[AARCH64][ACLE][NEON] Implement vcvt*_s64_f64 and vcvt*_u64_f64 NEON intrinsics.

[official-gcc.git] / gcc / config / aarch64 / arm_neon.h

/* ARM NEON intrinsics include file.

   Copyright (C) 2011-2016 Free Software Foundation, Inc.
   Contributed by ARM Ltd.

   This file is part of GCC.

   GCC is free software; you can redistribute it and/or modify it
   under the terms of the GNU General Public License as published
   by the Free Software Foundation; either version 3, or (at your
   option) any later version.

   GCC is distributed in the hope that it will be useful, but WITHOUT
   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
   or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public
   License for more details.

   Under Section 7 of GPL version 3, you are granted additional
   permissions described in the GCC Runtime Library Exception, version
   3.1, as published by the Free Software Foundation.

   You should have received a copy of the GNU General Public License and
   a copy of the GCC Runtime Library Exception along with this program;
   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
   <http://www.gnu.org/licenses/>.  */

#ifndef _AARCH64_NEON_H_
#define _AARCH64_NEON_H_

#pragma GCC push_options
#pragma GCC target ("+nothing+simd")

#include <stdint.h>

#define __AARCH64_UINT64_C(__C) ((uint64_t) __C)
#define __AARCH64_INT64_C(__C) ((int64_t) __C)

typedef __Int8x8_t int8x8_t;
typedef __Int16x4_t int16x4_t;
typedef __Int32x2_t int32x2_t;
typedef __Int64x1_t int64x1_t;
typedef __Float16x4_t float16x4_t;
typedef __Float32x2_t float32x2_t;
typedef __Poly8x8_t poly8x8_t;
typedef __Poly16x4_t poly16x4_t;
typedef __Uint8x8_t uint8x8_t;
typedef __Uint16x4_t uint16x4_t;
typedef __Uint32x2_t uint32x2_t;
typedef __Float64x1_t float64x1_t;
typedef __Uint64x1_t uint64x1_t;
typedef __Int8x16_t int8x16_t;
typedef __Int16x8_t int16x8_t;
typedef __Int32x4_t int32x4_t;
typedef __Int64x2_t int64x2_t;
typedef __Float16x8_t float16x8_t;
typedef __Float32x4_t float32x4_t;
typedef __Float64x2_t float64x2_t;
typedef __Poly8x16_t poly8x16_t;
typedef __Poly16x8_t poly16x8_t;
typedef __Poly64x2_t poly64x2_t;
typedef __Uint8x16_t uint8x16_t;
typedef __Uint16x8_t uint16x8_t;
typedef __Uint32x4_t uint32x4_t;
typedef __Uint64x2_t uint64x2_t;

typedef __Poly8_t poly8_t;
typedef __Poly16_t poly16_t;
typedef __Poly64_t poly64_t;
typedef __Poly128_t poly128_t;

typedef __fp16 float16_t;
typedef float float32_t;
typedef double float64_t;

typedef struct int8x8x2_t
{
  int8x8_t val[2];
} int8x8x2_t;

typedef struct int8x16x2_t
{
  int8x16_t val[2];
} int8x16x2_t;

typedef struct int16x4x2_t
{
  int16x4_t val[2];
} int16x4x2_t;

typedef struct int16x8x2_t
{
  int16x8_t val[2];
} int16x8x2_t;

typedef struct int32x2x2_t
{
  int32x2_t val[2];
} int32x2x2_t;

typedef struct int32x4x2_t
{
  int32x4_t val[2];
} int32x4x2_t;

typedef struct int64x1x2_t
{
  int64x1_t val[2];
} int64x1x2_t;

typedef struct int64x2x2_t
{
  int64x2_t val[2];
} int64x2x2_t;

typedef struct uint8x8x2_t
{
  uint8x8_t val[2];
} uint8x8x2_t;

typedef struct uint8x16x2_t
{
  uint8x16_t val[2];
} uint8x16x2_t;

typedef struct uint16x4x2_t
{
  uint16x4_t val[2];
} uint16x4x2_t;

typedef struct uint16x8x2_t
{
  uint16x8_t val[2];
} uint16x8x2_t;

typedef struct uint32x2x2_t
{
  uint32x2_t val[2];
} uint32x2x2_t;

typedef struct uint32x4x2_t
{
  uint32x4_t val[2];
} uint32x4x2_t;

