-//===- X86InstrInfo.td - Describe the X86 Instruction Set --*- tablegen -*-===//
+
//
// The LLVM Compiler Infrastructure
//
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 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,
def X86tcret : SDNode<"X86ISD::TC_RETURN", SDT_X86TCRET,
[SDNPHasChain, SDNPOptInFlag]>;
-def X86add_flag : SDNode<"X86ISD::ADD", SDTBinaryArithWithFlags>;
+def X86add_flag : SDNode<"X86ISD::ADD", SDTBinaryArithWithFlags,
+ [SDNPCommutative]>;
def X86sub_flag : SDNode<"X86ISD::SUB", SDTBinaryArithWithFlags>;
-def X86smul_flag : SDNode<"X86ISD::SMUL", SDTBinaryArithWithFlags>;
-def X86umul_flag : SDNode<"X86ISD::UMUL", SDTUnaryArithWithFlags>;
+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>;
// X86 Operand Definitions.
//
-def i32imm_pcrel : Operand<i32> {
- 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>;
let Name = "Mem";
let SuperClass = ?;
}
+def X86AbsMemAsmOperand : AsmOperandClass {
+ let Name = "AbsMem";
+ let SuperClass = X86MemAsmOperand;
+}
+def X86NoSegMemAsmOperand : AsmOperandClass {
+ let Name = "NoSegMem";
+ let SuperClass = 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 i256mem : X86MemOperand<"printi256mem">;
def f32mem : X86MemOperand<"printf32mem">;
def f64mem : X86MemOperand<"printf64mem">;
def f80mem : X86MemOperand<"printf80mem">;
def f128mem : X86MemOperand<"printf128mem">;
-def f256mem : X86MemOperand<"printf256mem">;
+//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 lea32mem : Operand<i32> {
let PrintMethod = "printlea32mem";
let MIOperandInfo = (ops GR32, i8imm, GR32_NOSP, i32imm);
- let ParserMatchClass = X86MemAsmOperand;
+ let ParserMatchClass = X86NoSegMemAsmOperand;
}
-def SSECC : Operand<i8> {
- let PrintMethod = "printSSECC";
+let ParserMatchClass = X86AbsMemAsmOperand,
+ PrintMethod = "print_pcrel_imm" in {
+def i32imm_pcrel : Operand<i32>;
+
+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 piclabel: Operand<i32> {
- let PrintMethod = "printPICLabel";
+def SSECC : Operand<i8> {
+ let PrintMethod = "printSSECC";
}
def ImmSExt8AsmOperand : AsmOperandClass {
let ParserMatchClass = ImmSExt8AsmOperand;
}
-// Branch targets have OtherVT type and print as pc-relative values.
-def brtarget : Operand<OtherVT> {
- let PrintMethod = "print_pcrel_imm";
-}
-
-def brtarget8 : Operand<OtherVT> {
- let PrintMethod = "print_pcrel_imm";
-}
-
//===----------------------------------------------------------------------===//
// X86 Complex Pattern Definitions.
//
def NearData : Predicate<"TM.getCodeModel() == CodeModel::Small ||"
"TM.getCodeModel() == CodeModel::Kernel">;
def IsStatic : Predicate<"TM.getRelocationModel() == Reloc::Static">;
+def OptForSize : Predicate<"OptForSize">;
def OptForSpeed : Predicate<"!OptForSize">;
def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">;
def CallImmAddr : Predicate<"Subtarget->IsLegalToCallImmediateAddr(TM)">;
def X86_COND_P : PatLeaf<(i8 14)>; // alt. COND_PE
def X86_COND_S : PatLeaf<(i8 15)>;
-def i16immSExt8 : PatLeaf<(i16 imm), [{
- // i16immSExt8 predicate - True if the 16-bit immediate fits in a 8-bit
- // sign extended field.
- return (int16_t)N->getZExtValue() == (int8_t)N->getZExtValue();
+def immSext8 : PatLeaf<(imm), [{
+ return N->getSExtValue() == (int8_t)N->getSExtValue();
}]>;
-def i32immSExt8 : PatLeaf<(i32 imm), [{
- // i32immSExt8 predicate - True if the 32-bit immediate fits in a 8-bit
- // sign extended field.
- return (int32_t)N->getZExtValue() == (int8_t)N->getZExtValue();
+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.
return false;
}]>;
-def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
+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()))
return false;
}]>;
-def nvloadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
- LoadSDNode *LD = cast<LoadSDNode>(N);
- if (const Value *Src = LD->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- if (LD->isVolatile())
- return false;
- ISD::LoadExtType ExtType = LD->getExtensionType();
- if (ExtType == ISD::NON_EXTLOAD)
- return true;
- if (ExtType == ISD::EXTLOAD)
- return LD->getAlignment() >= 4;
- return false;
-}]>;
-
-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;
-}]>;
-
-def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-
-def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
+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))>;
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());
+ else {
+ 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;
+ }
+}]>;
+
// 'shld' and 'shrd' instruction patterns. Note that even though these have
// the srl and shl in their patterns, the C++ code must still check for them,
// because predicates are tested before children nodes are explored.
}
// x86-64 va_start lowering magic.
-let usesCustomDAGSchedInserter = 1 in
+let usesCustomInserter = 1 in
def VASTART_SAVE_XMM_REGS : I<0, Pseudo,
(outs),
(ins GR8:$al,
// Nop
let neverHasSideEffects = 1 in {
def NOOP : I<0x90, RawFrm, (outs), (ins), "nop", []>;
+ def NOOPW : I<0x1f, MRM0m, (outs), (ins i16mem:$zero),
+ "nop{w}\t$zero", []>, TB, OpSize;
def NOOPL : I<0x1f, MRM0m, (outs), (ins i32mem:$zero),
- "nopl\t$zero", []>, TB;
+ "nop{l}\t$zero", []>, TB;
}
// Trap
-def INT3 : I<0xcc, RawFrm, (outs), (ins), "int 3", []>;
+def INT3 : I<0xcc, RawFrm, (outs), (ins), "int\t3", []>;
def INT : I<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
+// 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 piclabel:$label),
- "call\t$label\n\t"
- "pop{l}\t$reg", []>;
+ def MOVPC32r : Ii32<0xE8, Pseudo, (outs GR32:$reg), (ins i32imm:$label),
+ "", []>;
//===----------------------------------------------------------------------===//
-// Control Flow Instructions...
+// Control Flow Instructions.
//
// Return instructions.
[(X86retflag 0)]>;
def RETI : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops),
"ret\t$amt",
- [(X86retflag imm:$amt)]>;
+ [(X86retflag timm:$amt)]>;
+ def LRET : I <0xCB, RawFrm, (outs), (ins),
+ "lret", []>;
+ def LRETI : Ii16<0xCA, RawFrm, (outs), (ins i16imm:$amt),
+ "lret\t$amt", []>;
}
-// All branches are RawFrm, Void, Branch, and Terminators
-let isBranch = 1, isTerminator = 1 in
- class IBr<bits<8> opcode, dag ins, string asm, list<dag> pattern> :
- I<opcode, RawFrm, (outs), ins, asm, pattern>;
+// Unconditional branches.
+let isBarrier = 1, isBranch = 1, isTerminator = 1 in {
+ def JMP_4 : Ii32PCRel<0xE9, RawFrm, (outs), (ins brtarget:$dst),
+ "jmp\t$dst", [(br bb:$dst)]>;
+ def JMP_1 : Ii8PCRel<0xEB, RawFrm, (outs), (ins brtarget8:$dst),
+ "jmp\t$dst", []>;
+}
-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$dst", []>;
+// Conditional Branches.
