//===--- arm_neon.td - ARM NEON compiler interface ------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
//  This file defines the TableGen definitions from which the ARM NEON header
//  file will be generated.  See ARM document DUI0348B.
//
//===----------------------------------------------------------------------===//
//
// Each intrinsic is a subclass of the Inst class. An intrinsic can either
// generate a __builtin_* call or it can expand to a set of generic operations.
//
// The operations are subclasses of Operation providing a list of DAGs, the
// last of which is the return value. The available DAG nodes are documented
// below.
//
//===----------------------------------------------------------------------===//

// The base Operation class. All operations must subclass this.
class Operation<list<dag> ops=[]> {
  list<dag> Ops = ops;
  bit Unavailable = 0;
}
// An operation that only contains a single DAG.
class Op<dag op> : Operation<[op]>;
// A shorter version of Operation - takes a list of DAGs. The last of these will
// be the return value.
class LOp<list<dag> ops> : Operation<ops>;

// These defs and classes are used internally to implement the SetTheory
// expansion and should be ignored.
foreach Index = 0-63 in
  def sv##Index;
class MaskExpand;

//===----------------------------------------------------------------------===//
// Available operations
//===----------------------------------------------------------------------===//

// DAG arguments can either be operations (documented below) or variables.
// Variables are prefixed with '$'. There are variables for each input argument,
// with the name $pN, where N starts at zero. So the zero'th argument will be
// $p0, the first $p1 etc.

// op - Binary or unary operator, depending on the number of arguments. The
//      operator itself is just treated as a raw string and is not checked.
// example: (op "+", $p0, $p1) -> "__p0 + __p1".
//          (op "-", $p0)      -> "-__p0"
def op;
// call - Invoke another intrinsic. The input types are type checked and
//        disambiguated. If there is no intrinsic defined that takes
//        the given types (or if there is a type ambiguity) an error is
//        generated at tblgen time. The name of the intrinsic is the raw
//        name as given to the Inst class (not mangled).
// example: (call "vget_high", $p0) -> "vgetq_high_s16(__p0)"
//            (assuming $p0 has type int16x8_t).
def call;
// cast - Perform a cast to a different type. This gets emitted as a static
//        C-style cast. For a pure reinterpret cast (T x = *(T*)&y), use
//        "bitcast".
//
//        The syntax is (cast MOD* VAL). The last argument is the value to
//        cast, preceded by a sequence of type modifiers. The target type
//        starts off as the type of VAL, and is modified by MOD in sequence.
//        The available modifiers are:
//          - $X  - Take the type of parameter/variable X. For example:
//                  (cast $p0, $p1) would cast $p1 to the type of $p0.
//          - "R" - The type of the return type.
//          - A typedef string - A NEON or stdint.h type that is then parsed.
//                               for example: (cast "uint32x4_t", $p0).
//          - "U" - Make the type unsigned.
//          - "S" - Make the type signed.
//          - "H" - Halve the number of lanes in the type.
//          - "D" - Double the number of lanes in the type.
//          - "8" - Convert type to an equivalent vector of 8-bit signed
//                  integers.
// example: (cast "R", "U", $p0) -> "(uint32x4_t)__p0" (assuming the return
//           value is of type "int32x4_t".
//          (cast $p0, "D", "8", $p1) -> "(int8x16_t)__p1" (assuming __p0
//           has type float64x1_t or any other vector type of 64 bits).
//          (cast "int32_t", $p2) -> "(int32_t)__p2"
def cast;
// bitcast - Same as "cast", except a reinterpret-cast is produced:
//             (bitcast "T", $p0) -> "*(T*)&__p0".
//           The VAL argument is saved to a temporary so it can be used
//           as an l-value.
def bitcast;
// dup - Take a scalar argument and create a vector by duplicating it into
//       all lanes. The type of the vector is the base type of the intrinsic.
// example: (dup $p1) -> "(uint32x2_t) {__p1, __p1}" (assuming the base type
//          is uint32x2_t).
def dup;
// splat - Take a vector and a lane index, and return a vector of the same type
//         containing repeated instances of the source vector at the lane index.
// example: (splat $p0, $p1) ->
//            "__builtin_shufflevector(__p0, __p0, __p1, __p1, __p1, __p1)"
//          (assuming __p0 has four elements).
def splat;
// save_temp - Create a temporary (local) variable. The variable takes a name
//             based on the zero'th parameter and can be referenced using
//             using that name in subsequent DAGs in the same
//             operation. The scope of a temp is the operation. If a variable
//             with the given name already exists, an error will be given at
//             tblgen time.
// example: [(save_temp $var, (call "foo", $p0)),
//           (op "+", $var, $p1)] ->
//              "int32x2_t __var = foo(__p0); return __var + __p1;"
def save_temp;
// name_replace - Return the name of the current intrinsic with the first
//                argument replaced by the second argument. Raises an error if
//                the first argument does not exist in the intrinsic name.
// example: (call (name_replace "_high_", "_"), $p0) (to call the non-high
//            version of this intrinsic).
def name_replace;
// literal - Create a literal piece of code. The code is treated as a raw
//           string, and must be given a type. The type is a stdint.h or
//           NEON intrinsic type as given to (cast).
// example: (literal "int32_t", "0")
def literal;
// shuffle - Create a vector shuffle. The syntax is (shuffle ARG0, ARG1, MASK).
//           The MASK argument is a set of elements. The elements are generated
//           from the two special defs "mask0" and "mask1". "mask0" expands to
//           the lane indices in sequence for ARG0, and "mask1" expands to
//           the lane indices in sequence for ARG1. They can be used as-is, e.g.
//
//             (shuffle $p0, $p1, mask0) -> $p0
//             (shuffle $p0, $p1, mask1) -> $p1
//
//           or, more usefully, they can be manipulated using the SetTheory
//           operators plus some extra operators defined in the NEON emitter.
//           The operators are described below.
// example: (shuffle $p0, $p1, (add (highhalf mask0), (highhalf mask1))) ->
//            A concatenation of the high halves of the input vectors.
def shuffle;

// add, interleave, decimate: These set operators are vanilla SetTheory
// operators and take their normal definition.
def add;
def interleave;
def decimate;
// rotl - Rotate set left by a number of elements.
// example: (rotl mask0, 3) -> [3, 4, 5, 6, 0, 1, 2]
def rotl;
// rotl - Rotate set right by a number of elements.
// example: (rotr mask0, 3) -> [4, 5, 6, 0, 1, 2, 3]
def rotr;
// highhalf - Take only the high half of the input.
// example: (highhalf mask0) -> [4, 5, 6, 7] (assuming mask0 had 8 elements)
def highhalf;
// highhalf - Take only the low half of the input.
// example: (lowhalf mask0) -> [0, 1, 2, 3] (assuming mask0 had 8 elements)
def lowhalf;
// rev - Perform a variable-width reversal of the elements. The zero'th argument
//       is a width in bits to reverse. The lanes this maps to is determined
//       based on the element width of the underlying type.
// example: (rev 32, mask0) -> [3, 2, 1, 0, 7, 6, 5, 4] (if 8-bit elements)
// example: (rev 32, mask0) -> [1, 0, 3, 2]             (if 16-bit elements)
def rev;
// mask0 - The initial sequence of lanes for shuffle ARG0
def mask0 : MaskExpand;
// mask0 - The initial sequence of lanes for shuffle ARG1
def mask1 : MaskExpand;

def OP_NONE  : Operation;
def OP_UNAVAILABLE : Operation {
  let Unavailable = 1;
}

//===----------------------------------------------------------------------===//
// Instruction definitions
//===----------------------------------------------------------------------===//

// Every intrinsic subclasses "Inst". An intrinsic has a name, a prototype and
// a sequence of typespecs.
//
// The name is the base name of the intrinsic, for example "vget_lane". This is
// then mangled by the tblgen backend to add type information ("vget_lane_s16").
//
// A typespec is a sequence of uppercase characters (modifiers) followed by one
// lowercase character. A typespec encodes a particular "base type" of the
// intrinsic.
//
// An example typespec is "Qs" - quad-size short - uint16x8_t. The available
// typespec codes are given below.
//
// The string given to an Inst class is a sequence of typespecs. The intrinsic
// is instantiated for every typespec in the sequence. For example "sdQsQd".
//
// The prototype is a string that defines the return type of the intrinsic
// and the type of each argument. The return type and every argument gets a
// "modifier" that can change in some way the "base type" of the intrinsic.
//
// The modifier 'd' means "default" and does not modify the base type in any
// way. The available modifiers are given below.
//
// Typespecs
// ---------
// c: char
// s: short
// i: int
// l: long
// k: 128-bit long
// f: float
// h: half-float
// d: double
//
// Typespec modifiers
// ------------------
// S: scalar, only used for function mangling.
// U: unsigned
// Q: 128b
// H: 128b without mangling 'q'
// P: polynomial
//
// Prototype modifiers
// -------------------
// prototype: return (arg, arg, ...)
//
// v: void
// t: best-fit integer (int/poly args)
// x: signed integer   (int/float args)
// u: unsigned integer (int/float args)
// f: float (int args)
// F: double (int args)
// H: half (int args)
// d: default
// g: default, ignore 'Q' size modifier.
// j: default, force 'Q' size modifier.
// w: double width elements, same num elts
// n: double width elements, half num elts
// h: half width elements, double num elts
// q: half width elements, quad num elts
// e: half width elements, double num elts, unsigned
// m: half width elements, same num elts
// i: constant int
// l: constant uint64
// s: scalar of element type
// z: scalar of half width element type, signed
// r: scalar of double width element type, signed
// a: scalar of element type (splat to vector type)
// b: scalar of unsigned integer/long type (int/float args)
// $: scalar of signed integer/long type (int/float args)
// y: scalar of float
// o: scalar of double
// k: default elt width, double num elts
// 2,3,4: array of default vectors
// B,C,D: array of default elts, force 'Q' size modifier.
// p: pointer type
// c: const pointer type

// Every intrinsic subclasses Inst.
class Inst <string n, string p, string t, Operation o> {
  string Name = n;
  string Prototype = p;
  string Types = t;
  string ArchGuard = "";

  Operation Operation = o;
  bit CartesianProductOfTypes = 0;
  bit BigEndianSafe = 0;
  bit isShift = 0;
  bit isScalarShift = 0;
  bit isScalarNarrowShift = 0;
  bit isVCVT_N = 0;
  // For immediate checks: the immediate will be assumed to specify the lane of
  // a Q register. Only used for intrinsics which end up calling polymorphic
  // builtins.
  bit isLaneQ = 0;

  // Certain intrinsics have different names than their representative
  // instructions. This field allows us to handle this correctly when we
  // are generating tests.
  string InstName = "";

  // Certain intrinsics even though they are not a WOpInst or LOpInst,
  // generate a WOpInst/LOpInst instruction (see below for definition
  // of a WOpInst/LOpInst). For testing purposes we need to know
  // this. Ex: vset_lane which outputs vmov instructions.
  bit isHiddenWInst = 0;
  bit isHiddenLInst = 0;
}

// The following instruction classes are implemented via builtins.
// These declarations are used to generate Builtins.def:
//
// SInst: Instruction with signed/unsigned suffix (e.g., "s8", "u8", "p8")
// IInst: Instruction with generic integer suffix (e.g., "i8")
// WInst: Instruction with only bit size suffix (e.g., "8")
class SInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {}
class IInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {}
class WInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {}

// The following instruction classes are implemented via operators
// instead of builtins. As such these declarations are only used for
// the purpose of generating tests.
//
// SOpInst:       Instruction with signed/unsigned suffix (e.g., "s8",
//                "u8", "p8").
// IOpInst:       Instruction with generic integer suffix (e.g., "i8").
// WOpInst:       Instruction with bit size only suffix (e.g., "8").
// LOpInst:       Logical instruction with no bit size suffix.
// NoTestOpInst:  Intrinsic that has no corresponding instruction.
class SOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {}
class IOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {}
class WOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {}
class LOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {}
class NoTestOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {}