typedef struct uint64x1x2_t
{
  uint64x1_t val[2];
} uint64x1x2_t;

typedef struct uint64x2x2_t
{
  uint64x2_t val[2];
} uint64x2x2_t;

typedef struct float16x4x2_t
{
  float16x4_t val[2];
} float16x4x2_t;

typedef struct float16x8x2_t
{
  float16x8_t val[2];
} float16x8x2_t;

typedef struct float32x2x2_t
{
  float32x2_t val[2];
} float32x2x2_t;

typedef struct float32x4x2_t
{
  float32x4_t val[2];
} float32x4x2_t;

typedef struct float64x2x2_t
{
  float64x2_t val[2];
} float64x2x2_t;

typedef struct float64x1x2_t
{
  float64x1_t val[2];
} float64x1x2_t;

typedef struct poly8x8x2_t
{
  poly8x8_t val[2];
} poly8x8x2_t;

typedef struct poly8x16x2_t
{
  poly8x16_t val[2];
} poly8x16x2_t;

typedef struct poly16x4x2_t
{
  poly16x4_t val[2];
} poly16x4x2_t;

typedef struct poly16x8x2_t
{
  poly16x8_t val[2];
} poly16x8x2_t;

typedef struct int8x8x3_t
{
  int8x8_t val[3];
} int8x8x3_t;

typedef struct int8x16x3_t
{
  int8x16_t val[3];
} int8x16x3_t;

typedef struct int16x4x3_t
{
  int16x4_t val[3];
} int16x4x3_t;

typedef struct int16x8x3_t
{
  int16x8_t val[3];
} int16x8x3_t;

typedef struct int32x2x3_t
{
  int32x2_t val[3];
} int32x2x3_t;

typedef struct int32x4x3_t
{
  int32x4_t val[3];
} int32x4x3_t;

typedef struct int64x1x3_t
{
  int64x1_t val[3];
} int64x1x3_t;

typedef struct int64x2x3_t
{
  int64x2_t val[3];
} int64x2x3_t;

typedef struct uint8x8x3_t
{
  uint8x8_t val[3];
} uint8x8x3_t;

typedef struct uint8x16x3_t
{
  uint8x16_t val[3];
} uint8x16x3_t;

typedef struct uint16x4x3_t
{
  uint16x4_t val[3];
} uint16x4x3_t;

typedef struct uint16x8x3_t
{
  uint16x8_t val[3];
} uint16x8x3_t;

typedef struct uint32x2x3_t
{
  uint32x2_t val[3];
} uint32x2x3_t;

typedef struct uint32x4x3_t
{
  uint32x4_t val[3];
} uint32x4x3_t;

typedef struct uint64x1x3_t
{
  uint64x1_t val[3];
} uint64x1x3_t;

typedef struct uint64x2x3_t
{
  uint64x2_t val[3];
} uint64x2x3_t;

typedef struct float16x4x3_t
{
  float16x4_t val[3];
} float16x4x3_t;

typedef struct float16x8x3_t
{
  float16x8_t val[3];
} float16x8x3_t;

typedef struct float32x2x3_t
{
  float32x2_t val[3];
} float32x2x3_t;

typedef struct float32x4x3_t
{
  float32x4_t val[3];
} float32x4x3_t;

typedef struct float64x2x3_t
{
  float64x2_t val[3];
} float64x2x3_t;

typedef struct float64x1x3_t
{
  float64x1_t val[3];
} float64x1x3_t;

typedef struct poly8x8x3_t
{
  poly8x8_t val[3];
} poly8x8x3_t;

typedef struct poly8x16x3_t
{
  poly8x16_t val[3];
} poly8x16x3_t;

typedef struct poly16x4x3_t
{
  poly16x4_t val[3];
} poly16x4x3_t;

typedef struct poly16x8x3_t
{
  poly16x8_t val[3];
} poly16x8x3_t;

typedef struct int8x8x4_t
{
  int8x8_t val[4];
} int8x8x4_t;

typedef struct int8x16x4_t
{
  int8x16_t val[4];
} int8x16x4_t;

typedef struct int16x4x4_t
{
  int16x4_t val[4];
} int16x4x4_t;

typedef struct int16x8x4_t
{
  int16x8_t val[4];
} int16x8x4_t;

typedef struct int32x2x4_t
{
  int32x2_t val[4];
} int32x2x4_t;

