//===- X86RegisterInfo.td - Describe the X86 Register File --*- 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 Register file, defining the registers themselves,
// aliases between the registers, and the register classes built out of the
// registers.
//
//===----------------------------------------------------------------------===//

class X86Reg<string n, bits<16> Enc, list<Register> subregs = []> : Register<n> {
  let Namespace = "X86";
  let HWEncoding = Enc;
  let SubRegs = subregs;
}

// Subregister indices.
let Namespace = "X86" in {
  def sub_8bit    : SubRegIndex<8>;
  def sub_8bit_hi : SubRegIndex<8, 8>;
  def sub_16bit   : SubRegIndex<16>;
  def sub_32bit   : SubRegIndex<32>;
  def sub_xmm     : SubRegIndex<128>;
  def sub_ymm     : SubRegIndex<256>;
}

//===----------------------------------------------------------------------===//
//  Register definitions...
//

// In the register alias definitions below, we define which registers alias
// which others.  We only specify which registers the small registers alias,
// because the register file generator is smart enough to figure out that
// AL aliases AX if we tell it that AX aliased AL (for example).

// Dwarf numbering is different for 32-bit and 64-bit, and there are
// variations by target as well. Currently the first entry is for X86-64,
// second - for EH on X86-32/Darwin and third is 'generic' one (X86-32/Linux
// and debug information on X86-32/Darwin)

// 8-bit registers
// Low registers
def AL : X86Reg<"al", 0>;
def DL : X86Reg<"dl", 2>;
def CL : X86Reg<"cl", 1>;
def BL : X86Reg<"bl", 3>;

// High registers. On x86-64, these cannot be used in any instruction
// with a REX prefix.
def AH : X86Reg<"ah", 4>;
def DH : X86Reg<"dh", 6>;
def CH : X86Reg<"ch", 5>;
def BH : X86Reg<"bh", 7>;

// X86-64 only, requires REX.
let CostPerUse = 1 in {
def SIL  : X86Reg<"sil",   6>;
def DIL  : X86Reg<"dil",   7>;
def BPL  : X86Reg<"bpl",   5>;
def SPL  : X86Reg<"spl",   4>;
def R8B  : X86Reg<"r8b",   8>;
def R9B  : X86Reg<"r9b",   9>;
def R10B : X86Reg<"r10b", 10>;
def R11B : X86Reg<"r11b", 11>;
def R12B : X86Reg<"r12b", 12>;
def R13B : X86Reg<"r13b", 13>;
def R14B : X86Reg<"r14b", 14>;
def R15B : X86Reg<"r15b", 15>;
}

// 16-bit registers
let SubRegIndices = [sub_8bit, sub_8bit_hi], CoveredBySubRegs = 1 in {
def AX : X86Reg<"ax", 0, [AL,AH]>;
def DX : X86Reg<"dx", 2, [DL,DH]>;
def CX : X86Reg<"cx", 1, [CL,CH]>;
def BX : X86Reg<"bx", 3, [BL,BH]>;
}
let SubRegIndices = [sub_8bit] in {
def SI : X86Reg<"si", 6, [SIL]>;
def DI : X86Reg<"di", 7, [DIL]>;
def BP : X86Reg<"bp", 5, [BPL]>;
def SP : X86Reg<"sp", 4, [SPL]>;
}
def IP : X86Reg<"ip", 0>;

// X86-64 only, requires REX.
let SubRegIndices = [sub_8bit], CostPerUse = 1 in {
def R8W  : X86Reg<"r8w",   8, [R8B]>;
def R9W  : X86Reg<"r9w",   9, [R9B]>;
def R10W : X86Reg<"r10w", 10, [R10B]>;
def R11W : X86Reg<"r11w", 11, [R11B]>;
def R12W : X86Reg<"r12w", 12, [R12B]>;
def R13W : X86Reg<"r13w", 13, [R13B]>;
def R14W : X86Reg<"r14w", 14, [R14B]>;
def R15W : X86Reg<"r15w", 15, [R15B]>;
}