+let isBranch = 1, isTerminator = 1, Uses = [EFLAGS] in {
+ multiclass ICBr<bits<8> opc1, bits<8> opc4, string asm, PatFrag Cond> {
+ def _1 : Ii8PCRel <opc1, RawFrm, (outs), (ins brtarget8:$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{*}$dst", []>;
}
-// Conditional branches
-let Uses = [EFLAGS] in {
-// Short conditional jumps
-def JO8 : IBr<0x70, (ins brtarget8:$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",
- [(X86brcond bb:$dst, X86_COND_NE, EFLAGS)]>, TB;
-def JL : IBr<0x8C, (ins brtarget:$dst), "jl\t$dst",
- [(X86brcond bb:$dst, X86_COND_L, EFLAGS)]>, TB;
-def JLE : IBr<0x8E, (ins brtarget:$dst), "jle\t$dst",
- [(X86brcond bb:$dst, X86_COND_LE, EFLAGS)]>, TB;
-def JG : IBr<0x8F, (ins brtarget:$dst), "jg\t$dst",
- [(X86brcond bb:$dst, X86_COND_G, EFLAGS)]>, TB;
-def JGE : IBr<0x8D, (ins brtarget:$dst), "jge\t$dst",
- [(X86brcond bb:$dst, X86_COND_GE, EFLAGS)]>, TB;
-
-def JB : IBr<0x82, (ins brtarget:$dst), "jb\t$dst",
- [(X86brcond bb:$dst, X86_COND_B, EFLAGS)]>, TB;
-def JBE : IBr<0x86, (ins brtarget:$dst), "jbe\t$dst",
- [(X86brcond bb:$dst, X86_COND_BE, EFLAGS)]>, TB;
-def JA : IBr<0x87, (ins brtarget:$dst), "ja\t$dst",
- [(X86brcond bb:$dst, X86_COND_A, EFLAGS)]>, TB;
-def JAE : IBr<0x83, (ins brtarget:$dst), "jae\t$dst",
- [(X86brcond bb:$dst, X86_COND_AE, EFLAGS)]>, TB;
-
-def JS : IBr<0x88, (ins brtarget:$dst), "js\t$dst",
- [(X86brcond bb:$dst, X86_COND_S, EFLAGS)]>, TB;
-def JNS : IBr<0x89, (ins brtarget:$dst), "jns\t$dst",
- [(X86brcond bb:$dst, X86_COND_NS, EFLAGS)]>, TB;
-def JP : IBr<0x8A, (ins brtarget:$dst), "jp\t$dst",
- [(X86brcond bb:$dst, X86_COND_P, EFLAGS)]>, TB;
-def JNP : IBr<0x8B, (ins brtarget:$dst), "jnp\t$dst",
- [(X86brcond bb:$dst, X86_COND_NP, EFLAGS)]>, TB;
-def JO : IBr<0x80, (ins brtarget:$dst), "jo\t$dst",
- [(X86brcond bb:$dst, X86_COND_O, EFLAGS)]>, TB;
-def JNO : IBr<0x81, (ins brtarget:$dst), "jno\t$dst",
- [(X86brcond bb:$dst, X86_COND_NO, EFLAGS)]>, TB;
-} // Uses = [EFLAGS]
+
+// Loop instructions
+
+def LOOP : I<0xE2, RawFrm, (ins brtarget8:$dst), (outs), "loop\t$dst", []>;
+def LOOPE : I<0xE1, RawFrm, (ins brtarget8:$dst), (outs), "loope\t$dst", []>;
+def LOOPNE : I<0xE0, RawFrm, (ins brtarget8:$dst), (outs), "loopne\t$dst", []>;
//===----------------------------------------------------------------------===//
// Call Instructions...
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
Uses = [ESP] in {
- def CALLpcrel32 : Ii32<0xE8, RawFrm,
+ def CALLpcrel32 : Ii32PCRel<0xE8, RawFrm,
(outs), (ins i32imm_pcrel:$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{*}$dst", []>;
}
+// Constructing a stack frame.
+
+def ENTER : I<0xC8, RawFrm, (outs), (ins i16imm:$len, i8imm:$lvl),
+ "enter\t$len, $lvl", []>;
+
// Tail call stuff.
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
-def TCRETURNdi : I<0, Pseudo, (outs), (ins i32imm:$dst, i32imm:$offset, variable_ops),
+def TCRETURNdi : I<0, Pseudo, (outs),
+ (ins i32imm:$dst, i32imm:$offset, variable_ops),
"#TC_RETURN $dst $offset",
[]>;
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
-def TCRETURNri : I<0, Pseudo, (outs), (ins GR32:$dst, i32imm:$offset, variable_ops),
+def TCRETURNri : I<0, Pseudo, (outs),
+ (ins GR32:$dst, i32imm:$offset, variable_ops),
"#TC_RETURN $dst $offset",
[]>;
-let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
-
- def TAILJMPd : IBr<0xE9, (ins i32imm_pcrel:$dst), "jmp\t$dst # TAILCALL",
+// FIXME: The should be pseudo instructions that are lowered when going to
+// mcinst.
+let isCall = 1, isBranch = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
+ def TAILJMPd : Ii32<0xE9, RawFrm, (outs),(ins i32imm_pcrel:$dst,variable_ops),
+ "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{*}$dst # TAILCALL",
+ def TAILJMPr : I<0xFF, MRM4r, (outs), (ins GR32:$dst, variable_ops),
+ "jmp{l}\t{*}$dst # TAILCALL",
[]>;
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
- def TAILJMPm : I<0xFF, MRM4m, (outs), (ins i32mem:$dst),
+ def TAILJMPm : I<0xFF, MRM4m, (outs), (ins i32mem:$dst, variable_ops),
"jmp\t{*}$dst # TAILCALL", []>;
//===----------------------------------------------------------------------===//
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, $src}", []>, OpSize, XS;
+def POPCNT16rm : I<0xB8, MRMSrcMem, (outs GR16:$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, $src}", []>, XS;
+def POPCNT32rm : I<0xB8, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$src),
+ "popcnt{l}\t{$src, $dst|$dst, $src}", []>, XS;
+
let Defs = [ESP], Uses = [ESP], neverHasSideEffects=1 in {
-let mayLoad = 1 in
-def POP32r : I<0x58, AddRegFrm, (outs GR32:$reg), (ins), "pop{l}\t$reg", []>;
+let mayLoad = 1 in {
+def POP16r : I<0x58, AddRegFrm, (outs GR16:$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$dst", []>;
+}
-let mayStore = 1 in
+let mayStore = 1 in {
+def PUSH16r : I<0x50, AddRegFrm, (outs), (ins GR16:$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$src",[]>;
+}
}
let Defs = [ESP], Uses = [ESP], neverHasSideEffects = 1, mayStore = 1 in {
"push{l}\t$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
-def PUSHFD : I<0x9C, RawFrm, (outs), (ins), "pushf", []>;
+let Defs = [ESP, EFLAGS], Uses = [ESP], mayLoad = 1, neverHasSideEffects=1 in {
+def POPF : I<0x9D, RawFrm, (outs), (ins), "popf{w}", []>, OpSize;
+def POPFD : I<0x9D, RawFrm, (outs), (ins), "popf{l}", []>;
+}
+let Defs = [ESP], Uses = [ESP, EFLAGS], mayStore = 1, neverHasSideEffects=1 in {
+def PUSHF : I<0x9C, RawFrm, (outs), (ins), "pushf{w}", []>, OpSize;
+def PUSHFD : I<0x9C, RawFrm, (outs), (ins), "pushf{l}", []>;
+}
let isTwoAddress = 1 in // GR32 = bswap GR32
def BSWAP32r : I<0xC8, AddRegFrm,
let neverHasSideEffects = 1 in
def LEA16r : I<0x8D, MRMSrcMem,
- (outs GR16:$dst), (ins i32mem:$src),
+ (outs GR16:$dst), (ins lea32mem:$src),
"lea{w}\t{$src|$dst}, {$dst|$src}", []>, OpSize;
let isReMaterializable = 1 in
def LEA32r : I<0x8D, MRMSrcMem,
"lea{l}\t{$src|$dst}, {$dst|$src}",
[(set GR32:$dst, lea32addr:$src)]>, Requires<[In32BitMode]>;
-let Defs = [ECX,EDI,ESI], Uses = [ECX,EDI,ESI] in {
+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 i32)]>, REP;
}
-let Defs = [ECX,EDI], Uses = [AL,ECX,EDI] in
+// 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] in
+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] in
+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 isBarrier = 1, hasCtrlDep = 1 in {
def TRAP : I<0x0B, RawFrm, (outs), (ins), "ud2", [(trap)]>, TB;
}
def SYSEXIT : I<0x35, RawFrm,
(outs), (ins), "sysexit", []>, TB;
+def WAIT : I<0x9B, RawFrm, (outs), (ins), "wait", []>;
//===----------------------------------------------------------------------===//
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...
//
"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:$dst)]>;
"mov{l}\t{$src, $dst|$dst, $src}",
[(store (i32 imm:$src), addr:$dst)]>;
-let canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
+def MOV8o8a : Ii8 <0xA0, RawFrm, (outs), (ins offset8:$src),
+ "mov{b}\t{$src, %al|%al, $src}", []>;
+def MOV16o16a : Ii16 <0xA1, RawFrm, (outs), (ins offset16:$src),
+ "mov{w}\t{$src, %ax|%ax, $src}", []>, OpSize;
+def MOV32o32a : Ii32 <0xA1, RawFrm, (outs), (ins offset32:$src),
+ "mov{l}\t{$src, %eax|%eax, $src}", []>;
+
+def MOV8ao8 : Ii8 <0xA2, RawFrm, (outs offset8:$dst), (ins),
+ "mov{b}\t{%al, $dst|$dst, %al}", []>;
+def MOV16ao16 : Ii16 <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, $src}", []>;
+def MOV16ms : I<0x8C, MRMDestMem, (outs i16mem:$dst), (ins SEGMENT_REG:$src),
+ "mov{w}\t{$src, $dst|$dst, $src}", []>;
+def MOV16sr : I<0x8E, MRMSrcReg, (outs SEGMENT_REG:$dst), (ins GR16:$src),
+ "mov{w}\t{$src, $dst|$dst, $src}", []>;
+def MOV16sm : I<0x8E, MRMSrcMem, (outs SEGMENT_REG:$dst), (ins i16mem:$src),
+ "mov{w}\t{$src, $dst|$dst, $src}", []>;
+
+def MOV8rr_REV : I<0x8A, MRMSrcReg, (outs GR8:$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:$src))]>;
(outs), (ins i8mem_NOREX:$dst, GR8_NOREX:$src),
"mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>;
let mayLoad = 1,
- canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in
+ canFoldAsLoad = 1, isReMaterializable = 1 in
def MOV8rm_NOREX : I<0x8A, MRMSrcMem,
(outs GR8_NOREX:$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_32:$src),
+ "mov{q}\t{$src, $dst|$dst, $src}", []>, TB;
+def MOV32cr : I<0x22, MRMSrcReg, (outs CONTROL_REG_32:$dst), (ins GR32:$src),
+ "mov{q}\t{$src, $dst|$dst, $src}", []>, TB;
+
//===----------------------------------------------------------------------===//
// Fixed-Register Multiplication and Division Instructions...