//===----------------------------------------------------------------------===//
// Operations
//===----------------------------------------------------------------------===//

def OP_ADD      : Op<(op "+", $p0, $p1)>;
def OP_ADDL     : Op<(op "+", (call "vmovl", $p0), (call "vmovl", $p1))>;
def OP_ADDLHi   : Op<(op "+", (call "vmovl_high", $p0),
                              (call "vmovl_high", $p1))>;
def OP_ADDW     : Op<(op "+", $p0, (call "vmovl", $p1))>;
def OP_ADDWHi   : Op<(op "+", $p0, (call "vmovl_high", $p1))>;
def OP_SUB      : Op<(op "-", $p0, $p1)>;
def OP_SUBL     : Op<(op "-", (call "vmovl", $p0), (call "vmovl", $p1))>;
def OP_SUBLHi   : Op<(op "-", (call "vmovl_high", $p0),
                              (call "vmovl_high", $p1))>;
def OP_SUBW     : Op<(op "-", $p0, (call "vmovl", $p1))>;
def OP_SUBWHi   : Op<(op "-", $p0, (call "vmovl_high", $p1))>;
def OP_MUL      : Op<(op "*", $p0, $p1)>;
def OP_MLA      : Op<(op "+", $p0, (op "*", $p1, $p2))>;
def OP_MLAL     : Op<(op "+", $p0, (call "vmull", $p1, $p2))>;
def OP_MULLHi   : Op<(call "vmull", (call "vget_high", $p0),
                                    (call "vget_high", $p1))>;
def OP_MULLHi_P64 : Op<(call "vmull",
                         (cast "poly64_t", (call "vget_high", $p0)),
                         (cast "poly64_t", (call "vget_high", $p1)))>;
def OP_MULLHi_N : Op<(call "vmull_n", (call "vget_high", $p0), $p1)>;
def OP_MLALHi   : Op<(call "vmlal", $p0, (call "vget_high", $p1),
                                         (call "vget_high", $p2))>;
def OP_MLALHi_N : Op<(call "vmlal_n", $p0, (call "vget_high", $p1), $p2)>;
def OP_MLS      : Op<(op "-", $p0, (op "*", $p1, $p2))>;
def OP_FMLS     : Op<(call "vfma", $p0, (op "-", $p1), $p2)>;
def OP_MLSL     : Op<(op "-", $p0, (call "vmull", $p1, $p2))>;
def OP_MLSLHi   : Op<(call "vmlsl", $p0, (call "vget_high", $p1),
                                         (call "vget_high", $p2))>;
def OP_MLSLHi_N : Op<(call "vmlsl_n", $p0, (call "vget_high", $p1), $p2)>;
def OP_MUL_N    : Op<(op "*", $p0, (dup $p1))>;
def OP_MULX_N   : Op<(call "vmulx", $p0, (dup $p1))>;
def OP_MLA_N    : Op<(op "+", $p0, (op "*", $p1, (dup $p2)))>;
def OP_MLS_N    : Op<(op "-", $p0, (op "*", $p1, (dup $p2)))>;
def OP_FMLA_N   : Op<(call "vfma", $p0, $p1, (dup $p2))>;
def OP_FMLS_N   : Op<(call "vfma", $p0, (op "-", $p1), (dup $p2))>;
def OP_MLAL_N   : Op<(op "+", $p0, (call "vmull", $p1, (dup $p2)))>;
def OP_MLSL_N   : Op<(op "-", $p0, (call "vmull", $p1, (dup $p2)))>;
def OP_MUL_LN   : Op<(op "*", $p0, (splat $p1, $p2))>;
def OP_MULX_LN  : Op<(call "vmulx", $p0, (splat $p1, $p2))>;
def OP_MULL_LN  : Op<(call "vmull", $p0, (splat $p1, $p2))>;
def OP_MULLHi_LN: Op<(call "vmull", (call "vget_high", $p0), (splat $p1, $p2))>;
def OP_MLA_LN   : Op<(op "+", $p0, (op "*", $p1, (splat $p2, $p3)))>;
def OP_MLS_LN   : Op<(op "-", $p0, (op "*", $p1, (splat $p2, $p3)))>;
def OP_MLAL_LN  : Op<(op "+", $p0, (call "vmull", $p1, (splat $p2, $p3)))>;
def OP_MLALHi_LN: Op<(op "+", $p0, (call "vmull", (call "vget_high", $p1),
                                                  (splat $p2, $p3)))>;
def OP_MLSL_LN  : Op<(op "-", $p0, (call "vmull", $p1, (splat $p2, $p3)))>;
def OP_MLSLHi_LN : Op<(op "-", $p0, (call "vmull", (call "vget_high", $p1),
                                                   (splat $p2, $p3)))>;
def OP_QDMULL_LN : Op<(call "vqdmull", $p0, (splat $p1, $p2))>;
def OP_QDMULLHi_LN : Op<(call "vqdmull", (call "vget_high", $p0),
                                         (splat $p1, $p2))>;
def OP_QDMLAL_LN : Op<(call "vqdmlal", $p0, $p1, (splat $p2, $p3))>;
def OP_QDMLALHi_LN : Op<(call "vqdmlal", $p0, (call "vget_high", $p1),
                                              (splat $p2, $p3))>;
def OP_QDMLSL_LN : Op<(call "vqdmlsl", $p0, $p1, (splat $p2, $p3))>;
def OP_QDMLSLHi_LN : Op<(call "vqdmlsl", $p0, (call "vget_high", $p1),
                                              (splat $p2, $p3))>;
def OP_QDMULH_LN : Op<(call "vqdmulh", $p0, (splat $p1, $p2))>;
def OP_QRDMULH_LN : Op<(call "vqrdmulh", $p0, (splat $p1, $p2))>;
def OP_QRDMLAH : Op<(call "vqadd", $p0, (call "vqrdmulh", $p1, $p2))>;
def OP_QRDMLSH : Op<(call "vqsub", $p0, (call "vqrdmulh", $p1, $p2))>;
def OP_QRDMLAH_LN : Op<(call "vqadd", $p0, (call "vqrdmulh", $p1, (splat $p2, $p3)))>;
def OP_QRDMLSH_LN : Op<(call "vqsub", $p0, (call "vqrdmulh", $p1, (splat $p2, $p3)))>;
def OP_FMS_LN   : Op<(call "vfma_lane", $p0, (op "-", $p1), $p2, $p3)>;
def OP_FMS_LNQ  : Op<(call "vfma_laneq", $p0, (op "-", $p1), $p2, $p3)>;
def OP_TRN1     : Op<(shuffle $p0, $p1, (interleave (decimate mask0, 2),
                                                    (decimate mask1, 2)))>;
def OP_ZIP1     : Op<(shuffle $p0, $p1, (lowhalf (interleave mask0, mask1)))>;
def OP_UZP1     : Op<(shuffle $p0, $p1, (add (decimate mask0, 2),
                                             (decimate mask1, 2)))>;
def OP_TRN2     : Op<(shuffle $p0, $p1, (interleave
                                          (decimate (rotl mask0, 1), 2),
                                          (decimate (rotl mask1, 1), 2)))>;
def OP_ZIP2     : Op<(shuffle $p0, $p1, (highhalf (interleave mask0, mask1)))>;
def OP_UZP2     : Op<(shuffle $p0, $p1, (add (decimate (rotl mask0, 1), 2),
                                             (decimate (rotl mask1, 1), 2)))>;
def OP_EQ       : Op<(cast "R", (op "==", $p0, $p1))>;
def OP_GE       : Op<(cast "R", (op ">=", $p0, $p1))>;
def OP_LE       : Op<(cast "R", (op "<=", $p0, $p1))>;
def OP_GT       : Op<(cast "R", (op ">", $p0, $p1))>;
def OP_LT       : Op<(cast "R", (op "<", $p0, $p1))>;
def OP_NEG      : Op<(op "-", $p0)>;
def OP_NOT      : Op<(op "~", $p0)>;
def OP_AND      : Op<(op "&", $p0, $p1)>;
def OP_OR       : Op<(op "|", $p0, $p1)>;
def OP_XOR      : Op<(op "^", $p0, $p1)>;
def OP_ANDN     : Op<(op "&", $p0, (op "~", $p1))>;
def OP_ORN      : Op<(op "|", $p0, (op "~", $p1))>;
def OP_CAST     : Op<(cast "R", $p0)>;
def OP_HI       : Op<(shuffle $p0, $p0, (highhalf mask0))>;
def OP_LO       : Op<(shuffle $p0, $p0, (lowhalf mask0))>;
def OP_CONC     : Op<(shuffle $p0, $p1, (add mask0, mask1))>;
def OP_DUP      : Op<(dup $p0)>;
def OP_DUP_LN   : Op<(splat $p0, $p1)>;
def OP_SEL      : Op<(cast "R", (op "|",
                                    (op "&", $p0, (cast $p0, $p1)),
                                    (op "&", (op "~", $p0), (cast $p0, $p2))))>;
def OP_REV16    : Op<(shuffle $p0, $p0, (rev 16, mask0))>;
def OP_REV32    : Op<(shuffle $p0, $p0, (rev 32, mask0))>;
def OP_REV64    : Op<(shuffle $p0, $p0, (rev 64, mask0))>;
def OP_XTN      : Op<(call "vcombine", $p0, (call "vmovn", $p1))>;
def OP_SQXTUN   : Op<(call "vcombine", (cast $p0, "U", $p0),
                                       (call "vqmovun", $p1))>;
def OP_QXTN     : Op<(call "vcombine", $p0, (call "vqmovn", $p1))>;
def OP_VCVT_NA_HI_F16 : Op<(call "vcombine", $p0, (call "vcvt_f16_f32", $p1))>;
def OP_VCVT_NA_HI_F32 : Op<(call "vcombine", $p0, (call "vcvt_f32_f64", $p1))>;
def OP_VCVT_EX_HI_F32 : Op<(call "vcvt_f32_f16", (call "vget_high", $p0))>;
def OP_VCVT_EX_HI_F64 : Op<(call "vcvt_f64_f32", (call "vget_high", $p0))>;
def OP_VCVTX_HI : Op<(call "vcombine", $p0, (call "vcvtx_f32", $p1))>;
def OP_REINT    : Op<(cast "R", $p0)>;
def OP_ADDHNHi  : Op<(call "vcombine", $p0, (call "vaddhn", $p1, $p2))>;
def OP_RADDHNHi : Op<(call "vcombine", $p0, (call "vraddhn", $p1, $p2))>;
def OP_SUBHNHi  : Op<(call "vcombine", $p0, (call "vsubhn", $p1, $p2))>;
def OP_RSUBHNHi : Op<(call "vcombine", $p0, (call "vrsubhn", $p1, $p2))>;
def OP_ABDL     : Op<(cast "R", (call "vmovl", (cast $p0, "U",
                                                     (call "vabd", $p0, $p1))))>;
def OP_ABDLHi   : Op<(call "vabdl", (call "vget_high", $p0),
                                    (call "vget_high", $p1))>;
def OP_ABA      : Op<(op "+", $p0, (call "vabd", $p1, $p2))>;
def OP_ABAL     : Op<(op "+", $p0, (call "vabdl", $p1, $p2))>;
def OP_ABALHi   : Op<(call "vabal", $p0, (call "vget_high", $p1),
                                       (call "vget_high", $p2))>;
def OP_QDMULLHi : Op<(call "vqdmull", (call "vget_high", $p0),
                                      (call "vget_high", $p1))>;
def OP_QDMULLHi_N : Op<(call "vqdmull_n", (call "vget_high", $p0), $p1)>;
def OP_QDMLALHi : Op<(call "vqdmlal", $p0, (call "vget_high", $p1),
                                           (call "vget_high", $p2))>;
def OP_QDMLALHi_N : Op<(call "vqdmlal_n", $p0, (call "vget_high", $p1), $p2)>;
def OP_QDMLSLHi : Op<(call "vqdmlsl", $p0, (call "vget_high", $p1),
                                           (call "vget_high", $p2))>;
def OP_QDMLSLHi_N : Op<(call "vqdmlsl_n", $p0, (call "vget_high", $p1), $p2)>;
def OP_DIV  : Op<(op "/", $p0, $p1)>;
def OP_LONG_HI : Op<(cast "R", (call (name_replace "_high_", "_"),
                                                (call "vget_high", $p0), $p1))>;
def OP_NARROW_HI : Op<(cast "R", (call "vcombine",
                                       (cast "R", "H", $p0),
                                       (cast "R", "H",
                                           (call (name_replace "_high_", "_"),
                                                 $p1, $p2))))>;
def OP_MOVL_HI  : LOp<[(save_temp $a1, (call "vget_high", $p0)),
                       (cast "R",
                            (call "vshll_n", $a1, (literal "int32_t", "0")))]>;
def OP_COPY_LN : Op<(call "vset_lane", (call "vget_lane", $p2, $p3), $p0, $p1)>;
def OP_SCALAR_MUL_LN : Op<(op "*", $p0, (call "vget_lane", $p1, $p2))>;
def OP_SCALAR_MULX_LN : Op<(call "vmulx", $p0, (call "vget_lane", $p1, $p2))>;
def OP_SCALAR_VMULX_LN : LOp<[(save_temp $x, (call "vget_lane", $p0,
                                                    (literal "int32_t", "0"))),
                              (save_temp $y, (call "vget_lane", $p1, $p2)),
                              (save_temp $z, (call "vmulx", $x, $y)),
                              (call "vset_lane", $z, $p0, $p2)]>;
def OP_SCALAR_VMULX_LNQ : LOp<[(save_temp $x, (call "vget_lane", $p0,
                                                     (literal "int32_t", "0"))),
                               (save_temp $y, (call "vget_lane", $p1, $p2)),
                               (save_temp $z, (call "vmulx", $x, $y)),
                               (call "vset_lane", $z, $p0, (literal "int32_t",
                                                                     "0"))]>;
class ScalarMulOp<string opname> :
  Op<(call opname, $p0, (call "vget_lane", $p1, $p2))>;

def OP_SCALAR_QDMULL_LN : ScalarMulOp<"vqdmull">;
def OP_SCALAR_QDMULH_LN : ScalarMulOp<"vqdmulh">;
def OP_SCALAR_QRDMULH_LN : ScalarMulOp<"vqrdmulh">;

def OP_SCALAR_QRDMLAH_LN : Op<(call "vqadd", $p0, (call "vqrdmulh", $p1,
                              (call "vget_lane", $p2, $p3)))>;
def OP_SCALAR_QRDMLSH_LN : Op<(call "vqsub", $p0, (call "vqrdmulh", $p1,
                              (call "vget_lane", $p2, $p3)))>;

def OP_SCALAR_HALF_GET_LN : Op<(bitcast "float16_t",
                                   (call "vget_lane",
                                         (bitcast "int16x4_t", $p0), $p1))>;
def OP_SCALAR_HALF_GET_LNQ : Op<(bitcast "float16_t",
                                    (call "vget_lane",
                                          (bitcast "int16x8_t", $p0), $p1))>;
def OP_SCALAR_HALF_SET_LN : Op<(bitcast "float16x4_t",
                                   (call "vset_lane",
                                         (bitcast "int16_t", $p0),
                                         (bitcast "int16x4_t", $p1), $p2))>;
def OP_SCALAR_HALF_SET_LNQ : Op<(bitcast "float16x8_t",
                                    (call "vset_lane",
                                          (bitcast "int16_t", $p0),
                                          (bitcast "int16x8_t", $p1), $p2))>;

