forked from OSchip/llvm-project
2039 lines
99 KiB
TableGen
2039 lines
99 KiB
TableGen
//====- X86Instr64bit.td - Describe X86-64 Instructions ----*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file describes the X86-64 instruction set, defining the instructions,
|
|
// and properties of the instructions which are needed for code generation,
|
|
// machine code emission, and analysis.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Operand Definitions.
|
|
//
|
|
|
|
// 64-bits but only 32 bits are significant.
|
|
def i64i32imm : Operand<i64>;
|
|
|
|
// 64-bits but only 32 bits are significant, and those bits are treated as being
|
|
// pc relative.
|
|
def i64i32imm_pcrel : Operand<i64> {
|
|
let PrintMethod = "print_pcrel_imm";
|
|
}
|
|
|
|
|
|
// 64-bits but only 8 bits are significant.
|
|
def i64i8imm : Operand<i64> {
|
|
let ParserMatchClass = ImmSExt8AsmOperand;
|
|
}
|
|
|
|
def lea64mem : Operand<i64> {
|
|
let PrintMethod = "printlea64mem";
|
|
let MIOperandInfo = (ops GR64, i8imm, GR64_NOSP, i32imm);
|
|
let ParserMatchClass = X86MemAsmOperand;
|
|
}
|
|
|
|
def lea64_32mem : Operand<i32> {
|
|
let PrintMethod = "printlea64_32mem";
|
|
let AsmOperandLowerMethod = "lower_lea64_32mem";
|
|
let MIOperandInfo = (ops GR32, i8imm, GR32_NOSP, i32imm);
|
|
let ParserMatchClass = X86MemAsmOperand;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Complex Pattern Definitions.
|
|
//
|
|
def lea64addr : ComplexPattern<i64, 4, "SelectLEAAddr",
|
|
[add, sub, mul, X86mul_imm, shl, or, frameindex,
|
|
X86WrapperRIP], []>;
|
|
|
|
def tls64addr : ComplexPattern<i64, 4, "SelectTLSADDRAddr",
|
|
[tglobaltlsaddr], []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Pattern fragments.
|
|
//
|
|
|
|
def i64immSExt8 : PatLeaf<(i64 imm), [{
|
|
// i64immSExt8 predicate - True if the 64-bit immediate fits in a 8-bit
|
|
// sign extended field.
|
|
return (int64_t)N->getZExtValue() == (int8_t)N->getZExtValue();
|
|
}]>;
|
|
|
|
def i64immSExt32 : PatLeaf<(i64 imm), [{
|
|
// i64immSExt32 predicate - True if the 64-bit immediate fits in a 32-bit
|
|
// sign extended field.
|
|
return (int64_t)N->getZExtValue() == (int32_t)N->getZExtValue();
|
|
}]>;
|
|
|
|
def i64immZExt32 : PatLeaf<(i64 imm), [{
|
|
// i64immZExt32 predicate - True if the 64-bit immediate fits in a 32-bit
|
|
// unsignedsign extended field.
|
|
return (uint64_t)N->getZExtValue() == (uint32_t)N->getZExtValue();
|
|
}]>;
|
|
|
|
def sextloadi64i8 : PatFrag<(ops node:$ptr), (i64 (sextloadi8 node:$ptr))>;
|
|
def sextloadi64i16 : PatFrag<(ops node:$ptr), (i64 (sextloadi16 node:$ptr))>;
|
|
def sextloadi64i32 : PatFrag<(ops node:$ptr), (i64 (sextloadi32 node:$ptr))>;
|
|
|
|
def zextloadi64i1 : PatFrag<(ops node:$ptr), (i64 (zextloadi1 node:$ptr))>;
|
|
def zextloadi64i8 : PatFrag<(ops node:$ptr), (i64 (zextloadi8 node:$ptr))>;
|
|
def zextloadi64i16 : PatFrag<(ops node:$ptr), (i64 (zextloadi16 node:$ptr))>;
|
|
def zextloadi64i32 : PatFrag<(ops node:$ptr), (i64 (zextloadi32 node:$ptr))>;
|
|
|
|
def extloadi64i1 : PatFrag<(ops node:$ptr), (i64 (extloadi1 node:$ptr))>;
|
|
def extloadi64i8 : PatFrag<(ops node:$ptr), (i64 (extloadi8 node:$ptr))>;
|
|
def extloadi64i16 : PatFrag<(ops node:$ptr), (i64 (extloadi16 node:$ptr))>;
|
|
def extloadi64i32 : PatFrag<(ops node:$ptr), (i64 (extloadi32 node:$ptr))>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction list...
|
|
//
|
|
|
|
// ADJCALLSTACKDOWN/UP implicitly use/def RSP because they may be expanded into
|
|
// a stack adjustment and the codegen must know that they may modify the stack
|
|
// pointer before prolog-epilog rewriting occurs.
|
|
// Pessimistically assume ADJCALLSTACKDOWN / ADJCALLSTACKUP will become
|
|
// sub / add which can clobber EFLAGS.
|
|
let Defs = [RSP, EFLAGS], Uses = [RSP] in {
|
|
def ADJCALLSTACKDOWN64 : I<0, Pseudo, (outs), (ins i32imm:$amt),
|
|
"#ADJCALLSTACKDOWN",
|
|
[(X86callseq_start timm:$amt)]>,
|
|
Requires<[In64BitMode]>;
|
|
def ADJCALLSTACKUP64 : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
|
|
"#ADJCALLSTACKUP",
|
|
[(X86callseq_end timm:$amt1, timm:$amt2)]>,
|
|
Requires<[In64BitMode]>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Call Instructions...
|
|
//
|
|
let isCall = 1 in
|
|
// All calls clobber the non-callee saved registers. RSP is marked as
|
|
// a use to prevent stack-pointer assignments that appear immediately
|
|
// before calls from potentially appearing dead. Uses for argument
|
|
// registers are added manually.
|
|
let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
|
|
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
|
|
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
|
|
Uses = [RSP] in {
|
|
|
|
// NOTE: this pattern doesn't match "X86call imm", because we do not know
|
|
// that the offset between an arbitrary immediate and the call will fit in
|
|
// the 32-bit pcrel field that we have.
|
|
def CALL64pcrel32 : Ii32<0xE8, RawFrm,
|
|
(outs), (ins i64i32imm_pcrel:$dst, variable_ops),
|
|
"call\t$dst", []>,
|
|
Requires<[In64BitMode, NotWin64]>;
|
|
def CALL64r : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
|
|
"call\t{*}$dst", [(X86call GR64:$dst)]>,
|
|
Requires<[NotWin64]>;
|
|
def CALL64m : I<0xFF, MRM2m, (outs), (ins i64mem:$dst, variable_ops),
|
|
"call\t{*}$dst", [(X86call (loadi64 addr:$dst))]>,
|
|
Requires<[NotWin64]>;
|
|
}
|
|
|
|
// FIXME: We need to teach codegen about single list of call-clobbered registers.
|
|
let isCall = 1 in
|
|
// All calls clobber the non-callee saved registers. RSP is marked as
|
|
// a use to prevent stack-pointer assignments that appear immediately
|
|
// before calls from potentially appearing dead. Uses for argument
|
|
// registers are added manually.
|
|
let Defs = [RAX, RCX, RDX, R8, R9, R10, R11,
|
|
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, EFLAGS],
|
|
Uses = [RSP] in {
|
|
def WINCALL64pcrel32 : I<0xE8, RawFrm,
|
|
(outs), (ins i64i32imm_pcrel:$dst, variable_ops),
|
|
"call\t$dst", []>,
|
|
Requires<[IsWin64]>;
|
|
def WINCALL64r : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
|
|
"call\t{*}$dst",
|
|
[(X86call GR64:$dst)]>, Requires<[IsWin64]>;
|
|
def WINCALL64m : I<0xFF, MRM2m, (outs), (ins i64mem:$dst, variable_ops),
|
|
"call\t{*}$dst",
|
|
[(X86call (loadi64 addr:$dst))]>, Requires<[IsWin64]>;
|
|
}
|
|
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
|
|
def TCRETURNdi64 : I<0, Pseudo, (outs), (ins i64imm:$dst, i32imm:$offset,
|
|
variable_ops),
|
|
"#TC_RETURN $dst $offset",
|
|
[]>;
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
|
|
def TCRETURNri64 : I<0, Pseudo, (outs), (ins GR64:$dst, i32imm:$offset,
|
|
variable_ops),
|
|
"#TC_RETURN $dst $offset",
|
|
[]>;
|
|
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
|
|
def TAILJMPr64 : I<0xFF, MRM4r, (outs), (ins GR64:$dst),
|
|
"jmp{q}\t{*}$dst # TAILCALL",
|
|
[]>;
|
|
|
|
// Branches
|
|
let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in {
|
|
def JMP64r : I<0xFF, MRM4r, (outs), (ins GR64:$dst), "jmp{q}\t{*}$dst",
|
|
[(brind GR64:$dst)]>;
|
|
def JMP64m : I<0xFF, MRM4m, (outs), (ins i64mem:$dst), "jmp{q}\t{*}$dst",
|
|
[(brind (loadi64 addr:$dst))]>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// EH Pseudo Instructions
|
|
//
|
|
let isTerminator = 1, isReturn = 1, isBarrier = 1,
|
|
hasCtrlDep = 1 in {
|
|
def EH_RETURN64 : I<0xC3, RawFrm, (outs), (ins GR64:$addr),
|
|
"ret\t#eh_return, addr: $addr",
|
|
[(X86ehret GR64:$addr)]>;
|
|
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Miscellaneous Instructions...
|
|
//
|
|
let Defs = [RBP,RSP], Uses = [RBP,RSP], mayLoad = 1, neverHasSideEffects = 1 in
|
|
def LEAVE64 : I<0xC9, RawFrm,
|
|
(outs), (ins), "leave", []>;
|
|
let Defs = [RSP], Uses = [RSP], neverHasSideEffects=1 in {
|
|
let mayLoad = 1 in
|
|
def POP64r : I<0x58, AddRegFrm,
|
|
(outs GR64:$reg), (ins), "pop{q}\t$reg", []>;
|
|
let mayStore = 1 in
|
|
def PUSH64r : I<0x50, AddRegFrm,
|
|
(outs), (ins GR64:$reg), "push{q}\t$reg", []>;
|
|
}
|
|
|
|
let Defs = [RSP], Uses = [RSP], neverHasSideEffects = 1, mayStore = 1 in {
|
|
def PUSH64i8 : Ii8<0x6a, RawFrm, (outs), (ins i8imm:$imm),
|
|
"push{q}\t$imm", []>;
|
|
def PUSH64i16 : Ii16<0x68, RawFrm, (outs), (ins i16imm:$imm),
|
|
"push{q}\t$imm", []>;
|
|
def PUSH64i32 : Ii32<0x68, RawFrm, (outs), (ins i32imm:$imm),
|
|
"push{q}\t$imm", []>;
|
|
}
|
|
|
|
let Defs = [RSP, EFLAGS], Uses = [RSP], mayLoad = 1 in
|
|
def POPFQ : I<0x9D, RawFrm, (outs), (ins), "popf", []>, REX_W;
|
|
let Defs = [RSP], Uses = [RSP, EFLAGS], mayStore = 1 in
|
|
def PUSHFQ : I<0x9C, RawFrm, (outs), (ins), "pushf", []>;
|
|
|
|
def LEA64_32r : I<0x8D, MRMSrcMem,
|
|
(outs GR32:$dst), (ins lea64_32mem:$src),
|
|
"lea{l}\t{$src|$dst}, {$dst|$src}",
|
|
[(set GR32:$dst, lea32addr:$src)]>, Requires<[In64BitMode]>;
|
|
|
|
let isReMaterializable = 1 in
|
|
def LEA64r : RI<0x8D, MRMSrcMem, (outs GR64:$dst), (ins lea64mem:$src),
|
|
"lea{q}\t{$src|$dst}, {$dst|$src}",
|
|
[(set GR64:$dst, lea64addr:$src)]>;
|
|
|
|
let isTwoAddress = 1 in
|
|
def BSWAP64r : RI<0xC8, AddRegFrm, (outs GR64:$dst), (ins GR64:$src),
|
|
"bswap{q}\t$dst",
|
|
[(set GR64:$dst, (bswap GR64:$src))]>, TB;
|
|
|
|
// Bit scan instructions.