//
// Extra precision multiplication
-let Defs = [AL,AH,EFLAGS], Uses = [AL] in
+
+// AL is really implied by AX, by the registers in Defs must match the
+// SDNode results (i8, i32).
+let Defs = [AL,EFLAGS,AX], Uses = [AL] in
def MUL8r : I<0xF6, MRM4r, (outs), (ins GR8:$src), "mul{b}\t$src",
// FIXME: Used for 8-bit mul, ignore result upper 8 bits.
// This probably ought to be moved to a def : Pat<> if the
"mul{l}\t$src",
[]>; // EAX,EDX = EAX*GR32
-let Defs = [AL,AH,EFLAGS], Uses = [AL] in
+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.
}
let neverHasSideEffects = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AL] 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 IMUL32r : I<0xF7, MRM5r, (outs), (ins GR32:$src), "imul{l}\t$src", []>;
// EAX,EDX = EAX*GR32
let mayLoad = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AL] 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], Uses = [EAX] in
+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,AH,EFLAGS], Uses = [AX] in
-def DIV8r : I<0xF6, MRM6r, (outs), (ins GR8:$src), // AX/r8 = AL,AH
+let Defs = [AL,EFLAGS,AX], Uses = [AX] in
+def DIV8r : I<0xF6, MRM6r, (outs), (ins GR8:$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
+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:$src), // EDX:EAX/r32 = EAX,EDX
+def DIV32r : I<0xF7, MRM6r, (outs), (ins GR32:$src), // EDX:EAX/r32 = EAX,EDX
"div{l}\t$src", []>;
let mayLoad = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
-def DIV8m : I<0xF6, MRM6m, (outs), (ins i8mem:$src), // AX/[mem8] = AL,AH
+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:$src), // DX:AX/[mem16] = AX,DX
+def DIV16m : I<0xF7, MRM6m, (outs), (ins i16mem:$src), // DX:AX/[mem16] = AX,DX
"div{w}\t$src", []>, OpSize;
let Defs = [EAX,EDX,EFLAGS], Uses = [EAX,EDX] in
-def DIV32m : I<0xF7, MRM6m, (outs), (ins i32mem:$src), // EDX:EAX/[mem32] = EAX,EDX
+ // EDX:EAX/[mem32] = EAX,EDX
+def DIV32m : I<0xF7, MRM6m, (outs), (ins i32mem:$src),
"div{l}\t$src", []>;
}
// Signed division/remainder.
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
-def IDIV8r : I<0xF6, MRM7r, (outs), (ins GR8:$src), // AX/r8 = AL,AH
+let Defs = [AL,EFLAGS,AX], Uses = [AX] in
+def IDIV8r : I<0xF6, MRM7r, (outs), (ins GR8:$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
+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:$src), // EDX:EAX/r32 = EAX,EDX
+def IDIV32r: I<0xF7, MRM7r, (outs), (ins GR32:$src), // EDX:EAX/r32 = EAX,EDX
"idiv{l}\t$src", []>;
let mayLoad = 1, mayLoad = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
-def IDIV8m : I<0xF6, MRM7m, (outs), (ins i8mem:$src), // AX/[mem8] = AL,AH
+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:$src), // DX:AX/[mem16] = AX,DX
+def IDIV16m: I<0xF7, MRM7m, (outs), (ins i16mem:$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
+def IDIV32m: I<0xF7, MRM7m, (outs), (ins i32mem:$src),
+ // EDX:EAX/[mem32] = EAX,EDX
"idiv{l}\t$src", []>;
}
// Conditional moves
let Uses = [EFLAGS] in {
-// X86 doesn't have 8-bit conditional moves. Use a customDAGSchedInserter to
+// 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 usesCustomDAGSchedInserter = 1, isTwoAddress = 0, Defs = [EFLAGS] in
+let usesCustomInserter = 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!",
let isCommutable = 1 in {
def CMOVB16rr : I<0x42, MRMSrcReg, // if <u, GR16 = GR16
(outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
- "cmovb\t{$src2, $dst|$dst, $src2}",
+ "cmovb{w}\t{$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:$src2),
- "cmovb\t{$src2, $dst|$dst, $src2}",
+ "cmovb{l}\t{$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:$src2),
- "cmovae\t{$src2, $dst|$dst, $src2}",
+ "cmovae{w}\t{$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:$src2),
- "cmovae\t{$src2, $dst|$dst, $src2}",
+ "cmovae{l}\t{$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:$src2),
- "cmove\t{$src2, $dst|$dst, $src2}",
+ "cmove{w}\t{$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:$src2),
- "cmove\t{$src2, $dst|$dst, $src2}",
+ "cmove{l}\t{$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:$src2),
- "cmovne\t{$src2, $dst|$dst, $src2}",
+ "cmovne{w}\t{$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:$src2),
- "cmovne\t{$src2, $dst|$dst, $src2}",
+ "cmovne{l}\t{$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:$src2),
- "cmovbe\t{$src2, $dst|$dst, $src2}",
+ "cmovbe{w}\t{$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:$src2),
- "cmovbe\t{$src2, $dst|$dst, $src2}",
+ "cmovbe{l}\t{$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:$src2),
- "cmova\t{$src2, $dst|$dst, $src2}",
+ "cmova{w}\t{$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:$src2),
- "cmova\t{$src2, $dst|$dst, $src2}",
+ "cmova{l}\t{$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:$src2),
- "cmovl\t{$src2, $dst|$dst, $src2}",
+ "cmovl{w}\t{$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:$src2),
- "cmovl\t{$src2, $dst|$dst, $src2}",
+ "cmovl{l}\t{$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:$src2),
- "cmovge\t{$src2, $dst|$dst, $src2}",
+ "cmovge{w}\t{$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:$src2),
- "cmovge\t{$src2, $dst|$dst, $src2}",
+ "cmovge{l}\t{$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:$src2),
- "cmovle\t{$src2, $dst|$dst, $src2}",
+ "cmovle{w}\t{$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:$src2),
- "cmovle\t{$src2, $dst|$dst, $src2}",
+ "cmovle{l}\t{$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:$src2),
- "cmovg\t{$src2, $dst|$dst, $src2}",
+ "cmovg{w}\t{$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:$src2),
- "cmovg\t{$src2, $dst|$dst, $src2}",
+ "cmovg{l}\t{$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:$src2),
- "cmovs\t{$src2, $dst|$dst, $src2}",
+ "cmovs{w}\t{$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:$src2),
- "cmovs\t{$src2, $dst|$dst, $src2}",
+ "cmovs{l}\t{$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:$src2),
- "cmovns\t{$src2, $dst|$dst, $src2}",
+ "cmovns{w}\t{$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:$src2),
- "cmovns\t{$src2, $dst|$dst, $src2}",
+ "cmovns{l}\t{$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:$src2),
- "cmovp\t{$src2, $dst|$dst, $src2}",
+ "cmovp{w}\t{$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:$src2),
- "cmovp\t{$src2, $dst|$dst, $src2}",
+ "cmovp{l}\t{$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:$src2),
- "cmovnp\t{$src2, $dst|$dst, $src2}",
+ "cmovnp{w}\t{$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:$src2),
- "cmovnp\t{$src2, $dst|$dst, $src2}",
+ "cmovnp{l}\t{$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:$src2),
- "cmovo\t{$src2, $dst|$dst, $src2}",
+ "cmovo{w}\t{$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:$src2),
- "cmovo\t{$src2, $dst|$dst, $src2}",
+ "cmovo{l}\t{$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:$src2),
- "cmovno\t{$src2, $dst|$dst, $src2}",
+ "cmovno{w}\t{$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:$src2),
- "cmovno\t{$src2, $dst|$dst, $src2}",
+ "cmovno{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (X86cmov GR32:$src1, GR32:$src2,
X86_COND_NO, EFLAGS))]>,
TB;
def CMOVB16rm : I<0x42, MRMSrcMem, // if <u, GR16 = [mem16]
(outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
- "cmovb\t{$src2, $dst|$dst, $src2}",
+ "cmovb{w}\t{$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:$src2),
- "cmovb\t{$src2, $dst|$dst, $src2}",
+ "cmovb{l}\t{$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:$src2),
- "cmovae\t{$src2, $dst|$dst, $src2}",
+ "cmovae{w}\t{$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:$src2),
- "cmovae\t{$src2, $dst|$dst, $src2}",
+ "cmovae{l}\t{$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:$src2),
- "cmove\t{$src2, $dst|$dst, $src2}",
+ "cmove{w}\t{$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:$src2),
- "cmove\t{$src2, $dst|$dst, $src2}",
+ "cmove{l}\t{$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:$src2),
- "cmovne\t{$src2, $dst|$dst, $src2}",
+ "cmovne{w}\t{$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:$src2),