// 32-bit registers
let SubRegIndices = [sub_16bit] in {
def EAX : X86Reg<"eax", 0, [AX]>, DwarfRegNum<[-2, 0, 0]>;
def EDX : X86Reg<"edx", 2, [DX]>, DwarfRegNum<[-2, 2, 2]>;
def ECX : X86Reg<"ecx", 1, [CX]>, DwarfRegNum<[-2, 1, 1]>;
def EBX : X86Reg<"ebx", 3, [BX]>, DwarfRegNum<[-2, 3, 3]>;
def ESI : X86Reg<"esi", 6, [SI]>, DwarfRegNum<[-2, 6, 6]>;
def EDI : X86Reg<"edi", 7, [DI]>, DwarfRegNum<[-2, 7, 7]>;
def EBP : X86Reg<"ebp", 5, [BP]>, DwarfRegNum<[-2, 4, 5]>;
def ESP : X86Reg<"esp", 4, [SP]>, DwarfRegNum<[-2, 5, 4]>;
def EIP : X86Reg<"eip", 0, [IP]>, DwarfRegNum<[-2, 8, 8]>;

// X86-64 only, requires REX
let CostPerUse = 1 in {
def R8D  : X86Reg<"r8d",   8, [R8W]>;
def R9D  : X86Reg<"r9d",   9, [R9W]>;
def R10D : X86Reg<"r10d", 10, [R10W]>;
def R11D : X86Reg<"r11d", 11, [R11W]>;
def R12D : X86Reg<"r12d", 12, [R12W]>;
def R13D : X86Reg<"r13d", 13, [R13W]>;
def R14D : X86Reg<"r14d", 14, [R14W]>;
def R15D : X86Reg<"r15d", 15, [R15W]>;
}}

// 64-bit registers, X86-64 only
let SubRegIndices = [sub_32bit] in {
def RAX : X86Reg<"rax", 0, [EAX]>, DwarfRegNum<[0, -2, -2]>;
def RDX : X86Reg<"rdx", 2, [EDX]>, DwarfRegNum<[1, -2, -2]>;
def RCX : X86Reg<"rcx", 1, [ECX]>, DwarfRegNum<[2, -2, -2]>;
def RBX : X86Reg<"rbx", 3, [EBX]>, DwarfRegNum<[3, -2, -2]>;
def RSI : X86Reg<"rsi", 6, [ESI]>, DwarfRegNum<[4, -2, -2]>;
def RDI : X86Reg<"rdi", 7, [EDI]>, DwarfRegNum<[5, -2, -2]>;
def RBP : X86Reg<"rbp", 5, [EBP]>, DwarfRegNum<[6, -2, -2]>;
def RSP : X86Reg<"rsp", 4, [ESP]>, DwarfRegNum<[7, -2, -2]>;

// These also require REX.
let CostPerUse = 1 in {
def R8  : X86Reg<"r8",   8, [R8D]>,  DwarfRegNum<[ 8, -2, -2]>;
def R9  : X86Reg<"r9",   9, [R9D]>,  DwarfRegNum<[ 9, -2, -2]>;
def R10 : X86Reg<"r10", 10, [R10D]>, DwarfRegNum<[10, -2, -2]>;
def R11 : X86Reg<"r11", 11, [R11D]>, DwarfRegNum<[11, -2, -2]>;
def R12 : X86Reg<"r12", 12, [R12D]>, DwarfRegNum<[12, -2, -2]>;
def R13 : X86Reg<"r13", 13, [R13D]>, DwarfRegNum<[13, -2, -2]>;
def R14 : X86Reg<"r14", 14, [R14D]>, DwarfRegNum<[14, -2, -2]>;
def R15 : X86Reg<"r15", 15, [R15D]>, DwarfRegNum<[15, -2, -2]>;
def RIP : X86Reg<"rip",  0, [EIP]>,  DwarfRegNum<[16, -2, -2]>;
}}

