; +let Uses = [CL] in { +def RCR8rCL : I<0xD2, MRM3r, (outs GR8:$dst), (ins GR8:$src1), + "rcr{b}\t{%cl, $dst|$dst, CL}", []>; +} +def RCR8ri : Ii8<0xC0, MRM3r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$cnt), + "rcr{b}\t{$cnt, $dst|$dst, $cnt}", []>; + +def RCR16r1 : I<0xD1, MRM3r, (outs GR16:$dst), (ins GR16:$src1), + "rcr{w}\t{1, $dst|$dst, 1}", []>, OpSize; +let Uses = [CL] in { +def RCR16rCL : I<0xD3, MRM3r, (outs GR16:$dst), (ins GR16:$src1), + "rcr{w}\t{%cl, $dst|$dst, CL}", []>, OpSize; +} +def RCR16ri : Ii8<0xC1, MRM3r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$cnt), + "rcr{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize; + +def RCR32r1 : I<0xD1, MRM3r, (outs GR32:$dst), (ins GR32:$src1), + "rcr{l}\t{1, $dst|$dst, 1}", []>; +let Uses = [CL] in { +def RCR32rCL : I<0xD3, MRM3r, (outs GR32:$dst), (ins GR32:$src1), + "rcr{l}\t{%cl, $dst|$dst, CL}", []>; +} +def RCR32ri : Ii8<0xC1, MRM3r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$cnt), + "rcr{l}\t{$cnt, $dst|$dst, $cnt}", []>; + +let Constraints = "" in { +def RCL8m1 : I<0xD0, MRM2m, (outs), (ins i8mem:$dst), + "rcl{b}\t{1, $dst|$dst, 1}", []>; +def RCL8mi : Ii8<0xC0, MRM2m, (outs), (ins i8mem:$dst, i8imm:$cnt), + "rcl{b}\t{$cnt, $dst|$dst, $cnt}", []>; +def RCL16m1 : I<0xD1, MRM2m, (outs), (ins i16mem:$dst), + "rcl{w}\t{1, $dst|$dst, 1}", []>, OpSize; +def RCL16mi : Ii8<0xC1, MRM2m, (outs), (ins i16mem:$dst, i8imm:$cnt), + "rcl{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize; +def RCL32m1 : I<0xD1, MRM2m, (outs), (ins i32mem:$dst), + "rcl{l}\t{1, $dst|$dst, 1}", []>; +def RCL32mi : Ii8<0xC1, MRM2m, (outs), (ins i32mem:$dst, i8imm:$cnt), + "rcl{l}\t{$cnt, $dst|$dst, $cnt}", []>; +def RCR8m1 : I<0xD0, MRM3m, (outs), (ins i8mem:$dst), + "rcr{b}\t{1, $dst|$dst, 1}", []>; +def RCR8mi : Ii8<0xC0, MRM3m, (outs), (ins i8mem:$dst, i8imm:$cnt), + "rcr{b}\t{$cnt, $dst|$dst, $cnt}", []>; +def RCR16m1 : I<0xD1, MRM3m, (outs), (ins i16mem:$dst), + "rcr{w}\t{1, $dst|$dst, 1}", []>, OpSize; +def RCR16mi : Ii8<0xC1, MRM3m, (outs), (ins i16mem:$dst, i8imm:$cnt), + "rcr{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize; +def RCR32m1 : I<0xD1, MRM3m, (outs), (ins i32mem:$dst), + "rcr{l}\t{1, $dst|$dst, 1}", []>; +def RCR32mi : Ii8<0xC1, MRM3m, (outs), (ins i32mem:$dst, i8imm:$cnt), + "rcr{l}\t{$cnt, $dst|$dst, $cnt}", []>; + +let Uses = [CL] in { +def RCL8mCL : I<0xD2, MRM2m, (outs), (ins i8mem:$dst), + "rcl{b}\t{%cl, $dst|$dst, CL}", []>; +def RCL16mCL : I<0xD3, MRM2m, (outs), (ins i16mem:$dst), + "rcl{w}\t{%cl, $dst|$dst, CL}", []>, OpSize; +def RCL32mCL : I<0xD3, MRM2m, (outs), (ins i32mem:$dst), + "rcl{l}\t{%cl, $dst|$dst, CL}", []>; +def RCR8mCL : I<0xD2, MRM3m, (outs), (ins i8mem:$dst), + "rcr{b}\t{%cl, $dst|$dst, CL}", []>; +def RCR16mCL : I<0xD3, MRM3m, (outs), (ins i16mem:$dst), + "rcr{w}\t{%cl, $dst|$dst, CL}", []>, OpSize; +def RCR32mCL : I<0xD3, MRM3m, (outs), (ins i32mem:$dst), + "rcr{l}\t{%cl, $dst|$dst, CL}", []>; +} +} // Constraints = "" + +// FIXME: provide shorter instructions when imm8 == 1 +let Uses = [CL] in { +def ROL8rCL : I<0xD2, MRM0r, (outs GR8 :$dst), (ins GR8 :$src1), + "rol{b}\t{%cl, $dst|$dst, CL}", + [(set GR8:$dst, (rotl GR8:$src1, CL))]>; +def ROL16rCL : I<0xD3, MRM0r, (outs GR16:$dst), (ins GR16:$src1), + "rol{w}\t{%cl, $dst|$dst, CL}", + [(set GR16:$dst, (rotl GR16:$src1, CL))]>, OpSize; +def ROL32rCL : I<0xD3, MRM0r, (outs GR32:$dst), (ins GR32:$src1), + "rol{l}\t{%cl, $dst|$dst, CL}", + [(set GR32:$dst, (rotl GR32:$src1, CL))]>; +} + +def ROL8ri : Ii8<0xC0, MRM0r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2), + "rol{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (rotl GR8:$src1, (i8 imm:$src2)))]>; +def ROL16ri : Ii8<0xC1, MRM0r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2), + "rol{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (rotl GR16:$src1, (i8 imm:$src2)))]>, + OpSize; +def ROL32ri : Ii8<0xC1, MRM0r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2), + "rol{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (rotl GR32:$src1, (i8 imm:$src2)))]>; + +// Rotate by 1 +def ROL8r1 : I<0xD0, MRM0r, (outs GR8 :$dst), (ins GR8 :$src1), + "rol{b}\t$dst", + [(set GR8:$dst, (rotl GR8:$src1, (i8 1)))]>; +def ROL16r1 : I<0xD1, MRM0r, (outs GR16:$dst), (ins GR16:$src1), + "rol{w}\t$dst", + [(set GR16:$dst, (rotl GR16:$src1, (i8 1)))]>, OpSize; +def ROL32r1 : I<0xD1, MRM0r, (outs GR32:$dst), (ins GR32:$src1), + "rol{l}\t$dst", + [(set GR32:$dst, (rotl GR32:$src1, (i8 1)))]>; + +let Constraints = "" in { + let Uses = [CL] in { + def ROL8mCL : I<0xD2, MRM0m, (outs), (ins i8mem :$dst), + "rol{b}\t{%cl, $dst|$dst, CL}", + [(store (rotl (loadi8 addr:$dst), CL), addr:$dst)]>; + def ROL16mCL : I<0xD3, MRM0m, (outs), (ins i16mem:$dst), + "rol{w}\t{%cl, $dst|$dst, CL}", + [(store (rotl (loadi16 addr:$dst), CL), addr:$dst)]>, OpSize; + def ROL32mCL : I<0xD3, MRM0m, (outs), (ins i32mem:$dst), + "rol{l}\t{%cl, $dst|$dst, CL}", + [(store (rotl (loadi32 addr:$dst), CL), addr:$dst)]>; + } + def ROL8mi : Ii8<0xC0, MRM0m, (outs), (ins i8mem :$dst, i8imm:$src), + "rol{b}\t{$src, $dst|$dst, $src}", + [(store (rotl (loadi8 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + def ROL16mi : Ii8<0xC1, MRM0m, (outs), (ins i16mem:$dst, i8imm:$src), + "rol{w}\t{$src, $dst|$dst, $src}", + [(store (rotl (loadi16 addr:$dst), (i8 imm:$src)), addr:$dst)]>, + OpSize; + def ROL32mi : Ii8<0xC1, MRM0m, (outs), (ins i32mem:$dst, i8imm:$src), + "rol{l}\t{$src, $dst|$dst, $src}", + [(store (rotl (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + + // Rotate by 1 + def ROL8m1 : I<0xD0, MRM0m, (outs), (ins i8mem :$dst), + "rol{b}\t$dst", + [(store (rotl (loadi8 addr:$dst), (i8 1)), addr:$dst)]>; + def ROL16m1 : I<0xD1, MRM0m, (outs), (ins i16mem:$dst), + "rol{w}\t$dst", + [(store (rotl (loadi16 addr:$dst), (i8 1)), addr:$dst)]>, + OpSize; + def ROL32m1 : I<0xD1, MRM0m, (outs), (ins i32mem:$dst), + "rol{l}\t$dst", + [(store (rotl (loadi32 addr:$dst), (i8 1)), addr:$dst)]>; +} // Constraints = "" + +let Uses = [CL] in { +def ROR8rCL : I<0xD2, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1), + "ror{b}\t{%cl, $dst|$dst, CL}", + [(set GR8:$dst, (rotr GR8:$src1, CL))]>; +def ROR16rCL : I<0xD3, MRM1r, (outs GR16:$dst), (ins GR16:$src1), + "ror{w}\t{%cl, $dst|$dst, CL}", + [(set GR16:$dst, (rotr GR16:$src1, CL))]>, OpSize; +def ROR32rCL : I<0xD3, MRM1r, (outs GR32:$dst), (ins GR32:$src1), + "ror{l}\t{%cl, $dst|$dst, CL}", + [(set GR32:$dst, (rotr GR32:$src1, CL))]>; +} + +def ROR8ri : Ii8<0xC0, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2), + "ror{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (rotr GR8:$src1, (i8 imm:$src2)))]>; +def ROR16ri : Ii8<0xC1, MRM1r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2), + "ror{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (rotr GR16:$src1, (i8 imm:$src2)))]>, + OpSize; +def ROR32ri : Ii8<0xC1, MRM1r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2), + "ror{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, (rotr GR32:$src1, (i8 imm:$src2)))]>; + +// Rotate by 1 +def ROR8r1 : I<0xD0, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1), + "ror{b}\t$dst", + [(set GR8:$dst, (rotr GR8:$src1, (i8 1)))]>; +def ROR16r1 : I<0xD1, MRM1r, (outs GR16:$dst), (ins GR16:$src1), + "ror{w}\t$dst", + [(set GR16:$dst, (rotr GR16:$src1, (i8 1)))]>, OpSize; +def ROR32r1 : I<0xD1, MRM1r, (outs GR32:$dst), (ins GR32:$src1), + "ror{l}\t$dst", + [(set GR32:$dst, (rotr GR32:$src1, (i8 1)))]>; + +let Constraints = "" in { + let Uses = [CL] in { + def ROR8mCL : I<0xD2, MRM1m, (outs), (ins i8mem :$dst), + "ror{b}\t{%cl, $dst|$dst, CL}", + [(store (rotr (loadi8 addr:$dst), CL), addr:$dst)]>; + def ROR16mCL : I<0xD3, MRM1m, (outs), (ins i16mem:$dst), + "ror{w}\t{%cl, $dst|$dst, CL}", + [(store (rotr (loadi16 addr:$dst), CL), addr:$dst)]>, OpSize; + def ROR32mCL : I<0xD3, MRM1m, (outs), (ins i32mem:$dst), + "ror{l}\t{%cl, $dst|$dst, CL}", + [(store (rotr (loadi32 addr:$dst), CL), addr:$dst)]>; + } + def ROR8mi : Ii8<0xC0, MRM1m, (outs), (ins i8mem :$dst, i8imm:$src), + "ror{b}\t{$src, $dst|$dst, $src}", + [(store (rotr (loadi8 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + def ROR16mi : Ii8<0xC1, MRM1m, (outs), (ins i16mem:$dst, i8imm:$src), + "ror{w}\t{$src, $dst|$dst, $src}", + [(store (rotr (loadi16 addr:$dst), (i8 imm:$src)), addr:$dst)]>, + OpSize; + def ROR32mi : Ii8<0xC1, MRM1m, (outs), (ins i32mem:$dst, i8imm:$src), + "ror{l}\t{$src, $dst|$dst, $src}", + [(store (rotr (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>; + + // Rotate by 1 + def ROR8m1 : I<0xD0, MRM1m, (outs), (ins i8mem :$dst), + "ror{b}\t$dst", + [(store (rotr (loadi8 addr:$dst), (i8 1)), addr:$dst)]>; + def ROR16m1 : I<0xD1, MRM1m, (outs), (ins i16mem:$dst), + "ror{w}\t$dst", + [(store (rotr (loadi16 addr:$dst), (i8 1)), addr:$dst)]>, + OpSize; + def ROR32m1 : I<0xD1, MRM1m, (outs), (ins i32mem:$dst), + "ror{l}\t$dst", + [(store (rotr (loadi32 addr:$dst), (i8 1)), addr:$dst)]>; +} // Constraints = "" + + +// Double shift instructions (generalizations of rotate) +let Uses = [CL] in { +def SHLD32rrCL : I<0xA5, MRMDestReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "shld{l}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(set GR32:$dst, (X86shld GR32:$src1, GR32:$src2, CL))]>, TB; +def SHRD32rrCL : I<0xAD, MRMDestReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "shrd{l}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(set GR32:$dst, (X86shrd GR32:$src1, GR32:$src2, CL))]>, TB; +def SHLD16rrCL : I<0xA5, MRMDestReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "shld{w}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(set GR16:$dst, (X86shld GR16:$src1, GR16:$src2, CL))]>, + TB, OpSize; +def SHRD16rrCL : I<0xAD, MRMDestReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(set GR16:$dst, (X86shrd GR16:$src1, GR16:$src2, CL))]>, + TB, OpSize; +} + +let isCommutable = 1 in { // These instructions commute to each other. +def SHLD32rri8 : Ii8<0xA4, MRMDestReg, + (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2, i8imm:$src3), + "shld{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(set GR32:$dst, (X86shld GR32:$src1, GR32:$src2, + (i8 imm:$src3)))]>, + TB; +def SHRD32rri8 : Ii8<0xAC, MRMDestReg, + (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2, i8imm:$src3), + "shrd{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(set GR32:$dst, (X86shrd GR32:$src1, GR32:$src2, + (i8 imm:$src3)))]>, + TB; +def SHLD16rri8 : Ii8<0xA4, MRMDestReg, + (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2, i8imm:$src3), + "shld{w}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(set GR16:$dst, (X86shld GR16:$src1, GR16:$src2, + (i8 imm:$src3)))]>, + TB, OpSize; +def SHRD16rri8 : Ii8<0xAC, MRMDestReg, + (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2, i8imm:$src3), + "shrd{w}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(set GR16:$dst, (X86shrd GR16:$src1, GR16:$src2, + (i8 imm:$src3)))]>, + TB, OpSize; +} + +let Constraints = "" in { + let Uses = [CL] in { + def SHLD32mrCL : I<0xA5, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2), + "shld{l}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(store (X86shld (loadi32 addr:$dst), GR32:$src2, CL), + addr:$dst)]>, TB; + def SHRD32mrCL : I<0xAD, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2), + "shrd{l}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(store (X86shrd (loadi32 addr:$dst), GR32:$src2, CL), + addr:$dst)]>, TB; + } + def SHLD32mri8 : Ii8<0xA4, MRMDestMem, + (outs), (ins i32mem:$dst, GR32:$src2, i8imm:$src3), + "shld{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(store (X86shld (loadi32 addr:$dst), GR32:$src2, + (i8 imm:$src3)), addr:$dst)]>, + TB; + def SHRD32mri8 : Ii8<0xAC, MRMDestMem, + (outs), (ins i32mem:$dst, GR32:$src2, i8imm:$src3), + "shrd{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(store (X86shrd (loadi32 addr:$dst), GR32:$src2, + (i8 imm:$src3)), addr:$dst)]>, + TB; + + let Uses = [CL] in { + def SHLD16mrCL : I<0xA5, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), + "shld{w}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(store (X86shld (loadi16 addr:$dst), GR16:$src2, CL), + addr:$dst)]>, TB, OpSize; + def SHRD16mrCL : I<0xAD, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), + "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}", + [(store (X86shrd (loadi16 addr:$dst), GR16:$src2, CL), + addr:$dst)]>, TB, OpSize; + } + def SHLD16mri8 : Ii8<0xA4, MRMDestMem, + (outs), (ins i16mem:$dst, GR16:$src2, i8imm:$src3), + "shld{w}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(store (X86shld (loadi16 addr:$dst), GR16:$src2, + (i8 imm:$src3)), addr:$dst)]>, + TB, OpSize; + def SHRD16mri8 : Ii8<0xAC, MRMDestMem, + (outs), (ins i16mem:$dst, GR16:$src2, i8imm:$src3), + "shrd{w}\t{$src3, $src2, $dst|$dst, $src2, $src3}", + [(store (X86shrd (loadi16 addr:$dst), GR16:$src2, + (i8 imm:$src3)), addr:$dst)]>, + TB, OpSize; +} // Constraints = "" +} // Defs = [EFLAGS] + + +// Arithmetic. +let Defs = [EFLAGS] in { +let isCommutable = 1 in { // X = ADD Y, Z --> X = ADD Z, Y +// Register-Register Addition +def ADD8rr : I<0x00, MRMDestReg, (outs GR8 :$dst), + (ins GR8 :$src1, GR8 :$src2), + "add{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86add_flag GR8:$src1, GR8:$src2))]>; + +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, $src2}", + [(set GR16:$dst, EFLAGS, (X86add_flag GR16:$src1, + GR16:$src2))]>, OpSize; +def ADD32rr : I<0x01, MRMDestReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "add{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86add_flag GR32:$src1, + GR32:$src2))]>; +} // end isConvertibleToThreeAddress +} // end isCommutable + +// These are alternate spellings for use by the disassembler, we mark them as +// code gen only to ensure they aren't matched by the assembler. +let isCodeGenOnly = 1 in { + def ADD8rr_alt: I<0x02, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "add{b}\t{$src2, $dst|$dst, $src2}", []>; + def ADD16rr_alt: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2), + "add{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; + def ADD32rr_alt: I<0x03, MRMSrcReg,(outs GR32:$dst),(ins GR32:$src1, GR32:$src2), + "add{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +// Register-Memory Addition +def ADD8rm : I<0x02, MRMSrcMem, (outs GR8 :$dst), + (ins GR8 :$src1, i8mem :$src2), + "add{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, (X86add_flag GR8:$src1, + (load addr:$src2)))]>; +def ADD16rm : I<0x03, MRMSrcMem, (outs GR16:$dst), + (ins GR16:$src1, i16mem:$src2), + "add{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, (X86add_flag GR16:$src1, + (load addr:$src2)))]>, OpSize; +def ADD32rm : I<0x03, MRMSrcMem, (outs GR32:$dst), + (ins GR32:$src1, i32mem:$src2), + "add{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, (X86add_flag GR32:$src1, + (load addr:$src2)))]>; + +// 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, EFLAGS, + (X86add_flag GR8:$src1, imm:$src2))]>; + +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, $src2}", + [(set GR16:$dst, EFLAGS, + (X86add_flag GR16:$src1, imm:$src2))]>, OpSize; +def ADD32ri : Ii32<0x81, MRM0r, (outs GR32:$dst), + (ins GR32:$src1, i32imm:$src2), + "add{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, + (X86add_flag GR32:$src1, imm:$src2))]>; +def ADD16ri8 : Ii8<0x83, MRM0r, (outs GR16:$dst), + (ins GR16:$src1, i16i8imm:$src2), + "add{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, + (X86add_flag GR16:$src1, i16immSExt8:$src2))]>, OpSize; +def ADD32ri8 : Ii8<0x83, MRM0r, (outs GR32:$dst), + (ins GR32:$src1, i32i8imm:$src2), + "add{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, + (X86add_flag GR32:$src1, i32immSExt8:$src2))]>; +} + +let Constraints = "" in { + // 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; + 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), + (implicit EFLAGS)]>; + def ADD8mi : Ii8<0x80, MRM0m, (outs), (ins i8mem :$dst, i8imm :$src2), + "add{b}\t{$src2, $dst|$dst, $src2}", + [(store (add (loadi8 addr:$dst), imm:$src2), addr:$dst), + (implicit EFLAGS)]>; + 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; + 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)]>; + 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; + 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), + (implicit EFLAGS)]>; + + // addition to rAX + def ADD8i8 : Ii8<0x04, RawFrm, (outs), (ins i8imm:$src), + "add{b}\t{$src, %al|%al, $src}", []>; + def ADD16i16 : Ii16<0x05, RawFrm, (outs), (ins i16imm:$src), + "add{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def ADD32i32 : Ii32<0x05, RawFrm, (outs), (ins i32imm:$src), + "add{l}\t{$src, %eax|%eax, $src}", []>; +} // Constraints = "" + +let Uses = [EFLAGS] in { +let isCommutable = 1 in { // X = ADC Y, Z --> X = ADC Z, Y +def ADC8rr : I<0x10, MRMDestReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "adc{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (adde GR8:$src1, GR8:$src2))]>; +def ADC16rr : I<0x11, MRMDestReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (adde GR16:$src1, GR16:$src2))]>, OpSize; +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))]>; +} + +let isCodeGenOnly = 1 in { +def ADC8rr_REV : I<0x12, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "adc{b}\t{$src2, $dst|$dst, $src2}", []>; +def ADC16rr_REV : I<0x13, MRMSrcReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; +def ADC32rr_REV : I<0x13, MRMSrcReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "adc{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +def ADC8rm : I<0x12, MRMSrcMem , (outs GR8:$dst), + (ins GR8:$src1, i8mem:$src2), + "adc{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (adde GR8:$src1, (load addr:$src2)))]>; +def ADC16rm : I<0x13, MRMSrcMem , (outs GR16:$dst), + (ins GR16:$src1, i16mem:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (adde GR16:$src1, (load addr:$src2)))]>, + OpSize; +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)))]>; +def ADC8ri : Ii8<0x80, MRM2r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2), + "adc{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (adde GR8:$src1, imm:$src2))]>; +def ADC16ri : Ii16<0x81, MRM2r, (outs GR16:$dst), + (ins GR16:$src1, i16imm:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (adde GR16:$src1, imm:$src2))]>, OpSize; +def ADC16ri8 : Ii8<0x83, MRM2r, (outs GR16:$dst), + (ins GR16:$src1, i16i8imm:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (adde GR16:$src1, i16immSExt8:$src2))]>, + OpSize; +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))]>; +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))]>; + +let Constraints = "" in { + def ADC8mr : I<0x10, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src2), + "adc{b}\t{$src2, $dst|$dst, $src2}", + [(store (adde (load addr:$dst), GR8:$src2), addr:$dst)]>; + def ADC16mr : I<0x11, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(store (adde (load addr:$dst), GR16:$src2), addr:$dst)]>, + OpSize; + 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)]>; + def ADC8mi : Ii8<0x80, MRM2m, (outs), (ins i8mem:$dst, i8imm:$src2), + "adc{b}\t{$src2, $dst|$dst, $src2}", + [(store (adde (loadi8 addr:$dst), imm:$src2), addr:$dst)]>; + def ADC16mi : Ii16<0x81, MRM2m, (outs), (ins i16mem:$dst, i16imm:$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(store (adde (loadi16 addr:$dst), imm:$src2), addr:$dst)]>, + OpSize; + def ADC16mi8 : Ii8<0x83, MRM2m, (outs), (ins i16mem:$dst, i16i8imm :$src2), + "adc{w}\t{$src2, $dst|$dst, $src2}", + [(store (adde (load addr:$dst), i16immSExt8:$src2), addr:$dst)]>, + OpSize; + 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)]>; + 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)]>; + + def ADC8i8 : Ii8<0x14, RawFrm, (outs), (ins i8imm:$src), + "adc{b}\t{$src, %al|%al, $src}", []>; + def ADC16i16 : Ii16<0x15, RawFrm, (outs), (ins i16imm:$src), + "adc{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def ADC32i32 : Ii32<0x15, RawFrm, (outs), (ins i32imm:$src), + "adc{l}\t{$src, %eax|%eax, $src}", []>; +} // Constraints = "" +} // Uses = [EFLAGS] + +// Register-Register Subtraction +def SUB8rr : I<0x28, MRMDestReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "sub{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, + (X86sub_flag 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, EFLAGS, + (X86sub_flag 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, EFLAGS, + (X86sub_flag GR32:$src1, GR32:$src2))]>; + +let isCodeGenOnly = 1 in { +def SUB8rr_REV : I<0x2A, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "sub{b}\t{$src2, $dst|$dst, $src2}", []>; +def SUB16rr_REV : I<0x2B, MRMSrcReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "sub{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; +def SUB32rr_REV : I<0x2B, MRMSrcReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "sub{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +// Register-Memory Subtraction +def SUB8rm : I<0x2A, MRMSrcMem, (outs GR8 :$dst), + (ins GR8 :$src1, i8mem :$src2), + "sub{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, EFLAGS, + (X86sub_flag 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, EFLAGS, + (X86sub_flag 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, EFLAGS, + (X86sub_flag GR32:$src1, (load addr:$src2)))]>; + +// 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, EFLAGS, + (X86sub_flag GR8:$src1, imm:$src2))]>; +def SUB16ri : Ii16<0x81, MRM5r, (outs GR16:$dst), + (ins GR16:$src1, i16imm:$src2), + "sub{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, + (X86sub_flag GR16:$src1, imm:$src2))]>, OpSize; +def SUB32ri : Ii32<0x81, MRM5r, (outs GR32:$dst), + (ins GR32:$src1, i32imm:$src2), + "sub{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, + (X86sub_flag GR32:$src1, imm:$src2))]>; +def SUB16ri8 : Ii8<0x83, MRM5r, (outs GR16:$dst), + (ins GR16:$src1, i16i8imm:$src2), + "sub{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, EFLAGS, + (X86sub_flag GR16:$src1, i16immSExt8:$src2))]>, OpSize; +def SUB32ri8 : Ii8<0x83, MRM5r, (outs GR32:$dst), + (ins GR32:$src1, i32i8imm:$src2), + "sub{l}\t{$src2, $dst|$dst, $src2}", + [(set GR32:$dst, EFLAGS, + (X86sub_flag GR32:$src1, i32immSExt8:$src2))]>; + +let Constraints = "" 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), + (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), + (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), + (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), + (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), + (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), + (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), + (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), + (implicit EFLAGS)]>; + + def SUB8i8 : Ii8<0x2C, RawFrm, (outs), (ins i8imm:$src), + "sub{b}\t{$src, %al|%al, $src}", []>; + def SUB16i16 : Ii16<0x2D, RawFrm, (outs), (ins i16imm:$src), + "sub{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def SUB32i32 : Ii32<0x2D, RawFrm, (outs), (ins i32imm:$src), + "sub{l}\t{$src, %eax|%eax, $src}", []>; +} // Constraints = "" + +let Uses = [EFLAGS] in { +def SBB8rr : I<0x18, MRMDestReg, (outs GR8:$dst), + (ins GR8:$src1, GR8:$src2), + "sbb{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (sube GR8:$src1, GR8:$src2))]>; +def SBB16rr : I<0x19, MRMDestReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (sube GR16:$src1, GR16:$src2))]>, OpSize; +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 Constraints = "" in { + def SBB8mr : I<0x18, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src2), + "sbb{b}\t{$src2, $dst|$dst, $src2}", + [(store (sube (load addr:$dst), GR8:$src2), addr:$dst)]>; + def SBB16mr : I<0x19, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(store (sube (load addr:$dst), GR16:$src2), addr:$dst)]>, + OpSize; + 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 : Ii8<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 SBB16mi : Ii16<0x81, MRM3m, (outs), (ins i16mem:$dst, i16imm:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(store (sube (loadi16 addr:$dst), imm:$src2), addr:$dst)]>, + OpSize; + def SBB16mi8 : Ii8<0x83, MRM3m, (outs), (ins i16mem:$dst, i16i8imm :$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(store (sube (load addr:$dst), i16immSExt8:$src2), addr:$dst)]>, + OpSize; + 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 SBB8i8 : Ii8<0x1C, RawFrm, (outs), (ins i8imm:$src), + "sbb{b}\t{$src, %al|%al, $src}", []>; + def SBB16i16 : Ii16<0x1D, RawFrm, (outs), (ins i16imm:$src), + "sbb{w}\t{$src, %ax|%ax, $src}", []>, OpSize; + def SBB32i32 : Ii32<0x1D, RawFrm, (outs), (ins i32imm:$src), + "sbb{l}\t{$src, %eax|%eax, $src}", []>; +} // Constraints = "" + +let isCodeGenOnly = 1 in { +def SBB8rr_REV : I<0x1A, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2), + "sbb{b}\t{$src2, $dst|$dst, $src2}", []>; +def SBB16rr_REV : I<0x1B, MRMSrcReg, (outs GR16:$dst), + (ins GR16:$src1, GR16:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize; +def SBB32rr_REV : I<0x1B, MRMSrcReg, (outs GR32:$dst), + (ins GR32:$src1, GR32:$src2), + "sbb{l}\t{$src2, $dst|$dst, $src2}", []>; +} + +def SBB8rm : I<0x1A, MRMSrcMem, (outs GR8:$dst), (ins GR8:$src1, i8mem:$src2), + "sbb{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (sube GR8:$src1, (load addr:$src2)))]>; +def SBB16rm : I<0x1B, MRMSrcMem, (outs GR16:$dst), + (ins GR16:$src1, i16mem:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (sube GR16:$src1, (load addr:$src2)))]>, + OpSize; +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 SBB8ri : Ii8<0x80, MRM3r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2), + "sbb{b}\t{$src2, $dst|$dst, $src2}", + [(set GR8:$dst, (sube GR8:$src1, imm:$src2))]>; +def SBB16ri : Ii16<0x81, MRM3r, (outs GR16:$dst), + (ins GR16:$src1, i16imm:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (sube GR16:$src1, imm:$src2))]>, OpSize; +def SBB16ri8 : Ii8<0x83, MRM3r, (outs GR16:$dst), + (ins GR16:$src1, i16i8imm:$src2), + "sbb{w}\t{$src2, $dst|$dst, $src2}", + [(set GR16:$dst, (sube GR16:$src1, i16immSExt8:$src2))]>, + OpSize; +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 +// 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, EFLAGS, + (X86smul_flag 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, EFLAGS, + (X86smul_flag GR32:$src1, GR32:$src2))]>, TB; +} + +// 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, EFLAGS, + (X86smul_flag 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, EFLAGS, + (X86smul_flag GR32:$src1, (load addr:$src2)))]>, 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, EFLAGS, + (X86smul_flag 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, EFLAGS, + (X86smul_flag 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, EFLAGS, + (X86smul_flag 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, EFLAGS, + (X86smul_flag GR32:$src1, i32immSExt8:$src2))]>; + +// 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, EFLAGS, + (X86smul_flag (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, EFLAGS, + (X86smul_flag (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, EFLAGS, + (X86smul_flag (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, EFLAGS, + (X86smul_flag (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, MRMSrcReg, (outs), (ins GR8:$src1, GR8:$src2), + "test{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and_su GR8:$src1, GR8:$src2), 0))]>; +def TEST16rr : I<0x85, MRMSrcReg, (outs), (ins GR16:$src1, GR16:$src2), + "test{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and_su GR16:$src1, GR16:$src2), + 0))]>, + OpSize; +def TEST32rr : I<0x85, MRMSrcReg, (outs), (ins GR32:$src1, GR32:$src2), + "test{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and_su GR32:$src1, GR32:$src2), + 0))]>; +} + +def TEST8i8 : Ii8<0xA8, RawFrm, (outs), (ins i8imm:$src), + "test{b}\t{$src, %al|%al, $src}", []>; +def TEST16i16 : Ii16<0xA9, RawFrm, (outs), (ins i16imm:$src), + "test{w}\t{$src, %ax|%ax, $src}", []>, OpSize; +def TEST32i32 : Ii32<0xA9, RawFrm, (outs), (ins i32imm:$src), + "test{l}\t{$src, %eax|%eax, $src}", []>; + +def TEST8rm : I<0x84, MRMSrcMem, (outs), (ins GR8 :$src1, i8mem :$src2), + "test{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and GR8:$src1, (loadi8 addr:$src2)), + 0))]>; +def TEST16rm : I<0x85, MRMSrcMem, (outs), (ins GR16:$src1, i16mem:$src2), + "test{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and GR16:$src1, + (loadi16 addr:$src2)), 0))]>, OpSize; +def TEST32rm : I<0x85, MRMSrcMem, (outs), (ins GR32:$src1, i32mem:$src2), + "test{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and GR32:$src1, + (loadi32 addr:$src2)), 0))]>; + +def TEST8ri : Ii8 <0xF6, MRM0r, // flags = GR8 & imm8 + (outs), (ins GR8:$src1, i8imm:$src2), + "test{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and_su GR8:$src1, imm:$src2), 0))]>; +def TEST16ri : Ii16<0xF7, MRM0r, // flags = GR16 & imm16 + (outs), (ins GR16:$src1, i16imm:$src2), + "test{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and_su GR16:$src1, imm:$src2), 0))]>, + OpSize; +def TEST32ri : Ii32<0xF7, MRM0r, // flags = GR32 & imm32 + (outs), (ins GR32:$src1, i32imm:$src2), + "test{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and_su GR32:$src1, imm:$src2), 0))]>; + +def TEST8mi : Ii8 <0xF6, MRM0m, // flags = [mem8] & imm8 + (outs), (ins i8mem:$src1, i8imm:$src2), + "test{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and (loadi8 addr:$src1), imm:$src2), + 0))]>; +def TEST16mi : Ii16<0xF7, MRM0m, // flags = [mem16] & imm16 + (outs), (ins i16mem:$src1, i16imm:$src2), + "test{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and (loadi16 addr:$src1), imm:$src2), + 0))]>, OpSize; +def TEST32mi : Ii32<0xF7, MRM0m, // flags = [mem32] & imm32 + (outs), (ins i32mem:$src1, i32imm:$src2), + "test{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (and (loadi32 addr:$src1), imm:$src2), + 0))]>; +} // Defs = [EFLAGS] + + +// Condition code ops, incl. set if equal/not equal/... +let Defs = [EFLAGS], Uses = [AH], neverHasSideEffects = 1 in +def SAHF : I<0x9E, RawFrm, (outs), (ins), "sahf", []>; // flags = AH +let Defs = [AH], Uses = [EFLAGS], neverHasSideEffects = 1 in +def LAHF : I<0x9F, RawFrm, (outs), (ins), "lahf", []>; // AH = flags + +let Uses = [EFLAGS] in { +// Use sbb to materialize carry bit. +let Defs = [EFLAGS], isCodeGenOnly = 1 in { +// FIXME: These are pseudo ops that should be replaced with Pat<> patterns. +// However, Pat<> can't replicate the destination reg into the inputs of the +// result. +// FIXME: Change these to have encoding Pseudo when X86MCCodeEmitter replaces +// X86CodeEmitter. +def SETB_C8r : I<0x18, MRMInitReg, (outs GR8:$dst), (ins), "", + [(set GR8:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>; +def SETB_C16r : I<0x19, MRMInitReg, (outs GR16:$dst), (ins), "", + [(set GR16:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>, + OpSize; +def SETB_C32r : I<0x19, MRMInitReg, (outs GR32:$dst), (ins), "", + [(set GR32:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>; +} // isCodeGenOnly + +def SETEr : I<0x94, MRM0r, + (outs GR8 :$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:$dst)]>, + TB; // [mem8] = not parity + +def SETOr : I<0x90, MRM0r, + (outs GR8 :$dst), (ins), + "seto\t$dst", + [(set GR8:$dst, (X86setcc X86_COND_O, EFLAGS))]>, + TB; // GR8 = overflow +def SETOm : I<0x90, MRM0m, + (outs), (ins i8mem:$dst), + "seto\t$dst", + [(store (X86setcc X86_COND_O, EFLAGS), addr:$dst)]>, + TB; // [mem8] = overflow +def SETNOr : I<0x91, MRM0r, + (outs GR8 :$dst), (ins), + "setno\t$dst", + [(set GR8:$dst, (X86setcc X86_COND_NO, EFLAGS))]>, + TB; // GR8 = not overflow +def SETNOm : I<0x91, MRM0m, + (outs), (ins i8mem:$dst), + "setno\t$dst", + [(store (X86setcc X86_COND_NO, EFLAGS), addr:$dst)]>, + TB; // [mem8] = not overflow +} // Uses = [EFLAGS] + + +// Integer comparisons +let Defs = [EFLAGS] in { +def CMP8i8 : Ii8<0x3C, RawFrm, (outs), (ins i8imm:$src), + "cmp{b}\t{$src, %al|%al, $src}", []>; +def CMP16i16 : Ii16<0x3D, RawFrm, (outs), (ins i16imm:$src), + "cmp{w}\t{$src, %ax|%ax, $src}", []>, OpSize; +def CMP32i32 : Ii32<0x3D, RawFrm, (outs), (ins i32imm:$src), + "cmp{l}\t{$src, %eax|%eax, $src}", []>; + +def CMP8rr : I<0x38, MRMDestReg, + (outs), (ins GR8 :$src1, GR8 :$src2), + "cmp{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR8:$src1, GR8:$src2))]>; +def CMP16rr : I<0x39, MRMDestReg, + (outs), (ins GR16:$src1, GR16:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR16:$src1, GR16:$src2))]>, OpSize; +def CMP32rr : I<0x39, MRMDestReg, + (outs), (ins GR32:$src1, GR32:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR32:$src1, GR32:$src2))]>; +def CMP8mr : I<0x38, MRMDestMem, + (outs), (ins i8mem :$src1, GR8 :$src2), + "cmp{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi8 addr:$src1), GR8:$src2))]>; +def CMP16mr : I<0x39, MRMDestMem, + (outs), (ins i16mem:$src1, GR16:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi16 addr:$src1), GR16:$src2))]>, + OpSize; +def CMP32mr : I<0x39, MRMDestMem, + (outs), (ins i32mem:$src1, GR32:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi32 addr:$src1), GR32:$src2))]>; +def CMP8rm : I<0x3A, MRMSrcMem, + (outs), (ins GR8 :$src1, i8mem :$src2), + "cmp{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR8:$src1, (loadi8 addr:$src2)))]>; +def CMP16rm : I<0x3B, MRMSrcMem, + (outs), (ins GR16:$src1, i16mem:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR16:$src1, (loadi16 addr:$src2)))]>, + OpSize; +def CMP32rm : I<0x3B, MRMSrcMem, + (outs), (ins GR32:$src1, i32mem:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR32:$src1, (loadi32 addr:$src2)))]>; + +// These are alternate spellings for use by the disassembler, we mark them as +// code gen only to ensure they aren't matched by the assembler. +let isCodeGenOnly = 1 in { + def CMP8rr_alt : I<0x3A, MRMSrcReg, (outs), (ins GR8:$src1, GR8:$src2), + "cmp{b}\t{$src2, $src1|$src1, $src2}", []>; + def CMP16rr_alt : I<0x3B, MRMSrcReg, (outs), (ins GR16:$src1, GR16:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize; + def CMP32rr_alt : I<0x3B, MRMSrcReg, (outs), (ins GR32:$src1, GR32:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", []>; +} + +def CMP8ri : Ii8<0x80, MRM7r, + (outs), (ins GR8:$src1, i8imm:$src2), + "cmp{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR8:$src1, imm:$src2))]>; +def CMP16ri : Ii16<0x81, MRM7r, + (outs), (ins GR16:$src1, i16imm:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR16:$src1, imm:$src2))]>, OpSize; +def CMP32ri : Ii32<0x81, MRM7r, + (outs), (ins GR32:$src1, i32imm:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR32:$src1, imm:$src2))]>; +def CMP8mi : Ii8 <0x80, MRM7m, + (outs), (ins i8mem :$src1, i8imm :$src2), + "cmp{b}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi8 addr:$src1), imm:$src2))]>; +def CMP16mi : Ii16<0x81, MRM7m, + (outs), (ins i16mem:$src1, i16imm:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi16 addr:$src1), imm:$src2))]>, + OpSize; +def CMP32mi : Ii32<0x81, MRM7m, + (outs), (ins i32mem:$src1, i32imm:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi32 addr:$src1), imm:$src2))]>; +def CMP16ri8 : Ii8<0x83, MRM7r, + (outs), (ins GR16:$src1, i16i8imm:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR16:$src1, i16immSExt8:$src2))]>, + OpSize; +def CMP16mi8 : Ii8<0x83, MRM7m, + (outs), (ins i16mem:$src1, i16i8imm:$src2), + "cmp{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi16 addr:$src1), + i16immSExt8:$src2))]>, OpSize; +def CMP32mi8 : Ii8<0x83, MRM7m, + (outs), (ins i32mem:$src1, i32i8imm:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp (loadi32 addr:$src1), + i32immSExt8:$src2))]>; +def CMP32ri8 : Ii8<0x83, MRM7r, + (outs), (ins GR32:$src1, i32i8imm:$src2), + "cmp{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86cmp GR32:$src1, i32immSExt8:$src2))]>; +} // Defs = [EFLAGS] + +// Bit tests. +// TODO: BTC, BTR, and BTS +let Defs = [EFLAGS] in { +def BT16rr : I<0xA3, MRMDestReg, (outs), (ins GR16:$src1, GR16:$src2), + "bt{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86bt GR16:$src1, GR16:$src2))]>, OpSize, TB; +def BT32rr : I<0xA3, MRMDestReg, (outs), (ins GR32:$src1, GR32:$src2), + "bt{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86bt GR32:$src1, GR32:$src2))]>, TB; + +// Unlike with the register+register form, the memory+register form of the +// bt instruction does not ignore the high bits of the index. From ISel's +// perspective, this is pretty bizarre. Make these instructions disassembly +// only for now. + +def BT16mr : I<0xA3, MRMDestMem, (outs), (ins i16mem:$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, $src2}", + [(set EFLAGS, (X86bt GR16:$src1, i16immSExt8:$src2))]>, + OpSize, TB; +def BT32ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR32:$src1, i32i8imm:$src2), + "bt{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86bt GR32:$src1, i32immSExt8:$src2))]>, TB; +// Note that these instructions don't need FastBTMem because that +// only applies when the other operand is in a register. When it's +// an immediate, bt is still fast. +def BT16mi8 : Ii8<0xBA, MRM4m, (outs), (ins i16mem:$src1, i16i8imm:$src2), + "bt{w}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86bt (loadi16 addr:$src1), i16immSExt8:$src2)) + ]>, OpSize, TB; +def BT32mi8 : Ii8<0xBA, MRM4m, (outs), (ins i32mem:$src1, i32i8imm:$src2), + "bt{l}\t{$src2, $src1|$src1, $src2}", + [(set EFLAGS, (X86bt (loadi32 addr:$src1), i32immSExt8:$src2)) + ]>, TB; + +def BTC16rr : I<0xBB, MRMDestReg, (outs), (ins GR16:$src1, GR16:$src2), + "btc{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTC32rr : I<0xBB, MRMDestReg, (outs), (ins GR32:$src1, GR32:$src2), + "btc{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTC16mr : I<0xBB, MRMDestMem, (outs), (ins i16mem:$src1, GR16:$src2), + "btc{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTC32mr : I<0xBB, MRMDestMem, (outs), (ins i32mem:$src1, GR32:$src2), + "btc{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTC16ri8 : Ii8<0xBA, MRM7r, (outs), (ins GR16:$src1, i16i8imm:$src2), + "btc{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTC32ri8 : Ii8<0xBA, MRM7r, (outs), (ins GR32:$src1, i32i8imm:$src2), + "btc{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTC16mi8 : Ii8<0xBA, MRM7m, (outs), (ins i16mem:$src1, i16i8imm:$src2), + "btc{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTC32mi8 : Ii8<0xBA, MRM7m, (outs), (ins i32mem:$src1, i32i8imm:$src2), + "btc{l}\t{$src2, $src1|$src1, $src2}", []>, TB; + +def BTR16rr : I<0xB3, MRMDestReg, (outs), (ins GR16:$src1, GR16:$src2), + "btr{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTR32rr : I<0xB3, MRMDestReg, (outs), (ins GR32:$src1, GR32:$src2), + "btr{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTR16mr : I<0xB3, MRMDestMem, (outs), (ins i16mem:$src1, GR16:$src2), + "btr{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTR32mr : I<0xB3, MRMDestMem, (outs), (ins i32mem:$src1, GR32:$src2), + "btr{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTR16ri8 : Ii8<0xBA, MRM6r, (outs), (ins GR16:$src1, i16i8imm:$src2), + "btr{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTR32ri8 : Ii8<0xBA, MRM6r, (outs), (ins GR32:$src1, i32i8imm:$src2), + "btr{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTR16mi8 : Ii8<0xBA, MRM6m, (outs), (ins i16mem:$src1, i16i8imm:$src2), + "btr{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTR32mi8 : Ii8<0xBA, MRM6m, (outs), (ins i32mem:$src1, i32i8imm:$src2), + "btr{l}\t{$src2, $src1|$src1, $src2}", []>, TB; + +def BTS16rr : I<0xAB, MRMDestReg, (outs), (ins GR16:$src1, GR16:$src2), + "bts{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTS32rr : I<0xAB, MRMDestReg, (outs), (ins GR32:$src1, GR32:$src2), + "bts{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTS16mr : I<0xAB, MRMDestMem, (outs), (ins i16mem:$src1, GR16:$src2), + "bts{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTS32mr : I<0xAB, MRMDestMem, (outs), (ins i32mem:$src1, GR32:$src2), + "bts{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTS16ri8 : Ii8<0xBA, MRM5r, (outs), (ins GR16:$src1, i16i8imm:$src2), + "bts{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTS32ri8 : Ii8<0xBA, MRM5r, (outs), (ins GR32:$src1, i32i8imm:$src2), + "bts{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +def BTS16mi8 : Ii8<0xBA, MRM5m, (outs), (ins i16mem:$src1, i16i8imm:$src2), + "bts{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize, TB; +def BTS32mi8 : Ii8<0xBA, MRM5m, (outs), (ins i32mem:$src1, i32i8imm:$src2), + "bts{l}\t{$src2, $src1|$src1, $src2}", []>, TB; +} // Defs = [EFLAGS] + +// Sign/Zero extenders +// Use movsbl intead of movsbw; we don't care about the high 16 bits +// of the register here. This has a smaller encoding and avoids a +// partial-register update. Actual movsbw included for the disassembler. +def MOVSX16rr8W : I<0xBE, MRMSrcReg, (outs GR16:$dst), (ins GR8:$src), + "movs{bw|x}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def MOVSX16rm8W : I<0xBE, MRMSrcMem, (outs GR16:$dst), (ins i8mem:$src), + "movs{bw|x}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def MOVSX16rr8 : I<0xBE, MRMSrcReg, (outs GR16:$dst), (ins GR8 :$src), + "", [(set GR16:$dst, (sext GR8:$src))]>, TB; +def MOVSX16rm8 : I<0xBE, MRMSrcMem, (outs GR16:$dst), (ins i8mem :$src), + "", [(set GR16:$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:$src))]>, TB; + +// Use movzbl intead of movzbw; we don't care about the high 16 bits +// of the register here. This has a smaller encoding and avoids a +// partial-register update. Actual movzbw included for the disassembler. +def MOVZX16rr8W : I<0xB6, MRMSrcReg, (outs GR16:$dst), (ins GR8:$src), + "movz{bw|x}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def MOVZX16rm8W : I<0xB6, MRMSrcMem, (outs GR16:$dst), (ins i8mem:$src), + "movz{bw|x}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def MOVZX16rr8 : I<0xB6, MRMSrcReg, (outs GR16:$dst), (ins GR8 :$src), + "", [(set GR16:$dst, (zext GR8:$src))]>, TB; +def MOVZX16rm8 : I<0xB6, MRMSrcMem, (outs GR16:$dst), (ins i8mem :$src), + "", [(set GR16:$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:$src))]>, TB; + +// These are the same as the regular MOVZX32rr8 and MOVZX32rm8 +// except that they use GR32_NOREX for the output operand register class +// instead of GR32. This allows them to operate on h registers on x86-64. +def MOVZX32_NOREXrr8 : I<0xB6, MRMSrcReg, + (outs GR32_NOREX:$dst), (ins GR8:$src), + "movz{bl|x}\t{$src, $dst|$dst, $src} # NOREX", + []>, TB; +let mayLoad = 1 in +def MOVZX32_NOREXrm8 : I<0xB6, MRMSrcMem, + (outs GR32_NOREX:$dst), (ins i8mem:$src), + "movz{bl|x}\t{$src, $dst|$dst, $src} # NOREX", + []>, TB; + +let neverHasSideEffects = 1 in { + let Defs = [AX], Uses = [AL] in + def CBW : I<0x98, RawFrm, (outs), (ins), + "{cbtw|cbw}", []>, OpSize; // AX = signext(AL) + let Defs = [EAX], Uses = [AX] in + def CWDE : I<0x98, RawFrm, (outs), (ins), + "{cwtl|cwde}", []>; // EAX = signext(AX) + + let Defs = [AX,DX], Uses = [AX] in + def CWD : I<0x99, RawFrm, (outs), (ins), + "{cwtd|cwd}", []>, OpSize; // DX:AX = signext(AX) + let Defs = [EAX,EDX], Uses = [EAX] in + def CDQ : I<0x99, RawFrm, (outs), (ins), + "{cltd|cdq}", []>; // EDX:EAX = signext(EAX) +} + +//===----------------------------------------------------------------------===// +// Alias Instructions +//===----------------------------------------------------------------------===// + +// Alias instructions that map movr0 to xor. +// FIXME: remove when we can teach regalloc that xor reg, reg is ok. +// FIXME: Set encoding to pseudo. +let Defs = [EFLAGS], isReMaterializable = 1, isAsCheapAsAMove = 1, + isCodeGenOnly = 1 in { +def MOV8r0 : I<0x30, MRMInitReg, (outs GR8 :$dst), (ins), "", + [(set GR8:$dst, 0)]>; + +// We want to rewrite MOV16r0 in terms of MOV32r0, because it's a smaller +// encoding and avoids a partial-register update sometimes, but doing so +// at isel time interferes with rematerialization in the current register +// allocator. For now, this is rewritten when the instruction is lowered +// to an MCInst. +def MOV16r0 : I<0x31, MRMInitReg, (outs GR16:$dst), (ins), + "", + [(set GR16:$dst, 0)]>, OpSize; + +// FIXME: Set encoding to pseudo. +def MOV32r0 : I<0x31, MRMInitReg, (outs GR32:$dst), (ins), "", + [(set GR32:$dst, 0)]>; +} + +//===----------------------------------------------------------------------===// +// Thread Local Storage Instructions +// + +// ELF TLS Support +// All calls clobber the non-callee saved registers. ESP is marked as +// a use to prevent stack-pointer assignments that appear immediately +// before calls from potentially appearing dead. +let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, + MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7, + XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, + XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS], + Uses = [ESP] in +def TLS_addr32 : I<0, Pseudo, (outs), (ins i32mem:$sym), + "leal\t$sym, %eax; " + "call\t___tls_get_addr@PLT", + [(X86tlsaddr tls32addr:$sym)]>, + Requires<[In32BitMode]>; + +// Darwin TLS Support +// For i386, the address of the thunk is passed on the stack, on return the +// address of the variable is in %eax. %ecx is trashed during the function +// call. All other registers are preserved. +let Defs = [EAX, ECX], + Uses = [ESP], + usesCustomInserter = 1 in +def TLSCall_32 : I<0, Pseudo, (outs), (ins i32mem:$sym), + "# TLSCall_32", + [(X86TLSCall addr:$sym)]>, + Requires<[In32BitMode]>; + +let AddedComplexity = 5, isCodeGenOnly = 1 in +def GS_MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "movl\t%gs:$src, $dst", + [(set GR32:$dst, (gsload addr:$src))]>, SegGS; + +let AddedComplexity = 5, isCodeGenOnly = 1 in +def FS_MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "movl\t%fs:$src, $dst", + [(set GR32:$dst, (fsload addr:$src))]>, SegFS; + +//===----------------------------------------------------------------------===// +// EH Pseudo Instructions +// +let isTerminator = 1, isReturn = 1, isBarrier = 1, + hasCtrlDep = 1, isCodeGenOnly = 1 in { +def EH_RETURN : I<0xC3, RawFrm, (outs), (ins GR32:$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 GR32:$val, i32mem:$ptr), + "xchg{l}\t{$val, $ptr|$ptr, $val}", + [(set GR32:$dst, (atomic_swap_32 addr:$ptr, GR32:$val))]>; +def XCHG16rm : I<0x87, MRMSrcMem, (outs GR16:$dst), + (ins GR16:$val, i16mem:$ptr), + "xchg{w}\t{$val, $ptr|$ptr, $val}", + [(set GR16:$dst, (atomic_swap_16 addr:$ptr, GR16:$val))]>, + OpSize; +def XCHG8rm : I<0x86, MRMSrcMem, (outs GR8:$dst), (ins GR8:$val, i8mem:$ptr), + "xchg{b}\t{$val, $ptr|$ptr, $val}", + [(set GR8:$dst, (atomic_swap_8 addr:$ptr, GR8:$val))]>; + +def XCHG32rr : I<0x87, MRMSrcReg, (outs GR32:$dst), (ins GR32:$val, GR32:$src), + "xchg{l}\t{$val, $src|$src, $val}", []>; +def XCHG16rr : I<0x87, MRMSrcReg, (outs GR16:$dst), (ins GR16:$val, GR16:$src), + "xchg{w}\t{$val, $src|$src, $val}", []>, OpSize; +def XCHG8rr : I<0x86, MRMSrcReg, (outs GR8:$dst), (ins GR8:$val, GR8:$src), + "xchg{b}\t{$val, $src|$src, $val}", []>; +} + +def XCHG16ar : I<0x90, AddRegFrm, (outs), (ins GR16:$src), + "xchg{w}\t{$src, %ax|%ax, $src}", []>, OpSize; +def XCHG32ar : I<0x90, AddRegFrm, (outs), (ins GR32:$src), + "xchg{l}\t{$src, %eax|%eax, $src}", []>; + +// Atomic compare and swap. +let Defs = [EAX, EFLAGS], Uses = [EAX] in { +def LCMPXCHG32 : I<0xB1, MRMDestMem, (outs), (ins i32mem:$ptr, GR32:$swap), + "lock\n\t" + "cmpxchg{l}\t{$swap, $ptr|$ptr, $swap}", + [(X86cas addr:$ptr, GR32:$swap, 4)]>, TB, LOCK; +} +let Defs = [EAX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX] in { +def LCMPXCHG8B : I<0xC7, MRM1m, (outs), (ins i64mem:$ptr), + "lock\n\t" + "cmpxchg8b\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\t" + "cmpxchg{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:$swap), + "lock\n\t" + "cmpxchg{b}\t{$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 GR32:$val, i32mem:$ptr), + "lock\n\t" + "xadd{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:$dst), (ins GR16:$val, i16mem:$ptr), + "lock\n\t" + "xadd{w}\t{$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:$dst), (ins GR8:$val, i8mem:$ptr), + "lock\n\t" + "xadd{b}\t{$val, $ptr|$ptr, $val}", + [(set GR8:$dst, (atomic_load_add_8 addr:$ptr, GR8:$val))]>, + TB, LOCK; +} + +def XADD8rr : I<0xC0, MRMDestReg, (outs GR8:$dst), (ins GR8:$src), + "xadd{b}\t{$src, $dst|$dst, $src}", []>, TB; +def XADD16rr : I<0xC1, MRMDestReg, (outs GR16:$dst), (ins GR16:$src), + "xadd{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def XADD32rr : I<0xC1, MRMDestReg, (outs GR32:$dst), (ins GR32:$src), + "xadd{l}\t{$src, $dst|$dst, $src}", []>, TB; + +let mayLoad = 1, mayStore = 1 in { +def XADD8rm : I<0xC0, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src), + "xadd{b}\t{$src, $dst|$dst, $src}", []>, TB; +def XADD16rm : I<0xC1, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src), + "xadd{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def XADD32rm : I<0xC1, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src), + "xadd{l}\t{$src, $dst|$dst, $src}", []>, TB; +} + +def CMPXCHG8rr : I<0xB0, MRMDestReg, (outs GR8:$dst), (ins GR8:$src), + "cmpxchg{b}\t{$src, $dst|$dst, $src}", []>, TB; +def CMPXCHG16rr : I<0xB1, MRMDestReg, (outs GR16:$dst), (ins GR16:$src), + "cmpxchg{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def CMPXCHG32rr : I<0xB1, MRMDestReg, (outs GR32:$dst), (ins GR32:$src), + "cmpxchg{l}\t{$src, $dst|$dst, $src}", []>, TB; + +let mayLoad = 1, mayStore = 1 in { +def CMPXCHG8rm : I<0xB0, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src), + "cmpxchg{b}\t{$src, $dst|$dst, $src}", []>, TB; +def CMPXCHG16rm : I<0xB1, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src), + "cmpxchg{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def CMPXCHG32rm : I<0xB1, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src), + "cmpxchg{l}\t{$src, $dst|$dst, $src}", []>, TB; +} + +let Defs = [EAX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX] in +def CMPXCHG8B : I<0xC7, MRM1m, (outs), (ins i64mem:$dst), + "cmpxchg8b\t$dst", []>, TB; + +// Optimized codegen when the non-memory output is not used. +// FIXME: Use normal add / sub instructions