//===----------------------------------------------------------------------===//
// Instructions
//===----------------------------------------------------------------------===//

////////////////////////////////////////////////////////////////////////////////
// E.3.1 Addition
def VADD    : IOpInst<"vadd", "ddd",
                      "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUl", OP_ADD>;
def VADDL   : SOpInst<"vaddl", "wdd", "csiUcUsUi", OP_ADDL>;
def VADDW   : SOpInst<"vaddw", "wwd", "csiUcUsUi", OP_ADDW>;
def VHADD   : SInst<"vhadd", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">;
def VRHADD  : SInst<"vrhadd", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">;
def VQADD   : SInst<"vqadd", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VADDHN  : IInst<"vaddhn", "hkk", "silUsUiUl">;
def VRADDHN : IInst<"vraddhn", "hkk", "silUsUiUl">;

////////////////////////////////////////////////////////////////////////////////
// E.3.2 Multiplication
def VMUL     : IOpInst<"vmul", "ddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MUL>;
def VMULP    : SInst<"vmul", "ddd", "PcQPc">;
def VMLA     : IOpInst<"vmla", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLA>;
def VMLAL    : SOpInst<"vmlal", "wwdd", "csiUcUsUi", OP_MLAL>;
def VMLS     : IOpInst<"vmls", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLS>;
def VMLSL    : SOpInst<"vmlsl", "wwdd", "csiUcUsUi", OP_MLSL>;
def VQDMULH  : SInst<"vqdmulh", "ddd", "siQsQi">;
def VQRDMULH : SInst<"vqrdmulh", "ddd", "siQsQi">;

let ArchGuard = "defined(__ARM_FEATURE_QRDMX)" in {
def VQRDMLAH : SOpInst<"vqrdmlah", "dddd", "siQsQi", OP_QRDMLAH>;
def VQRDMLSH : SOpInst<"vqrdmlsh", "dddd", "siQsQi", OP_QRDMLSH>;
}

def VQDMLAL  : SInst<"vqdmlal", "wwdd", "si">;
def VQDMLSL  : SInst<"vqdmlsl", "wwdd", "si">;
def VMULL    : SInst<"vmull", "wdd", "csiUcUsUiPc">;
def VQDMULL  : SInst<"vqdmull", "wdd", "si">;

////////////////////////////////////////////////////////////////////////////////
// E.3.3 Subtraction
def VSUB    : IOpInst<"vsub", "ddd",
                      "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUl", OP_SUB>;
def VSUBL   : SOpInst<"vsubl", "wdd", "csiUcUsUi", OP_SUBL>;
def VSUBW   : SOpInst<"vsubw", "wwd", "csiUcUsUi", OP_SUBW>;
def VQSUB   : SInst<"vqsub", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VHSUB   : SInst<"vhsub", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">;
def VSUBHN  : IInst<"vsubhn", "hkk", "silUsUiUl">;
def VRSUBHN : IInst<"vrsubhn", "hkk", "silUsUiUl">;

////////////////////////////////////////////////////////////////////////////////
// E.3.4 Comparison
def VCEQ  : IOpInst<"vceq", "udd", "csifUcUsUiPcQcQsQiQfQUcQUsQUiQPc", OP_EQ>;
def VCGE  : SOpInst<"vcge", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GE>;
let InstName = "vcge" in
def VCLE  : SOpInst<"vcle", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LE>;
def VCGT  : SOpInst<"vcgt", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GT>;
let InstName = "vcgt" in
def VCLT  : SOpInst<"vclt", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LT>;
let InstName = "vacge" in {
def VCAGE : IInst<"vcage", "udd", "fQf">;
def VCALE : IInst<"vcale", "udd", "fQf">;
}
let InstName = "vacgt" in {
def VCAGT : IInst<"vcagt", "udd", "fQf">;
def VCALT : IInst<"vcalt", "udd", "fQf">;
}
def VTST  : WInst<"vtst", "udd", "csiUcUsUiPcPsQcQsQiQUcQUsQUiQPcQPs">;

////////////////////////////////////////////////////////////////////////////////
// E.3.5 Absolute Difference
def VABD  : SInst<"vabd", "ddd",  "csiUcUsUifQcQsQiQUcQUsQUiQf">;
def VABDL : SOpInst<"vabdl", "wdd",  "csiUcUsUi", OP_ABDL>;
def VABA  : SOpInst<"vaba", "dddd", "csiUcUsUiQcQsQiQUcQUsQUi", OP_ABA>;
def VABAL : SOpInst<"vabal", "wwdd", "csiUcUsUi", OP_ABAL>;

////////////////////////////////////////////////////////////////////////////////
// E.3.6 Max/Min
def VMAX : SInst<"vmax", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">;
def VMIN : SInst<"vmin", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">;

////////////////////////////////////////////////////////////////////////////////
// E.3.7 Pairwise Addition
def VPADD  : IInst<"vpadd", "ddd", "csiUcUsUif">;
def VPADDL : SInst<"vpaddl", "nd",  "csiUcUsUiQcQsQiQUcQUsQUi">;
def VPADAL : SInst<"vpadal", "nnd", "csiUcUsUiQcQsQiQUcQUsQUi">;

////////////////////////////////////////////////////////////////////////////////
// E.3.8-9 Folding Max/Min
def VPMAX : SInst<"vpmax", "ddd", "csiUcUsUif">;
def VPMIN : SInst<"vpmin", "ddd", "csiUcUsUif">;

////////////////////////////////////////////////////////////////////////////////
// E.3.10 Reciprocal/Sqrt
def VRECPS  : IInst<"vrecps", "ddd", "fQf">;
def VRSQRTS : IInst<"vrsqrts", "ddd", "fQf">;

////////////////////////////////////////////////////////////////////////////////
// E.3.11 Shifts by signed variable
def VSHL   : SInst<"vshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VQSHL  : SInst<"vqshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VRSHL  : SInst<"vrshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VQRSHL : SInst<"vqrshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;

////////////////////////////////////////////////////////////////////////////////
// E.3.12 Shifts by constant
let isShift = 1 in {
def VSHR_N     : SInst<"vshr_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VSHL_N     : IInst<"vshl_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VRSHR_N    : SInst<"vrshr_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VSRA_N     : SInst<"vsra_n", "dddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VRSRA_N    : SInst<"vrsra_n", "dddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VQSHL_N    : SInst<"vqshl_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
def VQSHLU_N   : SInst<"vqshlu_n", "udi", "csilQcQsQiQl">;
def VSHRN_N    : IInst<"vshrn_n", "hki", "silUsUiUl">;
def VQSHRUN_N  : SInst<"vqshrun_n", "eki", "sil">;
def VQRSHRUN_N : SInst<"vqrshrun_n", "eki", "sil">;
def VQSHRN_N   : SInst<"vqshrn_n", "hki", "silUsUiUl">;
def VRSHRN_N   : IInst<"vrshrn_n", "hki", "silUsUiUl">;
def VQRSHRN_N  : SInst<"vqrshrn_n", "hki", "silUsUiUl">;
def VSHLL_N    : SInst<"vshll_n", "wdi", "csiUcUsUi">;

////////////////////////////////////////////////////////////////////////////////
// E.3.13 Shifts with insert
def VSRI_N : WInst<"vsri_n", "dddi",
                   "csilUcUsUiUlPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">;
def VSLI_N : WInst<"vsli_n", "dddi",
                   "csilUcUsUiUlPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">;
}

////////////////////////////////////////////////////////////////////////////////
// E.3.14 Loads and stores of a single vector
def VLD1      : WInst<"vld1", "dc",
                      "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VLD1_LANE : WInst<"vld1_lane", "dcdi",
                      "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VLD1_DUP  : WInst<"vld1_dup", "dc",
                      "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VST1      : WInst<"vst1", "vpd",
                      "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VST1_LANE : WInst<"vst1_lane", "vpdi",
                      "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">;

////////////////////////////////////////////////////////////////////////////////
// E.3.15 Loads and stores of an N-element structure
def VLD2 : WInst<"vld2", "2c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VLD3 : WInst<"vld3", "3c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VLD4 : WInst<"vld4", "4c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VLD2_DUP  : WInst<"vld2_dup", "2c", "UcUsUiUlcsilhfPcPs">;
def VLD3_DUP  : WInst<"vld3_dup", "3c", "UcUsUiUlcsilhfPcPs">;
def VLD4_DUP  : WInst<"vld4_dup", "4c", "UcUsUiUlcsilhfPcPs">;
def VLD2_LANE : WInst<"vld2_lane", "2c2i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">;
def VLD3_LANE : WInst<"vld3_lane", "3c3i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">;
def VLD4_LANE : WInst<"vld4_lane", "4c4i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">;
def VST2 : WInst<"vst2", "vp2", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VST3 : WInst<"vst3", "vp3", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VST4 : WInst<"vst4", "vp4", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">;
def VST2_LANE : WInst<"vst2_lane", "vp2i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">;
def VST3_LANE : WInst<"vst3_lane", "vp3i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">;
def VST4_LANE : WInst<"vst4_lane", "vp4i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">;

////////////////////////////////////////////////////////////////////////////////
// E.3.16 Extract lanes from a vector
let InstName = "vmov" in
def VGET_LANE : IInst<"vget_lane", "sdi",
                      "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl">;

////////////////////////////////////////////////////////////////////////////////
// E.3.17 Set lanes within a vector
let InstName = "vmov" in
def VSET_LANE : IInst<"vset_lane", "dsdi",
                      "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl">;

////////////////////////////////////////////////////////////////////////////////
// E.3.18 Initialize a vector from bit pattern
def VCREATE : NoTestOpInst<"vcreate", "dl", "csihfUcUsUiUlPcPsl", OP_CAST> {
  let BigEndianSafe = 1;
}

////////////////////////////////////////////////////////////////////////////////
// E.3.19 Set all lanes to same value
let InstName = "vmov" in {
def VDUP_N   : WOpInst<"vdup_n", "ds",
                       "UcUsUicsiPcPshfQUcQUsQUiQcQsQiQPcQPsQhQflUlQlQUl",
                       OP_DUP>;
def VMOV_N   : WOpInst<"vmov_n", "ds",
                       "UcUsUicsiPcPshfQUcQUsQUiQcQsQiQPcQPsQhQflUlQlQUl",
                       OP_DUP>;
}
let InstName = "" in
def VDUP_LANE: WOpInst<"vdup_lane", "dgi",
                       "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl",
                       OP_DUP_LN>;

////////////////////////////////////////////////////////////////////////////////
// E.3.20 Combining vectors
def VCOMBINE : NoTestOpInst<"vcombine", "kdd", "csilhfUcUsUiUlPcPs", OP_CONC>;

////////////////////////////////////////////////////////////////////////////////
// E.3.21 Splitting vectors
let InstName = "vmov" in {
def VGET_HIGH : NoTestOpInst<"vget_high", "dk", "csilhfUcUsUiUlPcPs", OP_HI>;
def VGET_LOW  : NoTestOpInst<"vget_low", "dk", "csilhfUcUsUiUlPcPs", OP_LO>;
}

////////////////////////////////////////////////////////////////////////////////
// E.3.22 Converting vectors

let ArchGuard = "(__ARM_FP & 2)" in {
  def VCVT_F16_F32 : SInst<"vcvt_f16_f32", "md", "Hf">;
  def VCVT_F32_F16 : SInst<"vcvt_f32_f16", "wd", "h">;
}

def VCVT_S32     : SInst<"vcvt_s32", "xd",  "fQf">;
def VCVT_U32     : SInst<"vcvt_u32", "ud",  "fQf">;
def VCVT_F32     : SInst<"vcvt_f32", "fd",  "iUiQiQUi">;
let isVCVT_N = 1 in {
def VCVT_N_S32   : SInst<"vcvt_n_s32", "xdi", "fQf">;
def VCVT_N_U32   : SInst<"vcvt_n_u32", "udi", "fQf">;
def VCVT_N_F32   : SInst<"vcvt_n_f32", "fdi", "iUiQiQUi">;
}

def VMOVN        : IInst<"vmovn", "hk",  "silUsUiUl">;
def VMOVL        : SInst<"vmovl", "wd",  "csiUcUsUi">;
def VQMOVN       : SInst<"vqmovn", "hk",  "silUsUiUl">;
def VQMOVUN      : SInst<"vqmovun", "ek",  "sil">;

////////////////////////////////////////////////////////////////////////////////
// E.3.23-24 Table lookup, Extended table lookup
let InstName = "vtbl" in {
def VTBL1 : WInst<"vtbl1", "ddt",  "UccPc">;
def VTBL2 : WInst<"vtbl2", "d2t",  "UccPc">;
def VTBL3 : WInst<"vtbl3", "d3t",  "UccPc">;
def VTBL4 : WInst<"vtbl4", "d4t",  "UccPc">;
}
let InstName = "vtbx" in {
def VTBX1 : WInst<"vtbx1", "dddt", "UccPc">;
def VTBX2 : WInst<"vtbx2", "dd2t", "UccPc">;
def VTBX3 : WInst<"vtbx3", "dd3t", "UccPc">;
def VTBX4 : WInst<"vtbx4", "dd4t", "UccPc">;
}

