X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=lib%2FTarget%2FX86%2FX86InstrInfo.td;h=f4ca2b880badde1d9503f6887d1c360f3b675473;hp=3fb44172c6450c9e960ef4ed08e68c22b8f45d49;hb=803d7c055b7ac489d250469f0e529eee00f089de;hpb=e31d7f83c5edcc9f797bc7c9216a8c7a27249b8d diff --git a/lib/Target/X86/X86InstrInfo.td b/lib/Target/X86/X86InstrInfo.td index 3fb44172c64..f4ca2b880ba 100644 --- a/lib/Target/X86/X86InstrInfo.td +++ b/lib/Target/X86/X86InstrInfo.td @@ -106,8 +106,6 @@ def SDT_X86TLSCALL : SDTypeProfile<0, 1, [SDTCisInt<0>]>; def SDT_X86SEG_ALLOCA : SDTypeProfile<1, 1, [SDTCisVT<0, iPTR>, SDTCisVT<1, iPTR>]>; -def SDT_X86WIN_FTOL : SDTypeProfile<0, 1, [SDTCisFP<0>]>; - def SDT_X86EHRET : SDTypeProfile<0, 1, [SDTCisInt<0>]>; def SDT_X86TCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>, SDTCisVT<1, i32>]>; @@ -158,6 +156,8 @@ def X86cas16 : SDNode<"X86ISD::LCMPXCHG16_DAG", SDTX86caspair, def X86retflag : SDNode<"X86ISD::RET_FLAG", SDTX86Ret, [SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>; +def X86iret : SDNode<"X86ISD::IRET", SDTX86Ret, + [SDNPHasChain, SDNPOptInGlue]>; def X86vastart_save_xmm_regs : SDNode<"X86ISD::VASTART_SAVE_XMM_REGS", @@ -250,9 +250,6 @@ def X86SegAlloca : SDNode<"X86ISD::SEG_ALLOCA", SDT_X86SEG_ALLOCA, def X86TLSCall : SDNode<"X86ISD::TLSCALL", SDT_X86TLSCALL, [SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]>; -def X86WinFTOL : SDNode<"X86ISD::WIN_FTOL", SDT_X86WIN_FTOL, - [SDNPHasChain, SDNPOutGlue]>; - //===----------------------------------------------------------------------===// // X86 Operand Definitions. // @@ -344,18 +341,21 @@ def vy64xmem : X86VMemOperand; def vz32mem : X86VMemOperand; def vz64mem : X86VMemOperand; -// 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 { +// A version of i8mem for use on x86-64 and x32 that uses a NOREX GPR instead +// of a plain GPR, so that it doesn't potentially require a REX prefix. +def ptr_rc_norex : PointerLikeRegClass<2>; +def ptr_rc_norex_nosp : PointerLikeRegClass<3>; + +def i8mem_NOREX : Operand { let PrintMethod = "printi8mem"; - let MIOperandInfo = (ops GR64_NOREX, i8imm, GR64_NOREX_NOSP, i32imm, i8imm); + let MIOperandInfo = (ops ptr_rc_norex, i8imm, ptr_rc_norex_nosp, i32imm, i8imm); let ParserMatchClass = X86Mem8AsmOperand; let OperandType = "OPERAND_MEMORY"; } // GPRs available for tailcall. // It represents GR32_TC, GR64_TC or GR64_TCW64. -def ptr_rc_tailcall : PointerLikeRegClass<2>; +def ptr_rc_tailcall : PointerLikeRegClass<4>; // Special i32mem for addresses of load folding tail calls. These are not // allowed to use callee-saved registers since they must be scheduled @@ -697,34 +697,34 @@ def lea64mem : Operand { // X86 Complex Pattern Definitions. // -// Define X86 specific addressing mode. -def addr : ComplexPattern; -def lea32addr : ComplexPattern; +def lea32addr : ComplexPattern; // In 64-bit mode 32-bit LEAs can use RIP-relative addressing. -def lea64_32addr : ComplexPattern; -def tls32addr : ComplexPattern; -def tls32baseaddr : ComplexPattern; -def lea64addr : ComplexPattern; -def tls64addr : ComplexPattern; -def tls64baseaddr : ComplexPattern; -def vectoraddr : ComplexPattern; +def vectoraddr : ComplexPattern; //===----------------------------------------------------------------------===// // X86 