and add lock prefix dynamically. +let Defs = [EFLAGS], mayLoad = 1, mayStore = 1 in { +def LOCK_ADD8mr : I<0x00, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src2), + "lock\n\t" + "add{b}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_ADD16mr : I<0x01, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), + "lock\n\t" + "add{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize, LOCK; +def LOCK_ADD32mr : I<0x01, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2), + "lock\n\t" + "add{l}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_ADD8mi : Ii8<0x80, MRM0m, (outs), (ins i8mem :$dst, i8imm :$src2), + "lock\n\t" + "add{b}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_ADD16mi : Ii16<0x81, MRM0m, (outs), (ins i16mem:$dst, i16imm:$src2), + "lock\n\t" + "add{w}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_ADD32mi : Ii32<0x81, MRM0m, (outs), (ins i32mem:$dst, i32imm:$src2), + "lock\n\t" + "add{l}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_ADD16mi8 : Ii8<0x83, MRM0m, (outs), (ins i16mem:$dst, i16i8imm :$src2), + "lock\n\t" + "add{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize, LOCK; +def LOCK_ADD32mi8 : Ii8<0x83, MRM0m, (outs), (ins i32mem:$dst, i32i8imm :$src2), + "lock\n\t" + "add{l}\t{$src2, $dst|$dst, $src2}", []>, LOCK; + +def LOCK_INC8m : I<0xFE, MRM0m, (outs), (ins i8mem :$dst), + "lock\n\t" + "inc{b}\t$dst", []>, LOCK; +def LOCK_INC16m : I<0xFF, MRM0m, (outs), (ins i16mem:$dst), + "lock\n\t" + "inc{w}\t$dst", []>, OpSize, LOCK; +def LOCK_INC32m : I<0xFF, MRM0m, (outs), (ins i32mem:$dst), + "lock\n\t" + "inc{l}\t$dst", []>, LOCK; + +def LOCK_SUB8mr : I<0x28, MRMDestMem, (outs), (ins i8mem :$dst, GR8 :$src2), + "lock\n\t" + "sub{b}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_SUB16mr : I<0x29, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), + "lock\n\t" + "sub{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize, LOCK; +def LOCK_SUB32mr : I<0x29, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2), + "lock\n\t" + "sub{l}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_SUB8mi : Ii8<0x80, MRM5m, (outs), (ins i8mem :$dst, i8imm:$src2), + "lock\n\t" + "sub{b}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_SUB16mi : Ii16<0x81, MRM5m, (outs), (ins i16mem:$dst, i16imm:$src2), + "lock\n\t" + "sub{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize, LOCK; +def LOCK_SUB32mi : Ii32<0x81, MRM5m, (outs), (ins i32mem:$dst, i32imm:$src2), + "lock\n\t" + "sub{l}\t{$src2, $dst|$dst, $src2}", []>, LOCK; +def LOCK_SUB16mi8 : Ii8<0x83, MRM5m, (outs), (ins i16mem:$dst, i16i8imm :$src2), + "lock\n\t" + "sub{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize, LOCK; +def LOCK_SUB32mi8 : Ii8<0x83, MRM5m, (outs), (ins i32mem:$dst, i32i8imm :$src2), + "lock\n\t" + "sub{l}\t{$src2, $dst|$dst, $src2}", []>, LOCK; + +def LOCK_DEC8m : I<0xFE, MRM1m, (outs), (ins i8mem :$dst), + "lock\n\t" + "dec{b}\t$dst", []>, LOCK; +def LOCK_DEC16m : I<0xFF, MRM1m, (outs), (ins i16mem:$dst), + "lock\n\t" + "dec{w}\t$dst", []>, OpSize, LOCK; +def LOCK_DEC32m : I<0xFF, MRM1m, (outs), (ins i32mem:$dst), + "lock\n\t" + "dec{l}\t$dst", []>, LOCK; +} + +// Atomic exchange, and, or, xor +let Constraints = "$val = $dst", Defs = [EFLAGS], + usesCustomInserter = 1 in { +def ATOMAND32 : I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val), + "#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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 PSEUDO!", + [(set GR8:$dst, (atomic_load_nand_8 addr:$ptr, GR8:$val))]>; +} + +let Constraints = "$val1 = $dst1, $val2 = $dst2", + Defs = [EFLAGS, EAX, EBX, ECX, EDX], + Uses = [EAX, EBX, ECX, EDX], + mayLoad = 1, mayStore = 1, + usesCustomInserter = 1 in { +def ATOMAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMAND6432 PSEUDO!", []>; +def ATOMOR6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMOR6432 PSEUDO!", []>; +def ATOMXOR6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMXOR6432 PSEUDO!", []>; +def ATOMNAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMNAND6432 PSEUDO!", []>; +def ATOMADD6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMADD6432 PSEUDO!", []>; +def ATOMSUB6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMSUB6432 PSEUDO!", []>; +def ATOMSWAP6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMSWAP6432 PSEUDO!", []>; +} + +// Segmentation support instructions. + +def LAR16rm : I<0x02, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src), + "lar{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def LAR16rr : I<0x02, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src), + "lar{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; + +// i16mem operand in LAR32rm and GR32 operand in LAR32rr is not a typo. +def LAR32rm : I<0x02, MRMSrcMem, (outs GR32:$dst), (ins i16mem:$src), + "lar{l}\t{$src, $dst|$dst, $src}", []>, TB; +def LAR32rr : I<0x02, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "lar{l}\t{$src, $dst|$dst, $src}", []>, TB; + +def LSL16rm : I<0x03, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$src), + "lsl{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def LSL16rr : I<0x03, MRMSrcReg, (outs GR16:$dst), (ins GR16:$src), + "lsl{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def LSL32rm : I<0x03, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "lsl{l}\t{$src, $dst|$dst, $src}", []>, TB; +def LSL32rr : I<0x03, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "lsl{l}\t{$src, $dst|$dst, $src}", []>, TB; + +def INVLPG : I<0x01, MRM7m, (outs), (ins i8mem:$addr), "invlpg\t$addr", []>, TB; + +def STRr : I<0x00, MRM1r, (outs GR16:$dst), (ins), + "str{w}\t{$dst}", []>, TB; +def STRm : I<0x00, MRM1m, (outs i16mem:$dst), (ins), + "str{w}\t{$dst}", []>, TB; +def LTRr : I<0x00, MRM3r, (outs), (ins GR16:$src), + "ltr{w}\t{$src}", []>, TB; +def LTRm : I<0x00, MRM3m, (outs), (ins i16mem:$src), + "ltr{w}\t{$src}", []>, TB; + +def PUSHFS16 : I<0xa0, RawFrm, (outs), (ins), + "push{w}\t%fs", []>, OpSize, TB; +def PUSHFS32 : I<0xa0, RawFrm, (outs), (ins), + "push{l}\t%fs", []>, TB; +def PUSHGS16 : I<0xa8, RawFrm, (outs), (ins), + "push{w}\t%gs", []>, OpSize, TB; +def PUSHGS32 : I<0xa8, RawFrm, (outs), (ins), + "push{l}\t%gs", []>, TB; + +def POPFS16 : I<0xa1, RawFrm, (outs), (ins), + "pop{w}\t%fs", []>, OpSize, TB; +def POPFS32 : I<0xa1, RawFrm, (outs), (ins), + "pop{l}\t%fs", []>, TB; +def POPGS16 : I<0xa9, RawFrm, (outs), (ins), + "pop{w}\t%gs", []>, OpSize, TB; +def POPGS32 : I<0xa9, RawFrm, (outs), (ins), + "pop{l}\t%gs", []>, TB; + +def LDS16rm : I<0xc5, MRMSrcMem, (outs GR16:$dst), (ins opaque32mem:$src), + "lds{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def LDS32rm : I<0xc5, MRMSrcMem, (outs GR32:$dst), (ins opaque48mem:$src), + "lds{l}\t{$src, $dst|$dst, $src}", []>; +def LSS16rm : I<0xb2, MRMSrcMem, (outs GR16:$dst), (ins opaque32mem:$src), + "lss{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def LSS32rm : I<0xb2, MRMSrcMem, (outs GR32:$dst), (ins opaque48mem:$src), + "lss{l}\t{$src, $dst|$dst, $src}", []>, TB; +def LES16rm : I<0xc4, MRMSrcMem, (outs GR16:$dst), (ins opaque32mem:$src), + "les{w}\t{$src, $dst|$dst, $src}", []>, OpSize; +def LES32rm : I<0xc4, MRMSrcMem, (outs GR32:$dst), (ins opaque48mem:$src), + "les{l}\t{$src, $dst|$dst, $src}", []>; +def LFS16rm : I<0xb4, MRMSrcMem, (outs GR16:$dst), (ins opaque32mem:$src), + "lfs{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def LFS32rm : I<0xb4, MRMSrcMem, (outs GR32:$dst), (ins opaque48mem:$src), + "lfs{l}\t{$src, $dst|$dst, $src}", []>, TB; +def LGS16rm : I<0xb5, MRMSrcMem, (outs GR16:$dst), (ins opaque32mem:$src), + "lgs{w}\t{$src, $dst|$dst, $src}", []>, TB, OpSize; +def LGS32rm : I<0xb5, MRMSrcMem, (outs GR32:$dst), (ins opaque48mem:$src), + "lgs{l}\t{$src, $dst|$dst, $src}", []>, TB; + +def VERRr : I<0x00, MRM4r, (outs), (ins GR16:$seg), + "verr\t$seg", []>, TB; +def VERRm : I<0x00, MRM4m, (outs), (ins i16mem:$seg), + "verr\t$seg", []>, TB; +def VERWr : I<0x00, MRM5r, (outs), (ins GR16:$seg), + "verw\t$seg", []>, TB; +def VERWm : I<0x00, MRM5m, (outs), (ins i16mem:$seg), + "verw\t$seg", []>, TB; + +// Descriptor-table support instructions + +def SGDTm : I<0x01, MRM0m, (outs opaque48mem:$dst), (ins), + "sgdt\t$dst", []>, TB; +def SIDTm : I<0x01, MRM1m, (outs opaque48mem:$dst), (ins), + "sidt\t$dst", []>, TB; +def SLDT16r : I<0x00, MRM0r, (outs GR16:$dst), (ins), + "sldt{w}\t$dst", []>, TB; +def SLDT16m : I<0x00, MRM0m, (outs i16mem:$dst), (ins), + "sldt{w}\t$dst", []>, TB; +def LGDTm : I<0x01, MRM2m, (outs), (ins opaque48mem:$src), + "lgdt\t$src", []>, TB; +def LIDTm : I<0x01, MRM3m, (outs), (ins opaque48mem:$src), + "lidt\t$src", []>, TB; +def LLDT16r : I<0x00, MRM2r, (outs), (ins GR16:$src), + "lldt{w}\t$src", []>, TB; +def LLDT16m : I<0x00, MRM2m, (outs), (ins i16mem:$src), + "lldt{w}\t$src", []>, TB; + +// Lock instruction prefix +def LOCK_PREFIX : I<0xF0, RawFrm, (outs), (ins), "lock", []>; + +// Repeat string operation instruction prefixes +// These uses the DF flag in the EFLAGS register to inc or dec ECX +let Defs = [ECX], Uses = [ECX,EFLAGS] in { +// Repeat (used with INS, OUTS, MOVS, LODS and STOS) +def REP_PREFIX : I<0xF3, RawFrm, (outs), (ins), "rep", []>; +// Repeat while not equal (used with CMPS and SCAS) +def REPNE_PREFIX : I<0xF2, RawFrm, (outs), (ins), "repne", []>; +} + +// Segment override instruction prefixes +def CS_PREFIX : I<0x2E, RawFrm, (outs), (ins), "cs", []>; +def SS_PREFIX : I<0x36, RawFrm, (outs), (ins), "ss", []>; +def DS_PREFIX : I<0x3E, RawFrm, (outs), (ins), "ds", []>; +def ES_PREFIX : I<0x26, RawFrm, (outs), (ins), "es", []>; +def FS_PREFIX : I<0x64, RawFrm, (outs), (ins), "fs", []>; +def GS_PREFIX : I<0x65, RawFrm, (outs), (ins), "gs", []>; + +// String manipulation instructions + +def LODSB : I<0xAC, RawFrm, (outs), (ins), "lodsb", []>; +def LODSW : I<0xAD, RawFrm, (outs), (ins), "lodsw", []>, OpSize; +def LODSD : I<0xAD, RawFrm, (outs), (ins), "lods{l|d}", []>; + +def OUTSB : I<0x6E, RawFrm, (outs), (ins), "outsb", []>; +def OUTSW : I<0x6F, RawFrm, (outs), (ins), "outsw", []>, OpSize; +def