////////////////////////////////////////////////////////////////////////////////
// E.3.25 Operations with a scalar value
def VMLA_LANE     : IOpInst<"vmla_lane", "dddgi",
                            "siUsUifQsQiQUsQUiQf", OP_MLA_LN>;
def VMLAL_LANE    : SOpInst<"vmlal_lane", "wwddi", "siUsUi", OP_MLAL_LN>;
def VQDMLAL_LANE  : SOpInst<"vqdmlal_lane", "wwddi", "si", OP_QDMLAL_LN>;
def VMLS_LANE     : IOpInst<"vmls_lane", "dddgi",
                            "siUsUifQsQiQUsQUiQf", OP_MLS_LN>;
def VMLSL_LANE    : SOpInst<"vmlsl_lane", "wwddi", "siUsUi", OP_MLSL_LN>;
def VQDMLSL_LANE  : SOpInst<"vqdmlsl_lane", "wwddi", "si", OP_QDMLSL_LN>;
def VMUL_N        : IOpInst<"vmul_n", "dds", "sifUsUiQsQiQfQUsQUi", OP_MUL_N>;
def VMUL_LANE     : IOpInst<"vmul_lane", "ddgi",
                            "sifUsUiQsQiQfQUsQUi", OP_MUL_LN>;
def VMULL_N       : SInst<"vmull_n", "wda", "siUsUi">;
def VMULL_LANE    : SOpInst<"vmull_lane", "wddi", "siUsUi", OP_MULL_LN>;
def VQDMULL_N     : SInst<"vqdmull_n", "wda", "si">;
def VQDMULL_LANE  : SOpInst<"vqdmull_lane", "wddi", "si", OP_QDMULL_LN>;
def VQDMULH_N     : SInst<"vqdmulh_n", "dda", "siQsQi">;
def VQDMULH_LANE  : SOpInst<"vqdmulh_lane", "ddgi", "siQsQi", OP_QDMULH_LN>;
def VQRDMULH_N    : SInst<"vqrdmulh_n", "dda", "siQsQi">;
def VQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "ddgi", "siQsQi", OP_QRDMULH_LN>;

let ArchGuard = "defined(__ARM_FEATURE_QRDMX)" in {
def VQRDMLAH_LANE : SOpInst<"vqrdmlah_lane", "dddgi", "siQsQi", OP_QRDMLAH_LN>;
def VQRDMLSH_LANE : SOpInst<"vqrdmlsh_lane", "dddgi", "siQsQi", OP_QRDMLSH_LN>;
}

def VMLA_N        : IOpInst<"vmla_n", "ddda", "siUsUifQsQiQUsQUiQf", OP_MLA_N>;
def VMLAL_N       : SOpInst<"vmlal_n", "wwda", "siUsUi", OP_MLAL_N>;
def VQDMLAL_N     : SInst<"vqdmlal_n", "wwda", "si">;
def VMLS_N        : IOpInst<"vmls_n", "ddds", "siUsUifQsQiQUsQUiQf", OP_MLS_N>;
def VMLSL_N       : SOpInst<"vmlsl_n", "wwda", "siUsUi", OP_MLSL_N>;
def VQDMLSL_N     : SInst<"vqdmlsl_n", "wwda", "si">;

////////////////////////////////////////////////////////////////////////////////
// E.3.26 Vector Extract
def VEXT : WInst<"vext", "dddi",
                 "cUcPcsUsPsiUilUlfQcQUcQPcQsQUsQPsQiQUiQlQUlQf">;

////////////////////////////////////////////////////////////////////////////////
// E.3.27 Reverse vector elements
def VREV64 : WOpInst<"vrev64", "dd", "csiUcUsUiPcPsfQcQsQiQUcQUsQUiQPcQPsQf",
                  OP_REV64>;
def VREV32 : WOpInst<"vrev32", "dd", "csUcUsPcPsQcQsQUcQUsQPcQPs", OP_REV32>;
def VREV16 : WOpInst<"vrev16", "dd", "cUcPcQcQUcQPc", OP_REV16>;

////////////////////////////////////////////////////////////////////////////////
// E.3.28 Other single operand arithmetic
def VABS    : SInst<"vabs", "dd", "csifQcQsQiQf">;
def VQABS   : SInst<"vqabs", "dd", "csiQcQsQi">;
def VNEG    : SOpInst<"vneg", "dd", "csifQcQsQiQf", OP_NEG>;
def VQNEG   : SInst<"vqneg", "dd", "csiQcQsQi">;
def VCLS    : SInst<"vcls", "dd", "csiQcQsQi">;
def VCLZ    : IInst<"vclz", "dd", "csiUcUsUiQcQsQiQUcQUsQUi">;
def VCNT    : WInst<"vcnt", "dd", "UccPcQUcQcQPc">;
def VRECPE  : SInst<"vrecpe", "dd", "fUiQfQUi">;
def VRSQRTE : SInst<"vrsqrte", "dd", "fUiQfQUi">;

////////////////////////////////////////////////////////////////////////////////
// E.3.29 Logical operations
def VMVN : LOpInst<"vmvn", "dd", "csiUcUsUiPcQcQsQiQUcQUsQUiQPc", OP_NOT>;
def VAND : LOpInst<"vand", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_AND>;
def VORR : LOpInst<"vorr", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_OR>;
def VEOR : LOpInst<"veor", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_XOR>;
def VBIC : LOpInst<"vbic", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ANDN>;
def VORN : LOpInst<"vorn", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ORN>;
let isHiddenLInst = 1 in
def VBSL : SInst<"vbsl", "dudd",
                "csilUcUsUiUlfPcPsQcQsQiQlQUcQUsQUiQUlQfQPcQPs">;

////////////////////////////////////////////////////////////////////////////////
// E.3.30 Transposition operations
def VTRN : WInst<"vtrn", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
def VZIP : WInst<"vzip", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
def VUZP : WInst<"vuzp", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;

////////////////////////////////////////////////////////////////////////////////
// E.3.31 Vector reinterpret cast operations
def VREINTERPRET
  : NoTestOpInst<"vreinterpret", "dd",
         "csilUcUsUiUlhfPcPsQcQsQiQlQUcQUsQUiQUlQhQfQPcQPs", OP_REINT> {
  let CartesianProductOfTypes = 1;
  let ArchGuard = "!defined(__aarch64__)";
  let BigEndianSafe = 1;
}

////////////////////////////////////////////////////////////////////////////////
// Vector fused multiply-add operations

let ArchGuard = "defined(__ARM_FEATURE_FMA)" in {
  def VFMA : SInst<"vfma", "dddd", "fQf">;
  def VFMS : SOpInst<"vfms", "dddd", "fQf", OP_FMLS>;
}

////////////////////////////////////////////////////////////////////////////////
// fp16 vector operations
def SCALAR_HALF_GET_LANE : IOpInst<"vget_lane", "sdi", "h", OP_SCALAR_HALF_GET_LN>;
def SCALAR_HALF_SET_LANE : IOpInst<"vset_lane", "dsdi", "h", OP_SCALAR_HALF_SET_LN>;
def SCALAR_HALF_GET_LANEQ : IOpInst<"vget_lane", "sdi", "Qh", OP_SCALAR_HALF_GET_LNQ>;
def SCALAR_HALF_SET_LANEQ : IOpInst<"vset_lane", "dsdi", "Qh", OP_SCALAR_HALF_SET_LNQ>;

////////////////////////////////////////////////////////////////////////////////
// AArch64 Intrinsics

let ArchGuard = "defined(__aarch64__)" in {

////////////////////////////////////////////////////////////////////////////////
// Load/Store
def LD1 : WInst<"vld1", "dc", "dQdPlQPl">;
def LD2 : WInst<"vld2", "2c", "QUlQldQdPlQPl">;
def LD3 : WInst<"vld3", "3c", "QUlQldQdPlQPl">;
def LD4 : WInst<"vld4", "4c", "QUlQldQdPlQPl">;
def ST1 : WInst<"vst1", "vpd", "dQdPlQPl">;
def ST2 : WInst<"vst2", "vp2", "QUlQldQdPlQPl">;
def ST3 : WInst<"vst3", "vp3", "QUlQldQdPlQPl">;
def ST4 : WInst<"vst4", "vp4", "QUlQldQdPlQPl">;

def LD1_X2 : WInst<"vld1_x2", "2c",
                   "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPsQUlQldQdPlQPl">;
def LD3_x3 : WInst<"vld1_x3", "3c",
                   "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPsQUlQldQdPlQPl">;
def LD4_x4 : WInst<"vld1_x4", "4c",
                   "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPsQUlQldQdPlQPl">;

def ST1_X2 : WInst<"vst1_x2", "vp2",
                   "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPsQUlQldQdPlQPl">;
def ST1_X3 : WInst<"vst1_x3", "vp3",
                   "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPsQUlQldQdPlQPl">;
def ST1_X4 : WInst<"vst1_x4", "vp4",
                   "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPsQUlQldQdPlQPl">;

def LD1_LANE : WInst<"vld1_lane", "dcdi", "dQdPlQPl">;
def LD2_LANE : WInst<"vld2_lane", "2c2i", "lUlQcQUcQPcQlQUldQdPlQPl">;
def LD3_LANE : WInst<"vld3_lane", "3c3i", "lUlQcQUcQPcQlQUldQdPlQPl">;
def LD4_LANE : WInst<"vld4_lane", "4c4i", "lUlQcQUcQPcQlQUldQdPlQPl">;
def ST1_LANE : WInst<"vst1_lane", "vpdi", "dQdPlQPl">;
def ST2_LANE : WInst<"vst2_lane", "vp2i", "lUlQcQUcQPcQlQUldQdPlQPl">;
def ST3_LANE : WInst<"vst3_lane", "vp3i", "lUlQcQUcQPcQlQUldQdPlQPl">;
def ST4_LANE : WInst<"vst4_lane", "vp4i", "lUlQcQUcQPcQlQUldQdPlQPl">;

def LD1_DUP  : WInst<"vld1_dup", "dc", "dQdPlQPl">;
def LD2_DUP  : WInst<"vld2_dup", "2c",
                     "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsQPldPl">;
def LD3_DUP  : WInst<"vld3_dup", "3c",
                     "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsQPldPl">;
def LD4_DUP  : WInst<"vld4_dup", "4c",
                     "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsQPldPl">;

def VLDRQ : WInst<"vldrq", "sc", "Pk">;
def VSTRQ : WInst<"vstrq", "vps", "Pk">;

////////////////////////////////////////////////////////////////////////////////
// Addition
def ADD : IOpInst<"vadd", "ddd", "dQd", OP_ADD>;

////////////////////////////////////////////////////////////////////////////////
// Subtraction
def SUB : IOpInst<"vsub", "ddd", "dQd", OP_SUB>;

////////////////////////////////////////////////////////////////////////////////
// Multiplication
def MUL     : IOpInst<"vmul", "ddd", "dQd", OP_MUL>;
def MLA     : IOpInst<"vmla", "dddd", "dQd", OP_MLA>;
def MLS     : IOpInst<"vmls", "dddd", "dQd", OP_MLS>;

////////////////////////////////////////////////////////////////////////////////
// Multiplication Extended
def MULX : SInst<"vmulx", "ddd", "fdQfQd">;

////////////////////////////////////////////////////////////////////////////////
// Division
def FDIV : IOpInst<"vdiv", "ddd",  "fdQfQd", OP_DIV>;

////////////////////////////////////////////////////////////////////////////////
// Vector fused multiply-add operations
def FMLA : SInst<"vfma", "dddd", "dQd">;
def FMLS : SOpInst<"vfms", "dddd", "dQd", OP_FMLS>;

////////////////////////////////////////////////////////////////////////////////
// MUL, MLA, MLS, FMA, FMS definitions with scalar argument
def VMUL_N_A64 : IOpInst<"vmul_n", "dds", "Qd", OP_MUL_N>;

def FMLA_N : SOpInst<"vfma_n", "ddds", "fQfQd", OP_FMLA_N>;
def FMLS_N : SOpInst<"vfms_n", "ddds", "fQfQd", OP_FMLS_N>;

def MLA_N : SOpInst<"vmla_n", "ddds", "Qd", OP_MLA_N>;
def MLS_N : SOpInst<"vmls_n", "ddds", "Qd", OP_MLS_N>;

////////////////////////////////////////////////////////////////////////////////
// Logical operations
def BSL : SInst<"vbsl", "dudd", "dPlQdQPl">;

////////////////////////////////////////////////////////////////////////////////
// Absolute Difference
def ABD  : SInst<"vabd", "ddd",  "dQd">;

////////////////////////////////////////////////////////////////////////////////
// saturating absolute/negate
def ABS    : SInst<"vabs", "dd", "dQdlQl">;
def QABS   : SInst<"vqabs", "dd", "lQl">;
def NEG    : SOpInst<"vneg", "dd", "dlQdQl", OP_NEG>;
def QNEG   : SInst<"vqneg", "dd", "lQl">;

////////////////////////////////////////////////////////////////////////////////
// Signed Saturating Accumulated of Unsigned Value
def SUQADD : SInst<"vuqadd", "ddd", "csilQcQsQiQl">;

////////////////////////////////////////////////////////////////////////////////
// Unsigned Saturating Accumulated of Signed Value
def USQADD : SInst<"vsqadd", "ddd", "UcUsUiUlQUcQUsQUiQUl">;

////////////////////////////////////////////////////////////////////////////////
// Reciprocal/Sqrt
def FRECPS  : IInst<"vrecps", "ddd", "dQd">;
def FRSQRTS : IInst<"vrsqrts", "ddd", "dQd">;
def FRECPE  : SInst<"vrecpe", "dd", "dQd">;
def FRSQRTE : SInst<"vrsqrte", "dd", "dQd">;
def FSQRT   : SInst<"vsqrt", "dd", "fdQfQd">;

////////////////////////////////////////////////////////////////////////////////
// bitwise reverse
def RBIT : IInst<"vrbit", "dd", "cUcPcQcQUcQPc">;