- "cmovne\t{$src2, $dst|$dst, $src2}",
+ "cmovne{l}\t{$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:$src2),
- "cmovbe\t{$src2, $dst|$dst, $src2}",
+ "cmovbe{w}\t{$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:$src2),
- "cmovbe\t{$src2, $dst|$dst, $src2}",
+ "cmovbe{l}\t{$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:$src2),
- "cmova\t{$src2, $dst|$dst, $src2}",
+ "cmova{w}\t{$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:$src2),
- "cmova\t{$src2, $dst|$dst, $src2}",
+ "cmova{l}\t{$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:$src2),
- "cmovl\t{$src2, $dst|$dst, $src2}",
+ "cmovl{w}\t{$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:$src2),
- "cmovl\t{$src2, $dst|$dst, $src2}",
+ "cmovl{l}\t{$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:$src2),
- "cmovge\t{$src2, $dst|$dst, $src2}",
+ "cmovge{w}\t{$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:$src2),
- "cmovge\t{$src2, $dst|$dst, $src2}",
+ "cmovge{l}\t{$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:$src2),
- "cmovle\t{$src2, $dst|$dst, $src2}",
+ "cmovle{w}\t{$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:$src2),
- "cmovle\t{$src2, $dst|$dst, $src2}",
+ "cmovle{l}\t{$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:$src2),
- "cmovg\t{$src2, $dst|$dst, $src2}",
+ "cmovg{w}\t{$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:$src2),
- "cmovg\t{$src2, $dst|$dst, $src2}",
+ "cmovg{l}\t{$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:$src2),
- "cmovs\t{$src2, $dst|$dst, $src2}",
+ "cmovs{w}\t{$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:$src2),
- "cmovs\t{$src2, $dst|$dst, $src2}",
+ "cmovs{l}\t{$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:$src2),
- "cmovns\t{$src2, $dst|$dst, $src2}",
+ "cmovns{w}\t{$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:$src2),
- "cmovns\t{$src2, $dst|$dst, $src2}",
+ "cmovns{l}\t{$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:$src2),
- "cmovp\t{$src2, $dst|$dst, $src2}",
+ "cmovp{w}\t{$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:$src2),
- "cmovp\t{$src2, $dst|$dst, $src2}",
+ "cmovp{l}\t{$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:$src2),
- "cmovnp\t{$src2, $dst|$dst, $src2}",
+ "cmovnp{w}\t{$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:$src2),
- "cmovnp\t{$src2, $dst|$dst, $src2}",
+ "cmovnp{l}\t{$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:$src2),
- "cmovo\t{$src2, $dst|$dst, $src2}",
+ "cmovo{w}\t{$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:$src2),
- "cmovo\t{$src2, $dst|$dst, $src2}",
+ "cmovo{l}\t{$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:$src2),
- "cmovno\t{$src2, $dst|$dst, $src2}",
+ "cmovno{w}\t{$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:$src2),
- "cmovno\t{$src2, $dst|$dst, $src2}",
+ "cmovno{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (X86cmov GR32:$src1, (loadi32 addr:$src2),
X86_COND_NO, EFLAGS))]>,
TB;
[(set GR8:$dst, (add GR8:$src, 1)),
(implicit EFLAGS)]>;
let isConvertibleToThreeAddress = 1, CodeSize = 1 in { // Can xform into LEA.
-def INC16r : I<0x40, AddRegFrm, (outs GR16:$dst), (ins GR16:$src), "inc{w}\t$dst",
+def INC16r : I<0x40, AddRegFrm, (outs GR16:$dst), (ins GR16:$src),
+ "inc{w}\t$dst",
[(set GR16:$dst, (add GR16:$src, 1)),
(implicit EFLAGS)]>,
OpSize, Requires<[In32BitMode]>;
-def INC32r : I<0x40, AddRegFrm, (outs GR32:$dst), (ins GR32:$src), "inc{l}\t$dst",
+def INC32r : I<0x40, AddRegFrm, (outs GR32:$dst), (ins GR32:$src),
+ "inc{l}\t$dst",
[(set GR32:$dst, (add GR32:$src, 1)),
(implicit EFLAGS)]>, Requires<[In32BitMode]>;
}
[(set GR8:$dst, (add GR8:$src, -1)),
(implicit EFLAGS)]>;
let isConvertibleToThreeAddress = 1, CodeSize = 1 in { // Can xform into LEA.
-def DEC16r : I<0x48, AddRegFrm, (outs GR16:$dst), (ins GR16:$src), "dec{w}\t$dst",
+def DEC16r : I<0x48, AddRegFrm, (outs GR16:$dst), (ins GR16:$src),
+ "dec{w}\t$dst",
[(set GR16:$dst, (add GR16:$src, -1)),
(implicit EFLAGS)]>,
OpSize, Requires<[In32BitMode]>;
-def DEC32r : I<0x48, AddRegFrm, (outs GR32:$dst), (ins GR32:$src), "dec{l}\t$dst",
+def DEC32r : I<0x48, AddRegFrm, (outs GR32:$dst), (ins GR32:$src),
+ "dec{l}\t$dst",
[(set GR32:$dst, (add GR32:$src, -1)),
(implicit EFLAGS)]>, Requires<[In32BitMode]>;
}
(implicit EFLAGS)]>;
}
+// AND instructions with the destination register in REG and the source register
+// in R/M. Included for the disassembler.
+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, $src2}",
"and{l}\t{$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, $src}", []>;
+
}
let isCommutable = 1 in { // X = OR Y, Z --> X = OR Z, Y
-def OR8rr : I<0x08, MRMDestReg, (outs GR8 :$dst), (ins GR8 :$src1, GR8 :$src2),
+def OR8rr : I<0x08, MRMDestReg, (outs GR8 :$dst),
+ (ins GR8 :$src1, GR8 :$src2),
"or{b}\t{$src2, $dst|$dst, $src2}",
[(set GR8:$dst, (or GR8:$src1, GR8:$src2)),
(implicit EFLAGS)]>;
-def OR16rr : I<0x09, MRMDestReg, (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
+def OR16rr : I<0x09, MRMDestReg, (outs GR16:$dst),
+ (ins GR16:$src1, GR16:$src2),
"or{w}\t{$src2, $dst|$dst, $src2}",
[(set GR16:$dst, (or GR16:$src1, GR16:$src2)),
(implicit EFLAGS)]>, OpSize;
-def OR32rr : I<0x09, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
+def OR32rr : I<0x09, MRMDestReg, (outs GR32:$dst),
+ (ins GR32:$src1, GR32:$src2),
"or{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (or GR32:$src1, GR32:$src2)),
(implicit EFLAGS)]>;
}
-def OR8rm : I<0x0A, MRMSrcMem , (outs GR8 :$dst), (ins GR8 :$src1, i8mem :$src2),
+
+// OR instructions with the destination register in REG and the source register
+// in R/M. Included for the disassembler.
+def OR8rr_REV : I<0x0A, MRMSrcReg, (outs GR8:$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, (or GR8:$src1, (load addr:$src2))),
(implicit EFLAGS)]>;
-def OR16rm : I<0x0B, MRMSrcMem , (outs GR16:$dst), (ins GR16:$src1, i16mem:$src2),
+def OR16rm : I<0x0B, MRMSrcMem , (outs GR16:$dst),
+ (ins GR16:$src1, i16mem:$src2),
"or{w}\t{$src2, $dst|$dst, $src2}",
[(set GR16:$dst, (or GR16:$src1, (load addr:$src2))),
(implicit EFLAGS)]>, OpSize;
-def OR32rm : I<0x0B, MRMSrcMem , (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
+def OR32rm : I<0x0B, MRMSrcMem , (outs GR32:$dst),
+ (ins GR32:$src1, i32mem:$src2),
"or{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (or GR32:$src1, (load addr:$src2))),
(implicit EFLAGS)]>;
-def OR8ri : Ii8 <0x80, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2),
+def OR8ri : Ii8 <0x80, MRM1r, (outs GR8 :$dst),
+ (ins GR8 :$src1, i8imm:$src2),
"or{b}\t{$src2, $dst|$dst, $src2}",
[(set GR8:$dst, (or GR8:$src1, imm:$src2)),
(implicit EFLAGS)]>;
-def OR16ri : Ii16<0x81, MRM1r, (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2),
+def OR16ri : Ii16<0x81, MRM1r, (outs GR16:$dst),
+ (ins GR16:$src1, i16imm:$src2),
"or{w}\t{$src2, $dst|$dst, $src2}",
[(set GR16:$dst, (or GR16:$src1, imm:$src2)),
(implicit EFLAGS)]>, OpSize;
-def OR32ri : Ii32<0x81, MRM1r, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
+def OR32ri : Ii32<0x81, MRM1r, (outs GR32:$dst),
+ (ins GR32:$src1, i32imm:$src2),
"or{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (or GR32:$src1, imm:$src2)),
(implicit EFLAGS)]>;
-def OR16ri8 : Ii8<0x83, MRM1r, (outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2),
+def OR16ri8 : Ii8<0x83, MRM1r, (outs GR16:$dst),
+ (ins GR16:$src1, i16i8imm:$src2),
"or{w}\t{$src2, $dst|$dst, $src2}",
[(set GR16:$dst, (or GR16:$src1, i16immSExt8:$src2)),
(implicit EFLAGS)]>, OpSize;
-def OR32ri8 : Ii8<0x83, MRM1r, (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
+def OR32ri8 : Ii8<0x83, MRM1r, (outs GR32:$dst),
+ (ins GR32:$src1, i32i8imm:$src2),
"or{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (or GR32:$src1, i32immSExt8:$src2)),
(implicit EFLAGS)]>;
"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, $src}", []>;
} // isTwoAddress = 0
(implicit EFLAGS)]>;
} // isCommutable = 1
+// XOR instructions with the destination register in REG and the source register
+// in R/M. Included for the disassembler.