|
|
let Defs = [EFLAGS] in {
|
|
def BSF64rr : RI<0xBC, MRMSrcReg, (outs GR64:$dst), (ins GR64:$src),
|
|
"bsf{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (X86bsf GR64:$src)), (implicit EFLAGS)]>, TB;
|
|
def BSF64rm : RI<0xBC, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
|
|
"bsf{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (X86bsf (loadi64 addr:$src))),
|
|
(implicit EFLAGS)]>, TB;
|
|
|
|
def BSR64rr : RI<0xBD, MRMSrcReg, (outs GR64:$dst), (ins GR64:$src),
|
|
"bsr{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (X86bsr GR64:$src)), (implicit EFLAGS)]>, TB;
|
|
def BSR64rm : RI<0xBD, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
|
|
"bsr{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (X86bsr (loadi64 addr:$src))),
|
|
(implicit EFLAGS)]>, TB;
|
|
} // Defs = [EFLAGS]
|
|
|
|
// Repeat string ops
|
|
let Defs = [RCX,RDI,RSI], Uses = [RCX,RDI,RSI] in
|
|
def REP_MOVSQ : RI<0xA5, RawFrm, (outs), (ins), "{rep;movsq|rep movsq}",
|
|
[(X86rep_movs i64)]>, REP;
|
|
let Defs = [RCX,RDI], Uses = [RAX,RCX,RDI] in
|
|
def REP_STOSQ : RI<0xAB, RawFrm, (outs), (ins), "{rep;stosq|rep stosq}",
|
|
[(X86rep_stos i64)]>, REP;
|
|
|
|
// Fast system-call instructions
|
|
def SYSEXIT64 : RI<0x35, RawFrm,
|
|
(outs), (ins), "sysexit", []>, TB;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Move Instructions...
|
|
//
|
|
|
|
let neverHasSideEffects = 1 in
|
|
def MOV64rr : RI<0x89, MRMDestReg, (outs GR64:$dst), (ins GR64:$src),
|
|
"mov{q}\t{$src, $dst|$dst, $src}", []>;
|
|
|
|
let isReMaterializable = 1, isAsCheapAsAMove = 1 in {
|
|
def MOV64ri : RIi64<0xB8, AddRegFrm, (outs GR64:$dst), (ins i64imm:$src),
|
|
"movabs{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, imm:$src)]>;
|
|
def MOV64ri32 : RIi32<0xC7, MRM0r, (outs GR64:$dst), (ins i64i32imm:$src),
|
|
"mov{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, i64immSExt32:$src)]>;
|
|
}
|
|
|
|
let canFoldAsLoad = 1 in
|
|
def MOV64rm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
|
|
"mov{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (load addr:$src))]>;
|
|
|
|
def MOV64mr : RI<0x89, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
|
|
"mov{q}\t{$src, $dst|$dst, $src}",
|
|
[(store GR64:$src, addr:$dst)]>;
|
|
def MOV64mi32 : RIi32<0xC7, MRM0m, (outs), (ins i64mem:$dst, i64i32imm:$src),
|
|
"mov{q}\t{$src, $dst|$dst, $src}",
|
|
[(store i64immSExt32:$src, addr:$dst)]>;
|
|
|
|
// Sign/Zero extenders
|
|
|
|
// MOVSX64rr8 always has a REX prefix and it has an 8-bit register
|
|
// operand, which makes it a rare instruction with an 8-bit register
|
|
// operand that can never access an h register. If support for h registers
|
|
// were generalized, this would require a special register class.
|
|
def MOVSX64rr8 : RI<0xBE, MRMSrcReg, (outs GR64:$dst), (ins GR8 :$src),
|
|
"movs{bq|x}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (sext GR8:$src))]>, TB;
|
|
def MOVSX64rm8 : RI<0xBE, MRMSrcMem, (outs GR64:$dst), (ins i8mem :$src),
|
|
"movs{bq|x}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (sextloadi64i8 addr:$src))]>, TB;
|
|
def MOVSX64rr16: RI<0xBF, MRMSrcReg, (outs GR64:$dst), (ins GR16:$src),
|
|
"movs{wq|x}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (sext GR16:$src))]>, TB;
|
|
def MOVSX64rm16: RI<0xBF, MRMSrcMem, (outs GR64:$dst), (ins i16mem:$src),
|
|
"movs{wq|x}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (sextloadi64i16 addr:$src))]>, TB;
|
|
def MOVSX64rr32: RI<0x63, MRMSrcReg, (outs GR64:$dst), (ins GR32:$src),
|
|
"movs{lq|xd}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (sext GR32:$src))]>;
|
|
def MOVSX64rm32: RI<0x63, MRMSrcMem, (outs GR64:$dst), (ins i32mem:$src),
|
|
"movs{lq|xd}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (sextloadi64i32 addr:$src))]>;
|
|
|
|
// Use movzbl instead of movzbq when the destination is a register; it's
|
|
// equivalent due to implicit zero-extending, and it has a smaller encoding.
|
|
def MOVZX64rr8 : I<0xB6, MRMSrcReg, (outs GR64:$dst), (ins GR8 :$src),
|
|
"movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, (zext GR8:$src))]>, TB;
|
|
def MOVZX64rm8 : I<0xB6, MRMSrcMem, (outs GR64:$dst), (ins i8mem :$src),
|
|
"movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, (zextloadi64i8 addr:$src))]>, TB;
|
|
// Use movzwl instead of movzwq when the destination is a register; it's
|
|
// equivalent due to implicit zero-extending, and it has a smaller encoding.
|
|
def MOVZX64rr16: I<0xB7, MRMSrcReg, (outs GR64:$dst), (ins GR16:$src),
|
|
"movz{wl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, (zext GR16:$src))]>, TB;
|
|
def MOVZX64rm16: I<0xB7, MRMSrcMem, (outs GR64:$dst), (ins i16mem:$src),
|
|
"movz{wl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, (zextloadi64i16 addr:$src))]>, TB;
|
|
|
|
// There's no movzlq instruction, but movl can be used for this purpose, using
|
|
// implicit zero-extension. The preferred way to do 32-bit-to-64-bit zero
|
|
// extension on x86-64 is to use a SUBREG_TO_REG to utilize implicit
|
|
// zero-extension, however this isn't possible when the 32-bit value is
|
|
// defined by a truncate or is copied from something where the high bits aren't
|
|
// necessarily all zero. In such cases, we fall back to these explicit zext
|
|
// instructions.
|
|
def MOVZX64rr32 : I<0x89, MRMDestReg, (outs GR64:$dst), (ins GR32:$src),
|
|
"mov{l}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, (zext GR32:$src))]>;
|
|
def MOVZX64rm32 : I<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i32mem:$src),
|
|
"mov{l}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, (zextloadi64i32 addr:$src))]>;
|
|
|
|
// Any instruction that defines a 32-bit result leaves the high half of the
|
|
// register. Truncate can be lowered to EXTRACT_SUBREG, and CopyFromReg may
|
|
// be copying from a truncate, but any other 32-bit operation will zero-extend
|
|
// up to 64 bits.
|
|
def def32 : PatLeaf<(i32 GR32:$src), [{
|
|
return N->getOpcode() != ISD::TRUNCATE &&
|
|
N->getOpcode() != TargetInstrInfo::EXTRACT_SUBREG &&
|
|
N->getOpcode() != ISD::CopyFromReg;
|
|
}]>;
|
|
|
|
// In the case of a 32-bit def that is known to implicitly zero-extend,
|
|
// we can use a SUBREG_TO_REG.
|
|
def : Pat<(i64 (zext def32:$src)),
|
|
(SUBREG_TO_REG (i64 0), GR32:$src, x86_subreg_32bit)>;
|
|
|
|
let neverHasSideEffects = 1 in {
|
|
let Defs = [RAX], Uses = [EAX] in
|
|
def CDQE : RI<0x98, RawFrm, (outs), (ins),
|
|
"{cltq|cdqe}", []>; // RAX = signext(EAX)
|
|
|
|
let Defs = [RAX,RDX], Uses = [RAX] in
|
|
def CQO : RI<0x99, RawFrm, (outs), (ins),
|
|
"{cqto|cqo}", []>; // RDX:RAX = signext(RAX)
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Arithmetic Instructions...
|
|
//
|
|
|
|
let Defs = [EFLAGS] in {
|
|
let isTwoAddress = 1 in {
|
|
let isConvertibleToThreeAddress = 1 in {
|
|
let isCommutable = 1 in
|
|
// Register-Register Addition
|
|
def ADD64rr : RI<0x01, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (add GR64:$src1, GR64:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
|
|
// Register-Integer Addition
|
|
def ADD64ri8 : RIi8<0x83, MRM0r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (add GR64:$src1, i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def ADD64ri32 : RIi32<0x81, MRM0r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (add GR64:$src1, i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
} // isConvertibleToThreeAddress
|
|
|
|
// Register-Memory Addition
|
|
def ADD64rm : RI<0x03, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (add GR64:$src1, (load addr:$src2))),
|
|
(implicit EFLAGS)]>;
|
|
} // isTwoAddress
|
|
|
|
// Memory-Register Addition
|
|
def ADD64mr : RI<0x01, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (add (load addr:$dst), GR64:$src2), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def ADD64mi8 : RIi8<0x83, MRM0m, (outs), (ins i64mem:$dst, i64i8imm :$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (add (load addr:$dst), i64immSExt8:$src2), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def ADD64mi32 : RIi32<0x81, MRM0m, (outs), (ins i64mem:$dst, i64i32imm :$src2),
|
|
"add{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (add (load addr:$dst), i64immSExt32:$src2), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
let Uses = [EFLAGS] in {
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in
|
|
def ADC64rr : RI<0x11, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (adde GR64:$src1, GR64:$src2))]>;
|
|
|
|
def ADC64rm : RI<0x13, MRMSrcMem , (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (adde GR64:$src1, (load addr:$src2)))]>;
|
|
|
|
def ADC64ri8 : RIi8<0x83, MRM2r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (adde GR64:$src1, i64immSExt8:$src2))]>;
|
|
def ADC64ri32 : RIi32<0x81, MRM2r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (adde GR64:$src1, i64immSExt32:$src2))]>;
|
|
} // isTwoAddress
|
|
|
|
def ADC64mr : RI<0x11, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (adde (load addr:$dst), GR64:$src2), addr:$dst)]>;
|
|
def ADC64mi8 : RIi8<0x83, MRM2m, (outs), (ins i64mem:$dst, i64i8imm :$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (adde (load addr:$dst), i64immSExt8:$src2), addr:$dst)]>;
|
|
def ADC64mi32 : RIi32<0x81, MRM2m, (outs), (ins i64mem:$dst, i64i32imm:$src2),
|
|
"adc{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (adde (load addr:$dst), i64immSExt8:$src2), addr:$dst)]>;
|
|
} // Uses = [EFLAGS]
|
|
|
|
let isTwoAddress = 1 in {
|
|
// Register-Register Subtraction
|
|
def SUB64rr : RI<0x29, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sub GR64:$src1, GR64:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
|
|
// Register-Memory Subtraction
|
|
def SUB64rm : RI<0x2B, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sub GR64:$src1, (load addr:$src2))),
|
|
(implicit EFLAGS)]>;
|
|
|
|
// Register-Integer Subtraction
|
|
def SUB64ri8 : RIi8<0x83, MRM5r, (outs GR64:$dst),
|
|
(ins GR64:$src1, i64i8imm:$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sub GR64:$src1, i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def SUB64ri32 : RIi32<0x81, MRM5r, (outs GR64:$dst),
|
|
(ins GR64:$src1, i64i32imm:$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sub GR64:$src1, i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
} // isTwoAddress
|
|
|
|
// Memory-Register Subtraction
|
|
def SUB64mr : RI<0x29, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (sub (load addr:$dst), GR64:$src2), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
// Memory-Integer Subtraction
|
|
def SUB64mi8 : RIi8<0x83, MRM5m, (outs), (ins i64mem:$dst, i64i8imm :$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (sub (load addr:$dst), i64immSExt8:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def SUB64mi32 : RIi32<0x81, MRM5m, (outs), (ins i64mem:$dst, i64i32imm:$src2),
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (sub (load addr:$dst), i64immSExt32:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
let Uses = [EFLAGS] in {
|
|
let isTwoAddress = 1 in {
|
|
def SBB64rr : RI<0x19, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sube GR64:$src1, GR64:$src2))]>;
|
|
|
|
def SBB64rm : RI<0x1B, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sube GR64:$src1, (load addr:$src2)))]>;
|
|
|
|
def SBB64ri8 : RIi8<0x83, MRM3r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sube GR64:$src1, i64immSExt8:$src2))]>;
|
|
def SBB64ri32 : RIi32<0x81, MRM3r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sube GR64:$src1, i64immSExt32:$src2))]>;
|
|
} // isTwoAddress
|
|
|
|
def SBB64mr : RI<0x19, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (sube (load addr:$dst), GR64:$src2), addr:$dst)]>;
|
|
def SBB64mi8 : RIi8<0x83, MRM3m, (outs), (ins i64mem:$dst, i64i8imm :$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (sube (load addr:$dst), i64immSExt8:$src2), addr:$dst)]>;
|
|
def SBB64mi32 : RIi32<0x81, MRM3m, (outs), (ins i64mem:$dst, i64i32imm:$src2),
|
|
"sbb{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(store (sube (load addr:$dst), i64immSExt32:$src2), addr:$dst)]>;
|
|
} // Uses = [EFLAGS]
|
|
} // Defs = [EFLAGS]
|
|
|
|
// Unsigned multiplication
|
|
let Defs = [RAX,RDX,EFLAGS], Uses = [RAX], neverHasSideEffects = 1 in {
|
|
def MUL64r : RI<0xF7, MRM4r, (outs), (ins GR64:$src),
|
|
"mul{q}\t$src", []>; // RAX,RDX = RAX*GR64
|
|
let mayLoad = 1 in
|
|
def MUL64m : RI<0xF7, MRM4m, (outs), (ins i64mem:$src),
|
|
"mul{q}\t$src", []>; // RAX,RDX = RAX*[mem64]
|
|
|
|
// Signed multiplication
|
|
def IMUL64r : RI<0xF7, MRM5r, (outs), (ins GR64:$src),
|
|
"imul{q}\t$src", []>; // RAX,RDX = RAX*GR64
|
|
let mayLoad = 1 in
|
|
def IMUL64m : RI<0xF7, MRM5m, (outs), (ins i64mem:$src),
|
|
"imul{q}\t$src", []>; // RAX,RDX = RAX*[mem64]
|
|
}
|
|
|
|
let Defs = [EFLAGS] in {
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in
|
|
// Register-Register Signed Integer Multiplication
|
|
def IMUL64rr : RI<0xAF, MRMSrcReg, (outs GR64:$dst),
|
|
(ins GR64:$src1, GR64:$src2),
|
|
"imul{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (mul GR64:$src1, GR64:$src2)),
|
|
(implicit EFLAGS)]>, TB;
|
|
|
|
// Register-Memory Signed Integer Multiplication
|
|
def IMUL64rm : RI<0xAF, MRMSrcMem, (outs GR64:$dst),
|
|
(ins GR64:$src1, i64mem:$src2),
|
|
"imul{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (mul GR64:$src1, (load addr:$src2))),
|
|
(implicit EFLAGS)]>, TB;
|
|
} // isTwoAddress
|
|
|
|
// Suprisingly enough, these are not two address instructions!