////////////////////////////////////////////////////////////////////////////////
// Integer extract and narrow to high
def XTN2 : SOpInst<"vmovn_high", "qhk", "silUsUiUl", OP_XTN>;

////////////////////////////////////////////////////////////////////////////////
// Signed integer saturating extract and unsigned narrow to high
def SQXTUN2 : SOpInst<"vqmovun_high", "emd", "HsHiHl", OP_SQXTUN>;

////////////////////////////////////////////////////////////////////////////////
// Integer saturating extract and narrow to high
def QXTN2 : SOpInst<"vqmovn_high", "qhk", "silUsUiUl", OP_QXTN>;

////////////////////////////////////////////////////////////////////////////////
// Converting vectors

def VCVT_F32_F64 : SInst<"vcvt_f32_f64", "md", "Qd">;
def VCVT_F64_F32 : SInst<"vcvt_f64_f32", "wd", "f">;

def VCVT_S64 : SInst<"vcvt_s64", "xd",  "dQd">;
def VCVT_U64 : SInst<"vcvt_u64", "ud",  "dQd">;
def VCVT_F64 : SInst<"vcvt_f64", "Fd",  "lUlQlQUl">;

def VCVT_HIGH_F16_F32 : SOpInst<"vcvt_high_f16", "hmj", "Hf", OP_VCVT_NA_HI_F16>;
def VCVT_HIGH_F32_F16 : SOpInst<"vcvt_high_f32", "wk", "h", OP_VCVT_EX_HI_F32>;
def VCVT_HIGH_F32_F64 : SOpInst<"vcvt_high_f32", "qfj", "d", OP_VCVT_NA_HI_F32>;
def VCVT_HIGH_F64_F32 : SOpInst<"vcvt_high_f64", "wj", "f", OP_VCVT_EX_HI_F64>;

def VCVTX_F32_F64      : SInst<"vcvtx_f32", "fj",  "d">;
def VCVTX_HIGH_F32_F64 : SOpInst<"vcvtx_high_f32", "qfj", "d", OP_VCVTX_HI>;

////////////////////////////////////////////////////////////////////////////////
// Comparison
def FCAGE : IInst<"vcage", "udd", "dQd">;
def FCAGT : IInst<"vcagt", "udd", "dQd">;
def FCALE : IInst<"vcale", "udd", "dQd">;
def FCALT : IInst<"vcalt", "udd", "dQd">;
def CMTST  : WInst<"vtst", "udd", "lUlPlQlQUlQPl">;
def CFMEQ  : SOpInst<"vceq", "udd", "lUldQdQlQUlPlQPl", OP_EQ>;
def CFMGE  : SOpInst<"vcge", "udd", "lUldQdQlQUl", OP_GE>;
def CFMLE  : SOpInst<"vcle", "udd", "lUldQdQlQUl", OP_LE>;
def CFMGT  : SOpInst<"vcgt", "udd", "lUldQdQlQUl", OP_GT>;
def CFMLT  : SOpInst<"vclt", "udd", "lUldQdQlQUl", OP_LT>;

def CMEQ  : SInst<"vceqz", "ud",
                  "csilfUcUsUiUlPcPsPlQcQsQiQlQfQUcQUsQUiQUlQPcQPsdQdQPl">;
def CMGE  : SInst<"vcgez", "ud", "csilfdQcQsQiQlQfQd">;
def CMLE  : SInst<"vclez", "ud", "csilfdQcQsQiQlQfQd">;
def CMGT  : SInst<"vcgtz", "ud", "csilfdQcQsQiQlQfQd">;
def CMLT  : SInst<"vcltz", "ud", "csilfdQcQsQiQlQfQd">;

////////////////////////////////////////////////////////////////////////////////
// Max/Min Integer
def MAX : SInst<"vmax", "ddd", "dQd">;
def MIN : SInst<"vmin", "ddd", "dQd">;

////////////////////////////////////////////////////////////////////////////////
// Pairwise Max/Min
def MAXP : SInst<"vpmax", "ddd", "QcQsQiQUcQUsQUiQfQd">;
def MINP : SInst<"vpmin", "ddd", "QcQsQiQUcQUsQUiQfQd">;

////////////////////////////////////////////////////////////////////////////////
// Pairwise MaxNum/MinNum Floating Point
def FMAXNMP : SInst<"vpmaxnm", "ddd", "fQfQd">;
def FMINNMP : SInst<"vpminnm", "ddd", "fQfQd">;

////////////////////////////////////////////////////////////////////////////////
// Pairwise Addition
def ADDP  : IInst<"vpadd", "ddd", "QcQsQiQlQUcQUsQUiQUlQfQd">;

////////////////////////////////////////////////////////////////////////////////
// Shifts by constant
let isShift = 1 in {
// Left shift long high
def SHLL_HIGH_N    : SOpInst<"vshll_high_n", "ndi", "HcHsHiHUcHUsHUi",
                             OP_LONG_HI>;

////////////////////////////////////////////////////////////////////////////////
def SRI_N : WInst<"vsri_n", "dddi", "PlQPl">;
def SLI_N : WInst<"vsli_n", "dddi", "PlQPl">;

// Right shift narrow high
def SHRN_HIGH_N    : IOpInst<"vshrn_high_n", "hmdi",
                             "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
def QSHRUN_HIGH_N  : SOpInst<"vqshrun_high_n", "hmdi",
                             "HsHiHl", OP_NARROW_HI>;
def RSHRN_HIGH_N   : IOpInst<"vrshrn_high_n", "hmdi",
                             "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
def QRSHRUN_HIGH_N : SOpInst<"vqrshrun_high_n", "hmdi",
                             "HsHiHl", OP_NARROW_HI>;
def QSHRN_HIGH_N   : SOpInst<"vqshrn_high_n", "hmdi", 
                             "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
def QRSHRN_HIGH_N  : SOpInst<"vqrshrn_high_n", "hmdi", 
                             "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
}

////////////////////////////////////////////////////////////////////////////////
// Converting vectors
def VMOVL_HIGH   : SOpInst<"vmovl_high", "nd", "HcHsHiHUcHUsHUi", OP_MOVL_HI>;

let isVCVT_N = 1 in {
def CVTF_N_F64   : SInst<"vcvt_n_f64", "Fdi", "lUlQlQUl">;
def FCVTZS_N_S64 : SInst<"vcvt_n_s64", "xdi", "dQd">;
def FCVTZS_N_U64 : SInst<"vcvt_n_u64", "udi", "dQd">;
}

////////////////////////////////////////////////////////////////////////////////
// 3VDiff class using high 64-bit in operands
def VADDL_HIGH   : SOpInst<"vaddl_high", "wkk", "csiUcUsUi", OP_ADDLHi>;
def VADDW_HIGH   : SOpInst<"vaddw_high", "wwk", "csiUcUsUi", OP_ADDWHi>;
def VSUBL_HIGH   : SOpInst<"vsubl_high", "wkk", "csiUcUsUi", OP_SUBLHi>;
def VSUBW_HIGH   : SOpInst<"vsubw_high", "wwk", "csiUcUsUi", OP_SUBWHi>;

def VABDL_HIGH   : SOpInst<"vabdl_high", "wkk",  "csiUcUsUi", OP_ABDLHi>;
def VABAL_HIGH   : SOpInst<"vabal_high", "wwkk", "csiUcUsUi", OP_ABALHi>;

def VMULL_HIGH   : SOpInst<"vmull_high", "wkk", "csiUcUsUiPc", OP_MULLHi>;
def VMULL_HIGH_N : SOpInst<"vmull_high_n", "wks", "siUsUi", OP_MULLHi_N>;
def VMLAL_HIGH   : SOpInst<"vmlal_high", "wwkk", "csiUcUsUi", OP_MLALHi>;
def VMLAL_HIGH_N : SOpInst<"vmlal_high_n", "wwks", "siUsUi", OP_MLALHi_N>;
def VMLSL_HIGH   : SOpInst<"vmlsl_high", "wwkk", "csiUcUsUi", OP_MLSLHi>;
def VMLSL_HIGH_N : SOpInst<"vmlsl_high_n", "wwks", "siUsUi", OP_MLSLHi_N>;

def VADDHN_HIGH  : SOpInst<"vaddhn_high", "qhkk", "silUsUiUl", OP_ADDHNHi>;
def VRADDHN_HIGH : SOpInst<"vraddhn_high", "qhkk", "silUsUiUl", OP_RADDHNHi>;
def VSUBHN_HIGH  : SOpInst<"vsubhn_high", "qhkk", "silUsUiUl", OP_SUBHNHi>;
def VRSUBHN_HIGH : SOpInst<"vrsubhn_high", "qhkk", "silUsUiUl", OP_RSUBHNHi>;

def VQDMULL_HIGH : SOpInst<"vqdmull_high", "wkk", "si", OP_QDMULLHi>;
def VQDMULL_HIGH_N : SOpInst<"vqdmull_high_n", "wks", "si", OP_QDMULLHi_N>;
def VQDMLAL_HIGH : SOpInst<"vqdmlal_high", "wwkk", "si", OP_QDMLALHi>;
def VQDMLAL_HIGH_N : SOpInst<"vqdmlal_high_n", "wwks", "si", OP_QDMLALHi_N>;
def VQDMLSL_HIGH : SOpInst<"vqdmlsl_high", "wwkk", "si", OP_QDMLSLHi>;
def VQDMLSL_HIGH_N : SOpInst<"vqdmlsl_high_n", "wwks", "si", OP_QDMLSLHi_N>;
def VMULL_P64    : SInst<"vmull", "rss", "Pl">;
def VMULL_HIGH_P64 : SOpInst<"vmull_high", "rdd", "HPl", OP_MULLHi_P64>;


////////////////////////////////////////////////////////////////////////////////
// Extract or insert element from vector
def GET_LANE : IInst<"vget_lane", "sdi", "dQdPlQPl">;
def SET_LANE : IInst<"vset_lane", "dsdi", "dQdPlQPl">;
def COPY_LANE : IOpInst<"vcopy_lane", "ddidi",
                        "csilUcUsUiUlPcPsPlfd", OP_COPY_LN>;
def COPYQ_LANE : IOpInst<"vcopy_lane", "ddigi",
                        "QcQsQiQlQUcQUsQUiQUlQPcQPsQfQdQPl", OP_COPY_LN>;
def COPY_LANEQ : IOpInst<"vcopy_laneq", "ddiki",
                     "csilPcPsPlUcUsUiUlfd", OP_COPY_LN>;
def COPYQ_LANEQ : IOpInst<"vcopy_laneq", "ddidi",
                     "QcQsQiQlQUcQUsQUiQUlQPcQPsQfQdQPl", OP_COPY_LN>;

////////////////////////////////////////////////////////////////////////////////
// Set all lanes to same value
def VDUP_LANE1: WOpInst<"vdup_lane", "dgi", "hdQhQdPlQPl", OP_DUP_LN>;
def VDUP_LANE2: WOpInst<"vdup_laneq", "dji",
                  "csilUcUsUiUlPcPshfdQcQsQiQlQPcQPsQUcQUsQUiQUlQhQfQdPlQPl",
                        OP_DUP_LN>;
def DUP_N   : WOpInst<"vdup_n", "ds", "dQdPlQPl", OP_DUP>;
def MOV_N   : WOpInst<"vmov_n", "ds", "dQdPlQPl", OP_DUP>;

////////////////////////////////////////////////////////////////////////////////
def COMBINE : NoTestOpInst<"vcombine", "kdd", "dPl", OP_CONC>;

////////////////////////////////////////////////////////////////////////////////
//Initialize a vector from bit pattern
def CREATE : NoTestOpInst<"vcreate", "dl", "dPl", OP_CAST> {
  let BigEndianSafe = 1;
}

////////////////////////////////////////////////////////////////////////////////

def VMLA_LANEQ   : IOpInst<"vmla_laneq", "dddji",
                           "siUsUifQsQiQUsQUiQf", OP_MLA_LN>;
def VMLS_LANEQ   : IOpInst<"vmls_laneq", "dddji",
                           "siUsUifQsQiQUsQUiQf", OP_MLS_LN>;

def VFMA_LANE    : IInst<"vfma_lane", "dddgi", "fdQfQd">;
def VFMA_LANEQ   : IInst<"vfma_laneq", "dddji", "fdQfQd"> {
  let isLaneQ = 1;
}
def VFMS_LANE    : IOpInst<"vfms_lane", "dddgi", "fdQfQd", OP_FMS_LN>;
def VFMS_LANEQ   : IOpInst<"vfms_laneq", "dddji", "fdQfQd", OP_FMS_LNQ>;

def VMLAL_LANEQ  : SOpInst<"vmlal_laneq", "wwdki", "siUsUi", OP_MLAL_LN>;
def VMLAL_HIGH_LANE   : SOpInst<"vmlal_high_lane", "wwkdi", "siUsUi",
                                OP_MLALHi_LN>;
def VMLAL_HIGH_LANEQ  : SOpInst<"vmlal_high_laneq", "wwkki", "siUsUi",
                                OP_MLALHi_LN>;
def VMLSL_LANEQ  : SOpInst<"vmlsl_laneq", "wwdki", "siUsUi", OP_MLSL_LN>;
def VMLSL_HIGH_LANE   : SOpInst<"vmlsl_high_lane", "wwkdi", "siUsUi",
                                OP_MLSLHi_LN>;
def VMLSL_HIGH_LANEQ  : SOpInst<"vmlsl_high_laneq", "wwkki", "siUsUi",
                                OP_MLSLHi_LN>;

def VQDMLAL_LANEQ  : SOpInst<"vqdmlal_laneq", "wwdki", "si", OP_QDMLAL_LN>;
def VQDMLAL_HIGH_LANE   : SOpInst<"vqdmlal_high_lane", "wwkdi", "si",
                                OP_QDMLALHi_LN>;
def VQDMLAL_HIGH_LANEQ  : SOpInst<"vqdmlal_high_laneq", "wwkki", "si",
                                OP_QDMLALHi_LN>;
def VQDMLSL_LANEQ  : SOpInst<"vqdmlsl_laneq", "wwdki", "si", OP_QDMLSL_LN>;
def VQDMLSL_HIGH_LANE   : SOpInst<"vqdmlsl_high_lane", "wwkdi", "si",
                                OP_QDMLSLHi_LN>;
def VQDMLSL_HIGH_LANEQ  : SOpInst<"vqdmlsl_high_laneq", "wwkki", "si",
                                OP_QDMLSLHi_LN>;