+def XOR8rr_REV : I<0x32, MRMSrcReg, (outs GR8:$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, $src2}",
"xor{l}\t{$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, $src}", []>;
} // isTwoAddress = 0
} // Defs = [EFLAGS]
def SHL32ri : Ii8<0xC1, MRM4r, (outs GR32:$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 use shifts of a register by one, because 'add reg,reg' is
-// cheaper.
+
+// 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$dst", []>;
+
} // isConvertibleToThreeAddress = 1
let isTwoAddress = 0 in {
}
// Rotate instructions
+
+def RCL8r1 : I<0xD0, MRM2r, (outs GR8:$dst), (ins GR8:$src),
+ "rcl{b}\t{1, $dst|$dst, 1}", []>;
+let Uses = [CL] in {
+def RCL8rCL : I<0xD2, MRM2r, (outs GR8:$dst), (ins GR8:$src),
+ "rcl{b}\t{%cl, $dst|$dst, CL}", []>;
+}
+def RCL8ri : Ii8<0xC0, MRM2r, (outs GR8:$dst), (ins GR8:$src, i8imm:$cnt),
+ "rcl{b}\t{$cnt, $dst|$dst, $cnt}", []>;
+
+def RCL16r1 : I<0xD1, MRM2r, (outs GR16:$dst), (ins GR16:$src),
+ "rcl{w}\t{1, $dst|$dst, 1}", []>, OpSize;
+let Uses = [CL] in {
+def RCL16rCL : I<0xD3, MRM2r, (outs GR16:$dst), (ins GR16:$src),
+ "rcl{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
+}
+def RCL16ri : Ii8<0xC1, MRM2r, (outs GR16:$dst), (ins GR16:$src, i8imm:$cnt),
+ "rcl{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize;
+
+def RCL32r1 : I<0xD1, MRM2r, (outs GR32:$dst), (ins GR32:$src),
+ "rcl{l}\t{1, $dst|$dst, 1}", []>;
+let Uses = [CL] in {
+def RCL32rCL : I<0xD3, MRM2r, (outs GR32:$dst), (ins GR32:$src),
+ "rcl{l}\t{%cl, $dst|$dst, CL}", []>;
+}
+def RCL32ri : Ii8<0xC1, MRM2r, (outs GR32:$dst), (ins GR32:$src, i8imm:$cnt),
+ "rcl{l}\t{$cnt, $dst|$dst, $cnt}", []>;
+
+def RCR8r1 : I<0xD0, MRM3r, (outs GR8:$dst), (ins GR8:$src),
+ "rcr{b}\t{1, $dst|$dst, 1}", []>;
+let Uses = [CL] in {
+def RCR8rCL : I<0xD2, MRM3r, (outs GR8:$dst), (ins GR8:$src),
+ "rcr{b}\t{%cl, $dst|$dst, CL}", []>;
+}
+def RCR8ri : Ii8<0xC0, MRM3r, (outs GR8:$dst), (ins GR8:$src, i8imm:$cnt),
+ "rcr{b}\t{$cnt, $dst|$dst, $cnt}", []>;
+
+def RCR16r1 : I<0xD1, MRM3r, (outs GR16:$dst), (ins GR16:$src),
+ "rcr{w}\t{1, $dst|$dst, 1}", []>, OpSize;
+let Uses = [CL] in {
+def RCR16rCL : I<0xD3, MRM3r, (outs GR16:$dst), (ins GR16:$src),
+ "rcr{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
+}
+def RCR16ri : Ii8<0xC1, MRM3r, (outs GR16:$dst), (ins GR16:$src, i8imm:$cnt),
+ "rcr{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize;
+
+def RCR32r1 : I<0xD1, MRM3r, (outs GR32:$dst), (ins GR32:$src),
+ "rcr{l}\t{1, $dst|$dst, 1}", []>;
+let Uses = [CL] in {
+def RCR32rCL : I<0xD3, MRM3r, (outs GR32:$dst), (ins GR32:$src),
+ "rcr{l}\t{%cl, $dst|$dst, CL}", []>;
+}
+def RCR32ri : Ii8<0xC1, MRM3r, (outs GR32:$dst), (ins GR32:$src, i8imm:$cnt),
+ "rcr{l}\t{$cnt, $dst|$dst, $cnt}", []>;
+
+let isTwoAddress = 0 in {
+def RCL8m1 : I<0xD0, MRM2m, (outs), (ins i8mem:$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}", []>;
+}
+}
+
// FIXME: provide shorter instructions when imm8 == 1
let Uses = [CL] in {
def ROL8rCL : I<0xD2, MRM0r, (outs GR8 :$dst), (ins GR8 :$src),
[(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;
+ [(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)))]>;
[(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;
+ [(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)))]>;
// Double shift instructions (generalizations of rotate)
let Uses = [CL] in {
-def SHLD32rrCL : I<0xA5, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
+def SHLD32rrCL : I<0xA5, MRMDestReg, (outs GR32:$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:$src2),
+def SHRD32rrCL : I<0xAD, MRMDestReg, (outs GR32:$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:$src2),
+def SHLD16rrCL : I<0xA5, MRMDestReg, (outs GR16:$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:$src2),
+def SHRD16rrCL : I<0xAD, MRMDestReg, (outs GR16:$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),
+ (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:$src3),
+ (outs GR32:$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:$src3),
+ (outs GR16:$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:$src3),
+ (outs GR16:$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:$src3)))]>,
"add{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (add GR32:$src1, (load addr:$src2))),
(implicit EFLAGS)]>;
+
+// Register-Register Addition - Equivalent to the normal rr forms (ADD8rr,
+// ADD16rr, and ADD32rr), but differently encoded.
+def ADD8mrmrr: I<0x02, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2),
+ "add{b}\t{$src2, $dst|$dst, $src2}", []>;
+def ADD16mrmrr: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2),
+ "add{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize;
+def ADD32mrmrr: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2),
+ "add{l}\t{$src2, $dst|$dst, $src2}", []>;
// Register-Integer Addition
def ADD8ri : Ii8<0x80, MRM0r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2),
// addition to rAX
def ADD8i8 : Ii8<0x04, RawFrm, (outs), (ins i8imm:$src),
- "add\t{$src, %al|%al, $src}", []>;
+ "add{b}\t{$src, %al|%al, $src}", []>;
def ADD16i16 : Ii16<0x05, RawFrm, (outs), (ins i16imm:$src),
- "add\t{$src, %ax|%ax, $src}", []>, OpSize;
+ "add{w}\t{$src, %ax|%ax, $src}", []>, OpSize;
def ADD32i32 : Ii32<0x05, RawFrm, (outs), (ins i32imm:$src),
- "add\t{$src, %eax|%eax, $src}", []>;
+ "add{l}\t{$src, %eax|%eax, $src}", []>;
}
let Uses = [EFLAGS] in {
"adc{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (adde GR32:$src1, GR32:$src2))]>;
}
+
+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, $src2}",
def ADC32mi8 : Ii8<0x83, MRM2m, (outs), (ins i32mem:$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, $src}", []>;
}
} // Uses = [EFLAGS]
[(set GR32:$dst, (sub GR32:$src1, GR32:$src2)),
(implicit EFLAGS)]>;
+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),
[(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, $src}", []>;
}
let Uses = [EFLAGS] in {
def SBB32mr : I<0x19, MRMDestMem, (outs), (ins i32mem:$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, $src2}",
+ def SBB8mi : Ii8<0x80, MRM3m, (outs), (ins i8mem:$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, $src2}",
def SBB32mi8 : Ii8<0x83, MRM3m, (outs), (ins i32mem:$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, $src}", []>;
}
+
+def SBB8rr_REV : I<0x1A, MRMSrcReg, (outs GR8:$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)))]>;
"imul{w}\t{$src2, $dst|$dst, $src2}",
[(set GR16:$dst, (mul GR16:$src1, (load addr:$src2))),
(implicit EFLAGS)]>, TB, OpSize;
-def IMUL32rm : I<0xAF, MRMSrcMem, (outs GR32:$dst), (ins GR32:$src1, i32mem:$src2),
+def IMUL32rm : I<0xAF, MRMSrcMem, (outs GR32:$dst),
+ (ins GR32:$src1, i32mem:$src2),
"imul{l}\t{$src2, $dst|$dst, $src2}",
[(set GR32:$dst, (mul GR32:$src1, (load addr:$src2))),
(implicit EFLAGS)]>, TB;
(implicit EFLAGS)]>;
// Memory-Integer Signed Integer Multiply
-def IMUL16rmi : Ii16<0x69, MRMSrcMem, // GR16 = [mem16]*I16
+def IMUL16rmi : Ii16<0x69, MRMSrcMem, // GR16 = [mem16]*I16
(outs GR16:$dst), (ins i16mem:$src1, i16imm:$src2),
"imul{w}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
[(set GR16:$dst, (mul (load addr:$src1), imm:$src2)),
(implicit EFLAGS)]>, OpSize;
-def IMUL32rmi : Ii32<0x69, MRMSrcMem, // GR32 = [mem32]*I32
+def IMUL32rmi : Ii32<0x69, MRMSrcMem, // GR32 = [mem32]*I32
(outs GR32:$dst), (ins i32mem:$src1, i32imm:$src2),
"imul{l}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
[(set GR32:$dst, (mul (load addr:$src1), imm:$src2)),
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",
// 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, $src2}",
"cmp{l}\t{$src2, $src1|$src1, $src2}",
[(X86cmp GR32:$src1, (loadi32 addr:$src2)),
(implicit EFLAGS)]>;
+def CMP8mrmrr : I<0x3A, MRMSrcReg, (outs), (ins GR8:$src1, GR8:$src2),
+ "cmp{b}\t{$src2, $src1|$src1, $src2}", []>;
+def CMP16mrmrr : I<0x3B, MRMSrcReg, (outs), (ins GR16:$src1, GR16:$src2),
+ "cmp{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize;
+def CMP32mrmrr : I<0x3B, MRMSrcReg, (outs), (ins GR32:$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, $src2}",
// Unlike with the register+register form, the memory+register form of the
// bt instruction does not ignore the high bits of the index. From ISel's
-// perspective, this is pretty bizarre. Disable these instructions for now.
