X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;ds=sidebyside;f=lib%2FTarget%2FX86%2FX86InstrInfo.td;h=55c2eb431ac1ea5d83b496e59dc3f39e6d6a1e41;hb=6c4025773a1de0cde0e8e27e8954e48a0fabbcd7;hp=7cf1ad31fcbb8257738576804fc52b94adb39792;hpb=2ee3db3003deb18461a72b82166d8d417925d06f;p=oota-llvm.git diff --git a/lib/Target/X86/X86InstrInfo.td b/lib/Target/X86/X86InstrInfo.td index 7cf1ad31fcb..55c2eb431ac 100644 --- a/lib/Target/X86/X86InstrInfo.td +++ b/lib/Target/X86/X86InstrInfo.td @@ -34,7 +34,6 @@ def SDTBinaryArithWithFlags : SDTypeProfile<1, 2, [SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, SDTCisInt<0>]>; - def SDTX86BrCond : SDTypeProfile<0, 3, [SDTCisVT<0, OtherVT>, SDTCisVT<1, i8>, SDTCisVT<2, i32>]>; @@ -51,12 +50,16 @@ 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_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 SDTX86RdTsc : SDTypeProfile<0, 0, []>; @@ -115,6 +118,11 @@ def X86AtomSwap64 : SDNode<"X86ISD::ATOMSWAP64_DAG", SDTX86atomicBinary, def X86retflag : SDNode<"X86ISD::RET_FLAG", SDTX86Ret, [SDNPHasChain, SDNPOptInFlag]>; +def X86vastart_save_xmm_regs : + SDNode<"X86ISD::VASTART_SAVE_XMM_REGS", + SDT_X86VASTART_SAVE_XMM_REGS, + [SDNPHasChain]>; + def X86callseq_start : SDNode<"ISD::CALLSEQ_START", SDT_X86CallSeqStart, [SDNPHasChain, SDNPOutFlag]>; @@ -125,9 +133,6 @@ def X86callseq_end : def X86call : SDNode<"X86ISD::CALL", SDT_X86Call, [SDNPHasChain, SDNPOutFlag, SDNPOptInFlag]>; -def X86tailcall: SDNode<"X86ISD::TAILCALL", SDT_X86Call, - [SDNPHasChain, SDNPOutFlag, SDNPOptInFlag]>; - def X86rep_stos: SDNode<"X86ISD::REP_STOS", SDTX86RepStr, [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore]>; def X86rep_movs: SDNode<"X86ISD::REP_MOVS", SDTX86RepStr, @@ -164,33 +169,54 @@ def X86mul_imm : SDNode<"X86ISD::MUL_IMM", SDTIntBinOp>; // X86 Operand Definitions. // +def i32imm_pcrel : Operand { + let PrintMethod = "print_pcrel_imm"; +} + +// 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 SuperClass = ?; +} class X86MemOperand : Operand { let PrintMethod = printMethod; - let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc, i32imm, i8imm); + 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 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 { let PrintMethod = "printi8mem"; - let MIOperandInfo = (ops GR64_NOREX, i8imm, GR64_NOREX, i32imm, i8imm); + let MIOperandInfo = (ops GR64_NOREX, i8imm, GR64_NOREX_NOSP, i32imm, i8imm); + let ParserMatchClass = X86MemAsmOperand; } def lea32mem : Operand { let PrintMethod = "printlea32mem"; - let MIOperandInfo = (ops GR32, i8imm, GR32, i32imm); + let MIOperandInfo = (ops GR32, i8imm, GR32_NOSP, i32imm); + let ParserMatchClass = X86MemAsmOperand; } def SSECC : Operand { @@ -201,14 +227,29 @@ def piclabel: Operand { let PrintMethod = "printPICLabel"; } +def ImmSExt8AsmOperand : AsmOperandClass { + let Name = "ImmSExt8"; + let SuperClass = ImmAsmOperand; +} + // A couple of more descriptive operand definitions. // 16-bits but only 8 bits are significant. -def i16i8imm : Operand; +def i16i8imm : Operand { + let ParserMatchClass = ImmSExt8AsmOperand; +} // 32-bits but only 8 bits are significant. -def i32i8imm : Operand; +def i32i8imm : Operand { + let ParserMatchClass = ImmSExt8AsmOperand; +} -// Branch targets have OtherVT type. -def brtarget : Operand; +// Branch targets have OtherVT type and print as pc-relative values. +def brtarget : Operand { + let PrintMethod = "print_pcrel_imm"; +} + +def brtarget8 : Operand { + let PrintMethod = "print_pcrel_imm"; +} //===----------------------------------------------------------------------===// // X86 Complex Pattern Definitions. @@ -217,7 +258,10 @@ def brtarget : Operand; // Define X86 specific addressing mode. def addr : ComplexPattern; def lea32addr : ComplexPattern; + [add, sub, mul, X86mul_imm, shl, or, frameindex], + []>; +def tls32addr : ComplexPattern; //===----------------------------------------------------------------------===// // X86 Instruction Predicate Definitions. @@ -228,15 +272,26 @@ 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 NotSmallCode : 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 OptForSpeed : Predicate<"!OptForSize">; def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">; +def CallImmAddr : Predicate<"Subtarget->IsLegalToCallImmediateAddr(TM)">; //===----------------------------------------------------------------------===// // X86 Instruction Format Definitions. @@ -286,7 +341,7 @@ def loadi16 : PatFrag<(ops node:$ptr), (i16 (unindexedload node:$ptr)), [{ LoadSDNode *LD = cast(N); if (const Value *Src = LD->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; ISD::LoadExtType ExtType = LD->getExtensionType(); if (ExtType == ISD::NON_EXTLOAD) @@ -300,7 +355,7 @@ def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [ LoadSDNode *LD = cast(N); if (const Value *Src = LD->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; ISD::LoadExtType ExtType = LD->getExtensionType(); if (ExtType == ISD::EXTLOAD) @@ -312,7 +367,7 @@ def loadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{ LoadSDNode *LD = cast(N); if (const Value *Src = LD->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; ISD::LoadExtType ExtType = LD->getExtensionType(); if (ExtType == ISD::NON_EXTLOAD) @@ -326,7 +381,7 @@ def nvloadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{ LoadSDNode *LD = cast(N); if (const Value *Src = LD->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; if (LD->isVolatile()) return false; @@ -345,17 +400,24 @@ def gsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{ return false; }]>; +def fsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{ + if (const Value *Src = cast(N)->getSrcValue()) + if (const PointerType *PT = dyn_cast(Src->getType())) + return PT->getAddressSpace() == 257; + return false; +}]>; + def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr)), [{ if (const Value *Src = cast(N)->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; return true; }]>; def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr)), [{ if (const Value *Src = cast(N)->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; return true; }]>; @@ -363,21 +425,21 @@ def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr)), [{ def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr)), [{ if (const Value *Src = cast(N)->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; return true; }]>; def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr)), [{ if (const Value *Src = cast(N)->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; return true; }]>; def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr)), [{ if (const Value *Src = cast(N)->getSrcValue()) if (const PointerType *PT = dyn_cast(Src->getType())) - if (PT->getAddressSpace() != 0) + if (PT->getAddressSpace() > 255) return false; return true; }]>; @@ -462,14 +524,34 @@ def ADJCALLSTACKUP32 : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2), Requires<[In32BitMode]>; } +// x86-64 va_start lowering magic. +let usesCustomDAGSchedInserter = 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)]>; + // Nop -let neverHasSideEffects = 1 in +let neverHasSideEffects = 1 in { def NOOP : I<0x90, RawFrm, (outs), (ins), "nop", []>; + def NOOPL : I<0x1f, MRM0m, (outs), (ins i32mem:$zero), + "nopl\t$zero", []>, TB; +} + +// Trap +def INT3 : I<0xcc, RawFrm, (outs), (ins), "int 3", []>; +def INT : I<0xcd, RawFrm, (outs), (ins i8imm:$trap), "int\t$trap", []>; // PIC base let neverHasSideEffects = 1, isNotDuplicable = 1, Uses = [ESP] in def MOVPC32r : Ii32<0xE8, Pseudo, (outs GR32:$reg), (ins piclabel:$label), - "call\t$label\n\tpop{l}\t$reg", []>; + "call\t$label\n\t" + "pop{l}\t$reg", []>; //===----------------------------------------------------------------------===// // Control Flow Instructions... @@ -483,7 +565,7 @@ let isTerminator = 1, isReturn = 1, isBarrier = 1, [(X86retflag 0)]>; def RETI : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops), "ret\t$amt", - [(X86retflag imm:$amt)]>; + [(X86retflag timm:$amt)]>; } // All branches are RawFrm, Void, Branch, and Terminators @@ -491,8 +573,10 @@ let isBranch = 1, isTerminator = 1 in class IBr opcode, dag ins, string asm, list pattern> : I; -let isBranch = 1, isBarrier = 1 in +let isBranch = 1, isBarrier = 1 in { def JMP : IBr<0xE9, (ins brtarget:$dst), "jmp\t$dst", [(br bb:$dst)]>; + def JMP8 : IBr<0xEB, (ins brtarget8:$dst), "jmp\t$dst", []>; +} // Indirect branches let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in { @@ -500,10 +584,34 @@ let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in { [(brind GR32:$dst)]>; def JMP32m : I<0xFF, MRM4m, (outs), (ins i32mem:$dst), "jmp{l}\t{*}$dst", [(brind (loadi32 addr:$dst))]>; + def FARJMP16 : I<0xFF, MRM5m, (outs), (ins opaque32mem:$dst), + "ljmp{w}\t{*}$dst", []>, OpSize; + def FARJMP32 : I<0xFF, MRM5m, (outs), (ins opaque48mem:$dst), + "ljmp{l}\t{*}$dst", []>; } // Conditional branches let Uses = [EFLAGS] in { +// Short conditional jumps +def JO8 : IBr<0x70, (ins brtarget8:$dst), "jo\t$dst", []>; +def JNO8 : IBr<0x71, (ins brtarget8:$dst), "jno\t$dst", []>; +def JB8 : IBr<0x72, (ins brtarget8:$dst), "jb\t$dst", []>; +def JAE8 : IBr<0x73, (ins brtarget8:$dst), "jae\t$dst", []>; +def JE8 : IBr<0x74, (ins brtarget8:$dst), "je\t$dst", []>; +def JNE8 : IBr<0x75, (ins brtarget8:$dst), "jne\t$dst", []>; +def JBE8 : IBr<0x76, (ins brtarget8:$dst), "jbe\t$dst", []>; +def JA8 : IBr<0x77, (ins brtarget8:$dst), "ja\t$dst", []>; +def JS8 : IBr<0x78, (ins brtarget8:$dst), "js\t$dst", []>; +def JNS8 : IBr<0x79, (ins brtarget8:$dst), "jns\t$dst", []>; +def JP8 : IBr<0x7A, (ins brtarget8:$dst), "jp\t$dst", []>; +def JNP8 : IBr<0x7B, (ins brtarget8:$dst), "jnp\t$dst", []>; +def JL8 : IBr<0x7C, (ins brtarget8:$dst), "jl\t$dst", []>; +def JGE8 : IBr<0x7D, (ins brtarget8:$dst), "jge\t$dst", []>; +def JLE8 : IBr<0x7E, (ins brtarget8:$dst), "jle\t$dst", []>; +def JG8 : IBr<0x7F, (ins brtarget8:$dst), "jg\t$dst", []>; + +def JCXZ8 : IBr<0xE3, (ins brtarget8:$dst), "jcxz\t$dst", []>; + def JE : IBr<0x84, (ins brtarget:$dst), "je\t$dst", [(X86brcond bb:$dst, X86_COND_E, EFLAGS)]>, TB; def JNE : IBr<0x85, (ins brtarget:$dst), "jne\t$dst", @@ -553,21 +661,22 @@ let isCall = 1 in XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS], Uses = [ESP] in { - def CALLpcrel32 : Ii32<0xE8, RawFrm, (outs), (ins i32imm:$dst,variable_ops), - "call\t${dst:call}", [(X86call imm:$dst)]>, - Requires<[In32BitMode]>; + def CALLpcrel32 : Ii32<0xE8, RawFrm, + (outs), (ins i32imm_pcrel:$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:$dst))]>; + + def FARCALL16 : I<0xFF, MRM3m, (outs), (ins opaque32mem:$dst), + "lcall{w}\t{*}$dst", []>, OpSize; + def FARCALL32 : I<0xFF, MRM3m, (outs), (ins opaque48mem:$dst), + "lcall{l}\t{*}$dst", []>; } // Tail call stuff. -def TAILCALL : I<0, Pseudo, (outs), (ins), - "#TAILCALL", - []>; - let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in def TCRETURNdi : I<0, Pseudo, (outs), (ins i32imm:$dst, i32imm:$offset, variable_ops), "#TC_RETURN $dst $offset", @@ -580,7 +689,7 @@ def TCRETURNri : I<0, Pseudo, (outs), (ins GR32:$dst, i32imm:$offset, variable_o let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in - def TAILJMPd : IBr<0xE9, (ins i32imm:$dst), "jmp\t${dst:call} # TAILCALL", + def TAILJMPd : IBr<0xE9, (ins i32imm_pcrel:$dst), "jmp\t$dst # TAILCALL", []>; let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in def TAILJMPr : I<0xFF, MRM4r, (outs), (ins GR32:$dst), "jmp{l}\t{*}$dst # TAILCALL", @@ -604,6 +713,15 @@ let mayStore = 1 in def PUSH32r : I<0x50, AddRegFrm, (outs), (ins GR32:$reg), "push{l}\t$reg",[]>; } +let Defs = [ESP], Uses = [ESP], neverHasSideEffects = 1, mayStore = 1 in { +def PUSH32i8 : Ii8<0x6a, RawFrm, (outs), (ins i8imm:$imm), + "push{l}\t$imm", []>; +def PUSH32i16 : Ii16<0x68, RawFrm, (outs), (ins i16imm:$imm), + "push{l}\t$imm", []>; +def PUSH32i32 : Ii32<0x68, RawFrm, (outs), (ins i32imm:$imm), + "push{l}\t$imm", []>; +} + let Defs = [ESP, EFLAGS], Uses = [ESP], mayLoad = 1, neverHasSideEffects=1 in def POPFD : I<0x9D, RawFrm, (outs), (ins), "popf", []>; let Defs = [ESP], Uses = [ESP, EFLAGS], mayStore = 1, neverHasSideEffects=1 in @@ -686,6 +804,17 @@ let isBarrier = 1, hasCtrlDep = 1 in { def TRAP : I<0x0B, RawFrm, (outs), (ins), "ud2", [(trap)]>, TB; } +def SYSCALL : I<0x05, RawFrm, + (outs), (ins), "syscall", []>, TB; +def SYSRET : I<0x07, RawFrm, + (outs), (ins), "sysret", []>, TB; +def SYSENTER : I<0x34, RawFrm, + (outs), (ins), "sysenter", []>, TB; +def SYSEXIT : I<0x35, RawFrm, + (outs), (ins), "sysexit", []>, TB; + + + //===----------------------------------------------------------------------===// // Input/Output Instructions... // @@ -783,16 +912,22 @@ def MOV32mr : I<0x89, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src), "mov{l}\t{$src, $dst|$dst, $src}", [(store