typedef struct int32x4x4_t
{
  int32x4_t val[4];
} int32x4x4_t;

typedef struct int64x1x4_t
{
  int64x1_t val[4];
} int64x1x4_t;

typedef struct int64x2x4_t
{
  int64x2_t val[4];
} int64x2x4_t;

typedef struct uint8x8x4_t
{
  uint8x8_t val[4];
} uint8x8x4_t;

typedef struct uint8x16x4_t
{
  uint8x16_t val[4];
} uint8x16x4_t;

typedef struct uint16x4x4_t
{
  uint16x4_t val[4];
} uint16x4x4_t;

typedef struct uint16x8x4_t
{
  uint16x8_t val[4];
} uint16x8x4_t;

typedef struct uint32x2x4_t
{
  uint32x2_t val[4];
} uint32x2x4_t;

typedef struct uint32x4x4_t
{
  uint32x4_t val[4];
} uint32x4x4_t;

typedef struct uint64x1x4_t
{
  uint64x1_t val[4];
} uint64x1x4_t;

typedef struct uint64x2x4_t
{
  uint64x2_t val[4];
} uint64x2x4_t;

typedef struct float16x4x4_t
{
  float16x4_t val[4];
} float16x4x4_t;

typedef struct float16x8x4_t
{
  float16x8_t val[4];
} float16x8x4_t;

typedef struct float32x2x4_t
{
  float32x2_t val[4];
} float32x2x4_t;

typedef struct float32x4x4_t
{
  float32x4_t val[4];
} float32x4x4_t;

typedef struct float64x2x4_t
{
  float64x2_t val[4];
} float64x2x4_t;

typedef struct float64x1x4_t
{
  float64x1_t val[4];
} float64x1x4_t;

typedef struct poly8x8x4_t
{
  poly8x8_t val[4];
} poly8x8x4_t;

typedef struct poly8x16x4_t
{
  poly8x16_t val[4];
} poly8x16x4_t;

typedef struct poly16x4x4_t
{
  poly16x4_t val[4];
} poly16x4x4_t;

typedef struct poly16x8x4_t
{
  poly16x8_t val[4];
} poly16x8x4_t;

/* __aarch64_vdup_lane internal macros.  */
#define __aarch64_vdup_lane_any(__size, __q, __a, __b) \
  vdup##__q##_n_##__size (__aarch64_vget_lane_any (__a, __b))

#define __aarch64_vdup_lane_f32(__a, __b) \
   __aarch64_vdup_lane_any (f32, , __a, __b)
#define __aarch64_vdup_lane_f64(__a, __b) \
   __aarch64_vdup_lane_any (f64, , __a, __b)
#define __aarch64_vdup_lane_p8(__a, __b) \
   __aarch64_vdup_lane_any (p8, , __a, __b)
#define __aarch64_vdup_lane_p16(__a, __b) \
   __aarch64_vdup_lane_any (p16, , __a, __b)
#define __aarch64_vdup_lane_s8(__a, __b) \
   __aarch64_vdup_lane_any (s8, , __a, __b)
#define __aarch64_vdup_lane_s16(__a, __b) \
   __aarch64_vdup_lane_any (s16, , __a, __b)
#define __aarch64_vdup_lane_s32(__a, __b) \
   __aarch64_vdup_lane_any (s32, , __a, __b)
#define __aarch64_vdup_lane_s64(__a, __b) \
  __aarch64_vdup_lane_any (s64, , __a, __b)
#define __aarch64_vdup_lane_u8(__a, __b) \
   __aarch64_vdup_lane_any (u8, , __a, __b)
#define __aarch64_vdup_lane_u16(__a, __b) \
   __aarch64_vdup_lane_any (u16, , __a, __b)
#define __aarch64_vdup_lane_u32(__a, __b) \
   __aarch64_vdup_lane_any (u32, , __a, __b)
#define __aarch64_vdup_lane_u64(__a, __b) \
   __aarch64_vdup_lane_any (u64, , __a, __b)