Instruction Predicate Definitions. @@ -772,9 +772,16 @@ def HasVLX : Predicate<"Subtarget->hasVLX()">, AssemblerPredicate<"FeatureVLX", "AVX-512 VL ISA">; def NoVLX : Predicate<"!Subtarget->hasVLX()">; def NoVLX_Or_NoBWI : Predicate<"!Subtarget->hasVLX() || !Subtarget->hasBWI()">; +def NoVLX_Or_NoDQI : Predicate<"!Subtarget->hasVLX() || !Subtarget->hasDQI()">; +def PKU : Predicate<"!Subtarget->hasPKU()">; def HasPOPCNT : Predicate<"Subtarget->hasPOPCNT()">; def HasAES : Predicate<"Subtarget->hasAES()">; +def HasFXSR : Predicate<"Subtarget->hasFXSR()">; +def HasXSAVE : Predicate<"Subtarget->hasXSAVE()">; +def HasXSAVEOPT : Predicate<"Subtarget->hasXSAVEOPT()">; +def HasXSAVEC : Predicate<"Subtarget->hasXSAVEC()">; +def HasXSAVES : Predicate<"Subtarget->hasXSAVES()">; def HasPCLMUL : Predicate<"Subtarget->hasPCLMUL()">; def HasFMA : Predicate<"Subtarget->hasFMA()">; def UseFMAOnAVX : Predicate<"Subtarget->hasFMA() && !Subtarget->hasAVX512()">; @@ -796,6 +803,7 @@ def HasSHA : Predicate<"Subtarget->hasSHA()">; def HasPRFCHW : Predicate<"Subtarget->hasPRFCHW()">; def HasRDSEED : Predicate<"Subtarget->hasRDSEED()">; def HasPrefetchW : Predicate<"Subtarget->hasPRFCHW()">; +def HasLAHFSAHF : Predicate<"Subtarget->hasLAHFSAHF()">; def FPStackf32 : Predicate<"!Subtarget->hasSSE1()">; def FPStackf64 : Predicate<"!Subtarget->hasSSE2()">; def HasMPX : Predicate<"Subtarget->hasMPX()">; @@ -814,6 +822,8 @@ def In32BitMode : Predicate<"Subtarget->is32Bit()">, AssemblerPredicate<"Mode32Bit", "32-bit mode">; def IsWin64 : Predicate<"Subtarget->isTargetWin64()">; def NotWin64 : Predicate<"!Subtarget->isTargetWin64()">; +def NotWin64WithoutFP : Predicate<"!Subtarget->isTargetWin64() ||" + "Subtarget->getFrameLowering()->hasFP(*MF)">; def IsPS4 : Predicate<"Subtarget->isTargetPS4()">; def NotPS4 : Predicate<"!Subtarget->isTargetPS4()">; def IsNaCl : Predicate<"Subtarget->isTargetNaCl()">; @@ -827,6 +837,7 @@ def NearData : Predicate<"TM.getCodeModel() == CodeModel::Small ||" def IsStatic : Predicate<"TM.getRelocationModel() == Reloc::Static">; def IsNotPIC : Predicate<"TM.getRelocationModel() != Reloc::PIC_">; def OptForSize : Predicate<"OptForSize">; +def OptForMinSize : Predicate<"OptForMinSize">; def OptForSpeed : Predicate<"!OptForSize">; def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">; def CallImmAddr : Predicate<"Subtarget->IsLegalToCallImmediateAddr(TM)">; @@ -869,20 +880,54 @@ def X86_COND_E_OR_NE : ImmLeaf; -def i16immSExt8 : ImmLeaf; -def i32immSExt8 : ImmLeaf; -def i64immSExt8 : ImmLeaf; +def i16immSExt8 : ImmLeaf(Imm); }]>; +def i32immSExt8 : ImmLeaf(Imm); }]>; +def i64immSExt8 : ImmLeaf(Imm); }]>; + +// If we have multiple users of an immediate, it's much smaller to reuse +// the register, rather than encode the immediate in every instruction. +// This has the risk of increasing register pressure from stretched live +// ranges, however, the immediates should be trivial to rematerialize by +// the RA in the event of high register pressure. +// TODO : This is currently enabled for stores and binary ops. There are more +// cases for which this can be enabled, though this catches the bulk of the +// issues. +// TODO2 : This