|
|
|
|
// Register-Integer Signed Integer Multiplication
|
|
def IMUL64rri8 : RIi8<0x6B, MRMSrcReg, // GR64 = GR64*I8
|
|
(outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set GR64:$dst, (mul GR64:$src1, i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def IMUL64rri32 : RIi32<0x69, MRMSrcReg, // GR64 = GR64*I32
|
|
(outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set GR64:$dst, (mul GR64:$src1, i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
|
|
// Memory-Integer Signed Integer Multiplication
|
|
def IMUL64rmi8 : RIi8<0x6B, MRMSrcMem, // GR64 = [mem64]*I8
|
|
(outs GR64:$dst), (ins i64mem:$src1, i64i8imm: $src2),
|
|
"imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set GR64:$dst, (mul (load addr:$src1),
|
|
i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def IMUL64rmi32 : RIi32<0x69, MRMSrcMem, // GR64 = [mem64]*I32
|
|
(outs GR64:$dst), (ins i64mem:$src1, i64i32imm:$src2),
|
|
"imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set GR64:$dst, (mul (load addr:$src1),
|
|
i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
} // Defs = [EFLAGS]
|
|
|
|
// Unsigned division / remainder
|
|
let Defs = [RAX,RDX,EFLAGS], Uses = [RAX,RDX] in {
|
|
def DIV64r : RI<0xF7, MRM6r, (outs), (ins GR64:$src), // RDX:RAX/r64 = RAX,RDX
|
|
"div{q}\t$src", []>;
|
|
// Signed division / remainder
|
|
def IDIV64r: RI<0xF7, MRM7r, (outs), (ins GR64:$src), // RDX:RAX/r64 = RAX,RDX
|
|
"idiv{q}\t$src", []>;
|
|
let mayLoad = 1 in {
|
|
def DIV64m : RI<0xF7, MRM6m, (outs), (ins i64mem:$src), // RDX:RAX/[mem64] = RAX,RDX
|
|
"div{q}\t$src", []>;
|
|
def IDIV64m: RI<0xF7, MRM7m, (outs), (ins i64mem:$src), // RDX:RAX/[mem64] = RAX,RDX
|
|
"idiv{q}\t$src", []>;
|
|
}
|
|
}
|
|
|
|
// Unary instructions
|
|
let Defs = [EFLAGS], CodeSize = 2 in {
|
|
let isTwoAddress = 1 in
|
|
def NEG64r : RI<0xF7, MRM3r, (outs GR64:$dst), (ins GR64:$src), "neg{q}\t$dst",
|
|
[(set GR64:$dst, (ineg GR64:$src)),
|
|
(implicit EFLAGS)]>;
|
|
def NEG64m : RI<0xF7, MRM3m, (outs), (ins i64mem:$dst), "neg{q}\t$dst",
|
|
[(store (ineg (loadi64 addr:$dst)), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
let isTwoAddress = 1, isConvertibleToThreeAddress = 1 in
|
|
def INC64r : RI<0xFF, MRM0r, (outs GR64:$dst), (ins GR64:$src), "inc{q}\t$dst",
|
|
[(set GR64:$dst, (add GR64:$src, 1)),
|
|
(implicit EFLAGS)]>;
|
|
def INC64m : RI<0xFF, MRM0m, (outs), (ins i64mem:$dst), "inc{q}\t$dst",
|
|
[(store (add (loadi64 addr:$dst), 1), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
let isTwoAddress = 1, isConvertibleToThreeAddress = 1 in
|
|
def DEC64r : RI<0xFF, MRM1r, (outs GR64:$dst), (ins GR64:$src), "dec{q}\t$dst",
|
|
[(set GR64:$dst, (add GR64:$src, -1)),
|
|
(implicit EFLAGS)]>;
|
|
def DEC64m : RI<0xFF, MRM1m, (outs), (ins i64mem:$dst), "dec{q}\t$dst",
|
|
[(store (add (loadi64 addr:$dst), -1), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
// In 64-bit mode, single byte INC and DEC cannot be encoded.
|
|
let isTwoAddress = 1, isConvertibleToThreeAddress = 1 in {
|
|
// Can transform into LEA.
|
|
def INC64_16r : I<0xFF, MRM0r, (outs GR16:$dst), (ins GR16:$src), "inc{w}\t$dst",
|
|
[(set GR16:$dst, (add GR16:$src, 1)),
|
|
(implicit EFLAGS)]>,
|
|
OpSize, Requires<[In64BitMode]>;
|
|
def INC64_32r : I<0xFF, MRM0r, (outs GR32:$dst), (ins GR32:$src), "inc{l}\t$dst",
|
|
[(set GR32:$dst, (add GR32:$src, 1)),
|
|
(implicit EFLAGS)]>,
|
|
Requires<[In64BitMode]>;
|
|
def DEC64_16r : I<0xFF, MRM1r, (outs GR16:$dst), (ins GR16:$src), "dec{w}\t$dst",
|
|
[(set GR16:$dst, (add GR16:$src, -1)),
|
|
(implicit EFLAGS)]>,
|
|
OpSize, Requires<[In64BitMode]>;
|
|
def DEC64_32r : I<0xFF, MRM1r, (outs GR32:$dst), (ins GR32:$src), "dec{l}\t$dst",
|
|
[(set GR32:$dst, (add GR32:$src, -1)),
|
|
(implicit EFLAGS)]>,
|
|
Requires<[In64BitMode]>;
|
|
} // isConvertibleToThreeAddress
|
|
|
|
// These are duplicates of their 32-bit counterparts. Only needed so X86 knows
|
|
// how to unfold them.
|
|
let isTwoAddress = 0, CodeSize = 2 in {
|
|
def INC64_16m : I<0xFF, MRM0m, (outs), (ins i16mem:$dst), "inc{w}\t$dst",
|
|
[(store (add (loadi16 addr:$dst), 1), addr:$dst),
|
|
(implicit EFLAGS)]>,
|
|
OpSize, Requires<[In64BitMode]>;
|
|
def INC64_32m : I<0xFF, MRM0m, (outs), (ins i32mem:$dst), "inc{l}\t$dst",
|
|
[(store (add (loadi32 addr:$dst), 1), addr:$dst),
|
|
(implicit EFLAGS)]>,
|
|
Requires<[In64BitMode]>;
|
|
def DEC64_16m : I<0xFF, MRM1m, (outs), (ins i16mem:$dst), "dec{w}\t$dst",
|
|
[(store (add (loadi16 addr:$dst), -1), addr:$dst),
|
|
(implicit EFLAGS)]>,
|
|
OpSize, Requires<[In64BitMode]>;
|
|
def DEC64_32m : I<0xFF, MRM1m, (outs), (ins i32mem:$dst), "dec{l}\t$dst",
|
|
[(store (add (loadi32 addr:$dst), -1), addr:$dst),
|
|
(implicit EFLAGS)]>,
|
|
Requires<[In64BitMode]>;
|
|
}
|
|
} // Defs = [EFLAGS], CodeSize
|
|
|
|
|
|
let Defs = [EFLAGS] in {
|
|
// Shift instructions
|
|
let isTwoAddress = 1 in {
|
|
let Uses = [CL] in
|
|
def SHL64rCL : RI<0xD3, MRM4r, (outs GR64:$dst), (ins GR64:$src),
|
|
"shl{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(set GR64:$dst, (shl GR64:$src, CL))]>;
|
|
let isConvertibleToThreeAddress = 1 in // Can transform into LEA.
|
|
def SHL64ri : RIi8<0xC1, MRM4r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
|
|
"shl{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (shl GR64:$src1, (i8 imm:$src2)))]>;
|
|
// NOTE: We don't use shifts of a register by one, because 'add reg,reg' is
|
|
// cheaper.