// MMX Registers. These are actually aliased to ST0 .. ST7
def MM0 : X86Reg<"mm0", 0>, DwarfRegNum<[41, 29, 29]>;
def MM1 : X86Reg<"mm1", 1>, DwarfRegNum<[42, 30, 30]>;
def MM2 : X86Reg<"mm2", 2>, DwarfRegNum<[43, 31, 31]>;
def MM3 : X86Reg<"mm3", 3>, DwarfRegNum<[44, 32, 32]>;
def MM4 : X86Reg<"mm4", 4>, DwarfRegNum<[45, 33, 33]>;
def MM5 : X86Reg<"mm5", 5>, DwarfRegNum<[46, 34, 34]>;
def MM6 : X86Reg<"mm6", 6>, DwarfRegNum<[47, 35, 35]>;
def MM7 : X86Reg<"mm7", 7>, DwarfRegNum<[48, 36, 36]>;

// Pseudo Floating Point registers
def FP0 : X86Reg<"fp0", 0>;
def FP1 : X86Reg<"fp1", 0>;
def FP2 : X86Reg<"fp2", 0>;
def FP3 : X86Reg<"fp3", 0>;
def FP4 : X86Reg<"fp4", 0>;
def FP5 : X86Reg<"fp5", 0>;
def FP6 : X86Reg<"fp6", 0>;
def FP7 : X86Reg<"fp7", 0>;

// XMM Registers, used by the various SSE instruction set extensions.
def XMM0: X86Reg<"xmm0", 0>, DwarfRegNum<[17, 21, 21]>;
def XMM1: X86Reg<"xmm1", 1>, DwarfRegNum<[18, 22, 22]>;
def XMM2: X86Reg<"xmm2", 2>, DwarfRegNum<[19, 23, 23]>;
def XMM3: X86Reg<"xmm3", 3>, DwarfRegNum<[20, 24, 24]>;
def XMM4: X86Reg<"xmm4", 4>, DwarfRegNum<[21, 25, 25]>;
def XMM5: X86Reg<"xmm5", 5>, DwarfRegNum<[22, 26, 26]>;
def XMM6: X86Reg<"xmm6", 6>, DwarfRegNum<[23, 27, 27]>;
def XMM7: X86Reg<"xmm7", 7>, DwarfRegNum<[24, 28, 28]>;

// X86-64 only
let CostPerUse = 1 in {
def XMM8:  X86Reg<"xmm8",   8>, DwarfRegNum<[25, -2, -2]>;
def XMM9:  X86Reg<"xmm9",   9>, DwarfRegNum<[26, -2, -2]>;
def XMM10: X86Reg<"xmm10", 10>, DwarfRegNum<[27, -2, -2]>;
def XMM11: X86Reg<"xmm11", 11>, DwarfRegNum<[28, -2, -2]>;
def XMM12: X86Reg<"xmm12", 12>, DwarfRegNum<[29, -2, -2]>;
def XMM13: X86Reg<"xmm13", 13>, DwarfRegNum<[30, -2, -2]>;
def XMM14: X86Reg<"xmm14", 14>, DwarfRegNum<[31, -2, -2]>;
def XMM15: X86Reg<"xmm15", 15>, DwarfRegNum<[32, -2, -2]>;