/* __aarch64_vdup_laneq internal macros.  */
#define __aarch64_vdup_laneq_f32(__a, __b) \
   __aarch64_vdup_lane_any (f32, , __a, __b)
#define __aarch64_vdup_laneq_f64(__a, __b) \
   __aarch64_vdup_lane_any (f64, , __a, __b)
#define __aarch64_vdup_laneq_p8(__a, __b) \
   __aarch64_vdup_lane_any (p8, , __a, __b)
#define __aarch64_vdup_laneq_p16(__a, __b) \
   __aarch64_vdup_lane_any (p16, , __a, __b)
#define __aarch64_vdup_laneq_s8(__a, __b) \
   __aarch64_vdup_lane_any (s8, , __a, __b)
#define __aarch64_vdup_laneq_s16(__a, __b) \
   __aarch64_vdup_lane_any (s16, , __a, __b)
#define __aarch64_vdup_laneq_s32(__a, __b) \
   __aarch64_vdup_lane_any (s32, , __a, __b)
#define __aarch64_vdup_laneq_s64(__a, __b) \
   __aarch64_vdup_lane_any (s64, , __a, __b)
#define __aarch64_vdup_laneq_u8(__a, __b) \
   __aarch64_vdup_lane_any (u8, , __a, __b)
#define __aarch64_vdup_laneq_u16(__a, __b) \
   __aarch64_vdup_lane_any (u16, , __a, __b)
#define __aarch64_vdup_laneq_u32(__a, __b) \
   __aarch64_vdup_lane_any (u32, , __a, __b)
#define __aarch64_vdup_laneq_u64(__a, __b) \
   __aarch64_vdup_lane_any (u64, , __a, __b)

/* __aarch64_vdupq_lane internal macros.  */
#define __aarch64_vdupq_lane_f32(__a, __b) \
   __aarch64_vdup_lane_any (f32, q, __a, __b)
#define __aarch64_vdupq_lane_f64(__a, __b) \
   __aarch64_vdup_lane_any (f64, q, __a, __b)
#define __aarch64_vdupq_lane_p8(__a, __b) \
   __aarch64_vdup_lane_any (p8, q, __a, __b)
#define __aarch64_vdupq_lane_p16(__a, __b) \
   __aarch64_vdup_lane_any (p16, q, __a, __b)
#define __aarch64_vdupq_lane_s8(__a, __b) \
   __aarch64_vdup_lane_any (s8, q, __a, __b)
#define __aarch64_vdupq_lane_s16(__a, __b) \
   __aarch64_vdup_lane_any (s16, q, __a, __b)
#define __aarch64_vdupq_lane_s32(__a, __b) \
   __aarch64_vdup_lane_any (s32, q, __a, __b)
#define __aarch64_vdupq_lane_s64(__a, __b) \
   __aarch64_vdup_lane_any (s64, q, __a, __b)
#define __aarch64_vdupq_lane_u8(__a, __b) \
   __aarch64_vdup_lane_any (u8, q, __a, __b)
#define __aarch64_vdupq_lane_u16(__a, __b) \
   __aarch64_vdup_lane_any (u16, q, __a, __b)
#define __aarch64_vdupq_lane_u32(__a, __b) \
   __aarch64_vdup_lane_any (u32, q, __a, __b)
#define __aarch64_vdupq_lane_u64(__a, __b) \
   __aarch64_vdup_lane_any (u64, q, __a, __b)

/* __aarch64_vdupq_laneq internal macros.  */
#define __aarch64_vdupq_laneq_f32(__a, __b) \
   __aarch64_vdup_lane_any (f32, q, __a, __b)
#define __aarch64_vdupq_laneq_f64(__a, __b) \
   __aarch64_vdup_lane_any (f64, q, __a, __b)
#define __aarch64_vdupq_laneq_p8(__a, __b) \
   __aarch64_vdup_lane_any (p8, q, __a, __b)
#define __aarch64_vdupq_laneq_p16(__a, __b) \
   __aarch64_vdup_lane_any (p16, q, __a, __b)
#define __aarch64_vdupq_laneq_s8(__a, __b) \
   __aarch64_vdup_lane_any (s8, q, __a, __b)
#define __aarch64_vdupq_laneq_s16(__a, __b) \
   __aarch64_vdup_lane_any (s16, q, __a, __b)
#define __aarch64_vdupq_laneq_s32(__a, __b) \
   __aarch64_vdup_lane_any (s32, q, __a, __b)
#define __aarch64_vdupq_laneq_s64(__a, __b) \
   __aarch64_vdup_lane_any (s64, q, __a, __b)
#define __aarch64_vdupq_laneq_u8(__a, __b) \
   __aarch64_vdup_lane_any (u8, q, __a, __b)
#define __aarch64_vdupq_laneq_u16(__a, __b) \
   __aarch64_vdup_lane_any (u16, q, __a, __b)
#define __aarch64_vdupq_laneq_u32(__a, __b) \
   __aarch64_vdup_lane_any (u32, q, __a, __b)
#define __aarch64_vdupq_laneq_u64(__a, __b) \
   __aarch64_vdup_lane_any (u64, q, __a, __b)