OUTSD : I<0x6F, RawFrm, (outs), (ins), "outs{l|d}", []>; + +// CPU flow control instructions + +def HLT : I<0xF4, RawFrm, (outs), (ins), "hlt", []>; +def RSM : I<0xAA, RawFrm, (outs), (ins), "rsm", []>, TB; + +// FPU control instructions + +def FNINIT : I<0xE3, RawFrm, (outs), (ins), "fninit", []>, DB; + +// Flag instructions + +def CLC : I<0xF8, RawFrm, (outs), (ins), "clc", []>; +def STC : I<0xF9, RawFrm, (outs), (ins), "stc", []>; +def CLI : I<0xFA, RawFrm, (outs), (ins), "cli", []>; +def STI : I<0xFB, RawFrm, (outs), (ins), "sti", []>; +def CLD : I<0xFC, RawFrm, (outs), (ins), "cld", []>; +def STD : I<0xFD, RawFrm, (outs), (ins), "std", []>; +def CMC : I<0xF5, RawFrm, (outs), (ins), "cmc", []>; + +def CLTS : I<0x06, RawFrm, (outs), (ins), "clts", []>, TB; + +// Table lookup instructions + +def XLAT : I<0xD7, RawFrm, (outs), (ins), "xlatb", []>; + +// Specialized register support + +def WRMSR : I<0x30, RawFrm, (outs), (ins), "wrmsr", []>, TB; +def RDMSR : I<0x32, RawFrm, (outs), (ins), "rdmsr", []>, TB; +def RDPMC : I<0x33, RawFrm, (outs), (ins), "rdpmc", []>, TB; + +def SMSW16r : I<0x01, MRM4r, (outs GR16:$dst), (ins), + "smsw{w}\t$dst", []>, OpSize, TB; +def SMSW32r : I<0x01, MRM4r, (outs GR32:$dst), (ins), + "smsw{l}\t$dst", []>, TB; +// For memory operands, there is only a 16-bit form +def SMSW16m : I<0x01, MRM4m, (outs i16mem:$dst), (ins), + "smsw{w}\t$dst", []>, TB; + +def LMSW16r : I<0x01, MRM6r, (outs), (ins GR16:$src), + "lmsw{w}\t$src", []>, TB; +def LMSW16m : I<0x01, MRM6m, (outs), (ins i16mem:$src), + "lmsw{w}\t$src", []>, TB; + +def CPUID : I<0xA2, RawFrm, (outs), (ins), "cpuid", []>, TB; + +// Cache instructions + +def INVD : I<0x08, RawFrm, (outs), (ins), "invd", []>, TB; +def WBINVD : I<0x09, RawFrm, (outs), (ins), "wbinvd", []>, TB; + +// VMX instructions + +// 66 0F 38 80 +def INVEPT : I<0x80, RawFrm, (outs), (ins), "invept", []>, OpSize, T8; +// 66 0F 38 81 +def INVVPID : I<0x81, RawFrm, (outs), (ins), "invvpid", []>, OpSize, T8; +// 0F 01 C1 +def VMCALL : I<0x01, MRM_C1, (outs), (ins), "vmcall", []>, TB; +def VMCLEARm : I<0xC7, MRM6m, (outs), (ins i64mem:$vmcs), + "vmclear\t$vmcs", []>, OpSize, TB; +// 0F 01 C2 +def VMLAUNCH : I<0x01, MRM_C2, (outs), (ins), "vmlaunch", []>, TB; +// 0F 01 C3 +def VMRESUME : I<0x01, MRM_C3, (outs), (ins), "vmresume", []>, TB; +def VMPTRLDm : I<0xC7, MRM6m, (outs), (ins i64mem:$vmcs), + "vmptrld\t$vmcs", []>, TB; +def VMPTRSTm : I<0xC7, MRM7m, (outs i64mem:$vmcs), (ins), + "vmptrst\t$vmcs", []>, TB; +def VMREAD64rm : I<0x78, MRMDestMem, (outs i64mem:$dst), (ins GR64:$src), + "vmread{q}\t{$src, $dst|$dst, $src}", []>, TB; +def VMREAD64rr : I<0x78, MRMDestReg, (outs GR64:$dst), (ins GR64:$src), + "vmread{q}\t{$src, $dst|$dst, $src}", []>, TB; +def VMREAD32rm : I<0x78, MRMDestMem, (outs i32mem:$dst), (ins GR32:$src), + "vmread{l}\t{$src, $dst|$dst, $src}", []>, TB; +def VMREAD32rr : I<0x78, MRMDestReg, (outs GR32:$dst), (ins GR32:$src), + "vmread{l}\t{$src, $dst|$dst, $src}", []>, TB; +def VMWRITE64rm : I<0x79, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src), + "vmwrite{q}\t{$src, $dst|$dst, $src}", []>, TB; +def VMWRITE64rr : I<0x79, MRMSrcReg, (outs GR64:$dst), (ins GR64:$src), + "vmwrite{q}\t{$src, $dst|$dst, $src}", []>, TB; +def VMWRITE32rm : I<0x79, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src), + "vmwrite{l}\t{$src, $dst|$dst, $src}", []>, TB; +def VMWRITE32rr : I<0x79, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src), + "vmwrite{l}\t{$src, $dst|$dst, $src}", []>, TB; +// 0F 01 C4 +def VMXOFF : I<0x01, MRM_C4, (outs), (ins), "vmxoff", []>, TB; +def VMXON : I<0xC7, MRM6m, (outs), (ins i64mem:$vmxon), + "vmxon\t{$vmxon}", []>, XS; + +//===----------------------------------------------------------------------===// +// Non-Instruction Patterns +//===----------------------------------------------------------------------===// + +// ConstantPool GlobalAddress, ExternalSymbol, and JumpTable +def : Pat<(i32 (X86Wrapper tconstpool :$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:$dst)>; +def : Pat<(i32 (X86Wrapper tblockaddress:$dst)), (MOV32ri tblockaddress:$dst)>; + +def : Pat<(add GR32:$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:$src2)>; +def : Pat<(add GR32:$src1, (X86Wrapper tblockaddress:$src2)), + (ADD32ri GR32:$src1, tblockaddress:$src2)>; + +def : Pat<(store (i32 (X86Wrapper tglobaladdr:$src)), addr:$dst), + (MOV32mi addr:$dst, tglobaladdr:$src)>; +def : Pat<(store (i32 (X86Wrapper texternalsym:$src)), addr:$dst), + (MOV32mi addr:$dst, texternalsym:$src)>; +def : Pat<(store (i32 (X86Wrapper tblockaddress:$src)), addr:$dst), + (MOV32mi addr:$dst, tblockaddress:$src)>; + +// Calls +// tailcall stuff +def : Pat<(X86tcret GR32_TC:$dst, imm:$off), + (TCRETURNri GR32_TC:$dst, imm:$off)>, + Requires<[In32BitMode]>; + +// FIXME: This is disabled for 32-bit PIC mode because the global base +// register which is part of the address mode may be assigned a +// callee-saved register. +def : Pat<(X86tcret (load addr:$dst), imm:$off), + (TCRETURNmi addr:$dst, imm:$off)>, + Requires<[In32BitMode, IsNotPIC]>; + +def : Pat<(X86tcret (i32 tglobaladdr:$dst), imm:$off), + (TCRETURNdi texternalsym:$dst, imm:$off)>, + Requires<[In32BitMode]>; + +def : Pat<(X86tcret (i32 texternalsym:$dst), imm:$off), + (TCRETURNdi texternalsym:$dst, imm:$off)>, + Requires<[In32BitMode]>; + +// Normal calls, with various flavors of addresses. +def : Pat<(X86call (i32 tglobaladdr:$dst)), + (CALLpcrel32 tglobaladdr:$dst)>; +def : Pat<(X86call (i32 texternalsym:$dst)), + (CALLpcrel32 texternalsym:$dst)>; +def : Pat<(X86call (i32 imm:$dst)), + (CALLpcrel32 imm:$dst)>, Requires<[CallImmAddr]>; + +// X86 specific add which produces a flag. +def : Pat<(addc GR32:$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:$src2)>; + +// Comparisons. + +// TEST R,R is smaller than CMP R,0 +def : Pat<(X86cmp GR8:$src1, 0), + (TEST8rr GR8:$src1, GR8:$src1)>; +def : Pat<(X86cmp GR16:$src1, 0), + (TEST16rr GR16:$src1, GR16:$src1)>; +def : Pat<(X86cmp GR32:$src1, 0), + (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)>; +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)>; +def : Pat<(extloadi32i1 addr:$src), (MOVZX32rm8 addr:$src)>; +def : Pat<(extloadi16i8 addr:$src), (MOVZX16rm8 addr:$src)>; +def : Pat<(extloadi32i8 addr:$src), (MOVZX32rm8 addr:$src)>; +def : Pat<(extloadi32i16 addr:$src), (MOVZX32rm16 addr:$src)>; + +// anyext. Define these to do an explicit zero-extend to +// avoid partial-register updates. +def : Pat<(i16 (anyext GR8 :$src)), (MOVZX16rr8 GR8 :$src)>; +def : Pat<(i32 (anyext GR8 :$src)), (MOVZX32rr8 GR8 :$src)>; + +// Except for i16 -> i32 since isel expect i16 ops to be promoted to i32. +def : Pat<(i32 (anyext GR16:$src)), + (INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR16:$src, sub_16bit)>; + + +//===----------------------------------------------------------------------===// +// Some peepholes +//===----------------------------------------------------------------------===// + +// Odd encoding trick: -128 fits into an 8-bit immediate field while +// +128 doesn't, so in this special case use a sub instead of an add. +def : Pat<(add GR16:$src1, 128), + (SUB16ri8 GR16:$src1, -128)>; +def : Pat<(store (add (loadi16 addr:$dst), 128), addr:$dst), + (SUB16mi8 addr:$dst, -128)>; +def : Pat<(add GR32:$src1, 128), + (SUB32ri8 GR32:$src1, -128)>; +def : Pat<(store (add (loadi32 addr:$dst), 128), addr:$dst), + (SUB32mi8 addr:$dst, -128)>; + +// r & (2^16-1) ==> movz +def : Pat<(and GR32:$src1, 0xffff), + (MOVZX32rr16 (EXTRACT_SUBREG GR32:$src1, sub_16bit))>; +// r & (2^8-1) ==> movz +def : Pat<(and GR32:$src1, 0xff), + (MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src1, + GR32_ABCD)), + sub_8bit))>, + Requires<[In32BitMode]>; +// r & (2^8-1) ==> movz +def : Pat<(and GR16:$src1, 0xff), + (MOVZX16rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src1, + GR16_ABCD)), + sub_8bit))>, + Requires<[In32BitMode]>; + +// sext_inreg patterns +def : Pat<(sext_inreg GR32:$src, i16), + (MOVSX32rr16 (EXTRACT_SUBREG GR32:$src, sub_16bit))>; +def : Pat<(sext_inreg GR32:$src, i8), + (MOVSX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, + GR32_ABCD)), + sub_8bit))>, + Requires<[In32BitMode]>; +def : Pat<(sext_inreg GR16:$src, i8), + (MOVSX16rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, + GR16_ABCD)), + sub_8bit))>, + Requires<[In32BitMode]>; + +// trunc patterns +def : Pat<(i16 (trunc GR32:$src)), + (EXTRACT_SUBREG GR32:$src, sub_16bit)>; +def : Pat<(i8 (trunc GR32:$src)), + (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)), + sub_8bit)>, + Requires<[In32BitMode]>; +def : Pat<(i8 (trunc GR16:$src)), + (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)), + sub_8bit)>, + Requires<[In32BitMode]>; + +// h-register tricks +def : Pat<(i8 (trunc (srl_su GR16:$src, (i8 8)))), + (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)), + sub_8bit_hi)>, + Requires<[In32BitMode]>; +def : Pat<(i8 (trunc (srl_su GR32:$src, (i8 8)))), + (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)), + sub_8bit_hi)>, + Requires<[In32BitMode]>; +def : Pat<(srl GR16:$src, (i8 8)), + (EXTRACT_SUBREG + (MOVZX32rr8 + (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)), + sub_8bit_hi)), + sub_16bit)>, + Requires<[In32BitMode]>; +def : Pat<(i32 (zext (srl_su GR16:$src, (i8 8)))), + (MOVZX32rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, + GR16_ABCD)), + sub_8bit_hi))>, + Requires<[In32BitMode]>; +def : Pat<(i32 (anyext (srl_su GR16:$src, (i8 8)))), + (MOVZX32rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, + GR16_ABCD)), + sub_8bit_hi))>, + Requires<[In32BitMode]>; +def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)), + (MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, + GR32_ABCD)), + sub_8bit_hi))>, + Requires<[In32BitMode]>; +def : Pat<(srl (and_su GR32:$src, 0xff00), (i8 8)), + (MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, + GR32_ABCD)), + sub_8bit_hi))>, + 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, 31)), + (SHL8rCL