def XMM16:  X86Reg<"xmm16", 16>, DwarfRegNum<[67, -2, -2]>;
def XMM17:  X86Reg<"xmm17", 17>, DwarfRegNum<[68, -2, -2]>;
def XMM18:  X86Reg<"xmm18", 18>, DwarfRegNum<[69, -2, -2]>;
def XMM19:  X86Reg<"xmm19", 19>, DwarfRegNum<[70, -2, -2]>;
def XMM20:  X86Reg<"xmm20", 20>, DwarfRegNum<[71, -2, -2]>;
def XMM21:  X86Reg<"xmm21", 21>, DwarfRegNum<[72, -2, -2]>;
def XMM22:  X86Reg<"xmm22", 22>, DwarfRegNum<[73, -2, -2]>;
def XMM23:  X86Reg<"xmm23", 23>, DwarfRegNum<[74, -2, -2]>;
def XMM24:  X86Reg<"xmm24", 24>, DwarfRegNum<[75, -2, -2]>;
def XMM25:  X86Reg<"xmm25", 25>, DwarfRegNum<[76, -2, -2]>;
def XMM26:  X86Reg<"xmm26", 26>, DwarfRegNum<[77, -2, -2]>;
def XMM27:  X86Reg<"xmm27", 27>, DwarfRegNum<[78, -2, -2]>;
def XMM28:  X86Reg<"xmm28", 28>, DwarfRegNum<[79, -2, -2]>;
def XMM29:  X86Reg<"xmm29", 29>, DwarfRegNum<[80, -2, -2]>;
def XMM30:  X86Reg<"xmm30", 30>, DwarfRegNum<[81, -2, -2]>;
def XMM31:  X86Reg<"xmm31", 31>, DwarfRegNum<[82, -2, -2]>;

} // CostPerUse

// YMM0-15 registers, used by AVX instructions and
// YMM16-31 registers, used by AVX-512 instructions.
let SubRegIndices = [sub_xmm] in {
  foreach  Index = 0-31 in {
    def YMM#Index : X86Reg<"ymm"#Index, Index, [!cast<X86Reg>("XMM"#Index)]>,
                    DwarfRegAlias<!cast<X86Reg>("XMM"#Index)>;
  }
}

// ZMM Registers, used by AVX-512 instructions.
let SubRegIndices = [sub_ymm] in {
  foreach  Index = 0-31 in {
    def ZMM#Index : X86Reg<"zmm"#Index, Index, [!cast<X86Reg>("YMM"#Index)]>,
                    DwarfRegAlias<!cast<X86Reg>("XMM"#Index)>;
  }
}

// Mask Registers, used by AVX-512 instructions.
def K0 : X86Reg<"k0", 0>, DwarfRegNum<[118,  93,  93]>;
def K1 : X86Reg<"k1", 1>, DwarfRegNum<[119,  94,  94]>;
def K2 : X86Reg<"k2", 2>, DwarfRegNum<[120,  95,  95]>;
def K3 : X86Reg<"k3", 3>, DwarfRegNum<[121,  96,  96]>;
def K4 : X86Reg<"k4", 4>, DwarfRegNum<[122,  97,  97]>;
def K5 : X86Reg<"k5", 5>, DwarfRegNum<[123,  98,  98]>;
def K6 : X86Reg<"k6", 6>, DwarfRegNum<[124,  99,  99]>;
def K7 : X86Reg<"k7", 7>, DwarfRegNum<[125, 100, 100]>;

// Floating point stack registers. These don't map one-to-one to the FP
// pseudo registers, but we still mark them as aliasing FP registers. That
// way both kinds can be live without exceeding the stack depth. ST registers
// are only live around inline assembly.
def ST0 : X86Reg<"st(0)", 0>, DwarfRegNum<[33, 12, 11]>;
def ST1 : X86Reg<"st(1)", 1>, DwarfRegNum<[34, 13, 12]>;
def ST2 : X86Reg<"st(2)", 2>, DwarfRegNum<[35, 14, 13]>;
def ST3 : X86Reg<"st(3)", 3>, DwarfRegNum<[36, 15, 14]>;
def ST4 : X86Reg<"st(4)", 4>, DwarfRegNum<[37, 16, 15]>;
def ST5 : X86Reg<"st(5)", 5>, DwarfRegNum<[38, 17, 16]>;
def ST6 : X86Reg<"st(6)", 6>, DwarfRegNum<[39, 18, 17]>;
def ST7 : X86Reg<"st(7)", 7>, DwarfRegNum<[40, 19, 18]>;

// Floating-point status word
def FPSW : X86Reg<"fpsw", 0>;

// Status flags register
def EFLAGS : X86Reg<"flags", 0>;

// Segment registers
def CS : X86Reg<"cs", 1>;
def DS : X86Reg<"ds", 3>;
def SS : X86Reg<"ss", 2>;
def ES : X86Reg<"es", 0>;
def FS : X86Reg<"fs", 4>;
def GS : X86Reg<"gs", 5>;