-//def BT16mr : I<0xA3, MRMDestMem, (outs), (ins i16mem:$src1, GR16:$src2),
-// "bt{w}\t{$src2, $src1|$src1, $src2}",
+// perspective, this is pretty bizarre. Make these instructions disassembly
+// only for now.
+
+def BT16mr : I<0xA3, MRMDestMem, (outs), (ins i16mem:$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, $src2}",
+// (implicit EFLAGS)]
+ []
+ >, OpSize, TB, Requires<[FastBTMem]>;
+def BT32mr : I<0xA3, MRMDestMem, (outs), (ins i32mem:$src1, GR32:$src2),
+ "bt{l}\t{$src2, $src1|$src1, $src2}",
// [(X86bt (loadi32 addr:$src1), GR32:$src2),
-// (implicit EFLAGS)]>, TB, Requires<[FastBTMem]>;
+// (implicit EFLAGS)]
+ []
+ >, TB, Requires<[FastBTMem]>;
def BT16ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR16:$src1, i16i8imm:$src2),
"bt{w}\t{$src2, $src1|$src1, $src2}",
"bt{l}\t{$src2, $src1|$src1, $src2}",
[(X86bt (loadi32 addr:$src1), i32immSExt8:$src2),
(implicit EFLAGS)]>, TB;
+
+def BTC16rr : I<0xBB, MRMDestReg, (outs), (ins GR16:$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, $src2}", []>, TB;
} // Defs = [EFLAGS]
// Sign/Zero extenders
// Use movsbl intead of movsbw; we don't care about the high 16 bits
// of the register here. This has a smaller encoding and avoids a
-// partial-register update.
+// partial-register update. Actual movsbw included for the disassembler.
+def MOVSX16rr8W : I<0xBE, MRMSrcReg, (outs GR16:$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 :$src),
- "movs{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
- [(set GR16:$dst, (sext GR8:$src))]>, TB;
+ "", [(set GR16:$dst, (sext GR8:$src))]>, TB;
def MOVSX16rm8 : I<0xBE, MRMSrcMem, (outs GR16:$dst), (ins i8mem :$src),
- "movs{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
- [(set GR16:$dst, (sextloadi16i8 addr:$src))]>, TB;
+ "", [(set GR16:$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:$src))]>, TB;
// Use movzbl intead of movzbw; we don't care about the high 16 bits
// of the register here. This has a smaller encoding and avoids a
-// partial-register update.
+// partial-register update. Actual movzbw included for the disassembler.
+def MOVZX16rr8W : I<0xB6, MRMSrcReg, (outs GR16:$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 :$src),
- "movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
- [(set GR16:$dst, (zext GR8:$src))]>, TB;
+ "", [(set GR16:$dst, (zext GR8:$src))]>, TB;
def MOVZX16rm8 : I<0xB6, MRMSrcMem, (outs GR16:$dst), (ins i8mem :$src),
- "movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
- [(set GR16:$dst, (zextloadi16i8 addr:$src))]>, TB;
+ "", [(set GR16:$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:$src))]>, TB;
"movz{wl|x}\t{$src, $dst|$dst, $src}",
[(set GR32:$dst, (zextloadi32i16 addr:$src))]>, TB;
-// These are the same as the regular regular MOVZX32rr8 and MOVZX32rm8
+// These are the same as the regular MOVZX32rr8 and MOVZX32rm8
// except that they use GR32_NOREX for the output operand register class
// instead of GR32. This allows them to operate on h registers on x86-64.
def MOVZX32_NOREXrr8 : I<0xB6, MRMSrcReg,
// Alias instructions that map movr0 to xor.
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
+// FIXME: Set encoding to pseudo.
let Defs = [EFLAGS], isReMaterializable = 1, isAsCheapAsAMove = 1,
isCodeGenOnly = 1 in {
-def MOV8r0 : I<0x30, MRMInitReg, (outs GR8 :$dst), (ins),
- "xor{b}\t$dst, $dst",
+def MOV8r0 : I<0x30, MRMInitReg, (outs GR8 :$dst), (ins), "",
[(set GR8:$dst, 0)]>;
-// Use xorl instead of xorw since we don't care about the high 16 bits,
-// it's smaller, and it avoids a partial-register update.
-def MOV16r0 : I<0x31, MRMInitReg, (outs GR16:$dst), (ins),
- "xor{l}\t${dst:subreg32}, ${dst:subreg32}",
- [(set GR16:$dst, 0)]>;
-def MOV32r0 : I<0x31, MRMInitReg, (outs GR32:$dst), (ins),
- "xor{l}\t$dst, $dst",
+
+// We want to rewrite MOV16r0 in terms of MOV32r0, because it's a smaller
+// encoding and avoids a partial-register update sometimes, but doing so
+// at isel time interferes with rematerialization in the current register
+// allocator. For now, this is rewritten when the instruction is lowered
+// to an MCInst.
+def MOV16r0 : I<0x31, MRMInitReg, (outs GR16:$dst), (ins),
+ "",
+ [(set GR16:$dst, 0)]>, OpSize;
+
+// FIXME: Set encoding to pseudo.
+def MOV32r0 : I<0x31, MRMInitReg, (outs GR32:$dst), (ins), "",
[(set GR32:$dst, 0)]>;
}
"movl\t%fs:$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 $line $col",
- [(dwarf_loc (i32 imm:$line), (i32 imm:$col),
- (i32 imm:$file))]>;
-
//===----------------------------------------------------------------------===//
// EH Pseudo Instructions
//
// 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 i32mem:$ptr, GR32:$val),
+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:$dst), (ins i16mem:$ptr, GR16:$val),
+def XCHG16rm : I<0x87, MRMSrcMem, (outs GR16:$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:$dst), (ins i8mem:$ptr, GR8:$val),
+def XCHG8rm : I<0x86, MRMSrcMem, (outs GR8:$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:$swap),
[(X86cas addr:$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),
+def LCMPXCHG8B : I<0xC7, MRM1m, (outs), (ins i64mem:$ptr),
"lock\n\t"
"cmpxchg8b\t$ptr",
[(X86cas8 addr:$ptr)]>, TB, LOCK;
// Atomic exchange and add
let Constraints = "$val = $dst", Defs = [EFLAGS] in {
-def LXADD32 : I<0xC1, MRMSrcMem, (outs GR32:$dst), (ins i32mem:$ptr, GR32:$val),
+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:$dst), (ins i16mem:$ptr, GR16:$val),
+def LXADD16 : I<0xC1, MRMSrcMem, (outs GR16:$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:$dst), (ins i8mem:$ptr, GR8:$val),
+def LXADD8 : I<0xC0, MRMSrcMem, (outs GR8:$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, $src}", []>, TB;
+
+def XADD8rm : I<0xC0, MRMDestMem, (outs), (ins i8mem:$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, $src}", []>, TB;
+
+def CMPXCHG8rm : I<0xB0, MRMDestMem, (outs), (ins i8mem:$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$dst", []>, TB;
+
// Optimized codegen when the non-memory output is not used.
// FIXME: Use normal add / sub instructions and add lock prefix dynamically.