should really also be enabled under O2, but there's currently +// an issue with RA where we don't pull the constants into their users +// when we rematerialize them. I'll follow-up on enabling O2 after we fix that +// issue. +// TODO3 : This is currently limited to single basic blocks (DAG creation +// pulls block immediates to the top and merges them if necessary). +// Eventually, it would be nice to allow ConstantHoisting to merge constants +// globally for potentially added savings. +// +def imm8_su : PatLeaf<(i8 imm), [{ + return !shouldAvoidImmediateInstFormsForSize(N); +}]>; +def imm16_su : PatLeaf<(i16 imm), [{ + return !shouldAvoidImmediateInstFormsForSize(N); +}]>; +def imm32_su : PatLeaf<(i32 imm), [{ + return !shouldAvoidImmediateInstFormsForSize(N); +}]>; + +def i16immSExt8_su : PatLeaf<(i16immSExt8), [{ + return !shouldAvoidImmediateInstFormsForSize(N); +}]>; +def i32immSExt8_su : PatLeaf<(i32immSExt8), [{ + return !shouldAvoidImmediateInstFormsForSize(N); +}]>; -def i64immSExt32 : ImmLeaf; +def i64immSExt32 : ImmLeaf(Imm); }]>; // i64immZExt32 predicate - True if the 64-bit immediate fits in a 32-bit // unsigned field. -def i64immZExt32 : ImmLeaf; +def i64immZExt32 : ImmLeaf(Imm); }]>; def i64immZExt32SExt8 : ImmLeaf(Imm) && isInt<8>(static_cast(Imm)); }]>; // Helper fragments for loads. @@ -916,11 +961,12 @@ def loadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{ return false; }]>; -def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr))>; -def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr))>; -def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr))>; -def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr))>; -def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr))>; +def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr))>; +def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr))>; +def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr))>; +def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr))>; +def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr))>; +def loadf128 : PatFrag<(ops node:$ptr), (f128 (load node:$ptr))>; def sextloadi16i8 : PatFrag<(ops node:$ptr), (i16 (sextloadi8 node:$ptr))>; def sextloadi32i8 : PatFrag<(ops node:$ptr), (i32 (sextloadi8 node:$ptr))>; @@ -1283,13 +1329,13 @@ def MOV32ri_alt : Ii32<0xC7, MRM0r, (outs GR32:$dst), (ins i32imm:$src), let SchedRW = [WriteStore] in { def MOV8mi : Ii8 <0xC6, MRM0m, (outs), (ins i8mem :$dst, i8imm :$src), "mov{b}\t{$src, $dst|$dst, $src}", - [(store (i8 imm:$src), addr:$dst)], IIC_MOV_MEM>; + [(store (i8 imm8_su:$src), addr:$dst)], IIC_MOV_MEM>; def MOV16mi : Ii16<0xC7, MRM0m, (outs), (ins i16mem:$dst, i16imm:$src), "mov{w}\t{$src, $dst|$dst, $src}", - [(store (i16 imm:$src), addr:$dst)], IIC_MOV_MEM>, OpSize16; + [(store (i16 imm16_su:$src), addr:$dst)], IIC_MOV_MEM>, OpSize16; def MOV32mi : Ii32<0xC7, MRM0m, (outs), (ins i32mem:$dst, i32imm:$src), "mov{l}\t{$src, $dst|$dst, $src}", - [(store (i32 imm:$src), addr:$dst)], IIC_MOV_MEM>, OpSize32; + [(store (i32 imm32_su:$src), addr:$dst)], IIC_MOV_MEM>, OpSize32; def MOV64mi32 : RIi32S<0xC7, MRM0m, (outs), (ins i64mem:$dst, i64i32imm:$src), "mov{q}\t{$src, $dst|$dst, $src}", [(store