// Debug registers
def DR0  : X86Reg<"dr0",   0>;
def DR1  : X86Reg<"dr1",   1>;
def DR2  : X86Reg<"dr2",   2>;
def DR3  : X86Reg<"dr3",   3>;
def DR4  : X86Reg<"dr4",   4>;
def DR5  : X86Reg<"dr5",   5>;
def DR6  : X86Reg<"dr6",   6>;
def DR7  : X86Reg<"dr7",   7>;
def DR8  : X86Reg<"dr8",   8>;
def DR9  : X86Reg<"dr9",   9>;
def DR10 : X86Reg<"dr10", 10>;
def DR11 : X86Reg<"dr11", 11>;
def DR12 : X86Reg<"dr12", 12>;
def DR13 : X86Reg<"dr13", 13>;
def DR14 : X86Reg<"dr14", 14>;
def DR15 : X86Reg<"dr15", 15>;

// Control registers
def CR0  : X86Reg<"cr0",   0>;
def CR1  : X86Reg<"cr1",   1>;
def CR2  : X86Reg<"cr2",   2>;
def CR3  : X86Reg<"cr3",   3>;
def CR4  : X86Reg<"cr4",   4>;
def CR5  : X86Reg<"cr5",   5>;
def CR6  : X86Reg<"cr6",   6>;
def CR7  : X86Reg<"cr7",   7>;
def CR8  : X86Reg<"cr8",   8>;
def CR9  : X86Reg<"cr9",   9>;
def CR10 : X86Reg<"cr10", 10>;
def CR11 : X86Reg<"cr11", 11>;
def CR12 : X86Reg<"cr12", 12>;
def CR13 : X86Reg<"cr13", 13>;
def CR14 : X86Reg<"cr14", 14>;
def CR15 : X86Reg<"cr15", 15>;

// Pseudo index registers
def EIZ : X86Reg<"eiz", 4>;
def RIZ : X86Reg<"riz", 4>;

// Bound registers, used in MPX instructions
def BND0 : X86Reg<"bnd0",   0>;
def BND1 : X86Reg<"bnd1",   1>;
def BND2 : X86Reg<"bnd2",   2>;
def BND3 : X86Reg<"bnd3",   3>;

//===----------------------------------------------------------------------===//
// Register Class Definitions... now that we have all of the pieces, define the
// top-level register classes.  The order specified in the register list is
// implicitly defined to be the register allocation order.
//

// List call-clobbered registers before callee-save registers. RBX, RBP, (and
// R12, R13, R14, and R15 for X86-64) are callee-save registers.
// In 64-mode, there are 12 additional i8 registers, SIL, DIL, BPL, SPL, and
// R8B, ... R15B.
// Allocate R12 and R13 last, as these require an extra byte when
// encoded in x86_64 instructions.
// FIXME: Allow AH, CH, DH, BH to be used as general-purpose registers in
// 64-bit mode. The main complication is that they cannot be encoded in an
// instruction requiring a REX prefix, while SIL, DIL, BPL, R8D, etc.
// require a REX prefix. For example, "addb %ah, %dil" and "movzbl %ah, %r8d"
// cannot be encoded.
def GR8 : RegisterClass<"X86", [i8],  8,
                        (add AL, CL, DL, AH, CH, DH, BL, BH, SIL, DIL, BPL, SPL,
                             R8B, R9B, R10B, R11B, R14B, R15B, R12B, R13B)> {
  let AltOrders = [(sub GR8, AH, BH, CH, DH)];
  let AltOrderSelect = [{
    return MF.getSubtarget<X86Subtarget>().is64Bit();
  }];
}

def GR16 : RegisterClass<"X86", [i16], 16,
                         (add AX, CX, DX, SI, DI, BX, BP, SP,
                              R8W, R9W, R10W, R11W, R14W, R15W, R12W, R13W)>;

def GR32 : RegisterClass<"X86", [i32], 32,
                         (add EAX, ECX, EDX, ESI, EDI, EBX, EBP, ESP,
                              R8D, R9D, R10D, R11D, R14D, R15D, R12D, R13D)>;