|
|
} // isTwoAddress
|
|
|
|
let Uses = [CL] in
|
|
def SHL64mCL : RI<0xD3, MRM4m, (outs), (ins i64mem:$dst),
|
|
"shl{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(store (shl (loadi64 addr:$dst), CL), addr:$dst)]>;
|
|
def SHL64mi : RIi8<0xC1, MRM4m, (outs), (ins i64mem:$dst, i8imm:$src),
|
|
"shl{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (shl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
|
|
def SHL64m1 : RI<0xD1, MRM4m, (outs), (ins i64mem:$dst),
|
|
"shl{q}\t$dst",
|
|
[(store (shl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let Uses = [CL] in
|
|
def SHR64rCL : RI<0xD3, MRM5r, (outs GR64:$dst), (ins GR64:$src),
|
|
"shr{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(set GR64:$dst, (srl GR64:$src, CL))]>;
|
|
def SHR64ri : RIi8<0xC1, MRM5r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
|
|
"shr{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (srl GR64:$src1, (i8 imm:$src2)))]>;
|
|
def SHR64r1 : RI<0xD1, MRM5r, (outs GR64:$dst), (ins GR64:$src1),
|
|
"shr{q}\t$dst",
|
|
[(set GR64:$dst, (srl GR64:$src1, (i8 1)))]>;
|
|
} // isTwoAddress
|
|
|
|
let Uses = [CL] in
|
|
def SHR64mCL : RI<0xD3, MRM5m, (outs), (ins i64mem:$dst),
|
|
"shr{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(store (srl (loadi64 addr:$dst), CL), addr:$dst)]>;
|
|
def SHR64mi : RIi8<0xC1, MRM5m, (outs), (ins i64mem:$dst, i8imm:$src),
|
|
"shr{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (srl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
|
|
def SHR64m1 : RI<0xD1, MRM5m, (outs), (ins i64mem:$dst),
|
|
"shr{q}\t$dst",
|
|
[(store (srl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let Uses = [CL] in
|
|
def SAR64rCL : RI<0xD3, MRM7r, (outs GR64:$dst), (ins GR64:$src),
|
|
"sar{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(set GR64:$dst, (sra GR64:$src, CL))]>;
|
|
def SAR64ri : RIi8<0xC1, MRM7r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
|
|
"sar{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (sra GR64:$src1, (i8 imm:$src2)))]>;
|
|
def SAR64r1 : RI<0xD1, MRM7r, (outs GR64:$dst), (ins GR64:$src1),
|
|
"sar{q}\t$dst",
|
|
[(set GR64:$dst, (sra GR64:$src1, (i8 1)))]>;
|
|
} // isTwoAddress
|
|
|
|
let Uses = [CL] in
|
|
def SAR64mCL : RI<0xD3, MRM7m, (outs), (ins i64mem:$dst),
|
|
"sar{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(store (sra (loadi64 addr:$dst), CL), addr:$dst)]>;
|
|
def SAR64mi : RIi8<0xC1, MRM7m, (outs), (ins i64mem:$dst, i8imm:$src),
|
|
"sar{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (sra (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
|
|
def SAR64m1 : RI<0xD1, MRM7m, (outs), (ins i64mem:$dst),
|
|
"sar{q}\t$dst",
|
|
[(store (sra (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
|
|
|
|
// Rotate instructions
|
|
let isTwoAddress = 1 in {
|
|
let Uses = [CL] in
|
|
def ROL64rCL : RI<0xD3, MRM0r, (outs GR64:$dst), (ins GR64:$src),
|
|
"rol{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(set GR64:$dst, (rotl GR64:$src, CL))]>;
|
|
def ROL64ri : RIi8<0xC1, MRM0r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
|
|
"rol{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (rotl GR64:$src1, (i8 imm:$src2)))]>;
|
|
def ROL64r1 : RI<0xD1, MRM0r, (outs GR64:$dst), (ins GR64:$src1),
|
|
"rol{q}\t$dst",
|
|
[(set GR64:$dst, (rotl GR64:$src1, (i8 1)))]>;
|
|
} // isTwoAddress
|
|
|
|
let Uses = [CL] in
|
|
def ROL64mCL : I<0xD3, MRM0m, (outs), (ins i64mem:$dst),
|
|
"rol{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(store (rotl (loadi64 addr:$dst), CL), addr:$dst)]>;
|
|
def ROL64mi : RIi8<0xC1, MRM0m, (outs), (ins i64mem:$dst, i8imm:$src),
|
|
"rol{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (rotl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
|
|
def ROL64m1 : RI<0xD1, MRM0m, (outs), (ins i64mem:$dst),
|
|
"rol{q}\t$dst",
|
|
[(store (rotl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let Uses = [CL] in
|
|
def ROR64rCL : RI<0xD3, MRM1r, (outs GR64:$dst), (ins GR64:$src),
|
|
"ror{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(set GR64:$dst, (rotr GR64:$src, CL))]>;
|
|
def ROR64ri : RIi8<0xC1, MRM1r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
|
|
"ror{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (rotr GR64:$src1, (i8 imm:$src2)))]>;
|
|
def ROR64r1 : RI<0xD1, MRM1r, (outs GR64:$dst), (ins GR64:$src1),
|
|
"ror{q}\t$dst",
|
|
[(set GR64:$dst, (rotr GR64:$src1, (i8 1)))]>;
|
|
} // isTwoAddress
|
|
|
|
let Uses = [CL] in
|
|
def ROR64mCL : RI<0xD3, MRM1m, (outs), (ins i64mem:$dst),
|
|
"ror{q}\t{%cl, $dst|$dst, %CL}",
|
|
[(store (rotr (loadi64 addr:$dst), CL), addr:$dst)]>;
|
|
def ROR64mi : RIi8<0xC1, MRM1m, (outs), (ins i64mem:$dst, i8imm:$src),
|
|
"ror{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (rotr (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
|
|
def ROR64m1 : RI<0xD1, MRM1m, (outs), (ins i64mem:$dst),
|
|
"ror{q}\t$dst",
|
|
[(store (rotr (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
|
|
|
|
// Double shift instructions (generalizations of rotate)
|
|
let isTwoAddress = 1 in {
|
|
let Uses = [CL] in {
|
|
def SHLD64rrCL : RI<0xA5, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
|
|
[(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2, CL))]>, TB;
|
|
def SHRD64rrCL : RI<0xAD, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
|
|
[(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2, CL))]>, TB;
|
|
}
|
|
|
|
let isCommutable = 1 in { // FIXME: Update X86InstrInfo::commuteInstruction
|
|
def SHLD64rri8 : RIi8<0xA4, MRMDestReg,
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2, i8imm:$src3),
|
|
"shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2,
|
|
(i8 imm:$src3)))]>,
|
|
TB;
|
|
def SHRD64rri8 : RIi8<0xAC, MRMDestReg,
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2, i8imm:$src3),
|
|
"shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2,
|
|
(i8 imm:$src3)))]>,
|
|
TB;
|
|
} // isCommutable
|
|
} // isTwoAddress
|
|
|
|
let Uses = [CL] in {
|
|
def SHLD64mrCL : RI<0xA5, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
|
|
[(store (X86shld (loadi64 addr:$dst), GR64:$src2, CL),
|
|
addr:$dst)]>, TB;
|
|
def SHRD64mrCL : RI<0xAD, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
|
|
[(store (X86shrd (loadi64 addr:$dst), GR64:$src2, CL),
|
|
addr:$dst)]>, TB;
|
|
}
|
|
def SHLD64mri8 : RIi8<0xA4, MRMDestMem,
|
|
(outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
|
|
"shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(store (X86shld (loadi64 addr:$dst), GR64:$src2,
|
|
(i8 imm:$src3)), addr:$dst)]>,
|
|
TB;
|
|
def SHRD64mri8 : RIi8<0xAC, MRMDestMem,
|
|
(outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
|
|
"shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(store (X86shrd (loadi64 addr:$dst), GR64:$src2,
|
|
(i8 imm:$src3)), addr:$dst)]>,
|
|
TB;
|
|
} // Defs = [EFLAGS]
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Logical Instructions...
|
|
//
|
|
|
|
let isTwoAddress = 1 , AddedComplexity = 15 in
|
|
def NOT64r : RI<0xF7, MRM2r, (outs GR64:$dst), (ins GR64:$src), "not{q}\t$dst",
|
|
[(set GR64:$dst, (not GR64:$src))]>;
|
|
def NOT64m : RI<0xF7, MRM2m, (outs), (ins i64mem:$dst), "not{q}\t$dst",
|
|
[(store (not (loadi64 addr:$dst)), addr:$dst)]>;
|
|
|
|
let Defs = [EFLAGS] in {
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in
|
|
def AND64rr : RI<0x21, MRMDestReg,
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"and{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (and GR64:$src1, GR64:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def AND64rm : RI<0x23, MRMSrcMem,
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"and{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (and GR64:$src1, (load addr:$src2))),
|
|
(implicit EFLAGS)]>;
|
|
def AND64ri8 : RIi8<0x83, MRM4r,
|
|
(outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"and{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (and GR64:$src1, i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def AND64ri32 : RIi32<0x81, MRM4r,
|
|
(outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"and{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (and GR64:$src1, i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
} // isTwoAddress
|
|
|
|
def AND64mr : RI<0x21, MRMDestMem,
|
|
(outs), (ins i64mem:$dst, GR64:$src),
|
|
"and{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (and (load addr:$dst), GR64:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def AND64mi8 : RIi8<0x83, MRM4m,
|
|
(outs), (ins i64mem:$dst, i64i8imm :$src),
|
|
"and{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (and (load addr:$dst), i64immSExt8:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def AND64mi32 : RIi32<0x81, MRM4m,
|
|
(outs), (ins i64mem:$dst, i64i32imm:$src),
|
|
"and{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (and (loadi64 addr:$dst), i64immSExt32:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in
|
|
def OR64rr : RI<0x09, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"or{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (or GR64:$src1, GR64:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def OR64rm : RI<0x0B, MRMSrcMem , (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"or{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (or GR64:$src1, (load addr:$src2))),
|
|
(implicit EFLAGS)]>;
|
|
def OR64ri8 : RIi8<0x83, MRM1r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"or{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (or GR64:$src1, i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def OR64ri32 : RIi32<0x81, MRM1r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"or{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (or GR64:$src1, i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
} // isTwoAddress
|
|
|
|
def OR64mr : RI<0x09, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
|
|
"or{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (or (load addr:$dst), GR64:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def OR64mi8 : RIi8<0x83, MRM1m, (outs), (ins i64mem:$dst, i64i8imm:$src),
|
|
"or{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (or (load addr:$dst), i64immSExt8:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def OR64mi32 : RIi32<0x81, MRM1m, (outs), (ins i64mem:$dst, i64i32imm:$src),
|
|
"or{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (or (loadi64 addr:$dst), i64immSExt32:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in
|
|
def XOR64rr : RI<0x31, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"xor{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (xor GR64:$src1, GR64:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def XOR64rm : RI<0x33, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"xor{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (xor GR64:$src1, (load addr:$src2))),
|
|
(implicit EFLAGS)]>;
|
|
def XOR64ri8 : RIi8<0x83, MRM6r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
|
|
"xor{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (xor GR64:$src1, i64immSExt8:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def XOR64ri32 : RIi32<0x81, MRM6r,
|
|
(outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
|
|
"xor{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (xor GR64:$src1, i64immSExt32:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
} // isTwoAddress
|
|
|
|
def XOR64mr : RI<0x31, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
|
|
"xor{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (xor (load addr:$dst), GR64:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def XOR64mi8 : RIi8<0x83, MRM6m, (outs), (ins i64mem:$dst, i64i8imm :$src),
|
|
"xor{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (xor (load addr:$dst), i64immSExt8:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
def XOR64mi32 : RIi32<0x81, MRM6m, (outs), (ins i64mem:$dst, i64i32imm:$src),
|
|
"xor{q}\t{$src, $dst|$dst, $src}",
|
|
[(store (xor (loadi64 addr:$dst), i64immSExt32:$src), addr:$dst),
|
|
(implicit EFLAGS)]>;
|
|
} // Defs = [EFLAGS]
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Comparison Instructions...
|
|
//
|
|
|
|
// Integer comparison
|
|
let Defs = [EFLAGS] in {
|
|
let isCommutable = 1 in
|
|
def TEST64rr : RI<0x85, MRMDestReg, (outs), (ins GR64:$src1, GR64:$src2),
|
|
"test{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (and GR64:$src1, GR64:$src2), 0),
|
|
(implicit EFLAGS)]>;
|
|
def TEST64rm : RI<0x85, MRMSrcMem, (outs), (ins GR64:$src1, i64mem:$src2),
|
|
"test{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (and GR64:$src1, (loadi64 addr:$src2)), 0),
|
|
(implicit EFLAGS)]>;
|
|
def TEST64ri32 : RIi32<0xF7, MRM0r, (outs),
|
|
(ins GR64:$src1, i64i32imm:$src2),
|
|
"test{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (and GR64:$src1, i64immSExt32:$src2), 0),
|
|
(implicit EFLAGS)]>;
|
|
def TEST64mi32 : RIi32<0xF7, MRM0m, (outs),
|
|
(ins i64mem:$src1, i64i32imm:$src2),
|
|
"test{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (and (loadi64 addr:$src1), i64immSExt32:$src2), 0),
|
|
(implicit EFLAGS)]>;
|
|
|
|
def CMP64rr : RI<0x39, MRMDestReg, (outs), (ins GR64:$src1, GR64:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp GR64:$src1, GR64:$src2),
|
|
(implicit EFLAGS)]>;
|
|
def CMP64mr : RI<0x39, MRMDestMem, (outs), (ins i64mem:$src1, GR64:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (loadi64 addr:$src1), GR64:$src2),
|
|
(implicit EFLAGS)]>;
|
|
def CMP64rm : RI<0x3B, MRMSrcMem, (outs), (ins GR64:$src1, i64mem:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp GR64:$src1, (loadi64 addr:$src2)),
|
|
(implicit EFLAGS)]>;
|
|
def CMP64ri8 : RIi8<0x83, MRM7r, (outs), (ins GR64:$src1, i64i8imm:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp GR64:$src1, i64immSExt8:$src2),
|
|
(implicit EFLAGS)]>;
|
|
def CMP64ri32 : RIi32<0x81, MRM7r, (outs), (ins GR64:$src1, i64i32imm:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp GR64:$src1, i64immSExt32:$src2),
|
|
(implicit EFLAGS)]>;
|
|
def CMP64mi8 : RIi8<0x83, MRM7m, (outs), (ins i64mem:$src1, i64i8imm:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (loadi64 addr:$src1), i64immSExt8:$src2),
|
|
(implicit EFLAGS)]>;
|
|
def CMP64mi32 : RIi32<0x81, MRM7m, (outs),
|
|
(ins i64mem:$src1, i64i32imm:$src2),
|
|
"cmp{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86cmp (loadi64 addr:$src1), i64immSExt32:$src2),
|
|
(implicit EFLAGS)]>;
|
|
} // Defs = [EFLAGS]
|
|
|
|
// Bit tests.