GR32:$src, addr:$dst)]>; -// Versions of MOV8rr and MOV8mr that use i8mem_NOREX and GR8_NOREX so that they -// can be used for copying and storing h registers, which can't be encoded when -// a REX prefix is present. +// Versions of MOV8rr, MOV8mr, and MOV8rm that use i8mem_NOREX and GR8_NOREX so +// that they can be used for copying and storing h registers, which can't be +// encoded when a REX prefix is present. let neverHasSideEffects = 1 in def MOV8rr_NOREX : I<0x88, MRMDestReg, (outs GR8_NOREX:$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, $src} # NOREX", []>; +let mayLoad = 1, + canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in +def MOV8rm_NOREX : I<0x8A, MRMSrcMem, + (outs GR8_NOREX:$dst), (ins i8mem_NOREX:$src), + "mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>; //===----------------------------------------------------------------------===// // Fixed-Register Multiplication and Division Instructions... @@ -912,6 +1047,20 @@ let isTwoAddress = 1 in { // Conditional moves let Uses = [EFLAGS] in { + +// X86 doesn't have 8-bit conditional moves. Use a customDAGSchedInserter to +// emit control flow. An alternative to this is to mark i8 SELECT as Promote, +// however that requires promoting the operands, and can induce additional +// i8 register pressure. Note that CMOV_GR8 is conservatively considered to +// clobber EFLAGS, because if one of the operands is zero, the expansion +// could involve an xor. +let usesCustomDAGSchedInserter = 1, isTwoAddress = 0, Defs = [EFLAGS] in +def CMOV_GR8 : I<0, Pseudo, + (outs GR8:$dst), (ins GR8:$src1, GR8:$src2, i8imm:$cond), + "#CMOV_GR8 PSEUDO!", + [(set GR8:$dst, (X86cmov GR8:$src1, GR8:$src2, + imm:$cond, EFLAGS))]>; + let isCommutable = 1 in { def CMOVB16rr : I<0x42, MRMSrcReg, // if ; + + def AND8i8 : Ii8<0x24, RawFrm, (outs), (ins i8imm:$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, $src}", []>; + } @@ -1713,13 +1870,13 @@ let isTwoAddress = 0 in { let Defs = [EFLAGS] in { let Uses = [CL] in { def SHL8rCL : I<0xD2, MRM4r, (outs GR8 :$dst), (ins GR8 :$src), - "shl{b}\t{%cl, $dst|$dst, %CL}", + "shl{b}\t{%cl, $dst|$dst, CL}", [(set GR8:$dst, (shl GR8:$src, CL))]>; def SHL16rCL : I<0xD3, MRM4r, (outs GR16:$dst), (ins GR16:$src), - "shl{w}\t{%cl, $dst|$dst, %CL}", + "shl{w}\t{%cl, $dst|$dst, CL}", [(set GR16:$dst, (shl GR16:$src, CL))]>, OpSize; def SHL32rCL : I<0xD3, MRM4r, (outs GR32:$dst), (ins GR32:$src), - "shl{l}\t{%cl, $dst|$dst, %CL}", + "shl{l}\t{%cl, $dst|$dst, CL}", [(set GR32:$dst, (shl GR32:$src, CL))]>; } // Uses = [CL] @@ -1740,13 +1897,13 @@ def SHL32ri : Ii8<0xC1, MRM4r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2), let isTwoAddress = 0 in { let Uses = [CL] in { def SHL8mCL : I<0xD2, MRM4m, (outs), (ins i8mem :$dst), - "shl{b}\t{%cl, $dst|$dst, %CL}", + "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}", + "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}", + "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), @@ -1775,13 +1932,13 @@ let isTwoAddress = 0 in { let Uses = [CL] in { def SHR8rCL : I<0xD2, MRM5r, (outs GR8 :$dst), (ins GR8 :$src), - "shr{b}\t{%cl, $dst|$dst, %CL}", + "shr{b}\t{%cl, $dst|$dst, CL}", [(set GR8:$dst, (srl GR8:$src, CL))]>; def SHR16rCL : I<0xD3, MRM5r, (outs GR16:$dst), (ins GR16:$src), - "shr{w}\t{%cl, $dst|$dst, %CL}", + "shr{w}\t{%cl, $dst|$dst, CL}", [(set GR16:$dst, (srl GR16:$src, CL))]>, OpSize; def SHR32rCL : I<0xD3, MRM5r, (outs GR32:$dst), (ins GR32:$src), - "shr{l}\t{%cl, $dst|$dst, %CL}", + "shr{l}\t{%cl, $dst|$dst, CL}", [(set GR32:$dst, (srl GR32:$src, CL))]>; } @@ -1809,14 +1966,14 @@ def SHR32r1 : I<0xD1, MRM5r, (outs GR32:$dst), (ins GR32:$src1), let isTwoAddress = 0 in { let Uses = [CL] in { def SHR8mCL : I<0xD2, MRM5m, (outs), (ins i8mem :$dst), - "shr{b}\t{%cl, $dst|$dst, %CL}", + "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}", + "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}", + "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), @@ -1844,13 +2001,13 @@ let isTwoAddress = 0 in { let Uses = [CL] in { def SAR8rCL : I<0xD2, MRM7r, (outs GR8 :$dst), (ins GR8 :$src), - "sar{b}\t{%cl, $dst|$dst, %CL}", + "sar{b}\t{%cl, $dst|$dst, CL}", [(set GR8:$dst, (sra GR8:$src, CL))]>; def SAR16rCL : I<0xD3, MRM7r, (outs GR16:$dst), (ins GR16:$src), - "sar{w}\t{%cl, $dst|$dst, %CL}", + "sar{w}\t{%cl, $dst|$dst, CL}", [(set GR16:$dst, (sra GR16:$src, CL))]>, OpSize; def SAR32rCL : I<0xD3, MRM7r, (outs GR32:$dst), (ins GR32:$src), - "sar{l}\t{%cl, $dst|$dst, %CL}", + "sar{l}\t{%cl, $dst|$dst, CL}", [(set GR32:$dst, (sra GR32:$src, CL))]>; } @@ -1879,13 +2036,13 @@ def SAR32r1 : I<0xD1, MRM7r, (outs GR32:$dst), (ins GR32:$src1), let isTwoAddress = 0 in { let Uses = [CL] in { def SAR8mCL : I<0xD2, MRM7m, (outs), (ins i8mem :$dst), - "sar{b}\t{%cl, $dst|$dst, %CL}", + "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}", + "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}", + "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), @@ -1916,13 +2073,13 @@ let isTwoAddress = 0 in { // FIXME: provide shorter instructions when imm8 == 1 let Uses = [CL] in { def ROL8rCL : I<0xD2, MRM0r, (outs GR8 :$dst), (ins GR8 :$src), - "rol{b}\t{%cl, $dst|$dst, %CL}", + "rol{b}\t{%cl, $dst|$dst, CL}", [(set GR8:$dst, (rotl GR8:$src, CL))]>; def ROL16rCL : I<0xD3, MRM0r, (outs GR16:$dst), (ins GR16:$src), - "rol{w}\t{%cl, $dst|$dst, %CL}", + "rol{w}\t{%cl, $dst|$dst, CL}", [(set GR16:$dst, (rotl GR16:$src, CL))]>, OpSize; def ROL32rCL : I<0xD3, MRM0r, (outs GR32:$dst), (ins GR32:$src), - "rol{l}\t{%cl, $dst|$dst, %CL}", + "rol{l}\t{%cl, $dst|$dst, CL}", [(set GR32:$dst, (rotl GR32:$src, CL))]>; } @@ -1950,13 +2107,13 @@ def ROL32r1 : I<0xD1, MRM0r, (outs GR32:$dst), (ins GR32:$src1), let isTwoAddress = 0 in { let Uses = [CL] in { def ROL8mCL : I<0xD2, MRM0m, (outs), (ins i8mem :$dst), - "rol{b}\t{%cl, $dst|$dst, %CL}", + "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}", + "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}", + "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), @@ -1985,13 +2142,13 @@ let isTwoAddress = 0 in { let Uses = [CL] in { def ROR8rCL : I<0xD2, MRM1r, (outs GR8 :$dst), (ins GR8 :$src), - "ror{b}\t{%cl, $dst|$dst, %CL}", + "ror{b}\t{%cl, $dst|$dst, CL}", [(set GR8:$dst, (rotr GR8:$src, CL))]>; def ROR16rCL : I<0xD3, MRM1r, (outs GR16:$dst), (ins GR16:$src), - "ror{w}\t{%cl, $dst|$dst, %CL}", + "ror{w}\t{%cl, $dst|$dst, CL}", [(set GR16:$dst, (rotr GR16:$src, CL))]>, OpSize; def ROR32rCL : I<0xD3, MRM1r, (outs GR32:$dst), (ins GR32:$src), - "ror{l}\t{%cl, $dst|$dst, %CL}", + "ror{l}\t{%cl, $dst|$dst, CL}", [(set GR32:$dst, (rotr GR32:$src, CL))]>; } @@ -2019,13 +2176,13 @@ def ROR32r1 : I<0xD1, MRM1r, (outs GR32:$dst), (ins GR32:$src1), let isTwoAddress = 0 in { let Uses = [CL] in { def ROR8mCL : I<0xD2, MRM1m, (outs), (ins i8mem :$dst), - "ror{b}\t{%cl, $dst|$dst, %CL}", + "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}", + "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}", + "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), @@ -2057,17 +2214,17 @@ let isTwoAddress = 0 in { // 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}", + "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}", + "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}", + "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}", + "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}", [(set GR16:$dst, (X86shrd GR16:$src1, GR16:$src2, CL))]>, TB, OpSize; } @@ -2102,11 +2259,11 @@ def SHRD16rri8 : Ii8<0xAC, MRMDestReg, let isTwoAddress = 0 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}", + "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}", + "shrd{l}\t{%cl, $src2, $dst|$dst, $src2, CL}", [(store (X86shrd (loadi32 addr:$dst), GR32:$src2, CL), addr:$dst)]>, TB; } @@ -2125,11 +2282,11 @@ let isTwoAddress = 0 in { let Uses = [CL] in { def SHLD16mrCL : I<0xA5, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2), - "shld{w}\t{%cl, $src2, $dst|$dst, $src2, %CL}", + "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}", + "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}", [(store (X86shrd (loadi16 addr:$dst), GR16:$src2, CL), addr:$dst)]>, TB, OpSize; } @@ -2257,28 +2414,86 @@ let isTwoAddress = 0 in { [(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, $src}", []>; } let Uses = [EFLAGS] in { let isCommutable = 1 in { // X = ADC Y, Z --> X = ADC Z, Y -def ADC32rr : I<0x11, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), +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))]>; } -def