// GR64 - 64-bit GPRs. This oddly includes RIP, which isn't accurate, since
// RIP isn't really a register and it can't be used anywhere except in an
// address, but it doesn't cause trouble.
// FIXME: it *does* cause trouble - CheckBaseRegAndIndexReg() has extra
// tests because of the inclusion of RIP in this register class.
def GR64 : RegisterClass<"X86", [i64], 64,
                         (add RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
                              RBX, R14, R15, R12, R13, RBP, RSP, RIP)>;

// Segment registers for use by MOV instructions (and others) that have a
//   segment register as one operand.  Always contain a 16-bit segment
//   descriptor.
def SEGMENT_REG : RegisterClass<"X86", [i16], 16, (add CS, DS, SS, ES, FS, GS)>;

// Debug registers.
def DEBUG_REG : RegisterClass<"X86", [i32], 32, (sequence "DR%u", 0, 7)>;

// Control registers.
def CONTROL_REG : RegisterClass<"X86", [i64], 64, (sequence "CR%u", 0, 15)>;

// GR8_ABCD_L, GR8_ABCD_H, GR16_ABCD, GR32_ABCD, GR64_ABCD - Subclasses of
// GR8, GR16, GR32, and GR64 which contain just the "a" "b", "c", and "d"
// registers. On x86-32, GR16_ABCD and GR32_ABCD are classes for registers
// that support 8-bit subreg operations. On x86-64, GR16_ABCD, GR32_ABCD,
// and GR64_ABCD are classes for registers that support 8-bit h-register
// operations.
def GR8_ABCD_L : RegisterClass<"X86", [i8], 8, (add AL, CL, DL, BL)>;
def GR8_ABCD_H : RegisterClass<"X86", [i8], 8, (add AH, CH, DH, BH)>;
def GR16_ABCD : RegisterClass<"X86", [i16], 16, (add AX, CX, DX, BX)>;
def GR32_ABCD : RegisterClass<"X86", [i32], 32, (add EAX, ECX, EDX, EBX)>;
def GR64_ABCD : RegisterClass<"X86", [i64], 64, (add RAX, RCX, RDX, RBX)>;
def GR32_TC   : RegisterClass<"X86", [i32], 32, (add EAX, ECX, EDX)>;
def GR64_TC   : RegisterClass<"X86", [i64], 64, (add RAX, RCX, RDX, RSI, RDI,
                                                     R8, R9, R11, RIP)>;
def GR64_TCW64 : RegisterClass<"X86", [i64], 64, (add RAX, RCX, RDX,
                                                      R8, R9, R10, R11, RIP)>;

// GR8_NOREX - GR8 registers which do not require a REX prefix.
def GR8_NOREX : RegisterClass<"X86", [i8], 8,
                              (add AL, CL, DL, AH, CH, DH, BL, BH)> {
  let AltOrders = [(sub GR8_NOREX, AH, BH, CH, DH)];
  let AltOrderSelect = [{
    return MF.getSubtarget<X86Subtarget>().is64Bit();
  }];
}
// GR16_NOREX - GR16 registers which do not require a REX prefix.
def GR16_NOREX : RegisterClass<"X86", [i16], 16,
                               (add AX, CX, DX, SI, DI, BX, BP, SP)>;
// GR32_NOREX - GR32 registers which do not require a REX prefix.
def GR32_NOREX : RegisterClass<"X86", [i32], 32,
                               (add EAX, ECX, EDX, ESI, EDI, EBX, EBP, ESP)>;
// GR64_NOREX - GR64 registers which do not require a REX prefix.
def GR64_NOREX : RegisterClass<"X86", [i64], 64,
                            (add RAX, RCX, RDX, RSI, RDI, RBX, RBP, RSP, RIP)>;