// Newly add double parameter for vmul_lane in aarch64
// Note: d type is handled by SCALAR_VMUL_LANE
def VMUL_LANE_A64 : IOpInst<"vmul_lane", "ddgi", "Qd", OP_MUL_LN>;

// Note: d type is handled by SCALAR_VMUL_LANEQ
def VMUL_LANEQ   : IOpInst<"vmul_laneq", "ddji",
                           "sifUsUiQsQiQUsQUiQfQd", OP_MUL_LN>;
def VMULL_LANEQ  : SOpInst<"vmull_laneq", "wdki", "siUsUi", OP_MULL_LN>;
def VMULL_HIGH_LANE   : SOpInst<"vmull_high_lane", "wkdi", "siUsUi",
                                OP_MULLHi_LN>;
def VMULL_HIGH_LANEQ  : SOpInst<"vmull_high_laneq", "wkki", "siUsUi",
                                OP_MULLHi_LN>;

def VQDMULL_LANEQ  : SOpInst<"vqdmull_laneq", "wdki", "si", OP_QDMULL_LN>;
def VQDMULL_HIGH_LANE   : SOpInst<"vqdmull_high_lane", "wkdi", "si",
                                  OP_QDMULLHi_LN>;
def VQDMULL_HIGH_LANEQ  : SOpInst<"vqdmull_high_laneq", "wkki", "si",
                                  OP_QDMULLHi_LN>;

def VQDMULH_LANEQ  : SOpInst<"vqdmulh_laneq", "ddji", "siQsQi", OP_QDMULH_LN>;
def VQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "ddji", "siQsQi", OP_QRDMULH_LN>;

let ArchGuard = "defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)" in {
def VQRDMLAH_LANEQ : SOpInst<"vqrdmlah_laneq", "dddji", "siQsQi", OP_QRDMLAH_LN>;
def VQRDMLSH_LANEQ : SOpInst<"vqrdmlsh_laneq", "dddji", "siQsQi", OP_QRDMLSH_LN>;
}

// Note: d type implemented by SCALAR_VMULX_LANE
def VMULX_LANE : IOpInst<"vmulx_lane", "ddgi", "fQfQd", OP_MULX_LN>;
// Note: d type is implemented by SCALAR_VMULX_LANEQ
def VMULX_LANEQ : IOpInst<"vmulx_laneq", "ddji", "fQfQd", OP_MULX_LN>;

////////////////////////////////////////////////////////////////////////////////
// Across vectors class
def VADDLV  : SInst<"vaddlv", "rd", "csiUcUsUiQcQsQiQUcQUsQUi">;
def VMAXV   : SInst<"vmaxv", "sd", "csifUcUsUiQcQsQiQUcQUsQUiQfQd">;
def VMINV   : SInst<"vminv", "sd", "csifUcUsUiQcQsQiQUcQUsQUiQfQd">;
def VADDV   : SInst<"vaddv", "sd", "csifUcUsUiQcQsQiQUcQUsQUiQfQdQlQUl">;
def FMAXNMV : SInst<"vmaxnmv", "sd", "fQfQd">;
def FMINNMV : SInst<"vminnmv", "sd", "fQfQd">;
 
////////////////////////////////////////////////////////////////////////////////
// Newly added Vector Extract for f64
def VEXT_A64 : WInst<"vext", "dddi", "dQdPlQPl">;

////////////////////////////////////////////////////////////////////////////////
// Crypto
let ArchGuard = "__ARM_FEATURE_CRYPTO" in {
def AESE : SInst<"vaese", "ddd", "QUc">;
def AESD : SInst<"vaesd", "ddd", "QUc">;
def AESMC : SInst<"vaesmc", "dd", "QUc">;
def AESIMC : SInst<"vaesimc", "dd", "QUc">;

def SHA1H : SInst<"vsha1h", "ss", "Ui">;
def SHA1SU1 : SInst<"vsha1su1", "ddd", "QUi">;
def SHA256SU0 : SInst<"vsha256su0", "ddd", "QUi">;

def SHA1C : SInst<"vsha1c", "ddsd", "QUi">;
def SHA1P : SInst<"vsha1p", "ddsd", "QUi">;
def SHA1M : SInst<"vsha1m", "ddsd", "QUi">;
def SHA1SU0 : SInst<"vsha1su0", "dddd", "QUi">;
def SHA256H : SInst<"vsha256h", "dddd", "QUi">;
def SHA256H2 : SInst<"vsha256h2", "dddd", "QUi">;
def SHA256SU1 : SInst<"vsha256su1", "dddd", "QUi">;
}

////////////////////////////////////////////////////////////////////////////////
// Float -> Int conversions with explicit rounding mode

let ArchGuard = "__ARM_ARCH >= 8" in {
def FCVTNS_S32 : SInst<"vcvtn_s32", "xd", "fQf">;
def FCVTNU_S32 : SInst<"vcvtn_u32", "ud", "fQf">;
def FCVTPS_S32 : SInst<"vcvtp_s32", "xd", "fQf">;
def FCVTPU_S32 : SInst<"vcvtp_u32", "ud", "fQf">;
def FCVTMS_S32 : SInst<"vcvtm_s32", "xd", "fQf">;
def FCVTMU_S32 : SInst<"vcvtm_u32", "ud", "fQf">;
def FCVTAS_S32 : SInst<"vcvta_s32", "xd", "fQf">;
def FCVTAU_S32 : SInst<"vcvta_u32", "ud", "fQf">;
}

let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__)" in {
def FCVTNS_S64 : SInst<"vcvtn_s64", "xd", "dQd">;
def FCVTNU_S64 : SInst<"vcvtn_u64", "ud", "dQd">;
def FCVTPS_S64 : SInst<"vcvtp_s64", "xd", "dQd">;
def FCVTPU_S64 : SInst<"vcvtp_u64", "ud", "dQd">;
def FCVTMS_S64 : SInst<"vcvtm_s64", "xd", "dQd">;
def FCVTMU_S64 : SInst<"vcvtm_u64", "ud", "dQd">;
def FCVTAS_S64 : SInst<"vcvta_s64", "xd", "dQd">;
def FCVTAU_S64 : SInst<"vcvta_u64", "ud", "dQd">;
}

////////////////////////////////////////////////////////////////////////////////
// Round to Integral

let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_DIRECTED_ROUNDING)" in {
def FRINTN_S32 : SInst<"vrndn", "dd", "fQf">;
def FRINTA_S32 : SInst<"vrnda", "dd", "fQf">;
def FRINTP_S32 : SInst<"vrndp", "dd", "fQf">;
def FRINTM_S32 : SInst<"vrndm", "dd", "fQf">;
def FRINTX_S32 : SInst<"vrndx", "dd", "fQf">;
def FRINTZ_S32 : SInst<"vrnd", "dd", "fQf">;
}

let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_DIRECTED_ROUNDING)" in {
def FRINTN_S64 : SInst<"vrndn", "dd", "dQd">;
def FRINTA_S64 : SInst<"vrnda", "dd", "dQd">;
def FRINTP_S64 : SInst<"vrndp", "dd", "dQd">;
def FRINTM_S64 : SInst<"vrndm", "dd", "dQd">;
def FRINTX_S64 : SInst<"vrndx", "dd", "dQd">;
def FRINTZ_S64 : SInst<"vrnd", "dd", "dQd">;
def FRINTI_S64 : SInst<"vrndi", "dd", "fdQfQd">;
}

////////////////////////////////////////////////////////////////////////////////
// MaxNum/MinNum Floating Point

let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_NUMERIC_MAXMIN)" in {
def FMAXNM_S32 : SInst<"vmaxnm", "ddd", "fQf">;
def FMINNM_S32 : SInst<"vminnm", "ddd", "fQf">;
}

let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_NUMERIC_MAXMIN)" in {
def FMAXNM_S64 : SInst<"vmaxnm", "ddd", "dQd">;
def FMINNM_S64 : SInst<"vminnm", "ddd", "dQd">;
}

////////////////////////////////////////////////////////////////////////////////
// Permutation
def VTRN1 : SOpInst<"vtrn1", "ddd",
                    "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_TRN1>;
def VZIP1 : SOpInst<"vzip1", "ddd",
                    "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_ZIP1>;
def VUZP1 : SOpInst<"vuzp1", "ddd",
                    "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_UZP1>;
def VTRN2 : SOpInst<"vtrn2", "ddd",
                    "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_TRN2>;
def VZIP2 : SOpInst<"vzip2", "ddd",
                    "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_ZIP2>;
def VUZP2 : SOpInst<"vuzp2", "ddd",
                    "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_UZP2>;

////////////////////////////////////////////////////////////////////////////////
// Table lookup
let InstName = "vtbl" in {
def VQTBL1_A64 : WInst<"vqtbl1", "djt",  "UccPcQUcQcQPc">;
def VQTBL2_A64 : WInst<"vqtbl2", "dBt",  "UccPcQUcQcQPc">;
def VQTBL3_A64 : WInst<"vqtbl3", "dCt",  "UccPcQUcQcQPc">;
def VQTBL4_A64 : WInst<"vqtbl4", "dDt",  "UccPcQUcQcQPc">;
}
let InstName = "vtbx" in {
def VQTBX1_A64 : WInst<"vqtbx1", "ddjt", "UccPcQUcQcQPc">;
def VQTBX2_A64 : WInst<"vqtbx2", "ddBt", "UccPcQUcQcQPc">;
def VQTBX3_A64 : WInst<"vqtbx3", "ddCt", "UccPcQUcQcQPc">;
def VQTBX4_A64 : WInst<"vqtbx4", "ddDt", "UccPcQUcQcQPc">;
}

////////////////////////////////////////////////////////////////////////////////
// Vector reinterpret cast operations

// NeonEmitter implicitly takes the cartesian product of the type string with
// itself during generation so, unlike all other intrinsics, this one should
// include *all* types, not just additional ones.
def VVREINTERPRET
  : NoTestOpInst<"vreinterpret", "dd",
       "csilUcUsUiUlhfdPcPsPlQcQsQiQlQUcQUsQUiQUlQhQfQdQPcQPsQPlQPk", OP_REINT> {
  let CartesianProductOfTypes = 1;
  let BigEndianSafe = 1;
  let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__)";
}

////////////////////////////////////////////////////////////////////////////////
// Scalar Intrinsics
// Scalar Arithmetic

// Scalar Addition
def SCALAR_ADD : SInst<"vadd", "sss",  "SlSUl">;
// Scalar  Saturating Add
def SCALAR_QADD   : SInst<"vqadd", "sss", "ScSsSiSlSUcSUsSUiSUl">;

// Scalar Subtraction
def SCALAR_SUB : SInst<"vsub", "sss",  "SlSUl">;
// Scalar  Saturating Sub
def SCALAR_QSUB   : SInst<"vqsub", "sss", "ScSsSiSlSUcSUsSUiSUl">;

let InstName = "vmov" in {
def VGET_HIGH_A64 : NoTestOpInst<"vget_high", "dk", "dPl", OP_HI>;
def VGET_LOW_A64  : NoTestOpInst<"vget_low", "dk", "dPl", OP_LO>;
}

////////////////////////////////////////////////////////////////////////////////
// Scalar Shift
// Scalar Shift Left
def SCALAR_SHL: SInst<"vshl", "sss", "SlSUl">;
// Scalar Saturating Shift Left
def SCALAR_QSHL: SInst<"vqshl", "sss", "ScSsSiSlSUcSUsSUiSUl">;
// Scalar Saturating Rounding Shift Left
def SCALAR_QRSHL: SInst<"vqrshl", "sss", "ScSsSiSlSUcSUsSUiSUl">;
// Scalar Shift Rounding Left
def SCALAR_RSHL: SInst<"vrshl", "sss", "SlSUl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Shift (Immediate)
let isScalarShift = 1 in {
// Signed/Unsigned Shift Right (Immediate)
def SCALAR_SSHR_N: SInst<"vshr_n", "ssi", "SlSUl">;
// Signed/Unsigned Rounding Shift Right (Immediate)
def SCALAR_SRSHR_N: SInst<"vrshr_n", "ssi", "SlSUl">;

// Signed/Unsigned Shift Right and Accumulate (Immediate)
def SCALAR_SSRA_N: SInst<"vsra_n", "sssi", "SlSUl">;
// Signed/Unsigned Rounding Shift Right and Accumulate (Immediate)
def SCALAR_SRSRA_N: SInst<"vrsra_n", "sssi", "SlSUl">;

// Shift Left (Immediate)
def SCALAR_SHL_N: SInst<"vshl_n", "ssi", "SlSUl">;
// Signed/Unsigned Saturating Shift Left (Immediate)
def SCALAR_SQSHL_N: SInst<"vqshl_n", "ssi", "ScSsSiSlSUcSUsSUiSUl">;
// Signed Saturating Shift Left Unsigned (Immediate)
def SCALAR_SQSHLU_N: SInst<"vqshlu_n", "ssi", "ScSsSiSl">;