+let Defs = [EFLAGS] in {
def LOCK_ADD8mr : I<0x00, MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src2),
"lock\n\t"
"add{b}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_SUB32mi : Ii32<0x81, MRM5m, (outs), (ins i32mem:$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 :$src2),
+def LOCK_SUB16mi8 : Ii8<0x83, MRM5m, (outs), (ins i16mem:$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 :$src2),
def LOCK_DEC32m : I<0xFF, MRM1m, (outs), (ins i32mem:$dst),
"lock\n\t"
"dec{l}\t$dst", []>, LOCK;
+}
// Atomic exchange, and, or, xor
let Constraints = "$val = $dst", Defs = [EFLAGS],
- usesCustomDAGSchedInserter = 1 in {
+ usesCustomInserter = 1 in {
def ATOMAND32 : I<0, Pseudo, (outs GR32:$dst),(ins i32mem:$ptr, GR32:$val),
"#ATOMAND32 PSEUDO!",
[(set GR32:$dst, (atomic_load_and_32 addr:$ptr, GR32:$val))]>;
Defs = [EFLAGS, EAX, EBX, ECX, EDX],
Uses = [EAX, EBX, ECX, EDX],
mayLoad = 1, mayStore = 1,
- usesCustomDAGSchedInserter = 1 in {
+ usesCustomInserter = 1 in {
def ATOMAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2),
(ins i64mem:$ptr, GR32:$val1, GR32:$val2),
"#ATOMAND6432 PSEUDO!", []>;
"#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{$vmxon}", []>, XD;
+
//===----------------------------------------------------------------------===//
// Non-Instruction Patterns
//===----------------------------------------------------------------------===//
def : Pat<(i32 (X86Wrapper tglobaltlsaddr:$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:$src2)>;
(ADD32ri GR32:$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:$src)>;
// Calls
// tailcall stuff
def : Pat<(i32 (anyext GR8 :$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))),
- (MOVZX32rm8 addr:$src)>;
-def : Pat<(i32 (and (nvloadi32 addr:$src), (i32 65535))),
- (MOVZX32rm16 addr:$src)>;
-
//===----------------------------------------------------------------------===//
// Some peepholes
//===----------------------------------------------------------------------===//
(MOVZX32rr16 (EXTRACT_SUBREG GR32:$src1, x86_subreg_16bit))>;
// r & (2^8-1) ==> movz
def : Pat<(and GR32:$src1, 0xff),
- (MOVZX32rr8 (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src1, GR32_ABCD),
+ (MOVZX32rr8 (EXTRACT_SUBREG (i32 (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:$src1, GR16_ABCD),
+ (MOVZX16rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src1,
+ GR16_ABCD)),
x86_subreg_8bit))>,
Requires<[In32BitMode]>;
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_ABCD),
+ (MOVSX32rr8 (EXTRACT_SUBREG (i32 (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:$src, GR16_ABCD),
+ (MOVSX16rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src,
+ GR16_ABCD)),
x86_subreg_8bit))>,
Requires<[In32BitMode]>;
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_ABCD),
+ (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)),
x86_subreg_8bit)>,
Requires<[In32BitMode]>;
def : Pat<(i8 (trunc GR16:$src)),
- (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
+ (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$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_ABCD),
+ (EXTRACT_SUBREG (i32 (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:$src, GR32_ABCD),
+ (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)),
x86_subreg_8bit_hi)>,
Requires<[In32BitMode]>;
-def : Pat<(srl_su GR16:$src, (i8 8)),
+def : Pat<(srl GR16:$src, (i8 8)),
(EXTRACT_SUBREG
(MOVZX32rr8
- (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
+ (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$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),
+ (MOVZX32rr8 (EXTRACT_SUBREG (i16 (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:$src, GR16_ABCD),
+ (MOVZX32rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$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_ABCD),
+ (MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src,
+ GR32_ABCD)),
x86_subreg_8bit_hi))>,
Requires<[In32BitMode]>;
def : Pat<(shl GR32:$src1, (i8 1)), (ADD32rr GR32:$src1, GR32:$src1)>;
// (shl x (and y, 31)) ==> (shl x, y)
-def : Pat<(shl GR8:$src1, (and CL:$amt, 31)),
+def : Pat<(shl GR8:$src1, (and CL, 31)),
(SHL8rCL GR8:$src1)>;
-def : Pat<(shl GR16:$src1, (and CL:$amt, 31)),
+def : Pat<(shl GR16:$src1, (and CL, 31)),
(SHL16rCL GR16:$src1)>;
-def : Pat<(shl GR32:$src1, (and CL:$amt, 31)),
+def : Pat<(shl GR32:$src1, (and CL, 31)),
(SHL32rCL GR32:$src1)>;
-def : Pat<(store (shl (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (shl (loadi8 addr:$dst), (and CL, 31)), addr:$dst),
(SHL8mCL addr:$dst)>;
-def : Pat<(store (shl (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (shl (loadi16 addr:$dst), (and CL, 31)), addr:$dst),
(SHL16mCL addr:$dst)>;
-def : Pat<(store (shl (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (shl (loadi32 addr:$dst), (and CL, 31)), addr:$dst),
(SHL32mCL addr:$dst)>;
-def : Pat<(srl GR8:$src1, (and CL:$amt, 31)),
+def : Pat<(srl GR8:$src1, (and CL, 31)),
(SHR8rCL GR8:$src1)>;
-def : Pat<(srl GR16:$src1, (and CL:$amt, 31)),
+def : Pat<(srl GR16:$src1, (and CL, 31)),
(SHR16rCL GR16:$src1)>;
-def : Pat<(srl GR32:$src1, (and CL:$amt, 31)),
+def : Pat<(srl GR32:$src1, (and CL, 31)),
(SHR32rCL GR32:$src1)>;
-def : Pat<(store (srl (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (srl (loadi8 addr:$dst), (and CL, 31)), addr:$dst),
(SHR8mCL addr:$dst)>;
-def : Pat<(store (srl (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (srl (loadi16 addr:$dst), (and CL, 31)), addr:$dst),
(SHR16mCL addr:$dst)>;
-def : Pat<(store (srl (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (srl (loadi32 addr:$dst), (and CL, 31)), addr:$dst),
(SHR32mCL addr:$dst)>;
-def : Pat<(sra GR8:$src1, (and CL:$amt, 31)),
+def : Pat<(sra GR8:$src1, (and CL, 31)),
(SAR8rCL GR8:$src1)>;
-def : Pat<(sra GR16:$src1, (and CL:$amt, 31)),
+def : Pat<(sra GR16:$src1, (and CL, 31)),
(SAR16rCL GR16:$src1)>;
-def : Pat<(sra GR32:$src1, (and CL:$amt, 31)),
+def : Pat<(sra GR32:$src1, (and CL, 31)),
(SAR32rCL GR32:$src1)>;
-def : Pat<(store (sra (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (sra (loadi8 addr:$dst), (and CL, 31)), addr:$dst),
(SAR8mCL addr:$dst)>;
-def : Pat<(store (sra (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (sra (loadi16 addr:$dst), (and CL, 31)), addr:$dst),
(SAR16mCL addr:$dst)>;
-def : Pat<(store (sra (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (sra (loadi32 addr:$dst), (and CL, 31)), addr:$dst),
(SAR32mCL addr:$dst)>;
// (or (x >> c) | (y << (32 - c))) ==> (shrd32 x, y, c)
addr:$dst),
(SHRD32mrCL addr:$dst, GR32:$src2)>;
-def : Pat<(shrd GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm:$amt2)),
+def : Pat<(shrd GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm/*:$amt2*/)),
(SHRD32rri8 GR32:$src1, GR32:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shrd (loadi32 addr:$dst), (i8 imm:$amt1),
- GR32:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR32:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHRD32mri8 addr:$dst, GR32:$src2, (i8 imm:$amt1))>;
// (or (x << c) | (y >> (32 - c))) ==> (shld32 x, y, c)
addr:$dst),
(SHLD32mrCL addr:$dst, GR32:$src2)>;
-def : Pat<(shld GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm:$amt2)),
+def : Pat<(shld GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm/*:$amt2*/)),
(SHLD32rri8 GR32:$src1, GR32:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shld (loadi32 addr:$dst), (i8 imm:$amt1),
- GR32:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR32:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHLD32mri8 addr:$dst, GR32:$src2, (i8 imm:$amt1))>;
// (or (x >> c) | (y << (16 - c))) ==> (shrd16 x, y, c)
addr:$dst),
(SHRD16mrCL addr:$dst, GR16:$src2)>;
-def : Pat<(shrd GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm:$amt2)),
+def : Pat<(shrd GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm/*:$amt2*/)),
(SHRD16rri8 GR16:$src1, GR16:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shrd (loadi16 addr:$dst), (i8 imm:$amt1),
- GR16:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR16:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHRD16mri8 addr:$dst, GR16:$src2, (i8 imm:$amt1))>;
// (or (x << c) | (y >> (16 - c))) ==> (shld16 x, y, c)
addr:$dst),
(SHLD16mrCL addr:$dst, GR16:$src2)>;
-def : Pat<(shld GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm:$amt2)),
+def : Pat<(shld GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm/*:$amt2*/)),
(SHLD16rri8 GR16:$src1, GR16:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shld (loadi16 addr:$dst), (i8 imm:$amt1),
- GR16:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR16:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHLD16mri8 addr:$dst, GR16:$src2, (i8 imm:$amt1))>;
+// (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)>;
+
+// (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<(parallel (or_is_add GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (ADD16ri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (or_is_add GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (ADD32ri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (or_is_add GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (ADD16ri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (or_is_add GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (ADD32ri8 GR32:$src1, i32immSExt8:$src2)>;