GR8:$src1)>; +def : Pat<(shl GR16:$src1, (and CL, 31)), + (SHL16rCL GR16:$src1)>; +def : Pat<(shl GR32:$src1, (and CL, 31)), + (SHL32rCL GR32:$src1)>; +def : Pat<(store (shl (loadi8 addr:$dst), (and CL, 31)), addr:$dst), + (SHL8mCL addr:$dst)>; +def : Pat<(store (shl (loadi16 addr:$dst), (and CL, 31)), addr:$dst), + (SHL16mCL addr:$dst)>; +def : Pat<(store (shl (loadi32 addr:$dst), (and CL, 31)), addr:$dst), + (SHL32mCL addr:$dst)>; + +def : Pat<(srl GR8:$src1, (and CL, 31)), + (SHR8rCL GR8:$src1)>; +def : Pat<(srl GR16:$src1, (and CL, 31)), + (SHR16rCL GR16:$src1)>; +def : Pat<(srl GR32:$src1, (and CL, 31)), + (SHR32rCL GR32:$src1)>; +def : Pat<(store (srl (loadi8 addr:$dst), (and CL, 31)), addr:$dst), + (SHR8mCL addr:$dst)>; +def : Pat<(store (srl (loadi16 addr:$dst), (and CL, 31)), addr:$dst), + (SHR16mCL addr:$dst)>; +def : Pat<(store (srl (loadi32 addr:$dst), (and CL, 31)), addr:$dst), + (SHR32mCL addr:$dst)>; + +def : Pat<(sra GR8:$src1, (and CL, 31)), + (SAR8rCL GR8:$src1)>; +def : Pat<(sra GR16:$src1, (and CL, 31)), + (SAR16rCL GR16:$src1)>; +def : Pat<(sra GR32:$src1, (and CL, 31)), + (SAR32rCL GR32:$src1)>; +def : Pat<(store (sra (loadi8 addr:$dst), (and CL, 31)), addr:$dst), + (SAR8mCL addr:$dst)>; +def : Pat<(store (sra (loadi16 addr:$dst), (and CL, 31)), addr:$dst), + (SAR16mCL addr:$dst)>; +def : Pat<(store (sra (loadi32 addr:$dst), (and CL, 31)), addr:$dst), + (SAR32mCL addr:$dst)>; + +// (anyext (setcc_carry)) -> (setcc_carry) +def : Pat<(i16 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))), + (SETB_C16r)>; +def : Pat<(i32 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))), + (SETB_C32r)>; +def : Pat<(i32 (anyext (i16 (X86setcc_c X86_COND_B, EFLAGS)))), + (SETB_C32r)>; + +// (or x1, x2) -> (add x1, x2) if two operands are known not to share bits. +let AddedComplexity = 5 in { // Try this before the selecting to OR +def : Pat<(or_is_add GR16:$src1, imm:$src2), + (ADD16ri GR16:$src1, imm:$src2)>; +def : Pat<(or_is_add GR32:$src1, imm:$src2), + (ADD32ri GR32:$src1, imm:$src2)>; +def : Pat<(or_is_add GR16:$src1, i16immSExt8:$src2), + (ADD16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(or_is_add GR32:$src1, i32immSExt8:$src2), + (ADD32ri8 GR32:$src1, i32immSExt8:$src2)>; +def : Pat<(or_is_add GR16:$src1, GR16:$src2), + (ADD16rr GR16:$src1, GR16:$src2)>; +def : Pat<(or_is_add GR32:$src1, GR32:$src2), + (ADD32rr GR32:$src1, GR32:$src2)>; +} // AddedComplexity + +//===----------------------------------------------------------------------===// +// EFLAGS-defining Patterns +//===----------------------------------------------------------------------===// + +// add reg, reg +def : Pat<(add GR8 :$src1, GR8 :$src2), (ADD8rr GR8 :$src1, GR8 :$src2)>; +def : Pat<(add GR16:$src1, GR16:$src2), (ADD16rr GR16:$src1, GR16:$src2)>; +def : Pat<(add GR32:$src1, GR32:$src2), (ADD32rr GR32:$src1, GR32:$src2)>; + +// add reg, mem +def : Pat<(add GR8:$src1, (loadi8 addr:$src2)), + (ADD8rm GR8:$src1, addr:$src2)>; +def : Pat<(add GR16:$src1, (loadi16 addr:$src2)), + (ADD16rm GR16:$src1, addr:$src2)>; +def : Pat<(add GR32:$src1, (loadi32 addr:$src2)), + (ADD32rm GR32:$src1, addr:$src2)>; + +// add reg, imm +def : Pat<(add GR8 :$src1, imm:$src2), (ADD8ri GR8:$src1 , imm:$src2)>; +def : Pat<(add GR16:$src1, imm:$src2), (ADD16ri GR16:$src1, imm:$src2)>; +def : Pat<(add GR32:$src1, imm:$src2), (ADD32ri GR32:$src1, imm:$src2)>; +def : Pat<(add GR16:$src1, i16immSExt8:$src2), + (ADD16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(add GR32:$src1, i32immSExt8:$src2), + (ADD32ri8 GR32:$src1, i32immSExt8:$src2)>; + +// sub reg, reg +def : Pat<(sub GR8 :$src1, GR8 :$src2), (SUB8rr GR8 :$src1, GR8 :$src2)>; +def : Pat<(sub GR16:$src1, GR16:$src2), (SUB16rr GR16:$src1, GR16:$src2)>; +def : Pat<(sub GR32:$src1, GR32:$src2), (SUB32rr GR32:$src1, GR32:$src2)>; + +// sub reg, mem +def : Pat<(sub GR8:$src1, (loadi8 addr:$src2)), + (SUB8rm GR8:$src1, addr:$src2)>; +def : Pat<(sub GR16:$src1, (loadi16 addr:$src2)), + (SUB16rm GR16:$src1, addr:$src2)>; +def : Pat<(sub GR32:$src1, (loadi32 addr:$src2)), + (SUB32rm GR32:$src1, addr:$src2)>; + +// sub reg, imm +def : Pat<(sub GR8:$src1, imm:$src2), + (SUB8ri GR8:$src1, imm:$src2)>; +def : Pat<(sub GR16:$src1, imm:$src2), + (SUB16ri GR16:$src1, imm:$src2)>; +def : Pat<(sub GR32:$src1, imm:$src2), + (SUB32ri GR32:$src1, imm:$src2)>; +def : Pat<(sub GR16:$src1, i16immSExt8:$src2), + (SUB16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(sub GR32:$src1, i32immSExt8:$src2), + (SUB32ri8 GR32:$src1, i32immSExt8:$src2)>; + +// mul reg, reg +def : Pat<(mul GR16:$src1, GR16:$src2), + (IMUL16rr GR16:$src1, GR16:$src2)>; +def : Pat<(mul GR32:$src1, GR32:$src2), + (IMUL32rr GR32:$src1, GR32:$src2)>; + +// mul reg, mem +def : Pat<(mul GR16:$src1, (loadi16 addr:$src2)), + (IMUL16rm GR16:$src1, addr:$src2)>; +def : Pat<(mul GR32:$src1, (loadi32 addr:$src2)), + (IMUL32rm GR32:$src1, addr:$src2)>; + +// mul reg, imm +def : Pat<(mul GR16:$src1, imm:$src2), + (IMUL16rri GR16:$src1, imm:$src2)>; +def : Pat<(mul GR32:$src1, imm:$src2), + (IMUL32rri GR32:$src1, imm:$src2)>; +def : Pat<(mul GR16:$src1, i16immSExt8:$src2), + (IMUL16rri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(mul GR32:$src1, i32immSExt8:$src2), + (IMUL32rri8 GR32:$src1, i32immSExt8:$src2)>; + +// reg = mul mem, imm +def : Pat<(mul (loadi16 addr:$src1), imm:$src2), + (IMUL16rmi addr:$src1, imm:$src2)>; +def : Pat<(mul (loadi32 addr:$src1), imm:$src2), + (IMUL32rmi addr:$src1, imm:$src2)>; +def : Pat<(mul (loadi16 addr:$src1), i16immSExt8:$src2), + (IMUL16rmi8 addr:$src1, i16immSExt8:$src2)>; +def : Pat<(mul (loadi32 addr:$src1), i32immSExt8:$src2), + (IMUL32rmi8 addr:$src1, i32immSExt8:$src2)>; + +// Optimize multiply by 2 with EFLAGS result. +let AddedComplexity = 2 in { +def : Pat<(X86smul_flag GR16:$src1, 2), (ADD16rr GR16:$src1, GR16:$src1)>; +def : Pat<(X86smul_flag GR32:$src1, 2), (ADD32rr GR32:$src1, GR32:$src1)>; +} + +// Patterns for nodes that do not produce flags, for instructions that do. + +// Increment reg. +def : Pat<(add GR8:$src1 , 1), (INC8r GR8:$src1)>; +def : Pat<(add GR16:$src1, 1), (INC16r GR16:$src1)>, Requires<[In32BitMode]>; +def : Pat<(add GR32:$src1, 1), (INC32r GR32:$src1)>, Requires<[In32BitMode]>; + +// Decrement reg. +def : Pat<(add GR8:$src1 , -1), (DEC8r GR8:$src1)>; +def : Pat<(add GR16:$src1, -1), (DEC16r GR16:$src1)>, Requires<[In32BitMode]>; +def : Pat<(add GR32:$src1, -1), (DEC32r GR32:$src1)>, Requires<[In32BitMode]>; + +// or reg/reg. +def : Pat<(or GR8 :$src1, GR8 :$src2), (OR8rr GR8 :$src1, GR8 :$src2)>; +def : Pat<(or GR16:$src1, GR16:$src2), (OR16rr GR16:$src1, GR16:$src2)>; +def : Pat<(or GR32:$src1, GR32:$src2), (OR32rr GR32:$src1, GR32:$src2)>; + +// or reg/mem +def : Pat<(or GR8:$src1, (loadi8 addr:$src2)), + (OR8rm GR8:$src1, addr:$src2)>; +def : Pat<(or GR16:$src1, (loadi16 addr:$src2)), + (OR16rm GR16:$src1, addr:$src2)>; +def : Pat<(or GR32:$src1, (loadi32 addr:$src2)), + (OR32rm GR32:$src1, addr:$src2)>; + +// or reg/imm +def : Pat<(or GR8:$src1 , imm:$src2), (OR8ri GR8 :$src1, imm:$src2)>; +def : Pat<(or GR16:$src1, imm:$src2), (OR16ri GR16:$src1, imm:$src2)>; +def : Pat<(or GR32:$src1, imm:$src2), (OR32ri GR32:$src1, imm:$src2)>; +def : Pat<(or GR16:$src1, i16immSExt8:$src2), + (OR16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(or GR32:$src1, i32immSExt8:$src2), + (OR32ri8 GR32:$src1, i32immSExt8:$src2)>; + +// xor reg/reg +def : Pat<(xor GR8 :$src1, GR8 :$src2), (XOR8rr GR8 :$src1, GR8 :$src2)>; +def : Pat<(xor GR16:$src1, GR16:$src2), (XOR16rr GR16:$src1, GR16:$src2)>; +def : Pat<(xor GR32:$src1, GR32:$src2), (XOR32rr GR32:$src1, GR32:$src2)>; + +// xor reg/mem +def : Pat<(xor GR8:$src1, (loadi8 addr:$src2)), + (XOR8rm GR8:$src1, addr:$src2)>; +def : Pat<(xor GR16:$src1, (loadi16 addr:$src2)), + (XOR16rm GR16:$src1, addr:$src2)>; +def : Pat<(xor GR32:$src1, (loadi32 addr:$src2)), + (XOR32rm GR32:$src1, addr:$src2)>; + +// xor reg/imm +def : Pat<(xor GR8:$src1, imm:$src2), + (XOR8ri GR8:$src1, imm:$src2)>; +def : Pat<(xor GR16:$src1, imm:$src2), + (XOR16ri GR16:$src1, imm:$src2)>; +def : Pat<(xor GR32:$src1, imm:$src2), + (XOR32ri GR32:$src1, imm:$src2)>; +def : Pat<(xor GR16:$src1, i16immSExt8:$src2), + (XOR16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(xor GR32:$src1, i32immSExt8:$src2), + (XOR32ri8 GR32:$src1, i32immSExt8:$src2)>; + +// and reg/reg +def : Pat<(and GR8 :$src1, GR8 :$src2), (AND8rr GR8 :$src1, GR8 :$src2)>; +def : Pat<(and GR16:$src1, GR16:$src2), (AND16rr GR16:$src1, GR16:$src2)>; +def : Pat<(and GR32:$src1, GR32:$src2), (AND32rr GR32:$src1, GR32:$src2)>; + +// and reg/mem +def : Pat<(and GR8:$src1, (loadi8 addr:$src2)), + (AND8rm GR8:$src1, addr:$src2)>; +def : Pat<(and GR16:$src1, (loadi16 addr:$src2)), + (AND16rm GR16:$src1, addr:$src2)>; +def : Pat<(and GR32:$src1, (loadi32 addr:$src2)), + (AND32rm GR32:$src1, addr:$src2)>; + +// and reg/imm +def : Pat<(and GR8:$src1, imm:$src2), + (AND8ri GR8:$src1, imm:$src2)>; +def : Pat<(and GR16:$src1, imm:$src2), + (AND16ri GR16:$src1, imm:$src2)>; +def : Pat<(and GR32:$src1, imm:$src2), + (AND32ri GR32:$src1, imm:$src2)>; +def : Pat<(and GR16:$src1, i16immSExt8:$src2), + (AND16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(and GR32:$src1, i32immSExt8:$src2), + (AND32ri8 GR32:$src1, i32immSExt8:$src2)>; + +//===----------------------------------------------------------------------===// +// Floating Point Stack Support +//===----------------------------------------------------------------------===// + +include "X86InstrFPStack.td" + +//===----------------------------------------------------------------------===// +// X86-64 Support +//===----------------------------------------------------------------------===// + +include "X86Instr64bit.td" + +//===----------------------------------------------------------------------===// +// SIMD support (SSE, MMX and AVX) +//===----------------------------------------------------------------------===// + +include "X86InstrFragmentsSIMD.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" |