/* Internal macro for lane indices.  */

#define __AARCH64_NUM_LANES(__v) (sizeof (__v) / sizeof (__v[0]))
#define __AARCH64_LANE_CHECK(__vec, __idx)      \
        __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __idx)

/* For big-endian, GCC's vector indices are the opposite way around
   to the architectural lane indices used by Neon intrinsics.  */
#ifdef __AARCH64EB__
#define __aarch64_lane(__vec, __idx) (__AARCH64_NUM_LANES (__vec) - 1 - __idx)
#else
#define __aarch64_lane(__vec, __idx) __idx
#endif

/* vget_lane internal macro.  */
#define __aarch64_vget_lane_any(__vec, __index)                         \
  __extension__                                                         \
  ({                                                                    \
    __AARCH64_LANE_CHECK (__vec, __index);                              \
    __vec[__aarch64_lane (__vec, __index)];                             \
  })

/* vset_lane and vld1_lane internal macro.  */
#define __aarch64_vset_lane_any(__elem, __vec, __index)                 \
  __extension__                                                         \
  ({                                                                    \
    __AARCH64_LANE_CHECK (__vec, __index);                              \
    __vec[__aarch64_lane (__vec, __index)] = __elem;                    \
    __vec;                                                              \
  })

/* vadd  */
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vadd_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a + __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vadd_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a + __b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vadd_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a + __b;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vadd_f32 (float32x2_t __a, float32x2_t __b)
{
  return __a + __b;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vadd_f64 (float64x1_t __a, float64x1_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vadd_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vadd_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vadd_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a + __b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vadd_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vadd_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a + __b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vaddq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a + __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vaddq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a + __b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vaddq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a + __b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vaddq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a + __b;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vaddq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __a + __b;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vaddq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vaddq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vaddq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vaddq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vaddq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a + __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vaddl_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_saddlv8qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vaddl_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_saddlv4hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vaddl_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_saddlv2si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vaddl_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uaddlv8qi ((int8x8_t) __a,
                                                   (int8x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vaddl_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uaddlv4hi ((int16x4_t) __a,
                                                   (int16x4_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vaddl_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint64x2_t) __builtin_aarch64_uaddlv2si ((int32x2_t) __a,
                                                   (int32x2_t) __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vaddl_high_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int16x8_t) __builtin_aarch64_saddl2v16qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vaddl_high_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int32x4_t) __builtin_aarch64_saddl2v8hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vaddl_high_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int64x2_t) __builtin_aarch64_saddl2v4si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vaddl_high_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uaddl2v16qi ((int8x16_t) __a,
                                                     (int8x16_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vaddl_high_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uaddl2v8hi ((int16x8_t) __a,
                                                    (int16x8_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vaddl_high_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint64x2_t) __builtin_aarch64_uaddl2v4si ((int32x4_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vaddw_s8 (int16x8_t __a, int8x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_saddwv8qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vaddw_s16 (int32x4_t __a, int16x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_saddwv4hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vaddw_s32 (int64x2_t __a, int32x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_saddwv2si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vaddw_u8 (uint16x8_t __a, uint8x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uaddwv8qi ((int16x8_t) __a,
                                                   (int8x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vaddw_u16 (uint32x4_t __a, uint16x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uaddwv4hi ((int32x4_t) __a,
                                                   (int16x4_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vaddw_u32 (uint64x2_t __a, uint32x2_t __b)
{
  return (uint64x2_t) __builtin_aarch64_uaddwv2si ((int64x2_t) __a,
                                                   (int32x2_t) __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vaddw_high_s8 (int16x8_t __a, int8x16_t __b)
{
  return (int16x8_t) __builtin_aarch64_saddw2v16qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vaddw_high_s16 (int32x4_t __a, int16x8_t __b)
{
  return (int32x4_t) __builtin_aarch64_saddw2v8hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vaddw_high_s32 (int64x2_t __a, int32x4_t __b)
{
  return (int64x2_t) __builtin_aarch64_saddw2v4si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vaddw_high_u8 (uint16x8_t __a, uint8x16_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uaddw2v16qi ((int16x8_t) __a,
                                                     (int8x16_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vaddw_high_u16 (uint32x4_t __a, uint16x8_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uaddw2v8hi ((int32x4_t) __a,
                                                    (int16x8_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vaddw_high_u32 (uint64x2_t __a, uint32x4_t __b)
{
  return (uint64x2_t) __builtin_aarch64_uaddw2v4si ((int64x2_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vhadd_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_shaddv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vhadd_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_shaddv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vhadd_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_shaddv2si (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vhadd_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_uhaddv8qi ((int8x8_t) __a,
                                                  (int8x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vhadd_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_uhaddv4hi ((int16x4_t) __a,
                                                   (int16x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vhadd_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_uhaddv2si ((int32x2_t) __a,
                                                   (int32x2_t) __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vhaddq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int8x16_t) __builtin_aarch64_shaddv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vhaddq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_shaddv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vhaddq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_shaddv4si (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vhaddq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint8x16_t) __builtin_aarch64_uhaddv16qi ((int8x16_t) __a,
                                                    (int8x16_t) __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vhaddq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uhaddv8hi ((int16x8_t) __a,