+def : Pat<(parallel (or_is_add GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (ADD16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (or_is_add GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (ADD32rr GR32:$src1, GR32:$src2)>;
+} // AddedComplexity
+
//===----------------------------------------------------------------------===//
// EFLAGS-defining Patterns
//===----------------------------------------------------------------------===//
(implicit EFLAGS)),
(DEC32m addr:$dst)>, Requires<[In32BitMode]>;
+// Register-Register Or with EFLAGS result
+def : Pat<(parallel (X86or_flag GR8:$src1, GR8:$src2),
+ (implicit EFLAGS)),
+ (OR8rr GR8:$src1, GR8:$src2)>;
+def : Pat<(parallel (X86or_flag GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (OR16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (X86or_flag GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (OR32rr GR32:$src1, GR32:$src2)>;
+
+// Register-Memory Or with EFLAGS result
+def : Pat<(parallel (X86or_flag GR8:$src1, (loadi8 addr:$src2)),
+ (implicit EFLAGS)),
+ (OR8rm GR8:$src1, addr:$src2)>;
+def : Pat<(parallel (X86or_flag GR16:$src1, (loadi16 addr:$src2)),
+ (implicit EFLAGS)),
+ (OR16rm GR16:$src1, addr:$src2)>;
+def : Pat<(parallel (X86or_flag GR32:$src1, (loadi32 addr:$src2)),
+ (implicit EFLAGS)),
+ (OR32rm GR32:$src1, addr:$src2)>;
+
+// Register-Integer Or with EFLAGS result
+def : Pat<(parallel (X86or_flag GR8:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (OR8ri GR8:$src1, imm:$src2)>;
+def : Pat<(parallel (X86or_flag GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (OR16ri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (X86or_flag GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (OR32ri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (X86or_flag GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (OR16ri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86or_flag GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (OR32ri8 GR32:$src1, i32immSExt8:$src2)>;
+
+// Memory-Register Or with EFLAGS result
+def : Pat<(parallel (store (X86or_flag (loadi8 addr:$dst), GR8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR8mr addr:$dst, GR8:$src2)>;
+def : Pat<(parallel (store (X86or_flag (loadi16 addr:$dst), GR16:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR16mr addr:$dst, GR16:$src2)>;
+def : Pat<(parallel (store (X86or_flag (loadi32 addr:$dst), GR32:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR32mr addr:$dst, GR32:$src2)>;
+
+// Memory-Integer Or with EFLAGS result
+def : Pat<(parallel (store (X86or_flag (loadi8 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR8mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86or_flag (loadi16 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR16mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86or_flag (loadi32 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR32mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86or_flag (loadi16 addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR16mi8 addr:$dst, i16immSExt8:$src2)>;
+def : Pat<(parallel (store (X86or_flag (loadi32 addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (OR32mi8 addr:$dst, i32immSExt8:$src2)>;
+
+// Register-Register XOr with EFLAGS result
+def : Pat<(parallel (X86xor_flag GR8:$src1, GR8:$src2),
+ (implicit EFLAGS)),
+ (XOR8rr GR8:$src1, GR8:$src2)>;
+def : Pat<(parallel (X86xor_flag GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (XOR16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (X86xor_flag GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (XOR32rr GR32:$src1, GR32:$src2)>;
+
+// Register-Memory XOr with EFLAGS result
+def : Pat<(parallel (X86xor_flag GR8:$src1, (loadi8 addr:$src2)),
+ (implicit EFLAGS)),
+ (XOR8rm GR8:$src1, addr:$src2)>;
+def : Pat<(parallel (X86xor_flag GR16:$src1, (loadi16 addr:$src2)),
+ (implicit EFLAGS)),
+ (XOR16rm GR16:$src1, addr:$src2)>;
+def : Pat<(parallel (X86xor_flag GR32:$src1, (loadi32 addr:$src2)),
+ (implicit EFLAGS)),
+ (XOR32rm GR32:$src1, addr:$src2)>;
+
+// Register-Integer XOr with EFLAGS result
+def : Pat<(parallel (X86xor_flag GR8:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (XOR8ri GR8:$src1, imm:$src2)>;
+def : Pat<(parallel (X86xor_flag GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (XOR16ri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (X86xor_flag GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (XOR32ri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (X86xor_flag GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (XOR16ri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86xor_flag GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (XOR32ri8 GR32:$src1, i32immSExt8:$src2)>;
+
+// Memory-Register XOr with EFLAGS result
+def : Pat<(parallel (store (X86xor_flag (loadi8 addr:$dst), GR8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR8mr addr:$dst, GR8:$src2)>;
+def : Pat<(parallel (store (X86xor_flag (loadi16 addr:$dst), GR16:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR16mr addr:$dst, GR16:$src2)>;
+def : Pat<(parallel (store (X86xor_flag (loadi32 addr:$dst), GR32:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR32mr addr:$dst, GR32:$src2)>;
+
+// Memory-Integer XOr with EFLAGS result
+def : Pat<(parallel (store (X86xor_flag (loadi8 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR8mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86xor_flag (loadi16 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR16mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86xor_flag (loadi32 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR32mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86xor_flag (loadi16 addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR16mi8 addr:$dst, i16immSExt8:$src2)>;
+def : Pat<(parallel (store (X86xor_flag (loadi32 addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (XOR32mi8 addr:$dst, i32immSExt8:$src2)>;
+
+// Register-Register And with EFLAGS result
+def : Pat<(parallel (X86and_flag GR8:$src1, GR8:$src2),
+ (implicit EFLAGS)),
+ (AND8rr GR8:$src1, GR8:$src2)>;
+def : Pat<(parallel (X86and_flag GR16:$src1, GR16:$src2),
+ (implicit EFLAGS)),
+ (AND16rr GR16:$src1, GR16:$src2)>;
+def : Pat<(parallel (X86and_flag GR32:$src1, GR32:$src2),
+ (implicit EFLAGS)),
+ (AND32rr GR32:$src1, GR32:$src2)>;
+
+// Register-Memory And with EFLAGS result
+def : Pat<(parallel (X86and_flag GR8:$src1, (loadi8 addr:$src2)),
+ (implicit EFLAGS)),
+ (AND8rm GR8:$src1, addr:$src2)>;
+def : Pat<(parallel (X86and_flag GR16:$src1, (loadi16 addr:$src2)),
+ (implicit EFLAGS)),
+ (AND16rm GR16:$src1, addr:$src2)>;
+def : Pat<(parallel (X86and_flag GR32:$src1, (loadi32 addr:$src2)),
+ (implicit EFLAGS)),
+ (AND32rm GR32:$src1, addr:$src2)>;
+
+// Register-Integer And with EFLAGS result
+def : Pat<(parallel (X86and_flag GR8:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (AND8ri GR8:$src1, imm:$src2)>;
+def : Pat<(parallel (X86and_flag GR16:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (AND16ri GR16:$src1, imm:$src2)>;
+def : Pat<(parallel (X86and_flag GR32:$src1, imm:$src2),
+ (implicit EFLAGS)),
+ (AND32ri GR32:$src1, imm:$src2)>;
+def : Pat<(parallel (X86and_flag GR16:$src1, i16immSExt8:$src2),
+ (implicit EFLAGS)),
+ (AND16ri8 GR16:$src1, i16immSExt8:$src2)>;
+def : Pat<(parallel (X86and_flag GR32:$src1, i32immSExt8:$src2),
+ (implicit EFLAGS)),
+ (AND32ri8 GR32:$src1, i32immSExt8:$src2)>;
+
+// Memory-Register And with EFLAGS result
+def : Pat<(parallel (store (X86and_flag (loadi8 addr:$dst), GR8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND8mr addr:$dst, GR8:$src2)>;
+def : Pat<(parallel (store (X86and_flag (loadi16 addr:$dst), GR16:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND16mr addr:$dst, GR16:$src2)>;
+def : Pat<(parallel (store (X86and_flag (loadi32 addr:$dst), GR32:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND32mr addr:$dst, GR32:$src2)>;
+
+// Memory-Integer And with EFLAGS result
+def : Pat<(parallel (store (X86and_flag (loadi8 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND8mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86and_flag (loadi16 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND16mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86and_flag (loadi32 addr:$dst), imm:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND32mi addr:$dst, imm:$src2)>;
+def : Pat<(parallel (store (X86and_flag (loadi16 addr:$dst), i16immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND16mi8 addr:$dst, i16immSExt8:$src2)>;
+def : Pat<(parallel (store (X86and_flag (loadi32 addr:$dst), i32immSExt8:$src2),
+ addr:$dst),
+ (implicit EFLAGS)),
+ (AND32mi8 addr:$dst, i32immSExt8:$src2)>;
+
+// -disable-16bit support.
+def : Pat<(truncstorei16 (i32 imm:$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
//===----------------------------------------------------------------------===//
include "X86Instr64bit.td"
+//===----------------------------------------------------------------------===//
+// SIMD support (SSE, MMX and AVX)
+//===----------------------------------------------------------------------===//
+
+include "X86InstrFragmentsSIMD.td"
+
//===----------------------------------------------------------------------===//
// XMM Floating point support (requires SSE / SSE2)
//===----------------------------------------------------------------------===//