|
|
// TODO: BTC, BTR, and BTS
|
|
let Defs = [EFLAGS] in {
|
|
def BT64rr : RI<0xA3, MRMDestReg, (outs), (ins GR64:$src1, GR64:$src2),
|
|
"bt{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86bt GR64:$src1, GR64:$src2),
|
|
(implicit EFLAGS)]>, TB;
|
|
|
|
// Unlike with the register+register form, the memory+register form of the
|
|
// bt instruction does not ignore the high bits of the index. From ISel's
|
|
// perspective, this is pretty bizarre. Disable these instructions for now.
|
|
//def BT64mr : RI<0xA3, MRMDestMem, (outs), (ins i64mem:$src1, GR64:$src2),
|
|
// "bt{q}\t{$src2, $src1|$src1, $src2}",
|
|
// [(X86bt (loadi64 addr:$src1), GR64:$src2),
|
|
// (implicit EFLAGS)]>, TB;
|
|
|
|
def BT64ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR64:$src1, i64i8imm:$src2),
|
|
"bt{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86bt GR64:$src1, i64immSExt8:$src2),
|
|
(implicit EFLAGS)]>, TB;
|
|
// Note that these instructions don't need FastBTMem because that
|
|
// only applies when the other operand is in a register. When it's
|
|
// an immediate, bt is still fast.
|
|
def BT64mi8 : Ii8<0xBA, MRM4m, (outs), (ins i64mem:$src1, i64i8imm:$src2),
|
|
"bt{q}\t{$src2, $src1|$src1, $src2}",
|
|
[(X86bt (loadi64 addr:$src1), i64immSExt8:$src2),
|
|
(implicit EFLAGS)]>, TB;
|
|
} // Defs = [EFLAGS]
|
|
|
|
// Conditional moves
|
|
let Uses = [EFLAGS], isTwoAddress = 1 in {
|
|
let isCommutable = 1 in {
|
|
def CMOVB64rr : RI<0x42, MRMSrcReg, // if <u, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovb\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_B, EFLAGS))]>, TB;
|
|
def CMOVAE64rr: RI<0x43, MRMSrcReg, // if >=u, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovae\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_AE, EFLAGS))]>, TB;
|
|
def CMOVE64rr : RI<0x44, MRMSrcReg, // if ==, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmove\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_E, EFLAGS))]>, TB;
|
|
def CMOVNE64rr: RI<0x45, MRMSrcReg, // if !=, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovne\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_NE, EFLAGS))]>, TB;
|
|
def CMOVBE64rr: RI<0x46, MRMSrcReg, // if <=u, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovbe\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_BE, EFLAGS))]>, TB;
|
|
def CMOVA64rr : RI<0x47, MRMSrcReg, // if >u, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmova\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_A, EFLAGS))]>, TB;
|
|
def CMOVL64rr : RI<0x4C, MRMSrcReg, // if <s, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovl\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_L, EFLAGS))]>, TB;
|
|
def CMOVGE64rr: RI<0x4D, MRMSrcReg, // if >=s, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovge\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_GE, EFLAGS))]>, TB;
|
|
def CMOVLE64rr: RI<0x4E, MRMSrcReg, // if <=s, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovle\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_LE, EFLAGS))]>, TB;
|
|
def CMOVG64rr : RI<0x4F, MRMSrcReg, // if >s, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovg\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_G, EFLAGS))]>, TB;
|
|
def CMOVS64rr : RI<0x48, MRMSrcReg, // if signed, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovs\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_S, EFLAGS))]>, TB;
|
|
def CMOVNS64rr: RI<0x49, MRMSrcReg, // if !signed, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovns\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_NS, EFLAGS))]>, TB;
|
|
def CMOVP64rr : RI<0x4A, MRMSrcReg, // if parity, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovp\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_P, EFLAGS))]>, TB;
|
|
def CMOVNP64rr : RI<0x4B, MRMSrcReg, // if !parity, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovnp\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_NP, EFLAGS))]>, TB;
|
|
def CMOVO64rr : RI<0x40, MRMSrcReg, // if overflow, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovo\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_O, EFLAGS))]>, TB;
|
|
def CMOVNO64rr : RI<0x41, MRMSrcReg, // if !overflow, GR64 = GR64
|
|
(outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
|
|
"cmovno\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
|
|
X86_COND_NO, EFLAGS))]>, TB;
|
|
} // isCommutable = 1
|
|
|
|
def CMOVB64rm : RI<0x42, MRMSrcMem, // if <u, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovb\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_B, EFLAGS))]>, TB;
|
|
def CMOVAE64rm: RI<0x43, MRMSrcMem, // if >=u, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovae\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_AE, EFLAGS))]>, TB;
|
|
def CMOVE64rm : RI<0x44, MRMSrcMem, // if ==, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmove\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_E, EFLAGS))]>, TB;
|
|
def CMOVNE64rm: RI<0x45, MRMSrcMem, // if !=, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovne\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_NE, EFLAGS))]>, TB;
|
|
def CMOVBE64rm: RI<0x46, MRMSrcMem, // if <=u, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovbe\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_BE, EFLAGS))]>, TB;
|
|
def CMOVA64rm : RI<0x47, MRMSrcMem, // if >u, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmova\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_A, EFLAGS))]>, TB;
|
|
def CMOVL64rm : RI<0x4C, MRMSrcMem, // if <s, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovl\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_L, EFLAGS))]>, TB;
|
|
def CMOVGE64rm: RI<0x4D, MRMSrcMem, // if >=s, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovge\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_GE, EFLAGS))]>, TB;
|
|
def CMOVLE64rm: RI<0x4E, MRMSrcMem, // if <=s, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovle\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_LE, EFLAGS))]>, TB;
|
|
def CMOVG64rm : RI<0x4F, MRMSrcMem, // if >s, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovg\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_G, EFLAGS))]>, TB;
|
|
def CMOVS64rm : RI<0x48, MRMSrcMem, // if signed, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovs\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_S, EFLAGS))]>, TB;
|
|
def CMOVNS64rm: RI<0x49, MRMSrcMem, // if !signed, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovns\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_NS, EFLAGS))]>, TB;
|
|
def CMOVP64rm : RI<0x4A, MRMSrcMem, // if parity, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovp\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_P, EFLAGS))]>, TB;
|
|
def CMOVNP64rm : RI<0x4B, MRMSrcMem, // if !parity, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovnp\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_NP, EFLAGS))]>, TB;
|
|
def CMOVO64rm : RI<0x40, MRMSrcMem, // if overflow, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovo\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_O, EFLAGS))]>, TB;
|
|
def CMOVNO64rm : RI<0x41, MRMSrcMem, // if !overflow, GR64 = [mem64]
|
|
(outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
|
|
"cmovno\t{$src2, $dst|$dst, $src2}",
|
|
[(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
|
|
X86_COND_NO, EFLAGS))]>, TB;
|
|
} // isTwoAddress
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conversion Instructions...
|
|
//
|
|
|
|
// f64 -> signed i64
|
|
def Int_CVTSD2SI64rr: RSDI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
|
|
"cvtsd2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst,
|
|
(int_x86_sse2_cvtsd2si64 VR128:$src))]>;
|
|
def Int_CVTSD2SI64rm: RSDI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f128mem:$src),
|
|
"cvtsd2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (int_x86_sse2_cvtsd2si64
|
|
(load addr:$src)))]>;
|
|
def CVTTSD2SI64rr: RSDI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins FR64:$src),
|
|
"cvttsd2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (fp_to_sint FR64:$src))]>;
|
|
def CVTTSD2SI64rm: RSDI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f64mem:$src),
|
|
"cvttsd2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (fp_to_sint (loadf64 addr:$src)))]>;
|
|
def Int_CVTTSD2SI64rr: RSDI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
|
|
"cvttsd2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst,
|
|
(int_x86_sse2_cvttsd2si64 VR128:$src))]>;
|
|
def Int_CVTTSD2SI64rm: RSDI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f128mem:$src),
|
|
"cvttsd2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst,
|
|
(int_x86_sse2_cvttsd2si64
|
|
(load addr:$src)))]>;
|
|
|
|
// Signed i64 -> f64
|
|
def CVTSI2SD64rr: RSDI<0x2A, MRMSrcReg, (outs FR64:$dst), (ins GR64:$src),
|
|
"cvtsi2sd{q}\t{$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (sint_to_fp GR64:$src))]>;
|
|
def CVTSI2SD64rm: RSDI<0x2A, MRMSrcMem, (outs FR64:$dst), (ins i64mem:$src),
|
|
"cvtsi2sd{q}\t{$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (sint_to_fp (loadi64 addr:$src)))]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
def Int_CVTSI2SD64rr: RSDI<0x2A, MRMSrcReg,
|
|
(outs VR128:$dst), (ins VR128:$src1, GR64:$src2),
|
|
"cvtsi2sd{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(int_x86_sse2_cvtsi642sd VR128:$src1,
|
|
GR64:$src2))]>;
|
|
def Int_CVTSI2SD64rm: RSDI<0x2A, MRMSrcMem,
|
|
(outs VR128:$dst), (ins VR128:$src1, i64mem:$src2),
|
|
"cvtsi2sd{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(int_x86_sse2_cvtsi642sd VR128:$src1,
|
|
(loadi64 addr:$src2)))]>;
|
|
} // isTwoAddress
|
|
|
|
// Signed i64 -> f32
|
|
def CVTSI2SS64rr: RSSI<0x2A, MRMSrcReg, (outs FR32:$dst), (ins GR64:$src),
|
|
"cvtsi2ss{q}\t{$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (sint_to_fp GR64:$src))]>;
|
|
def CVTSI2SS64rm: RSSI<0x2A, MRMSrcMem, (outs FR32:$dst), (ins i64mem:$src),
|
|
"cvtsi2ss{q}\t{$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (sint_to_fp (loadi64 addr:$src)))]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
def Int_CVTSI2SS64rr : RSSI<0x2A, MRMSrcReg,
|
|
(outs VR128:$dst), (ins VR128:$src1, GR64:$src2),
|
|
"cvtsi2ss{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(int_x86_sse_cvtsi642ss VR128:$src1,
|
|
GR64:$src2))]>;
|
|
def Int_CVTSI2SS64rm : RSSI<0x2A, MRMSrcMem,
|
|
(outs VR128:$dst), (ins VR128:$src1, i64mem:$src2),
|
|
"cvtsi2ss{q}\t{$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(int_x86_sse_cvtsi642ss VR128:$src1,
|
|
(loadi64 addr:$src2)))]>;
|
|
}
|
|
|
|
// f32 -> signed i64
|
|
def Int_CVTSS2SI64rr: RSSI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
|
|
"cvtss2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst,
|
|
(int_x86_sse_cvtss2si64 VR128:$src))]>;
|
|
def Int_CVTSS2SI64rm: RSSI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
|
|
"cvtss2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (int_x86_sse_cvtss2si64
|
|
(load addr:$src)))]>;
|
|
def CVTTSS2SI64rr: RSSI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins FR32:$src),
|
|
"cvttss2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (fp_to_sint FR32:$src))]>;
|
|
def CVTTSS2SI64rm: RSSI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
|
|
"cvttss2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (fp_to_sint (loadf32 addr:$src)))]>;
|
|
def Int_CVTTSS2SI64rr: RSSI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
|
|
"cvttss2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst,
|
|
(int_x86_sse_cvttss2si64 VR128:$src))]>;
|
|
def Int_CVTTSS2SI64rm: RSSI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
|
|
"cvttss2si{q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst,
|
|
(int_x86_sse_cvttss2si64 (load addr:$src)))]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Alias Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Alias instructions that map movr0 to xor. Use xorl instead of xorq; it's
|
|
// equivalent due to implicit zero-extending, and it sometimes has a smaller
|
|
// encoding.