i64immSExt32:$src, addr:$dst)], IIC_MOV_MEM>; @@ -1465,10 +1511,12 @@ def MOV8rm_NOREX : I<0x8A, MRMSrcMem, let SchedRW = [WriteALU] in { let Defs = [EFLAGS], Uses = [AH] in def SAHF : I<0x9E, RawFrm, (outs), (ins), "sahf", - [(set EFLAGS, (X86sahf AH))], IIC_AHF>; + [(set EFLAGS, (X86sahf AH))], IIC_AHF>, + Requires<[HasLAHFSAHF]>; let Defs = [AH], Uses = [EFLAGS], hasSideEffects = 0 in def LAHF : I<0x9F, RawFrm, (outs), (ins), "lahf", [], - IIC_AHF>; // AH = flags + IIC_AHF>, // AH = flags + Requires<[HasLAHFSAHF]>; } // SchedRW //===----------------------------------------------------------------------===// @@ -1902,37 +1950,38 @@ def CLTS : I<0x06, RawFrm, (outs), (ins), "clts", [], IIC_CLTS>, TB; } // Table lookup instructions +let Uses = [AL,EBX], Defs = [AL], hasSideEffects = 0, mayLoad = 1 in def XLAT : I<0xD7, RawFrm, (outs), (ins), "xlatb", [], IIC_XLAT>, Sched<[WriteLoad]>; let SchedRW = [WriteMicrocoded] in { // ASCII Adjust After Addition -// sets AL, AH and CF and AF of EFLAGS and uses AL and AF of EFLAGS +let Uses = [AL,EFLAGS], Defs = [AX,EFLAGS], hasSideEffects = 0 in def AAA : I<0x37, RawFrm, (outs), (ins), "aaa", [], IIC_AAA>, Requires<[Not64BitMode]>; // ASCII Adjust AX Before Division -// sets AL, AH and EFLAGS and uses AL and AH +let Uses = [AX], Defs = [AX,EFLAGS], hasSideEffects = 0 in def AAD8i8 : Ii8<0xD5, RawFrm, (outs), (ins i8imm:$src), "aad\t$src", [], IIC_AAD>, Requires<[Not64BitMode]>; // ASCII Adjust AX After Multiply -// sets AL, AH and EFLAGS and uses AL +let Uses = [AL], Defs = [AX,EFLAGS], hasSideEffects = 0 in def AAM8i8 : Ii8<0xD4, RawFrm, (outs), (ins i8imm:$src), "aam\t$src", [], IIC_AAM>, Requires<[Not64BitMode]>; // ASCII Adjust AL After Subtraction - sets -// sets AL, AH and CF and AF of EFLAGS and uses AL and AF of EFLAGS +let Uses = [AL,EFLAGS], Defs = [AX,EFLAGS], hasSideEffects = 0 in def AAS : I<0x3F, RawFrm, (outs), (ins), "aas", [], IIC_AAS>, Requires<[Not64BitMode]>; // Decimal Adjust AL after Addition -// sets AL, CF and AF of EFLAGS and uses AL, CF and AF of EFLAGS +let Uses = [AL,EFLAGS], Defs = [AL,EFLAGS], hasSideEffects = 0 in def DAA : I<0x27, RawFrm, (outs), (ins), "daa", [], IIC_DAA>, Requires<[Not64BitMode]>; // Decimal Adjust AL after Subtraction -// sets AL, CF and AF of EFLAGS and uses AL, CF and AF of EFLAGS +let Uses = [AL,EFLAGS], Defs = [AL,EFLAGS], hasSideEffects = 0 in def DAS : I<0x2F, RawFrm, (outs), (ins), "das", [], IIC_DAS>, Requires<[Not64BitMode]>; } // SchedRW @@ -2364,6 +2413,32 @@ defm T1MSKC : tbm_binary_intr<0x01, "t1mskc", MRM7r, MRM7m>; defm TZMSK : tbm_binary_intr<0x01, "tzmsk", MRM4r, MRM4m>; } // HasTBM, EFLAGS +//===----------------------------------------------------------------------===// +// MONITORX/MWAITX Instructions +// +let SchedRW = [WriteSystem] in { +let Uses = [EAX, ECX, EDX] in +def MONITORXrrr : I<0x01, MRM_FA, (outs), (ins), "monitorx", [], + IIC_SSE_MONITOR>, TB; +let Uses = [ECX, EAX, EBX] in +def MWAITXrr : I<0x01, MRM_FB, (outs), (ins), "mwaitx", [], IIC_SSE_MWAIT>, + TB; +} // SchedRW + +def : InstAlias<"mwaitx\t{%eax, %ecx, %ebx|ebx, ecx, eax}", (MWAITXrr)>, Requires<[Not64BitMode]>; +def : InstAlias<"mwaitx\t{%rax, %rcx, %rbx|rbx, rcx, rax}", (MWAITXrr)>, Requires<[In64BitMode]>; + +def : InstAlias<"monitorx\t{%eax, %ecx, %edx|edx, ecx, eax}", (MONITORXrrr)>, + Requires<[Not64BitMode]>; +def : InstAlias<"monitorx\t{%rax, %rcx, %rdx|rdx, rcx, rax}", (MONITORXrrr)>, + Requires<[In64BitMode]>; + +//===----------------------------------------------------------------------===// +// CLZERO Instruction +// +let Uses = [EAX] in +def CLZEROr : I<0x01, MRM_FC, (outs), (ins), "clzero", []>, TB; + //===----------------------------------------------------------------------===// // Pattern fragments to auto generate TBM instructions. //===----------------------------------------------------------------------===// @@ -2506,8 +2581,8 @@ def : MnemonicAlias<"lret", "lretl", "att">, Requires<[Not16BitMode]>; def : MnemonicAlias<"leavel", "leave", "att">, Requires<[Not64BitMode]>; def : MnemonicAlias<"leaveq", "leave", "att">, Requires<[In64BitMode]>; -def : MnemonicAlias<"loopz", "loope", "att">; -def : MnemonicAlias<"loopnz", "loopne", "att">; +def : MnemonicAlias<"loopz", "loope">; +def : MnemonicAlias<"loopnz", "loopne">; def : MnemonicAlias<"pop", "popw", "att">, Requires<[In16BitMode]>; def : MnemonicAlias<"pop", "popl", "att">, Requires<[In32BitMode]>; @@ -2540,14 +2615,15 @@ def : MnemonicAlias<"pusha", "pushaw", "att">, Requires<[In16BitMode]>; def : MnemonicAlias<"popa", "popal", "att">, Requires<[In32BitMode]>; def : MnemonicAlias<"pusha", "pushal", "att">, Requires<[In32BitMode]>; -def : MnemonicAlias<"repe", "rep", "att">; -def : MnemonicAlias<"repz", "rep", "att">; -def : MnemonicAlias<"repnz", "repne", "att">; +def : MnemonicAlias<"repe", "rep">; +def : MnemonicAlias<"repz", "rep">; +def : MnemonicAlias<"repnz", "repne">; def : MnemonicAlias<"ret", "retw", "att">, Requires<[In16BitMode]>; def : MnemonicAlias<"ret", "retl", "att">, Requires<[In32BitMode]>; def : MnemonicAlias<"ret", "retq", "att">, Requires<[In64BitMode]>; +def : MnemonicAlias<"sal", "shl", "intel">; def : MnemonicAlias<"salb", "shlb", "att">; def : MnemonicAlias<"salw", "shlw", "att">; def : MnemonicAlias<"sall", "shll", "att">; @@ -2587,14 +2663,14 @@ def : MnemonicAlias<"fcmova", "fcmovnbe", "att">; def : MnemonicAlias<"fcmovnae", "fcmovb", "att">; def : MnemonicAlias<"fcmovna", "fcmovbe", "att">; def : MnemonicAlias<"fcmovae", "fcmovnb", "att">; -def : MnemonicAlias<"fcomip", "fcompi", "att">; +def : MnemonicAlias<"fcomip", "fcompi">; def : MnemonicAlias<"fildq", "fildll", "att">; def : MnemonicAlias<"fistpq", "fistpll", "att">; def : MnemonicAlias<"fisttpq", "fisttpll", "att">; def : MnemonicAlias<"fldcww", "fldcw", "att">; def : MnemonicAlias<"fnstcww", "fnstcw", "att">; def : MnemonicAlias<"fnstsww", "fnstsw", "att">; -def : MnemonicAlias<"fucomip", "fucompi", "att">; +def : MnemonicAlias<"fucomip", "fucompi">; def : MnemonicAlias<"fwait", "wait">; def : MnemonicAlias<"fxsaveq", "fxsave64", "att">; @@ -2602,7 +2678,9 @@ def : MnemonicAlias<"fxrstorq", "fxrstor64", "att">; def : MnemonicAlias<"xsaveq", "xsave64", "att">; def : MnemonicAlias<"xrstorq", "xrstor64", "att">; def : MnemonicAlias<"xsaveoptq", "xsaveopt64", "att">; - +def : MnemonicAlias<"xrstorsq", "xrstors64", "att">; +def : MnemonicAlias<"xsavecq", "xsavec64", "att">; +def : MnemonicAlias<"xsavesq", "xsaves64", "att">; class