ADC32rm : I<0x13, MRMSrcMem , (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), +def ADC8rm : I<0x12, MRMSrcMem , (outs GR8:$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 ADC32ri : Ii32<0x81, MRM2r, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2), +def ADC8ri : Ii8<0x80, MRM2r, (outs GR8:$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:$src2), +def ADC32ri8 : Ii8<0x83, MRM2r, (outs GR32:$dst), + (ins GR32:$src1, i32i8imm:$src2), "adc{l}\t{$src2, $dst|$dst, $src2}", [(set GR32:$dst, (adde GR32:$src1, i32immSExt8:$src2))]>; let isTwoAddress = 0 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)]>; @@ -2387,17 +2602,41 @@ let isTwoAddress = 0 in { } let Uses = [EFLAGS] in { -def SBB32rr : I<0x19, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), +def SBB8rr : I<0x18, MRMDestReg, (outs GR8:$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 isTwoAddress = 0 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 : Ii32<0x80, MRM3m, (outs), (ins i8mem:$dst, i8imm:$src2), "sbb{b}\t{$src2, $dst|$dst, $src2}", [(store (sube (loadi8 addr:$dst), imm:$src2), addr:$dst)]>; + def 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)]>; @@ -2405,13 +2644,36 @@ let isTwoAddress = 0 in { "sbb{l}\t{$src2, $dst|$dst, $src2}", [(store (sube (load addr:$dst), i32immSExt8:$src2), addr:$dst)]>; } -def SBB32rm : I<0x1B, MRMSrcMem, (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2), +def SBB8rm : I<0x1A, MRMSrcMem, (outs GR8:$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 SBB32ri : Ii32<0x81, MRM3r, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2), +def SBB8ri : Ii8<0x80, MRM3r, (outs GR8:$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:$src2), +def SBB32ri8 : Ii8<0x83, MRM3r, (outs GR32:$dst), + (ins GR32:$src1, i32i8imm:$src2), "sbb{l}\t{$src2, $dst|$dst, $src2}", [(set GR32:$dst, (sube GR32:$src1, i32immSExt8:$src2))]>; } // Uses = [EFLAGS] @@ -2512,6 +2774,13 @@ def TEST32rr : I<0x85, MRMDestReg, (outs), (ins GR32:$src1, GR32:$src2), (implicit EFLAGS)]>; } +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, $src2}", [(X86cmp (and GR8:$src1, (loadi8 addr:$src2)), 0), @@ -2743,6 +3012,13 @@ def SETNOm : I<0x91, MRM0m, // Integer comparisons let Defs = [EFLAGS] in { +def CMP8i8 : Ii8<0x3C, RawFrm, (outs), (ins i8imm:$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, $src2}", @@ -2932,6 +3208,7 @@ def MOVZX32_NOREXrr8 : I<0xB6, MRMSrcReg, (outs GR32_NOREX:$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, $src} # NOREX", @@ -2959,7 +3236,8 @@ let neverHasSideEffects = 1 in { // Alias instructions that map movr0 to xor. // FIXME: remove when we can teach regalloc that xor reg, reg is ok. -let Defs = [EFLAGS], isReMaterializable = 1, isAsCheapAsAMove = 1 in { +let Defs = [EFLAGS], isReMaterializable = 1, isAsCheapAsAMove = 1, + isCodeGenOnly = 1 in { def MOV8r0 : I<0x30, MRMInitReg, (outs GR8 :$dst), (ins), "xor{b}\t$dst, $dst", [(set GR8:$dst, 0)]>; @@ -2977,24 +3255,37 @@ def MOV32r0 : I<0x31, MRMInitReg, (outs GR32:$dst), (ins), // Thread Local Storage Instructions // -let hasSideEffects = 1, Uses = [EAX, EBX] in -def TLS_addr32 : I<0, Pseudo, (outs), (ins i32imm:$sym), - "leal\t${sym:mem}(,%ebx,1), %eax", - [(X86tlsaddr tglobaltlsaddr:$sym)]>, +// 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 lea32mem:$sym), + "leal\t$sym, %eax; " + "call\t___tls_get_addr@PLT", + [(X86tlsaddr tls32addr:$sym)]>, Requires<[In32BitMode]>; -let AddedComplexity = 5 in +let AddedComplexity = 5, isCodeGenOnly = 1 in def GS_MOV32rm : I<0x8B, MRMSrcMem, (outs GR32:$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:$src))]>, SegFS; + //===----------------------------------------------------------------------===// // DWARF Pseudo Instructions // def DWARF_LOC : I<0, Pseudo, (outs), (ins i32imm:$line, i32imm:$col, i32imm:$file), - ".loc\t${file:debug} ${line:debug} ${col:debug}", + ".loc\t$file $line $col", [(dwarf_loc (i32 imm:$line), (i32 imm:$col), (i32 imm:$file))]>; @@ -3002,7 +3293,7 @@ def DWARF_LOC : I<0, Pseudo, (outs), // EH Pseudo Instructions // let isTerminator = 1, isReturn = 1, isBarrier = 1, - hasCtrlDep = 1 in { + hasCtrlDep = 1, isCodeGenOnly = 1 in { def EH_RETURN : I<0xC3, RawFrm, (outs), (ins