|
|
// FIXME: AddedComplexity gives this a higher priority than MOV64ri32. Remove
|
|
// when we have a better way to specify isel priority.
|
|
let AddedComplexity = 1 in
|
|
def : Pat<(i64 0),
|
|
(SUBREG_TO_REG (i64 0), (MOV32r0), x86_subreg_32bit)>;
|
|
|
|
|
|
// Materialize i64 constant where top 32-bits are zero.
|
|
let AddedComplexity = 1, isReMaterializable = 1, isAsCheapAsAMove = 1 in
|
|
def MOV64ri64i32 : Ii32<0xB8, AddRegFrm, (outs GR64:$dst), (ins i64i32imm:$src),
|
|
"mov{l}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
|
|
[(set GR64:$dst, i64immZExt32:$src)]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Thread Local Storage Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// All calls clobber the non-callee saved registers. RSP is marked as
|
|
// a use to prevent stack-pointer assignments that appear immediately
|
|
// before calls from potentially appearing dead.
|
|
let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
|
|
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
|
|
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
|
|
Uses = [RSP] in
|
|
def TLS_addr64 : I<0, Pseudo, (outs), (ins lea64mem:$sym),
|
|
".byte\t0x66; "
|
|
"leaq\t$sym(%rip), %rdi; "
|
|
".word\t0x6666; "
|
|
"rex64; "
|
|
"call\t__tls_get_addr@PLT",
|
|
[(X86tlsaddr tls64addr:$sym)]>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
let AddedComplexity = 5 in
|
|
def MOV64GSrm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
|
|
"movq\t%gs:$src, $dst",
|
|
[(set GR64:$dst, (gsload addr:$src))]>, SegGS;
|
|
|
|
let AddedComplexity = 5 in
|
|
def MOV64FSrm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
|
|
"movq\t%fs:$src, $dst",
|
|
[(set GR64:$dst, (fsload addr:$src))]>, SegFS;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Atomic Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let Defs = [RAX, EFLAGS], Uses = [RAX] in {
|
|
def LCMPXCHG64 : RI<0xB1, MRMDestMem, (outs), (ins i64mem:$ptr, GR64:$swap),
|
|
"lock\n\t"
|
|
"cmpxchgq\t$swap,$ptr",
|
|
[(X86cas addr:$ptr, GR64:$swap, 8)]>, TB, LOCK;
|
|
}
|
|
|
|
let Constraints = "$val = $dst" in {
|
|
let Defs = [EFLAGS] in
|
|
def LXADD64 : RI<0xC1, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$ptr,GR64:$val),
|
|
"lock\n\t"
|
|
"xadd\t$val, $ptr",
|
|
[(set GR64:$dst, (atomic_load_add_64 addr:$ptr, GR64:$val))]>,
|
|
TB, LOCK;
|
|
|
|
def XCHG64rm : RI<0x87, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$ptr,GR64:$val),
|
|
"xchg\t$val, $ptr",
|
|
[(set GR64:$dst, (atomic_swap_64 addr:$ptr, GR64:$val))]>;
|
|
}
|
|
|
|
// Optimized codegen when the non-memory output is not used.
|
|
// FIXME: Use normal add / sub instructions and add lock prefix dynamically.
|
|
def LOCK_ADD64mr : RI<0x03, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"lock\n\t"
|
|
"add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
|
|
def LOCK_ADD64mi8 : RIi8<0x83, MRM0m, (outs),
|
|
(ins i64mem:$dst, i64i8imm :$src2),
|
|
"lock\n\t"
|
|
"add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
|
|
def LOCK_ADD64mi32 : RIi32<0x81, MRM0m, (outs),
|
|
(ins i64mem:$dst, i64i32imm :$src2),
|
|
"lock\n\t"
|
|
"add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
|
|
def LOCK_SUB64mr : RI<0x29, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
|
|
"lock\n\t"
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
|
|
def LOCK_SUB64mi8 : RIi8<0x83, MRM5m, (outs),
|
|
(ins i64mem:$dst, i64i8imm :$src2),
|
|
"lock\n\t"
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
|
|
def LOCK_SUB64mi32 : RIi32<0x81, MRM5m, (outs),
|
|
(ins i64mem:$dst, i64i32imm:$src2),
|
|
"lock\n\t"
|
|
"sub{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
|
|
def LOCK_INC64m : RI<0xFF, MRM0m, (outs), (ins i64mem:$dst),
|
|
"lock\n\t"
|
|
"inc{q}\t$dst", []>, LOCK;
|
|
def LOCK_DEC64m : RI<0xFF, MRM1m, (outs), (ins i64mem:$dst),
|
|
"lock\n\t"
|
|
"dec{q}\t$dst", []>, LOCK;
|
|
|
|
// Atomic exchange, and, or, xor
|
|
let Constraints = "$val = $dst", Defs = [EFLAGS],
|
|
usesCustomDAGSchedInserter = 1 in {
|
|
def ATOMAND64 : I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMAND64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_and_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMOR64 : I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMOR64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_or_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMXOR64 : I<0, Pseudo,(outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMXOR64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_xor_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMNAND64 : I<0, Pseudo,(outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMNAND64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_nand_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMMIN64: I<0, Pseudo, (outs GR64:$dst), (ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMMIN64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_min_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMMAX64: I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMMAX64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_max_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMUMIN64: I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMUMIN64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_umin_64 addr:$ptr, GR64:$val))]>;
|
|
def ATOMUMAX64: I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
|
|
"#ATOMUMAX64 PSEUDO!",
|
|
[(set GR64:$dst, (atomic_load_umax_64 addr:$ptr, GR64:$val))]>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Non-Instruction Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// ConstantPool GlobalAddress, ExternalSymbol, and JumpTable when not in small
|
|
// code model mode, should use 'movabs'. FIXME: This is really a hack, the
|
|
// 'movabs' predicate should handle this sort of thing.
|
|
def : Pat<(i64 (X86Wrapper tconstpool :$dst)),
|
|
(MOV64ri tconstpool :$dst)>, Requires<[FarData]>;
|
|
def : Pat<(i64 (X86Wrapper tjumptable :$dst)),
|
|
(MOV64ri tjumptable :$dst)>, Requires<[FarData]>;
|
|
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
|
|
(MOV64ri tglobaladdr :$dst)>, Requires<[FarData]>;
|
|
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
|
|
(MOV64ri texternalsym:$dst)>, Requires<[FarData]>;
|
|
|
|
// In static codegen with small code model, we can get the address of a label
|
|
// into a register with 'movl'. FIXME: This is a hack, the 'imm' predicate of
|
|
// the MOV64ri64i32 should accept these.
|
|
def : Pat<(i64 (X86Wrapper tconstpool :$dst)),
|
|
(MOV64ri64i32 tconstpool :$dst)>, Requires<[SmallCode]>;
|
|
def : Pat<(i64 (X86Wrapper tjumptable :$dst)),
|
|
(MOV64ri64i32 tjumptable :$dst)>, Requires<[SmallCode]>;
|
|
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
|
|
(MOV64ri64i32 tglobaladdr :$dst)>, Requires<[SmallCode]>;
|
|
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
|
|
(MOV64ri64i32 texternalsym:$dst)>, Requires<[SmallCode]>;
|
|
|
|
// In kernel code model, we can get the address of a label
|
|
// into a register with 'movq'. FIXME: This is a hack, the 'imm' predicate of
|
|
// the MOV64ri32 should accept these.
|
|
def : Pat<(i64 (X86Wrapper tconstpool :$dst)),
|
|
(MOV64ri32 tconstpool :$dst)>, Requires<[KernelCode]>;
|
|
def : Pat<(i64 (X86Wrapper tjumptable :$dst)),
|
|
(MOV64ri32 tjumptable :$dst)>, Requires<[KernelCode]>;
|
|
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
|
|
(MOV64ri32 tglobaladdr :$dst)>, Requires<[KernelCode]>;
|
|
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
|
|
(MOV64ri32 texternalsym:$dst)>, Requires<[KernelCode]>;
|
|
|
|
// If we have small model and -static mode, it is safe to store global addresses
|
|
// directly as immediates. FIXME: This is really a hack, the 'imm' predicate
|
|
// for MOV64mi32 should handle this sort of thing.
|
|
def : Pat<(store (i64 (X86Wrapper tconstpool:$src)), addr:$dst),
|
|
(MOV64mi32 addr:$dst, tconstpool:$src)>,
|
|
Requires<[NearData, IsStatic]>;
|
|
def : Pat<(store (i64 (X86Wrapper tjumptable:$src)), addr:$dst),
|
|
(MOV64mi32 addr:$dst, tjumptable:$src)>,
|
|
Requires<[NearData, IsStatic]>;
|
|
def : Pat<(store (i64 (X86Wrapper tglobaladdr:$src)), addr:$dst),
|
|
(MOV64mi32 addr:$dst, tglobaladdr:$src)>,
|
|
Requires<[NearData, IsStatic]>;
|
|
def : Pat<(store (i64 (X86Wrapper texternalsym:$src)), addr:$dst),
|
|
(MOV64mi32 addr:$dst, texternalsym:$src)>,
|
|
Requires<[NearData, IsStatic]>;
|
|
|
|
// Calls
|
|
// Direct PC relative function call for small code model. 32-bit displacement
|
|
// sign extended to 64-bit.
|
|
def : Pat<(X86call (i64 tglobaladdr:$dst)),
|
|
(CALL64pcrel32 tglobaladdr:$dst)>, Requires<[NotWin64]>;
|
|
def : Pat<(X86call (i64 texternalsym:$dst)),
|
|
(CALL64pcrel32 texternalsym:$dst)>, Requires<[NotWin64]>;
|
|
|
|
def : Pat<(X86call (i64 tglobaladdr:$dst)),
|
|
(WINCALL64pcrel32 tglobaladdr:$dst)>, Requires<[IsWin64]>;
|
|
def : Pat<(X86call (i64 texternalsym:$dst)),
|
|
(WINCALL64pcrel32 texternalsym:$dst)>, Requires<[IsWin64]>;
|
|
|
|
// tailcall stuff
|
|
def : Pat<(X86tcret GR64:$dst, imm:$off),
|
|
(TCRETURNri64 GR64:$dst, imm:$off)>;
|
|
|
|
def : Pat<(X86tcret (i64 tglobaladdr:$dst), imm:$off),
|
|
(TCRETURNdi64 texternalsym:$dst, imm:$off)>;
|
|
|
|
def : Pat<(X86tcret (i64 texternalsym:$dst), imm:$off),
|
|
(TCRETURNdi64 texternalsym:$dst, imm:$off)>;
|
|
|
|
// Comparisons.
|
|
|
|
// TEST R,R is smaller than CMP R,0
|
|
def : Pat<(parallel (X86cmp GR64:$src1, 0), (implicit EFLAGS)),
|
|
(TEST64rr GR64:$src1, GR64:$src1)>;
|
|
|
|
// Conditional moves with folded loads with operands swapped and conditions
|
|
// inverted.