                                                   (int16x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vhaddq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uhaddv4si ((int32x4_t) __a,
                                                   (int32x4_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrhadd_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_srhaddv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrhadd_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_srhaddv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vrhadd_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_srhaddv2si (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrhadd_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_urhaddv8qi ((int8x8_t) __a,
                                                   (int8x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrhadd_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_urhaddv4hi ((int16x4_t) __a,
                                                    (int16x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrhadd_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_urhaddv2si ((int32x2_t) __a,
                                                    (int32x2_t) __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrhaddq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int8x16_t) __builtin_aarch64_srhaddv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrhaddq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_srhaddv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vrhaddq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_srhaddv4si (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrhaddq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint8x16_t) __builtin_aarch64_urhaddv16qi ((int8x16_t) __a,
                                                     (int8x16_t) __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrhaddq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_urhaddv8hi ((int16x8_t) __a,
                                                    (int16x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrhaddq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_urhaddv4si ((int32x4_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vaddhn_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_addhnv8hi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vaddhn_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_addhnv4si (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vaddhn_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_addhnv2di (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vaddhn_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_addhnv8hi ((int16x8_t) __a,
                                                  (int16x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vaddhn_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_addhnv4si ((int32x4_t) __a,
                                                   (int32x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vaddhn_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_addhnv2di ((int64x2_t) __a,
                                                   (int64x2_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vraddhn_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_raddhnv8hi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vraddhn_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_raddhnv4si (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vraddhn_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_raddhnv2di (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vraddhn_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_raddhnv8hi ((int16x8_t) __a,
                                                   (int16x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vraddhn_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_raddhnv4si ((int32x4_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vraddhn_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_raddhnv2di ((int64x2_t) __a,
                                                    (int64x2_t) __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vaddhn_high_s16 (int8x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return (int8x16_t) __builtin_aarch64_addhn2v8hi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vaddhn_high_s32 (int16x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return (int16x8_t) __builtin_aarch64_addhn2v4si (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vaddhn_high_s64 (int32x2_t __a, int64x2_t __b, int64x2_t __c)
{
  return (int32x4_t) __builtin_aarch64_addhn2v2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vaddhn_high_u16 (uint8x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
  return (uint8x16_t) __builtin_aarch64_addhn2v8hi ((int8x8_t) __a,
                                                    (int16x8_t) __b,
                                                    (int16x8_t) __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vaddhn_high_u32 (uint16x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
  return (uint16x8_t) __builtin_aarch64_addhn2v4si ((int16x4_t) __a,
                                                    (int32x4_t) __b,
                                                    (int32x4_t) __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vaddhn_high_u64 (uint32x2_t __a, uint64x2_t __b, uint64x2_t __c)
{
  return (uint32x4_t) __builtin_aarch64_addhn2v2di ((int32x2_t) __a,
                                                    (int64x2_t) __b,
                                                    (int64x2_t) __c);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vraddhn_high_s16 (int8x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return (int8x16_t) __builtin_aarch64_raddhn2v8hi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vraddhn_high_s32 (int16x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return (int16x8_t) __builtin_aarch64_raddhn2v4si (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vraddhn_high_s64 (int32x2_t __a, int64x2_t __b, int64x2_t __c)
{
  return (int32x4_t) __builtin_aarch64_raddhn2v2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vraddhn_high_u16 (uint8x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
  return (uint8x16_t) __builtin_aarch64_raddhn2v8hi ((int8x8_t) __a,
                                                     (int16x8_t) __b,
                                                     (int16x8_t) __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vraddhn_high_u32 (uint16x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
  return (uint16x8_t) __builtin_aarch64_raddhn2v4si ((int16x4_t) __a,
                                                     (int32x4_t) __b,
                                                     (int32x4_t) __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vraddhn_high_u64 (uint32x2_t __a, uint64x2_t __b, uint64x2_t __c)
{
  return (uint32x4_t) __builtin_aarch64_raddhn2v2di ((int32x2_t) __a,
                                                     (int64x2_t) __b,
                                                     (int64x2_t) __c);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vdiv_f32 (float32x2_t __a, float32x2_t __b)
{
  return __a / __b;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vdiv_f64 (float64x1_t __a, float64x1_t __b)
{
  return __a / __b;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vdivq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __a / __b;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vdivq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __a / __b;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmul_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a * __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmul_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a * __b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmul_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a * __b;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_f32 (float32x2_t __a, float32x2_t __b)
{
  return __a * __b;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmul_f64 (float64x1_t __a, float64x1_t __b)
{
  return __a * __b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmul_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a * __b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmul_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a * __b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmul_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a * __b;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vmul_p8 (poly8x8_t __a, poly8x8_t __b)
{
  return (poly8x8_t) __builtin_aarch64_pmulv8qi ((int8x8_t) __a,