// GR32_NOAX - GR32 registers except EAX. Used by AddRegFrm of XCHG32 in 64-bit
// mode to prevent encoding using the 0x90 NOP encoding. xchg %eax, %eax needs
// to clear upper 32-bits of RAX so is not a NOP.
def GR32_NOAX : RegisterClass<"X86", [i32], 32, (sub GR32, EAX)>;

// GR32_NOSP - GR32 registers except ESP.
def GR32_NOSP : RegisterClass<"X86", [i32], 32, (sub GR32, ESP)>;

// GR64_NOSP - GR64 registers except RSP (and RIP).
def GR64_NOSP : RegisterClass<"X86", [i64], 64, (sub GR64, RSP, RIP)>;

// GR32_NOREX_NOSP - GR32 registers which do not require a REX prefix except
// ESP.
def GR32_NOREX_NOSP : RegisterClass<"X86", [i32], 32,
                                    (and GR32_NOREX, GR32_NOSP)>;

// GR64_NOREX_NOSP - GR64_NOREX registers except RSP.
def GR64_NOREX_NOSP : RegisterClass<"X86", [i64], 64,
                                    (and GR64_NOREX, GR64_NOSP)>;

// Register classes used for ABIs that use 32-bit address accesses,
// while using the whole x84_64 ISA.

// In such cases, it is fine to use RIP as we are sure the 32 high
// bits are not set. We do not need variants for NOSP as RIP is not
// allowed there.
// RIP is not spilled anywhere for now, so stick to 32-bit alignment
// to save on memory space.
// FIXME: We could allow all 64bit registers, but we would need
// something to check that the 32 high bits are not set,
// which we do not have right now.
def LOW32_ADDR_ACCESS : RegisterClass<"X86", [i32], 32, (add GR32, RIP)>;

// When RBP is used as a base pointer in a 32-bit addresses environement,
// this is also safe to use the full register to access addresses.
// Since RBP will never be spilled, stick to a 32 alignment to save
// on memory consumption.
def LOW32_ADDR_ACCESS_RBP : RegisterClass<"X86", [i32], 32,
                                          (add LOW32_ADDR_ACCESS, RBP)>;

// A class to support the 'A' assembler constraint: [ER]AX then [ER]DX.
def GR32_AD : RegisterClass<"X86", [i32], 32, (add EAX, EDX)>;
def GR64_AD : RegisterClass<"X86", [i64], 64, (add RAX, RDX)>;

// Scalar SSE2 floating point registers.
def FR32 : RegisterClass<"X86", [f32], 32, (sequence "XMM%u", 0, 15)>;

def FR64 : RegisterClass<"X86", [f64], 64, (add FR32)>;

def FR128 : RegisterClass<"X86", [i128, f128], 128, (add FR32)>;


// FIXME: This sets up the floating point register files as though they are f64
// values, though they really are f80 values.  This will cause us to spill
// values as 64-bit quantities instead of 80-bit quantities, which is much much
// faster on common hardware.  In reality, this should be controlled by a
// command line option or something.

def RFP32 : RegisterClass<"X86",[f32], 32, (sequence "FP%u", 0, 6)>;
def RFP64 : RegisterClass<"X86",[f64], 32, (add RFP32)>;
def RFP80 : RegisterClass<"X86",[f80], 32, (add RFP32)>;

// Floating point stack registers (these are not allocatable by the
// register allocator - the floating point stackifier is responsible
// for transforming FPn allocations to STn registers)
def RST : RegisterClass<"X86", [f80, f64, f32], 32, (sequence "ST%u", 0, 7)> {
  let isAllocatable = 0;
}

// Generic vector registers: VR64 and VR128.
// Ensure that float types are declared first - only float is legal on SSE1.
def VR64: RegisterClass<"X86", [x86mmx], 64, (sequence "MM%u", 0, 7)>;
def VR128 : RegisterClass<"X86", [v4f32, v2f64, v16i8, v8i16, v4i32, v2i64],
                          128, (add FR32)>;
def VR256 : RegisterClass<"X86", [v8f32, v4f64, v32i8, v16i16, v8i32, v4i64],
                          256, (sequence "YMM%u", 0, 15)>;