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_B, EFLAGS),
|
|
(CMOVAE64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_AE, EFLAGS),
|
|
(CMOVB64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_E, EFLAGS),
|
|
(CMOVNE64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NE, EFLAGS),
|
|
(CMOVE64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_BE, EFLAGS),
|
|
(CMOVA64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_A, EFLAGS),
|
|
(CMOVBE64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_L, EFLAGS),
|
|
(CMOVGE64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_GE, EFLAGS),
|
|
(CMOVL64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_LE, EFLAGS),
|
|
(CMOVG64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_G, EFLAGS),
|
|
(CMOVLE64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_P, EFLAGS),
|
|
(CMOVNP64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NP, EFLAGS),
|
|
(CMOVP64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_S, EFLAGS),
|
|
(CMOVNS64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NS, EFLAGS),
|
|
(CMOVS64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_O, EFLAGS),
|
|
(CMOVNO64rm GR64:$src2, addr:$src1)>;
|
|
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NO, EFLAGS),
|
|
(CMOVO64rm GR64:$src2, addr:$src1)>;
|
|
|
|
// zextload bool -> zextload byte
|
|
def : Pat<(zextloadi64i1 addr:$src), (MOVZX64rm8 addr:$src)>;
|
|
|
|
// extload
|
|
// When extloading from 16-bit and smaller memory locations into 64-bit registers,
|
|
// use zero-extending loads so that the entire 64-bit register is defined, avoiding
|
|
// partial-register updates.
|
|
def : Pat<(extloadi64i1 addr:$src), (MOVZX64rm8 addr:$src)>;
|
|
def : Pat<(extloadi64i8 addr:$src), (MOVZX64rm8 addr:$src)>;
|
|
def : Pat<(extloadi64i16 addr:$src), (MOVZX64rm16 addr:$src)>;
|
|
// For other extloads, use subregs, since the high contents of the register are
|
|
// defined after an extload.
|
|
def : Pat<(extloadi64i32 addr:$src),
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), (MOV32rm addr:$src),
|
|
x86_subreg_32bit)>;
|
|
def : Pat<(extloadi16i1 addr:$src),
|
|
(INSERT_SUBREG (i16 (IMPLICIT_DEF)), (MOV8rm addr:$src),
|
|
x86_subreg_8bit)>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(extloadi16i8 addr:$src),
|
|
(INSERT_SUBREG (i16 (IMPLICIT_DEF)), (MOV8rm addr:$src),
|
|
x86_subreg_8bit)>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
// anyext
|
|
def : Pat<(i64 (anyext GR8:$src)),
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR8:$src, x86_subreg_8bit)>;
|
|
def : Pat<(i64 (anyext GR16:$src)),
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR16:$src, x86_subreg_16bit)>;
|
|
def : Pat<(i64 (anyext GR32:$src)),
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, x86_subreg_32bit)>;
|
|
def : Pat<(i16 (anyext GR8:$src)),
|
|
(INSERT_SUBREG (i16 (IMPLICIT_DEF)), GR8:$src, x86_subreg_8bit)>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(i32 (anyext GR8:$src)),
|
|
(INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR8:$src, x86_subreg_8bit)>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Some peepholes
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Odd encoding trick: -128 fits into an 8-bit immediate field while
|
|
// +128 doesn't, so in this special case use a sub instead of an add.
|
|
def : Pat<(add GR64:$src1, 128),
|
|
(SUB64ri8 GR64:$src1, -128)>;
|
|
def : Pat<(store (add (loadi64 addr:$dst), 128), addr:$dst),
|
|
(SUB64mi8 addr:$dst, -128)>;
|
|
|
|
// The same trick applies for 32-bit immediate fields in 64-bit
|
|
// instructions.
|
|
def : Pat<(add GR64:$src1, 0x0000000080000000),
|
|
(SUB64ri32 GR64:$src1, 0xffffffff80000000)>;
|
|
def : Pat<(store (add (loadi64 addr:$dst), 0x00000000800000000), addr:$dst),
|
|
(SUB64mi32 addr:$dst, 0xffffffff80000000)>;
|
|
|
|
// r & (2^32-1) ==> movz
|
|
def : Pat<(and GR64:$src, 0x00000000FFFFFFFF),
|
|
(MOVZX64rr32 (EXTRACT_SUBREG GR64:$src, x86_subreg_32bit))>;
|
|
// r & (2^16-1) ==> movz
|
|
def : Pat<(and GR64:$src, 0xffff),
|
|
(MOVZX64rr16 (i16 (EXTRACT_SUBREG GR64:$src, x86_subreg_16bit)))>;
|
|
// r & (2^8-1) ==> movz
|
|
def : Pat<(and GR64:$src, 0xff),
|
|
(MOVZX64rr8 (i8 (EXTRACT_SUBREG GR64:$src, x86_subreg_8bit)))>;
|
|
// r & (2^8-1) ==> movz
|
|
def : Pat<(and GR32:$src1, 0xff),
|
|
(MOVZX32rr8 (EXTRACT_SUBREG GR32:$src1, x86_subreg_8bit))>,
|
|
Requires<[In64BitMode]>;
|
|
// r & (2^8-1) ==> movz
|
|
def : Pat<(and GR16:$src1, 0xff),
|
|
(MOVZX16rr8 (i8 (EXTRACT_SUBREG GR16:$src1, x86_subreg_8bit)))>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
// sext_inreg patterns
|
|
def : Pat<(sext_inreg GR64:$src, i32),
|
|
(MOVSX64rr32 (EXTRACT_SUBREG GR64:$src, x86_subreg_32bit))>;
|
|
def : Pat<(sext_inreg GR64:$src, i16),
|
|
(MOVSX64rr16 (EXTRACT_SUBREG GR64:$src, x86_subreg_16bit))>;
|
|
def : Pat<(sext_inreg GR64:$src, i8),
|
|
(MOVSX64rr8 (EXTRACT_SUBREG GR64:$src, x86_subreg_8bit))>;
|
|
def : Pat<(sext_inreg GR32:$src, i8),
|
|
(MOVSX32rr8 (EXTRACT_SUBREG GR32:$src, x86_subreg_8bit))>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(sext_inreg GR16:$src, i8),
|
|
(MOVSX16rr8 (i8 (EXTRACT_SUBREG GR16:$src, x86_subreg_8bit)))>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
// trunc patterns
|
|
def : Pat<(i32 (trunc GR64:$src)),
|
|
(EXTRACT_SUBREG GR64:$src, x86_subreg_32bit)>;
|
|
def : Pat<(i16 (trunc GR64:$src)),
|
|
(EXTRACT_SUBREG GR64:$src, x86_subreg_16bit)>;
|
|
def : Pat<(i8 (trunc GR64:$src)),
|
|
(EXTRACT_SUBREG GR64:$src, x86_subreg_8bit)>;
|
|
def : Pat<(i8 (trunc GR32:$src)),
|
|
(EXTRACT_SUBREG GR32:$src, x86_subreg_8bit)>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(i8 (trunc GR16:$src)),
|
|
(EXTRACT_SUBREG GR16:$src, x86_subreg_8bit)>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
// h-register tricks.
|
|
// For now, be conservative on x86-64 and use an h-register extract only if the
|
|
// value is immediately zero-extended or stored, which are somewhat common
|
|
// cases. This uses a bunch of code to prevent a register requiring a REX prefix
|
|
// from being allocated in the same instruction as the h register, as there's
|
|
// currently no way to describe this requirement to the register allocator.
|
|
|
|
// h-register extract and zero-extend.
|
|
def : Pat<(and (srl_su GR64:$src, (i8 8)), (i64 255)),
|
|
(SUBREG_TO_REG
|
|
(i64 0),
|
|
(MOVZX32_NOREXrr8
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR64:$src, GR64_ABCD),
|
|
x86_subreg_8bit_hi)),
|
|
x86_subreg_32bit)>;
|
|
def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)),
|
|
(MOVZX32_NOREXrr8
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD),
|
|
x86_subreg_8bit_hi))>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(srl_su GR16:$src, (i8 8)),
|
|
(EXTRACT_SUBREG
|
|
(MOVZX32_NOREXrr8
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
|
|
x86_subreg_8bit_hi)),
|
|
x86_subreg_16bit)>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(i32 (zext (srl_su GR16:$src, (i8 8)))),
|
|
(MOVZX32_NOREXrr8
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
|
|
x86_subreg_8bit_hi))>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(i64 (zext (srl_su GR16:$src, (i8 8)))),
|
|
(SUBREG_TO_REG
|
|
(i64 0),
|
|
(MOVZX32_NOREXrr8
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
|
|
x86_subreg_8bit_hi)),
|
|
x86_subreg_32bit)>;
|
|
|
|
// h-register extract and store.
|
|
def : Pat<(store (i8 (trunc_su (srl_su GR64:$src, (i8 8)))), addr:$dst),
|
|
(MOV8mr_NOREX
|
|
addr:$dst,
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR64:$src, GR64_ABCD),
|
|
x86_subreg_8bit_hi))>;
|
|
def : Pat<(store (i8 (trunc_su (srl_su GR32:$src, (i8 8)))), addr:$dst),
|
|
(MOV8mr_NOREX
|
|
addr:$dst,
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD),
|
|
x86_subreg_8bit_hi))>,
|
|
Requires<[In64BitMode]>;
|
|
def : Pat<(store (i8 (trunc_su (srl_su GR16:$src, (i8 8)))), addr:$dst),
|
|
(MOV8mr_NOREX
|
|
addr:$dst,
|
|
(EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
|
|
x86_subreg_8bit_hi))>,
|
|
Requires<[In64BitMode]>;
|
|
|
|
// (shl x, 1) ==> (add x, x)
|
|
def : Pat<(shl GR64:$src1, (i8 1)), (ADD64rr GR64:$src1, GR64:$src1)>;
|
|
|
|
// (shl x (and y, 63)) ==> (shl x, y)
|
|
def : Pat<(shl GR64:$src1, (and CL:$amt, 63)),
|
|
(SHL64rCL GR64:$src1)>;
|
|
def : Pat<(store (shl (loadi64 addr:$dst), (and CL:$amt, 63)), addr:$dst),
|
|
(SHL64mCL addr:$dst)>;
|
|
|
|
def : Pat<(srl GR64:$src1, (and CL:$amt, 63)),
|
|
(SHR64rCL GR64:$src1)>;
|
|
def : Pat<(store (srl (loadi64 addr:$dst), (and CL:$amt, 63)), addr:$dst),
|
|
(SHR64mCL addr:$dst)>;
|
|
|
|
def : Pat<(sra GR64:$src1, (and CL:$amt, 63)),
|
|
(SAR64rCL GR64:$src1)>;
|
|
def : Pat<(store (sra (loadi64 addr:$dst), (and CL:$amt, 63)), addr:$dst),
|
|
(SAR64mCL addr:$dst)>;
|
|
|
|
// (or (x >> c) | (y << (64 - c))) ==> (shrd64 x, y, c)
|
|
def : Pat<(or (srl GR64:$src1, CL:$amt),
|
|
(shl GR64:$src2, (sub 64, CL:$amt))),
|
|
(SHRD64rrCL GR64:$src1, GR64:$src2)>;
|
|
|
|
def : Pat<(store (or (srl (loadi64 addr:$dst), CL:$amt),
|
|
(shl GR64:$src2, (sub 64, CL:$amt))), addr:$dst),
|
|
(SHRD64mrCL addr:$dst, GR64:$src2)>;
|
|
|
|
def : Pat<(or (srl GR64:$src1, (i8 (trunc RCX:$amt))),
|
|
(shl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
|
|
(SHRD64rrCL GR64:$src1, GR64:$src2)>;
|
|
|
|
def : Pat<(store (or (srl (loadi64 addr:$dst), (i8 (trunc RCX:$amt))),
|
|
(shl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
|
|
addr:$dst),
|
|
(SHRD64mrCL addr:$dst, GR64:$src2)>;
|
|
|
|
def : Pat<(shrd GR64:$src1, (i8 imm:$amt1), GR64:$src2, (i8 imm:$amt2)),
|
|
(SHRD64rri8 GR64:$src1, GR64:$src2, (i8 imm:$amt1))>;
|
|
|
|
def : Pat<(store (shrd (loadi64 addr:$dst), (i8 imm:$amt1),
|
|
GR64:$src2, (i8 imm:$amt2)), addr:$dst),
|
|
(SHRD64mri8 addr:$dst, GR64:$src2, (i8 imm:$amt1))>;
|
|
|
|
// (or (x << c) | (y >> (64 - c))) ==> (shld64 x, y, c)
|
|
def : Pat<(or (shl GR64:$src1, CL:$amt),
|
|
(srl GR64:$src2, (sub 64, CL:$amt))),
|
|
(SHLD64rrCL GR64:$src1, GR64:$src2)>;
|
|
|
|
def : Pat<(store (or (shl (loadi64 addr:$dst), CL:$amt),
|
|
(srl GR64:$src2, (sub 64, CL:$amt))), addr:$dst),
|
|
(SHLD64mrCL addr:$dst, GR64:$src2)>;
|
|
|
|
def : Pat<(or (shl GR64:$src1, (i8 (trunc RCX:$amt))),
|
|
(srl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
|
|
(SHLD64rrCL GR64:$src1, GR64:$src2)>;
|
|
|
|
def : Pat<(store (or (shl (loadi64 addr:$dst), (i8 (trunc RCX:$amt))),
|
|
(srl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
|
|
addr:$dst),
|
|
(SHLD64mrCL addr:$dst, GR64:$src2)>;
|
|
|
|
def : Pat<(shld GR64:$src1, (i8 imm:$amt1), GR64:$src2, (i8 imm:$amt2)),
|
|
(SHLD64rri8 GR64:$src1, GR64:$src2, (i8 imm:$amt1))>;
|
|
|
|
def : Pat<(store (shld (loadi64 addr:$dst), (i8 imm:$amt1),
|
|
GR64:$src2, (i8 imm:$amt2)), addr:$dst),
|
|
(SHLD64mri8 addr:$dst, GR64:$src2, (i8 imm:$amt1))>;
|
|
|
|
// X86 specific add which produces a flag.