CondCodeAlias @@ -2648,8 +2726,8 @@ defm : IntegerCondCodeMnemonicAlias<"cmov", "", "intel">; //===----------------------------------------------------------------------===// // aad/aam default to base 10 if no operand is specified. -def : InstAlias<"aad", (AAD8i8 10)>; -def : InstAlias<"aam", (AAM8i8 10)>; +def : InstAlias<"aad", (AAD8i8 10)>, Requires<[Not64BitMode]>; +def : InstAlias<"aam", (AAM8i8 10)>, Requires<[Not64BitMode]>; // Disambiguate the mem/imm form of bt-without-a-suffix as btl. // Likewise for btc/btr/bts. @@ -2727,8 +2805,10 @@ def : InstAlias<"idiv{q}\t{$src, %rax|rax, $src}", (IDIV64m i64mem:$src)>; // Various unary fpstack operations default to operating on on ST1. // For example, "fxch" -> "fxch %st(1)" def : InstAlias<"faddp", (ADD_FPrST0 ST1), 0>; +def: InstAlias<"fadd", (ADD_FPrST0 ST1), 0>; def : InstAlias<"fsub{|r}p", (SUBR_FPrST0 ST1), 0>; def : InstAlias<"fsub{r|}p", (SUB_FPrST0 ST1), 0>; +def : InstAlias<"fmul", (MUL_FPrST0 ST1), 0>; def : InstAlias<"fmulp", (MUL_FPrST0 ST1), 0>; def : InstAlias<"fdiv{|r}p", (DIVR_FPrST0 ST1), 0>; def : InstAlias<"fdiv{r|}p", (DIV_FPrST0 ST1), 0>; @@ -2806,20 +2886,20 @@ def : InstAlias<"jmp {*}$dst", (JMP16m i16mem:$dst), 0>, Requires<[In16Bit // "imul , B" is an alias for "imul , B, B". -def : InstAlias<"imulw {$imm, $r|$r, $imm}", (IMUL16rri GR16:$r, GR16:$r, i16imm:$imm), 0>; -def : InstAlias<"imulw {$imm, $r|$r, $imm}", (IMUL16rri8 GR16:$r, GR16:$r, i16i8imm:$imm), 0>; -def : InstAlias<"imull {$imm, $r|$r, $imm}", (IMUL32rri GR32:$r, GR32:$r, i32imm:$imm), 0>; -def : InstAlias<"imull {$imm, $r|$r, $imm}", (IMUL32rri8 GR32:$r, GR32:$r, i32i8imm:$imm), 0>; -def : InstAlias<"imulq {$imm, $r|$r, $imm}", (IMUL64rri32 GR64:$r, GR64:$r, i64i32imm:$imm), 0>; -def : InstAlias<"imulq {$imm, $r|$r, $imm}", (IMUL64rri8 GR64:$r, GR64:$r, i64i8imm:$imm), 0>; +def : InstAlias<"imul{w} {$imm, $r|$r, $imm}", (IMUL16rri GR16:$r, GR16:$r, i16imm:$imm), 0>; +def : InstAlias<"imul{w} {$imm, $r|$r, $imm}", (IMUL16rri8 GR16:$r, GR16:$r, i16i8imm:$imm), 0>; +def : InstAlias<"imul{l} {$imm, $r|$r, $imm}", (IMUL32rri GR32:$r, GR32:$r, i32imm:$imm), 0>; +def : InstAlias<"imul{l} {$imm, $r|$r, $imm}", (IMUL32rri8 GR32:$r, GR32:$r, i32i8imm:$imm), 0>; +def : InstAlias<"imul{q} {$imm, $r|$r, $imm}", (IMUL64rri32 GR64:$r, GR64:$r, i64i32imm:$imm), 0>; +def : InstAlias<"imul{q} {$imm, $r|$r, $imm}", (IMUL64rri8 GR64:$r, GR64:$r, i64i8imm:$imm), 0>; // inb %dx -> inb %al, %dx def : InstAlias<"inb\t{%dx|dx}", (IN8rr), 0>; def : InstAlias<"inw\t{%dx|dx}", (IN16rr), 0>; def : InstAlias<"inl\t{%dx|dx}", (IN32rr), 0>; -def : InstAlias<"inb\t$port", (IN8ri i8imm:$port), 0>; -def : InstAlias<"inw\t$port", (IN16ri i8imm:$port), 0>; -def : InstAlias<"inl\t$port", (IN32ri i8imm:$port), 0>; +def : InstAlias<"inb\t$port", (IN8ri u8imm:$port), 0>; +def : InstAlias<"inw\t$port", (IN16ri u8imm:$port), 0>; +def : InstAlias<"inl\t$port", (IN32ri u8imm:$port), 0>; // jmp and call aliases for lcall and ljmp. jmp $42,$5 -> ljmp @@ -2869,9 +2949,9 @@ def : InstAlias<"movzx {$src, $dst|$dst, $src}", (MOVZX64rr16_Q GR64:$dst, GR16: def : InstAlias<"outb\t{%dx|dx}", (OUT8rr), 0>; def : InstAlias<"outw\t{%dx|dx}", (OUT16rr), 0>; def : InstAlias<"outl\t{%dx|dx}", (OUT32rr), 0>; -def : InstAlias<"outb\t$port", (OUT8ir i8imm:$port), 0>; -def : InstAlias<"outw\t$port", (OUT16ir i8imm:$port), 0>; -def : InstAlias<"outl\t$port", (OUT32ir i8imm:$port), 0>; +def : InstAlias<"outb\t$port", (OUT8ir u8imm:$port), 0>; +def : InstAlias<"outw\t$port", (OUT16ir u8imm:$port), 0>; +def : InstAlias<"outl\t$port", (OUT32ir u8imm:$port), 0>; // 'sldt ' can be encoded with either sldtw or sldtq with the same // effect (both store to a 16-bit mem). Force to sldtw to avoid ambiguity @@ -2948,3 +3028,34 @@ def : InstAlias<"xchg{l}\t{%eax, $src|$src, eax}", def : InstAlias<"xchg{l}\t{%eax, $src|$src, eax}", (XCHG32ar64 GR32_NOAX:$src), 0>, Requires<[In64BitMode]>; def : InstAlias<"xchg{q}\t{%rax, $src|$src, rax}", (XCHG64ar GR64:$src), 0>; + +// These aliases exist to get the parser to prioritize matching 8-bit +// immediate encodings over matching the implicit ax/eax/rax encodings. By +// explicitly mentioning the A register here, these entries will be ordered +// first due to the more explicit immediate type. +def : InstAlias<"adc{w}\t{$imm, %ax|ax, $imm}", (ADC16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"add{w}\t{$imm, %ax|ax, $imm}", (ADD16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"and{w}\t{$imm, %ax|ax, $imm}", (AND16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"cmp{w}\t{$imm, %ax|ax, $imm}", (CMP16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"or{w}\t{$imm, %ax|ax, $imm}", (OR16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"sbb{w}\t{$imm, %ax|ax, $imm}", (SBB16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"sub{w}\t{$imm, %ax|ax, $imm}", (SUB16ri8 AX, i16i8imm:$imm), 0>; +def : InstAlias<"xor{w}\t{$imm, %ax|ax, $imm}", (XOR16ri8 AX, i16i8imm:$imm), 0>; + +def : InstAlias<"adc{l}\t{$imm, %eax|eax, $imm}", (ADC32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"add{l}\t{$imm, %eax|eax, $imm}", (ADD32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"and{l}\t{$imm, %eax|eax, $imm}", (AND32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"cmp{l}\t{$imm, %eax|eax, $imm}", (CMP32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"or{l}\t{$imm, %eax|eax, $imm}", (OR32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"sbb{l}\t{$imm, %eax|eax, $imm}", (SBB32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"sub{l}\t{$imm, %eax|eax, $imm}", (SUB32ri8 EAX, i32i8imm:$imm), 0>; +def : InstAlias<"xor{l}\t{$imm, %eax|eax, $imm}", (XOR32ri8 EAX, i32i8imm:$imm), 0>; + +def : InstAlias<"adc{q}\t{$imm, %rax|rax, $imm}", (ADC64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"add{q}\t{$imm, %rax|rax, $imm}", (ADD64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"and{q}\t{$imm, %rax|rax, $imm}", (AND64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"cmp{q}\t{$imm, %rax|rax, $imm}", (CMP64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"or{q}\t{$imm, %rax|rax, $imm}", (OR64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"sbb{q}\t{$imm, %rax|rax, $imm}", (SBB64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"sub{q}\t{$imm, %rax|rax, $imm}", (SUB64ri8 RAX, i64i8imm:$imm), 0>; +def : InstAlias<"xor{q}\t{$imm, %rax|rax, $imm}", (XOR64ri8 RAX, i64i8imm:$imm), 0>;