// Special classes that help the assembly parser choose some alternate
// instructions to favor 2-byte VEX encodings.
def VR128L : RegisterClass<"X86", [v4f32, v2f64, v16i8, v8i16, v4i32, v2i64],
                           128, (sequence "XMM%u", 0, 7)>;
def VR128H : RegisterClass<"X86", [v4f32, v2f64, v16i8, v8i16, v4i32, v2i64],
                           128, (sequence "XMM%u", 8, 15)>;
def VR256L : RegisterClass<"X86", [v8f32, v4f64, v32i8, v16i16, v8i32, v4i64],
                           256, (sequence "YMM%u", 0, 7)>;
def VR256H : RegisterClass<"X86", [v8f32, v4f64, v32i8, v16i16, v8i32, v4i64],
                           256, (sequence "YMM%u", 8, 15)>;

// Status flags registers.
def CCR : RegisterClass<"X86", [i32], 32, (add EFLAGS)> {
  let CopyCost = -1;  // Don't allow copying of status registers.
  let isAllocatable = 0;
}
def FPCCR : RegisterClass<"X86", [i16], 16, (add FPSW)> {
  let CopyCost = -1;  // Don't allow copying of status registers.
  let isAllocatable = 0;
}

// AVX-512 vector/mask registers.
def VR512 : RegisterClass<"X86", [v16f32, v8f64, v64i8, v32i16, v16i32, v8i64],
                          512, (sequence "ZMM%u", 0, 31)>;

// Scalar AVX-512 floating point registers.
def FR32X : RegisterClass<"X86", [f32], 32, (sequence "XMM%u", 0, 31)>;

def FR64X : RegisterClass<"X86", [f64], 64, (add FR32X)>;

// Extended VR128 and VR256 for AVX-512 instructions
def VR128X : RegisterClass<"X86", [v4f32, v2f64, v16i8, v8i16, v4i32, v2i64],
                           128, (add FR32X)>;
def VR256X : RegisterClass<"X86", [v8f32, v4f64, v32i8, v16i16, v8i32, v4i64],
                           256, (sequence "YMM%u", 0, 31)>;

// Mask registers
def VK1     : RegisterClass<"X86", [v1i1],  16,  (sequence "K%u", 0, 7)> {let Size = 16;}
def VK2     : RegisterClass<"X86", [v2i1],  16,  (add VK1)> {let Size = 16;}
def VK4     : RegisterClass<"X86", [v4i1],  16,  (add VK2)> {let Size = 16;}
def VK8     : RegisterClass<"X86", [v8i1],  16,  (add VK4)> {let Size = 16;}
def VK16    : RegisterClass<"X86", [v16i1], 16, (add VK8)> {let Size = 16;}
def VK32    : RegisterClass<"X86", [v32i1], 32, (add VK16)> {let Size = 32;}
def VK64    : RegisterClass<"X86", [v64i1], 64, (add VK32)> {let Size = 64;}

def VK1WM   : RegisterClass<"X86", [v1i1],  16,  (sub VK1, K0)> {let Size = 16;}
def VK2WM   : RegisterClass<"X86", [v2i1],  16,  (sub VK2, K0)> {let Size = 16;}
def VK4WM   : RegisterClass<"X86", [v4i1],  16,  (sub VK4, K0)> {let Size = 16;}
def VK8WM   : RegisterClass<"X86", [v8i1],  16,  (sub VK8, K0)> {let Size = 16;}
def VK16WM  : RegisterClass<"X86", [v16i1], 16, (add VK8WM)>   {let Size = 16;}
def VK32WM  : RegisterClass<"X86", [v32i1], 32, (add VK16WM)> {let Size = 32;}
def VK64WM  : RegisterClass<"X86", [v64i1], 64, (add VK32WM)> {let Size = 64;}

// Bound registers
def BNDR : RegisterClass<"X86", [v2i64], 128, (sequence "BND%u", 0, 3)>;