GR32:$addr), "ret\t#eh_return, addr: $addr", [(X86ehret GR32:$addr)]>; @@ -3031,42 +3322,121 @@ def XCHG8rm : I<0x86, MRMSrcMem, (outs GR8:$dst), (ins i8mem:$ptr, GR8:$val), // Atomic compare and swap. let Defs = [EAX, EFLAGS], Uses = [EAX] in { def LCMPXCHG32 : I<0xB1, MRMDestMem, (outs), (ins i32mem:$ptr, GR32:$swap), - "lock\n\tcmpxchg{l}\t{$swap, $ptr|$ptr, $swap}", + "lock\n\t" + "cmpxchg{l}\t{$swap, $ptr|$ptr, $swap}", [(X86cas addr:$ptr, GR32:$swap, 4)]>, TB, LOCK; } let Defs = [EAX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX] in { def LCMPXCHG8B : I<0xC7, MRM1m, (outs), (ins i32mem:$ptr), - "lock\n\tcmpxchg8b\t$ptr", + "lock\n\t" + "cmpxchg8b\t$ptr", [(X86cas8 addr:$ptr)]>, TB, LOCK; } let Defs = [AX, EFLAGS], Uses = [AX] in { def LCMPXCHG16 : I<0xB1, MRMDestMem, (outs), (ins i16mem:$ptr, GR16:$swap), - "lock\n\tcmpxchg{w}\t{$swap, $ptr|$ptr, $swap}", + "lock\n\t" + "cmpxchg{w}\t{$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:$swap), - "lock\n\tcmpxchg{b}\t{$swap, $ptr|$ptr, $swap}", + "lock\n\t" + "cmpxchg{b}\t{$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 i32mem:$ptr, GR32:$val), - "lock\n\txadd{l}\t{$val, $ptr|$ptr, $val}", + "lock\n\t" + "xadd{l}\t{$val, $ptr|$ptr, $val}", [(set GR32:$dst, (atomic_load_add_32 addr:$ptr, GR32:$val))]>, TB, LOCK; def LXADD16 : I<0xC1, MRMSrcMem, (outs GR16:$dst), (ins i16mem:$ptr, GR16:$val), - "lock\n\txadd{w}\t{$val, $ptr|$ptr, $val}", + "lock\n\t" + "xadd{w}\t{$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:$dst), (ins i8mem:$ptr, GR8:$val), - "lock\n\txadd{b}\t{$val, $ptr|$ptr, $val}", + "lock\n\t" + "xadd{b}\t{$val, $ptr|$ptr, $val}", [(set GR8:$dst, (atomic_load_add_8 addr:$ptr, GR8:$val))]>, TB, LOCK; } +// Optimized codegen when the non-memory output is not used. +// FIXME: Use normal add / sub instructions and add lock prefix dynamically. +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 = $dst", Defs = [EFLAGS], usesCustomDAGSchedInserter = 1 in { @@ -3189,14 +3559,6 @@ def : Pat<(store (i32 (X86Wrapper texternalsym:$src)), addr:$dst), // Calls // tailcall stuff -def : Pat<(X86tailcall GR32:$dst), - (TAILCALL)>; - -def : Pat<(X86tailcall (i32 tglobaladdr:$dst)), - (TAILCALL)>; -def : Pat<(X86tailcall (i32 texternalsym:$dst)), - (TAILCALL)>; - def : Pat<(X86tcret GR32:$dst, imm:$off), (TCRETURNri GR32:$dst, imm:$off)>; @@ -3206,10 +3568,13 @@ def : Pat<(X86tcret (i32 tglobaladdr:$dst), imm:$off), def : Pat<(X86tcret (i32 texternalsym:$dst), imm:$off), (TCRETURNdi texternalsym:$dst, imm:$off)>; +// 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), @@ -3314,21 +3679,17 @@ def : Pat<(zextloadi32i1 addr:$src), (MOVZX32rm8 addr:$src)>; // extload bool -> extload byte def : Pat<(extloadi8i1 addr:$src), (MOV8rm addr:$src)>; -def : Pat<(extloadi16i1 addr:$src), (MOVZX16rm8 addr:$src)>, - Requires<[In32BitMode]>; +def : Pat<(extloadi16i1 addr:$src), (MOVZX16rm8 addr:$src)>; def : Pat<(extloadi32i1 addr:$src), (MOVZX32rm8 addr:$src)>; -def : Pat<(extloadi16i8 addr:$src), (MOVZX16rm8 addr:$src)>, - Requires<[In32BitMode]>; +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 -def : Pat<(i16 (anyext GR8 :$src)), (MOVZX16rr8 GR8 :$src)>, - Requires<[In32BitMode]>; -def : Pat<(i32 (anyext GR8 :$src)), (MOVZX32rr8 GR8 :$src)>, - Requires<[In32BitMode]>; -def : Pat<(i32 (anyext GR16:$src)), - (INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR16:$src, x86_subreg_16bit)>; +// 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)>; +def : Pat<(i32 (anyext GR16:$src)), (MOVZX32rr16 GR16:$src)>; // (and (i32 load), 255) -> (zextload i8) def : Pat<(i32 (and (nvloadi32 addr:$src), (i32 255))), @@ -3356,12 +3717,12 @@ def : Pat<(and GR32:$src1, 0xffff), (MOVZX32rr16 (EXTRACT_SUBREG GR32:$src1, x86_subreg_16bit))>; // r & (2^8-1) ==> movz def : Pat<(and GR32:$src1, 0xff), - (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src1, GR32_), + (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src1, GR32_ABCD), x86_subreg_8bit))>, Requires<[In32BitMode]>; // r & (2^8-1) ==> movz def : Pat<(and GR16:$src1, 0xff), - (MOVZX16rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src1, GR16_), + (MOVZX16rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src1, GR16_ABCD), x86_subreg_8bit))>, Requires<[In32BitMode]>; @@ -3369,11 +3730,11 @@ def : Pat<(and GR16:$src1, 0xff), def : Pat<(sext_inreg GR32:$src, i16), (MOVSX32rr16 (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit))>; def : Pat<(sext_inreg GR32:$src, i8), - (MOVSX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_), + (MOVSX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD), x86_subreg_8bit))>, Requires<[In32BitMode]>; def : Pat<(sext_inreg GR16:$src, i8), - (MOVSX16rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_), + (MOVSX16rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD), x86_subreg_8bit))>, Requires<[In32BitMode]>; @@ -3381,32 +3742,40 @@ def : Pat<(sext_inreg GR16:$src, i8), def : Pat<(i16 (trunc GR32:$src)), (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit)>; def : Pat<(i8 (trunc GR32:$src)), - (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_), + (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD), x86_subreg_8bit)>, Requires<[In32BitMode]>; def : Pat<(i8 (trunc GR16:$src)), - (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_), + (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD), x86_subreg_8bit)>, Requires<[In32BitMode]>; // h-register tricks def : Pat<(i8 (trunc (srl_su GR16:$src, (i8 8)))), - (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_), + (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD), x86_subreg_8bit_hi)>, Requires<[In32BitMode]>; def : Pat<(i8 (trunc (srl_su GR32:$src, (i8 8)))), - (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_), + (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD), x86_subreg_8bit_hi)>, Requires<[In32BitMode]>; def : Pat<(srl_su GR16:$src, (i8 8)), (EXTRACT_SUBREG (MOVZX32rr8 - (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_), + (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD), x86_subreg_8bit_hi)), x86_subreg_16bit)>, Requires<[In32BitMode]>; +def : Pat<(i32 (zext (srl_su GR16:$src, (i8 8)))), + (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD), + x86_subreg_8bit_hi))>, + Requires<[In32BitMode]>; +def : Pat<(i32 (anyext (srl_su GR16:$src, (i8 8)))), + (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD), + x86_subreg_8bit_hi))>, + Requires<[In32BitMode]>; def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)), - (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_), + (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD), x86_subreg_8bit_hi))>, Requires<[In32BitMode]>; @@ -3563,8 +3932,6 @@ def : Pat<(store (shld (loadi16 addr:$dst), (i8 imm:$amt1), def : Pat<(parallel (X86add_flag GR8:$src1, GR8:$src2), (implicit EFLAGS)), (ADD8rr GR8:$src1, GR8:$src2)>; - -// Register-Register Addition with EFLAGS result def : Pat<(parallel (X86add_flag GR16:$src1, GR16:$src2), (implicit EFLAGS)), (ADD16rr GR16:$src1, GR16:$src2)>; @@ -3587,8 +3954,6 @@ def : Pat<(parallel (X86add_flag GR32:$src1, (loadi32 addr:$src2)), def : Pat<(parallel (X86add_flag GR8:$src1, imm:$src2), (implicit EFLAGS)), (ADD8ri GR8:$src1, imm:$src2)>; - -// Register-Integer Addition with EFLAGS result def : Pat<(parallel (X86add_flag GR16:$src1, imm:$src2), (implicit EFLAGS)), (ADD16ri GR16:$src1, imm:$src2)>; @@ -3615,6 +3980,8 @@ def : Pat<(parallel (store (X86add_flag (loadi32 addr:$dst), GR32:$src2), addr:$dst), (implicit EFLAGS)), (ADD32mr addr:$dst, GR32:$src2)>; + +// Memory-Integer Addition with EFLAGS result def : Pat<(parallel (store (X86add_flag (loadi8 addr:$dst), imm:$src2), addr:$dst), (implicit EFLAGS)), @@ -3801,6 +4168,18 @@ def : Pat<(parallel (store (i32 (X86dec_flag (loadi32 addr:$dst))), addr:$dst), (implicit EFLAGS)), (DEC32m addr:$dst)>, Requires<[In32BitMode]>; +// -disable-16bit support. +def : Pat<(truncstorei16 (i32 imm:$src), addr:$dst), + (MOV16mi addr:$dst, imm:$src)>; +def : Pat<(truncstorei16 GR32:$src, addr:$dst), + (MOV16mr addr:$dst, (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit))>; +def : Pat<(i32 (sextloadi16 addr:$dst)), + (MOVSX32rm16 addr:$dst)>; +def : Pat<(i32 (zextloadi16 addr:$dst)), + (MOVZX32rm16 addr:$dst)>; +def : Pat<(i32 (extloadi16 addr:$dst)), + (MOVZX32rm16 addr:$dst)>; + //===----------------------------------------------------------------------===// // Floating Point Stack Support //===----------------------------------------------------------------------===//