// Shift Right And Insert (Immediate)
def SCALAR_SRI_N: SInst<"vsri_n", "sssi", "SlSUl">;
// Shift Left And Insert (Immediate)
def SCALAR_SLI_N: SInst<"vsli_n", "sssi", "SlSUl">;

let isScalarNarrowShift = 1 in {
  // Signed/Unsigned Saturating Shift Right Narrow (Immediate)
  def SCALAR_SQSHRN_N: SInst<"vqshrn_n", "zsi", "SsSiSlSUsSUiSUl">;
  // Signed/Unsigned Saturating Rounded Shift Right Narrow (Immediate)
  def SCALAR_SQRSHRN_N: SInst<"vqrshrn_n", "zsi", "SsSiSlSUsSUiSUl">;
  // Signed Saturating Shift Right Unsigned Narrow (Immediate)
  def SCALAR_SQSHRUN_N: SInst<"vqshrun_n", "zsi", "SsSiSl">;
  // Signed Saturating Rounded Shift Right Unsigned Narrow (Immediate)
  def SCALAR_SQRSHRUN_N: SInst<"vqrshrun_n", "zsi", "SsSiSl">;
}

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed/Unsigned Fixed-point Convert To Floating-Point (Immediate)
def SCALAR_SCVTF_N_F32: SInst<"vcvt_n_f32", "ysi", "SiSUi">;
def SCALAR_SCVTF_N_F64: SInst<"vcvt_n_f64", "osi", "SlSUl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Convert To Signed/Unsigned Fixed-point (Immediate)
def SCALAR_FCVTZS_N_S32 : SInst<"vcvt_n_s32", "$si", "Sf">;
def SCALAR_FCVTZU_N_U32 : SInst<"vcvt_n_u32", "bsi", "Sf">;
def SCALAR_FCVTZS_N_S64 : SInst<"vcvt_n_s64", "$si", "Sd">;
def SCALAR_FCVTZU_N_U64 : SInst<"vcvt_n_u64", "bsi", "Sd">;
}

////////////////////////////////////////////////////////////////////////////////
// Scalar Reduce Pairwise Addition (Scalar and Floating Point)
def SCALAR_ADDP  : SInst<"vpadd", "sd", "SfSHlSHdSHUl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Reduce Floating Point Pairwise Max/Min
def SCALAR_FMAXP : SInst<"vpmax", "sd", "SfSQd">;

def SCALAR_FMINP : SInst<"vpmin", "sd", "SfSQd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Reduce Floating Point Pairwise maxNum/minNum
def SCALAR_FMAXNMP : SInst<"vpmaxnm", "sd", "SfSQd">;
def SCALAR_FMINNMP : SInst<"vpminnm", "sd", "SfSQd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Integer Saturating Doubling Multiply Half High
def SCALAR_SQDMULH : SInst<"vqdmulh", "sss", "SsSi">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Integer Saturating Rounding Doubling Multiply Half High
def SCALAR_SQRDMULH : SInst<"vqrdmulh", "sss", "SsSi">;

let ArchGuard = "defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)" in {
////////////////////////////////////////////////////////////////////////////////
// Signed Saturating Rounding Doubling Multiply Accumulate Returning High Half
def SCALAR_SQRDMLAH : SOpInst<"vqrdmlah", "ssss", "SsSi", OP_QRDMLAH>;

////////////////////////////////////////////////////////////////////////////////
// Signed Saturating Rounding Doubling Multiply Subtract Returning High Half
def SCALAR_SQRDMLSH : SOpInst<"vqrdmlsh", "ssss", "SsSi", OP_QRDMLSH>;
}

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Multiply Extended
def SCALAR_FMULX : IInst<"vmulx", "sss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Reciprocal Step
def SCALAR_FRECPS : IInst<"vrecps", "sss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Reciprocal Square Root Step
def SCALAR_FRSQRTS : IInst<"vrsqrts", "sss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed Integer Convert To Floating-point
def SCALAR_SCVTFS : SInst<"vcvt_f32", "ys", "Si">;
def SCALAR_SCVTFD : SInst<"vcvt_f64", "os", "Sl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Unsigned Integer Convert To Floating-point
def SCALAR_UCVTFS : SInst<"vcvt_f32", "ys", "SUi">;
def SCALAR_UCVTFD : SInst<"vcvt_f64", "os", "SUl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Converts
def SCALAR_FCVTXN  : IInst<"vcvtx_f32", "ys", "Sd">;
def SCALAR_FCVTNSS : SInst<"vcvtn_s32", "$s", "Sf">;
def SCALAR_FCVTNUS : SInst<"vcvtn_u32", "bs", "Sf">;
def SCALAR_FCVTNSD : SInst<"vcvtn_s64", "$s", "Sd">;
def SCALAR_FCVTNUD : SInst<"vcvtn_u64", "bs", "Sd">;
def SCALAR_FCVTMSS : SInst<"vcvtm_s32", "$s", "Sf">;
def SCALAR_FCVTMUS : SInst<"vcvtm_u32", "bs", "Sf">;
def SCALAR_FCVTMSD : SInst<"vcvtm_s64", "$s", "Sd">;
def SCALAR_FCVTMUD : SInst<"vcvtm_u64", "bs", "Sd">;
def SCALAR_FCVTASS : SInst<"vcvta_s32", "$s", "Sf">;
def SCALAR_FCVTAUS : SInst<"vcvta_u32", "bs", "Sf">;
def SCALAR_FCVTASD : SInst<"vcvta_s64", "$s", "Sd">;
def SCALAR_FCVTAUD : SInst<"vcvta_u64", "bs", "Sd">;
def SCALAR_FCVTPSS : SInst<"vcvtp_s32", "$s", "Sf">;
def SCALAR_FCVTPUS : SInst<"vcvtp_u32", "bs", "Sf">;
def SCALAR_FCVTPSD : SInst<"vcvtp_s64", "$s", "Sd">;
def SCALAR_FCVTPUD : SInst<"vcvtp_u64", "bs", "Sd">;
def SCALAR_FCVTZSS : SInst<"vcvt_s32", "$s", "Sf">;
def SCALAR_FCVTZUS : SInst<"vcvt_u32", "bs", "Sf">;
def SCALAR_FCVTZSD : SInst<"vcvt_s64", "$s", "Sd">;
def SCALAR_FCVTZUD : SInst<"vcvt_u64", "bs", "Sd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Reciprocal Estimate
def SCALAR_FRECPE : IInst<"vrecpe", "ss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Reciprocal Exponent
def SCALAR_FRECPX : IInst<"vrecpx", "ss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Reciprocal Square Root Estimate
def SCALAR_FRSQRTE : IInst<"vrsqrte", "ss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Integer Comparison
def SCALAR_CMEQ : SInst<"vceq", "sss", "SlSUl">;
def SCALAR_CMEQZ : SInst<"vceqz", "ss", "SlSUl">;
def SCALAR_CMGE : SInst<"vcge", "sss", "Sl">;
def SCALAR_CMGEZ : SInst<"vcgez", "ss", "Sl">;
def SCALAR_CMHS : SInst<"vcge", "sss", "SUl">;
def SCALAR_CMLE : SInst<"vcle", "sss", "SlSUl">;
def SCALAR_CMLEZ : SInst<"vclez", "ss", "Sl">;
def SCALAR_CMLT : SInst<"vclt", "sss", "SlSUl">;
def SCALAR_CMLTZ : SInst<"vcltz", "ss", "Sl">;
def SCALAR_CMGT : SInst<"vcgt", "sss", "Sl">;
def SCALAR_CMGTZ : SInst<"vcgtz", "ss", "Sl">;
def SCALAR_CMHI : SInst<"vcgt", "sss", "SUl">;
def SCALAR_CMTST : SInst<"vtst", "sss", "SlSUl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Comparison
def SCALAR_FCMEQ : IInst<"vceq", "bss", "SfSd">;
def SCALAR_FCMEQZ : IInst<"vceqz", "bs", "SfSd">;
def SCALAR_FCMGE : IInst<"vcge", "bss", "SfSd">;
def SCALAR_FCMGEZ : IInst<"vcgez", "bs", "SfSd">;
def SCALAR_FCMGT : IInst<"vcgt", "bss", "SfSd">;
def SCALAR_FCMGTZ : IInst<"vcgtz", "bs", "SfSd">;
def SCALAR_FCMLE : IInst<"vcle", "bss", "SfSd">;
def SCALAR_FCMLEZ : IInst<"vclez", "bs", "SfSd">;
def SCALAR_FCMLT : IInst<"vclt", "bss", "SfSd">;
def SCALAR_FCMLTZ : IInst<"vcltz", "bs", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Absolute Compare Mask Greater Than Or Equal
def SCALAR_FACGE : IInst<"vcage", "bss", "SfSd">;
def SCALAR_FACLE : IInst<"vcale", "bss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Floating-point Absolute Compare Mask Greater Than
def SCALAR_FACGT : IInst<"vcagt", "bss", "SfSd">;
def SCALAR_FACLT : IInst<"vcalt", "bss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Absolute Value
def SCALAR_ABS : SInst<"vabs", "ss", "Sl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Absolute Difference
def SCALAR_ABD : IInst<"vabd", "sss", "SfSd">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed Saturating Absolute Value
def SCALAR_SQABS : SInst<"vqabs", "ss", "ScSsSiSl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Negate
def SCALAR_NEG : SInst<"vneg", "ss", "Sl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed Saturating Negate
def SCALAR_SQNEG : SInst<"vqneg", "ss", "ScSsSiSl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed Saturating Accumulated of Unsigned Value
def SCALAR_SUQADD : SInst<"vuqadd", "sss", "ScSsSiSl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Unsigned Saturating Accumulated of Signed Value
def SCALAR_USQADD : SInst<"vsqadd", "sss", "SUcSUsSUiSUl">;

////////////////////////////////////////////////////////////////////////////////
// Signed Saturating Doubling Multiply-Add Long
def SCALAR_SQDMLAL : SInst<"vqdmlal", "rrss", "SsSi">;

////////////////////////////////////////////////////////////////////////////////
// Signed Saturating Doubling Multiply-Subtract Long
def SCALAR_SQDMLSL : SInst<"vqdmlsl", "rrss", "SsSi">;

////////////////////////////////////////////////////////////////////////////////
// Signed Saturating Doubling Multiply Long
def SCALAR_SQDMULL : SInst<"vqdmull", "rss", "SsSi">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed Saturating Extract Unsigned Narrow
def SCALAR_SQXTUN : SInst<"vqmovun", "zs", "SsSiSl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Signed Saturating Extract Narrow
def SCALAR_SQXTN : SInst<"vqmovn", "zs", "SsSiSl">;

////////////////////////////////////////////////////////////////////////////////
// Scalar Unsigned Saturating Extract Narrow
def SCALAR_UQXTN : SInst<"vqmovn", "zs", "SUsSUiSUl">;

// Scalar Floating Point  multiply (scalar, by element)
def SCALAR_FMUL_LANE : IOpInst<"vmul_lane", "ssdi", "SfSd", OP_SCALAR_MUL_LN>;
def SCALAR_FMUL_LANEQ : IOpInst<"vmul_laneq", "ssji", "SfSd", OP_SCALAR_MUL_LN>;

// Scalar Floating Point  multiply extended (scalar, by element)
def SCALAR_FMULX_LANE : IOpInst<"vmulx_lane", "ssdi", "SfSd", OP_SCALAR_MULX_LN>;
def SCALAR_FMULX_LANEQ : IOpInst<"vmulx_laneq", "ssji", "SfSd", OP_SCALAR_MULX_LN>;

def SCALAR_VMUL_N : IInst<"vmul_n", "dds", "d">;

// VMUL_LANE_A64 d type implemented using scalar mul lane
def SCALAR_VMUL_LANE : IInst<"vmul_lane", "ddgi", "d">;

// VMUL_LANEQ d type implemented using scalar mul lane
def SCALAR_VMUL_LANEQ   : IInst<"vmul_laneq", "ddji", "d"> {
  let isLaneQ = 1;
}

// VMULX_LANE d type implemented using scalar vmulx_lane
def SCALAR_VMULX_LANE : IOpInst<"vmulx_lane", "ddgi", "d", OP_SCALAR_VMULX_LN>;

// VMULX_LANEQ d type implemented using scalar vmulx_laneq
def SCALAR_VMULX_LANEQ : IOpInst<"vmulx_laneq", "ddji", "d", OP_SCALAR_VMULX_LNQ>;

// Scalar Floating Point fused multiply-add (scalar, by element)
def SCALAR_FMLA_LANE : IInst<"vfma_lane", "sssdi", "SfSd">;
def SCALAR_FMLA_LANEQ : IInst<"vfma_laneq", "sssji", "SfSd">;

// Scalar Floating Point fused multiply-subtract (scalar, by element)
def SCALAR_FMLS_LANE : IOpInst<"vfms_lane", "sssdi", "SfSd", OP_FMS_LN>;
def SCALAR_FMLS_LANEQ : IOpInst<"vfms_laneq", "sssji", "SfSd", OP_FMS_LNQ>;

// Signed Saturating Doubling Multiply Long (scalar by element)
def SCALAR_SQDMULL_LANE : SOpInst<"vqdmull_lane", "rsdi", "SsSi", OP_SCALAR_QDMULL_LN>;
def SCALAR_SQDMULL_LANEQ : SOpInst<"vqdmull_laneq", "rsji", "SsSi", OP_SCALAR_QDMULL_LN>;

// Signed Saturating Doubling Multiply-Add Long (scalar by element)
def SCALAR_SQDMLAL_LANE : SInst<"vqdmlal_lane", "rrsdi", "SsSi">;
def SCALAR_SQDMLAL_LANEQ : SInst<"vqdmlal_laneq", "rrsji", "SsSi">;