|
|
def : Pat<(addc GR64:$src1, GR64:$src2),
|
|
(ADD64rr GR64:$src1, GR64:$src2)>;
|
|
def : Pat<(addc GR64:$src1, (load addr:$src2)),
|
|
(ADD64rm GR64:$src1, addr:$src2)>;
|
|
def : Pat<(addc GR64:$src1, i64immSExt8:$src2),
|
|
(ADD64ri8 GR64:$src1, i64immSExt8:$src2)>;
|
|
def : Pat<(addc GR64:$src1, i64immSExt32:$src2),
|
|
(ADD64ri32 GR64:$src1, imm:$src2)>;
|
|
|
|
def : Pat<(subc GR64:$src1, GR64:$src2),
|
|
(SUB64rr GR64:$src1, GR64:$src2)>;
|
|
def : Pat<(subc GR64:$src1, (load addr:$src2)),
|
|
(SUB64rm GR64:$src1, addr:$src2)>;
|
|
def : Pat<(subc GR64:$src1, i64immSExt8:$src2),
|
|
(SUB64ri8 GR64:$src1, i64immSExt8:$src2)>;
|
|
def : Pat<(subc GR64:$src1, imm:$src2),
|
|
(SUB64ri32 GR64:$src1, i64immSExt32:$src2)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// EFLAGS-defining Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Register-Register Addition with EFLAGS result
|
|
def : Pat<(parallel (X86add_flag GR64:$src1, GR64:$src2),
|
|
(implicit EFLAGS)),
|
|
(ADD64rr GR64:$src1, GR64:$src2)>;
|
|
|
|
// Register-Integer Addition with EFLAGS result
|
|
def : Pat<(parallel (X86add_flag GR64:$src1, i64immSExt8:$src2),
|
|
(implicit EFLAGS)),
|
|
(ADD64ri8 GR64:$src1, i64immSExt8:$src2)>;
|
|
def : Pat<(parallel (X86add_flag GR64:$src1, i64immSExt32:$src2),
|
|
(implicit EFLAGS)),
|
|
(ADD64ri32 GR64:$src1, i64immSExt32:$src2)>;
|
|
|
|
// Register-Memory Addition with EFLAGS result
|
|
def : Pat<(parallel (X86add_flag GR64:$src1, (loadi64 addr:$src2)),
|
|
(implicit EFLAGS)),
|
|
(ADD64rm GR64:$src1, addr:$src2)>;
|
|
|
|
// Memory-Register Addition with EFLAGS result
|
|
def : Pat<(parallel (store (X86add_flag (loadi64 addr:$dst), GR64:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(ADD64mr addr:$dst, GR64:$src2)>;
|
|
def : Pat<(parallel (store (X86add_flag (loadi64 addr:$dst), i64immSExt8:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(ADD64mi8 addr:$dst, i64immSExt8:$src2)>;
|
|
def : Pat<(parallel (store (X86add_flag (loadi64 addr:$dst), i64immSExt32:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(ADD64mi32 addr:$dst, i64immSExt32:$src2)>;
|
|
|
|
// Register-Register Subtraction with EFLAGS result
|
|
def : Pat<(parallel (X86sub_flag GR64:$src1, GR64:$src2),
|
|
(implicit EFLAGS)),
|
|
(SUB64rr GR64:$src1, GR64:$src2)>;
|
|
|
|
// Register-Memory Subtraction with EFLAGS result
|
|
def : Pat<(parallel (X86sub_flag GR64:$src1, (loadi64 addr:$src2)),
|
|
(implicit EFLAGS)),
|
|
(SUB64rm GR64:$src1, addr:$src2)>;
|
|
|
|
// Register-Integer Subtraction with EFLAGS result
|
|
def : Pat<(parallel (X86sub_flag GR64:$src1, i64immSExt8:$src2),
|
|
(implicit EFLAGS)),
|
|
(SUB64ri8 GR64:$src1, i64immSExt8:$src2)>;
|
|
def : Pat<(parallel (X86sub_flag GR64:$src1, i64immSExt32:$src2),
|
|
(implicit EFLAGS)),
|
|
(SUB64ri32 GR64:$src1, i64immSExt32:$src2)>;
|
|
|
|
// Memory-Register Subtraction with EFLAGS result
|
|
def : Pat<(parallel (store (X86sub_flag (loadi64 addr:$dst), GR64:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(SUB64mr addr:$dst, GR64:$src2)>;
|
|
|
|
// Memory-Integer Subtraction with EFLAGS result
|
|
def : Pat<(parallel (store (X86sub_flag (loadi64 addr:$dst), i64immSExt8:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(SUB64mi8 addr:$dst, i64immSExt8:$src2)>;
|
|
def : Pat<(parallel (store (X86sub_flag (loadi64 addr:$dst), i64immSExt32:$src2),
|
|
addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(SUB64mi32 addr:$dst, i64immSExt32:$src2)>;
|
|
|
|
// Register-Register Signed Integer Multiplication with EFLAGS result
|
|
def : Pat<(parallel (X86smul_flag GR64:$src1, GR64:$src2),
|
|
(implicit EFLAGS)),
|
|
(IMUL64rr GR64:$src1, GR64:$src2)>;
|
|
|
|
// Register-Memory Signed Integer Multiplication with EFLAGS result
|
|
def : Pat<(parallel (X86smul_flag GR64:$src1, (loadi64 addr:$src2)),
|
|
(implicit EFLAGS)),
|
|
(IMUL64rm GR64:$src1, addr:$src2)>;
|
|
|
|
// Register-Integer Signed Integer Multiplication with EFLAGS result
|
|
def : Pat<(parallel (X86smul_flag GR64:$src1, i64immSExt8:$src2),
|
|
(implicit EFLAGS)),
|
|
(IMUL64rri8 GR64:$src1, i64immSExt8:$src2)>;
|
|
def : Pat<(parallel (X86smul_flag GR64:$src1, i64immSExt32:$src2),
|
|
(implicit EFLAGS)),
|
|
(IMUL64rri32 GR64:$src1, i64immSExt32:$src2)>;
|
|
|
|
// Memory-Integer Signed Integer Multiplication with EFLAGS result
|
|
def : Pat<(parallel (X86smul_flag (loadi64 addr:$src1), i64immSExt8:$src2),
|
|
(implicit EFLAGS)),
|
|
(IMUL64rmi8 addr:$src1, i64immSExt8:$src2)>;
|
|
def : Pat<(parallel (X86smul_flag (loadi64 addr:$src1), i64immSExt32:$src2),
|
|
(implicit EFLAGS)),
|
|
(IMUL64rmi32 addr:$src1, i64immSExt32:$src2)>;
|
|
|
|
// INC and DEC with EFLAGS result. Note that these do not set CF.
|
|
def : Pat<(parallel (X86inc_flag GR16:$src), (implicit EFLAGS)),
|
|
(INC64_16r GR16:$src)>, Requires<[In64BitMode]>;
|
|
def : Pat<(parallel (store (i16 (X86inc_flag (loadi16 addr:$dst))), addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(INC64_16m addr:$dst)>, Requires<[In64BitMode]>;
|
|
def : Pat<(parallel (X86dec_flag GR16:$src), (implicit EFLAGS)),
|
|
(DEC64_16r GR16:$src)>, Requires<[In64BitMode]>;
|
|
def : Pat<(parallel (store (i16 (X86dec_flag (loadi16 addr:$dst))), addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(DEC64_16m addr:$dst)>, Requires<[In64BitMode]>;
|
|
|
|
def : Pat<(parallel (X86inc_flag GR32:$src), (implicit EFLAGS)),
|
|
(INC64_32r GR32:$src)>, Requires<[In64BitMode]>;
|
|
def : Pat<(parallel (store (i32 (X86inc_flag (loadi32 addr:$dst))), addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(INC64_32m addr:$dst)>, Requires<[In64BitMode]>;
|
|
def : Pat<(parallel (X86dec_flag GR32:$src), (implicit EFLAGS)),
|
|
(DEC64_32r GR32:$src)>, Requires<[In64BitMode]>;
|
|
def : Pat<(parallel (store (i32 (X86dec_flag (loadi32 addr:$dst))), addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(DEC64_32m addr:$dst)>, Requires<[In64BitMode]>;
|
|
|
|
def : Pat<(parallel (X86inc_flag GR64:$src), (implicit EFLAGS)),
|
|
(INC64r GR64:$src)>;
|
|
def : Pat<(parallel (store (i64 (X86inc_flag (loadi64 addr:$dst))), addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(INC64m addr:$dst)>;
|
|
def : Pat<(parallel (X86dec_flag GR64:$src), (implicit EFLAGS)),
|
|
(DEC64r GR64:$src)>;
|
|
def : Pat<(parallel (store (i64 (X86dec_flag (loadi64 addr:$dst))), addr:$dst),
|
|
(implicit EFLAGS)),
|
|
(DEC64m addr:$dst)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86-64 SSE Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Move instructions...
|
|
|
|
def MOV64toPQIrr : RPDI<0x6E, MRMSrcReg, (outs VR128:$dst), (ins GR64:$src),
|
|
"mov{d|q}\t{$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (scalar_to_vector GR64:$src)))]>;
|
|
def MOVPQIto64rr : RPDI<0x7E, MRMDestReg, (outs GR64:$dst), (ins VR128:$src),
|
|
"mov{d|q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (vector_extract (v2i64 VR128:$src),
|
|
(iPTR 0)))]>;
|
|
|
|
def MOV64toSDrr : RPDI<0x6E, MRMSrcReg, (outs FR64:$dst), (ins GR64:$src),
|
|
"mov{d|q}\t{$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (bitconvert GR64:$src))]>;
|
|
def MOV64toSDrm : RPDI<0x6E, MRMSrcMem, (outs FR64:$dst), (ins i64mem:$src),
|
|
"movq\t{$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (bitconvert (loadi64 addr:$src)))]>;
|
|
|
|
def MOVSDto64rr : RPDI<0x7E, MRMDestReg, (outs GR64:$dst), (ins FR64:$src),
|
|
"mov{d|q}\t{$src, $dst|$dst, $src}",
|
|
[(set GR64:$dst, (bitconvert FR64:$src))]>;
|
|
def MOVSDto64mr : RPDI<0x7E, MRMDestMem, (outs), (ins i64mem:$dst, FR64:$src),
|
|
"movq\t{$src, $dst|$dst, $src}",
|
|
[(store (i64 (bitconvert FR64:$src)), addr:$dst)]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86-64 SSE4.1 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/// SS41I_extract32 - SSE 4.1 extract 32 bits to int reg or memory destination
|
|
multiclass SS41I_extract64<bits<8> opc, string OpcodeStr> {
|
|
def rr : SS4AIi8<opc, MRMDestReg, (outs GR64:$dst),
|
|
(ins VR128:$src1, i32i8imm:$src2),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
|
|
[(set GR64:$dst,
|
|
(extractelt (v2i64 VR128:$src1), imm:$src2))]>, OpSize, REX_W;
|
|
def mr : SS4AIi8<opc, MRMDestMem, (outs),
|
|
(ins i64mem:$dst, VR128:$src1, i32i8imm:$src2),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
|
|
[(store (extractelt (v2i64 VR128:$src1), imm:$src2),
|
|
addr:$dst)]>, OpSize, REX_W;
|
|
}
|
|
|
|
defm PEXTRQ : SS41I_extract64<0x16, "pextrq">;
|
|
|
|
let isTwoAddress = 1 in {
|
|
multiclass SS41I_insert64<bits<8> opc, string OpcodeStr> {
|
|
def rr : SS4AIi8<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, GR64:$src2, i32i8imm:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(v2i64 (insertelt VR128:$src1, GR64:$src2, imm:$src3)))]>,
|
|
OpSize, REX_W;
|
|
def rm : SS4AIi8<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, i64mem:$src2, i32i8imm:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(v2i64 (insertelt VR128:$src1, (loadi64 addr:$src2),
|
|
imm:$src3)))]>, OpSize, REX_W;
|
|
}
|
|
}
|
|
|
|
defm PINSRQ : SS41I_insert64<0x22, "pinsrq">;
|