// Signed Saturating Doubling Multiply-Subtract Long (scalar by element)
def SCALAR_SQDMLS_LANE : SInst<"vqdmlsl_lane", "rrsdi", "SsSi">;
def SCALAR_SQDMLS_LANEQ : SInst<"vqdmlsl_laneq", "rrsji", "SsSi">;

// Scalar Integer Saturating Doubling Multiply Half High (scalar by element)
def SCALAR_SQDMULH_LANE : SOpInst<"vqdmulh_lane", "ssdi", "SsSi", OP_SCALAR_QDMULH_LN>;
def SCALAR_SQDMULH_LANEQ : SOpInst<"vqdmulh_laneq", "ssji", "SsSi", OP_SCALAR_QDMULH_LN>;

// Scalar Integer Saturating Rounding Doubling Multiply Half High
def SCALAR_SQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "ssdi", "SsSi", OP_SCALAR_QRDMULH_LN>;
def SCALAR_SQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "ssji", "SsSi", OP_SCALAR_QRDMULH_LN>;

let ArchGuard = "defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)" in {
// Signed Saturating Rounding Doubling Multiply Accumulate Returning High Half
def SCALAR_SQRDMLAH_LANE : SOpInst<"vqrdmlah_lane", "sssdi", "SsSi", OP_SCALAR_QRDMLAH_LN>;
def SCALAR_SQRDMLAH_LANEQ : SOpInst<"vqrdmlah_laneq", "sssji", "SsSi", OP_SCALAR_QRDMLAH_LN>;

// Signed Saturating Rounding Doubling Multiply Subtract Returning High Half
def SCALAR_SQRDMLSH_LANE : SOpInst<"vqrdmlsh_lane", "sssdi", "SsSi", OP_SCALAR_QRDMLSH_LN>;
def SCALAR_SQRDMLSH_LANEQ : SOpInst<"vqrdmlsh_laneq", "sssji", "SsSi", OP_SCALAR_QRDMLSH_LN>;
}

def SCALAR_VDUP_LANE : IInst<"vdup_lane", "sdi", "ScSsSiSlSfSdSUcSUsSUiSUlSPcSPs">;
def SCALAR_VDUP_LANEQ : IInst<"vdup_laneq", "sji", "ScSsSiSlSfSdSUcSUsSUiSUlSPcSPs">;
}

// ARMv8.2-A FP16 intrinsics.
let ArchGuard = "defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(__aarch64__)" in {

  // ARMv8.2-A FP16 one-operand vector intrinsics.

  // Comparison
  def CMEQH    : SInst<"vceqz", "ud", "hQh">;
  def CMGEH    : SInst<"vcgez", "ud", "hQh">;
  def CMGTH    : SInst<"vcgtz", "ud", "hQh">;
  def CMLEH    : SInst<"vclez", "ud", "hQh">;
  def CMLTH    : SInst<"vcltz", "ud", "hQh">;

  // Vector conversion
  def VCVT_F16     : SInst<"vcvt_f16", "Hd",  "sUsQsQUs">;
  def VCVT_S16     : SInst<"vcvt_s16", "xd",  "hQh">;
  def VCVT_U16     : SInst<"vcvt_u16", "ud",  "hQh">;
  def VCVTA_S16    : SInst<"vcvta_s16", "xd", "hQh">;
  def VCVTA_U16    : SInst<"vcvta_u16", "ud", "hQh">;
  def VCVTM_S16    : SInst<"vcvtm_s16", "xd", "hQh">;
  def VCVTM_U16    : SInst<"vcvtm_u16", "ud", "hQh">;
  def VCVTN_S16    : SInst<"vcvtn_s16", "xd", "hQh">;
  def VCVTN_U16    : SInst<"vcvtn_u16", "ud", "hQh">;
  def VCVTP_S16    : SInst<"vcvtp_s16", "xd", "hQh">;
  def VCVTP_U16    : SInst<"vcvtp_u16", "ud", "hQh">;

  // Vector rounding
  def FRINTZH      : SInst<"vrnd",  "dd", "hQh">;
  def FRINTNH      : SInst<"vrndn", "dd", "hQh">;
  def FRINTAH      : SInst<"vrnda", "dd", "hQh">;
  def FRINTPH      : SInst<"vrndp", "dd", "hQh">;
  def FRINTMH      : SInst<"vrndm", "dd", "hQh">;
  def FRINTXH      : SInst<"vrndx", "dd", "hQh">;
  def FRINTIH      : SInst<"vrndi", "dd", "hQh">;

  // Misc.
  def VABSH        : SInst<"vabs", "dd", "hQh">;
  def VNEGH        : SOpInst<"vneg", "dd", "hQh", OP_NEG>;
  def VRECPEH      : SInst<"vrecpe", "dd", "hQh">;
  def FRSQRTEH     : SInst<"vrsqrte", "dd", "hQh">;
  def FSQRTH       : SInst<"vsqrt", "dd", "hQh">;

  // ARMv8.2-A FP16 two-operands vector intrinsics.

  // Misc.
  def VADDH        : SOpInst<"vadd", "ddd", "hQh", OP_ADD>;
  def VABDH        : SInst<"vabd", "ddd",  "hQh">;
  def VSUBH         : SOpInst<"vsub", "ddd", "hQh", OP_SUB>;

  // Comparison
  let InstName = "vacge" in {
	  def VCAGEH     : SInst<"vcage", "udd", "hQh">;
	  def VCALEH     : SInst<"vcale", "udd", "hQh">;
  }
  let InstName = "vacgt" in {
    def VCAGTH     : SInst<"vcagt", "udd", "hQh">;
	  def VCALTH     : SInst<"vcalt", "udd", "hQh">;
  }
  def VCEQH        : SOpInst<"vceq", "udd", "hQh", OP_EQ>;
  def VCGEH        : SOpInst<"vcge", "udd", "hQh", OP_GE>;
  def VCGTH        : SOpInst<"vcgt", "udd", "hQh", OP_GT>;
  let InstName = "vcge" in
    def VCLEH      : SOpInst<"vcle", "udd", "hQh", OP_LE>;
  let InstName = "vcgt" in
    def VCLTH      : SOpInst<"vclt", "udd", "hQh", OP_LT>;

  // Vector conversion
  let isVCVT_N = 1 in {
    def VCVT_N_F16 : SInst<"vcvt_n_f16", "Hdi", "sUsQsQUs">;
    def VCVT_N_S16 : SInst<"vcvt_n_s16", "xdi", "hQh">;
    def VCVT_N_U16 : SInst<"vcvt_n_u16", "udi", "hQh">;
  }

  // Max/Min
  def VMAXH         : SInst<"vmax", "ddd", "hQh">;
  def VMINH         : SInst<"vmin", "ddd", "hQh">;
  def FMAXNMH       : SInst<"vmaxnm", "ddd", "hQh">;
  def FMINNMH       : SInst<"vminnm", "ddd", "hQh">;

  // Multiplication/Division
  def VMULH         : SOpInst<"vmul", "ddd", "hQh", OP_MUL>;
  def MULXH         : SInst<"vmulx", "ddd", "hQh">;
  def FDIVH         : IOpInst<"vdiv", "ddd",  "hQh", OP_DIV>;

  // Pairwise addition
  def VPADDH        : SInst<"vpadd", "ddd", "hQh">;

  // Pairwise Max/Min
  def VPMAXH        : SInst<"vpmax", "ddd", "hQh">;
  def VPMINH        : SInst<"vpmin", "ddd", "hQh">;
  // Pairwise MaxNum/MinNum
  def FMAXNMPH      : SInst<"vpmaxnm", "ddd", "hQh">;
  def FMINNMPH      : SInst<"vpminnm", "ddd", "hQh">;

  // Reciprocal/Sqrt
  def VRECPSH       : SInst<"vrecps", "ddd", "hQh">;
  def VRSQRTSH      : SInst<"vrsqrts", "ddd", "hQh">;

  // ARMv8.2-A FP16 three-operands vector intrinsics.

  // Vector fused multiply-add operations
  def VFMAH        : SInst<"vfma", "dddd", "hQh">;
  def VFMSH        : SOpInst<"vfms", "dddd", "hQh", OP_FMLS>;

  // ARMv8.2-A FP16 lane vector intrinsics.

  // FMA lane
  def VFMA_LANEH   : IInst<"vfma_lane", "dddgi", "hQh">;
  def VFMA_LANEQH  : IInst<"vfma_laneq", "dddji", "hQh">;

  // FMA lane with scalar argument
  def FMLA_NH      : SOpInst<"vfma_n", "ddds", "hQh", OP_FMLA_N>;
  // Scalar floating point fused multiply-add (scalar, by element)
  def SCALAR_FMLA_LANEH  : IInst<"vfma_lane", "sssdi", "Sh">;
  def SCALAR_FMLA_LANEQH : IInst<"vfma_laneq", "sssji", "Sh">;

  // FMS lane
  def VFMS_LANEH   : IOpInst<"vfms_lane", "dddgi", "hQh", OP_FMS_LN>;
  def VFMS_LANEQH  : IOpInst<"vfms_laneq", "dddji", "hQh", OP_FMS_LNQ>;
  // FMS lane with scalar argument
  def FMLS_NH      : SOpInst<"vfms_n", "ddds", "hQh", OP_FMLS_N>;
  // Scalar floating foint fused multiply-subtract (scalar, by element)
  def SCALAR_FMLS_LANEH  : IOpInst<"vfms_lane", "sssdi", "Sh", OP_FMS_LN>;
  def SCALAR_FMLS_LANEQH : IOpInst<"vfms_laneq", "sssji", "Sh", OP_FMS_LNQ>;

  // Mul lane
  def VMUL_LANEH    : IOpInst<"vmul_lane", "ddgi", "hQh", OP_MUL_LN>;
  def VMUL_LANEQH   : IOpInst<"vmul_laneq", "ddji", "hQh", OP_MUL_LN>;
  def VMUL_NH       : IOpInst<"vmul_n", "dds", "hQh", OP_MUL_N>;
  // Scalar floating point  multiply (scalar, by element)
  def SCALAR_FMUL_LANEH  : IOpInst<"vmul_lane", "ssdi", "Sh", OP_SCALAR_MUL_LN>;
  def SCALAR_FMUL_LANEQH : IOpInst<"vmul_laneq", "ssji", "Sh", OP_SCALAR_MUL_LN>;

  // Mulx lane
  def VMULX_LANEH   : IOpInst<"vmulx_lane", "ddgi", "hQh", OP_MULX_LN>;
  def VMULX_LANEQH  : IOpInst<"vmulx_laneq", "ddji", "hQh", OP_MULX_LN>;
  def VMULX_NH      : IOpInst<"vmulx_n", "dds", "hQh", OP_MULX_N>;
  // TODO: Scalar floating point multiply extended (scalar, by element)
  // Below ones are commented out because they need vmulx_f16(float16_t, float16_t)
  // which will be implemented later with fp16 scalar intrinsic (arm_fp16.h)
  //def SCALAR_FMULX_LANEH : IOpInst<"vmulx_lane", "ssdi", "Sh", OP_SCALAR_MUL_LN>;
  //def SCALAR_FMULX_LANEQH : IOpInst<"vmulx_laneq", "ssji", "Sh", OP_SCALAR_MUL_LN>;

  // ARMv8.2-A FP16 reduction vector intrinsics.
  def VMAXVH   : SInst<"vmaxv", "sd", "hQh">;
  def VMINVH   : SInst<"vminv", "sd", "hQh">;
  def FMAXNMVH : SInst<"vmaxnmv", "sd", "hQh">;
  def FMINNMVH : SInst<"vminnmv", "sd", "hQh">;

  // Data processing intrinsics - section 5

  // Logical operations
  let isHiddenLInst = 1 in
  def VBSLH    : SInst<"vbsl", "dudd", "hQh">;

  // Transposition operations
  def VZIPH    : WInst<"vzip", "2dd", "hQh">;
  def VUZPH    : WInst<"vuzp", "2dd", "hQh">;
  def VTRNH    : WInst<"vtrn", "2dd", "hQh">;

  // Set all lanes to same value.
  /* Already implemented prior to ARMv8.2-A.
  def VMOV_NH  : WOpInst<"vmov_n", "ds", "hQh", OP_DUP>;
  def VDUP_NH  : WOpInst<"vdup_n", "ds", "hQh", OP_DUP>;
  def VDUP_LANE1H : WOpInst<"vdup_lane", "dgi", "hQh", OP_DUP_LN>;*/

  // Vector Extract
  def VEXTH      : WInst<"vext", "dddi", "hQh">;

  // Reverse vector elements
  def VREV64H    : WOpInst<"vrev64", "dd", "hQh", OP_REV64>;

  // Permutation
  def VTRN1H     : SOpInst<"vtrn1", "ddd", "hQh", OP_TRN1>;
  def VZIP1H     : SOpInst<"vzip1", "ddd", "hQh", OP_ZIP1>;
  def VUZP1H     : SOpInst<"vuzp1", "ddd", "hQh", OP_UZP1>;
  def VTRN2H     : SOpInst<"vtrn2", "ddd", "hQh", OP_TRN2>;
  def VZIP2H     : SOpInst<"vzip2", "ddd", "hQh", OP_ZIP2>;
  def VUZP2H     : SOpInst<"vuzp2", "ddd", "hQh", OP_UZP2>;

  def SCALAR_VDUP_LANEH  : IInst<"vdup_lane", "sdi", "Sh">;
  def SCALAR_VDUP_LANEQH : IInst<"vdup_laneq", "sji", "Sh">;
}