                                                 (int8x8_t) __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmulq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a * __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmulq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a * __b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmulq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a * __b;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __a * __b;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __a * __b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmulq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a * __b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmulq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a * __b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmulq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a * __b;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vmulq_p8 (poly8x16_t __a, poly8x16_t __b)
{
  return (poly8x16_t) __builtin_aarch64_pmulv16qi ((int8x16_t) __a,
                                                   (int8x16_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vand_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a & __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vand_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a & __b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vand_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vand_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vand_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vand_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a & __b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vand_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vand_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a & __b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vandq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a & __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vandq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a & __b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vandq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a & __b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vandq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vandq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vandq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vandq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a & __b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vandq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a & __b;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vorr_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a | __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vorr_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a | __b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vorr_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vorr_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vorr_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vorr_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a | __b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vorr_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vorr_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a | __b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vorrq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a | __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vorrq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a | __b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vorrq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a | __b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vorrq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vorrq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vorrq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vorrq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a | __b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vorrq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a | __b;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
veor_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
veor_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
veor_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
veor_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
veor_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
veor_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
veor_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
veor_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
veorq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
veorq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
veorq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
veorq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
veorq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
veorq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
veorq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
veorq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a ^ __b;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vbic_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vbic_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vbic_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vbic_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vbic_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vbic_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vbic_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vbic_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vbicq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vbicq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vbicq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vbicq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vbicq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vbicq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vbicq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vbicq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a & ~__b;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vorn_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vorn_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vorn_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vorn_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vorn_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vorn_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vorn_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vorn_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vornq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vornq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vornq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vornq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vornq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vornq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vornq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vornq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a | ~__b;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vsub_s8 (int8x8_t __a, int8x8_t __b)
{
  return __a - __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vsub_s16 (int16x4_t __a, int16x4_t __b)
{
  return __a - __b;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vsub_s32 (int32x2_t __a, int32x2_t __b)
{
  return __a - __b;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vsub_f32 (float32x2_t __a, float32x2_t __b)
{
  return __a - __b;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vsub_f64 (float64x1_t __a, float64x1_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsub_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vsub_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vsub_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __a - __b;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vsub_s64 (int64x1_t __a, int64x1_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vsub_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return __a - __b;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsubq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __a - __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsubq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __a - __b;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsubq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __a - __b;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsubq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __a - __b;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vsubq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __a - __b;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vsubq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsubq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsubq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsubq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsubq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __a - __b;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsubl_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_ssublv8qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsubl_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_ssublv4hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsubl_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_ssublv2si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsubl_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_usublv8qi ((int8x8_t) __a,
                                                   (int8x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsubl_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_usublv4hi ((int16x4_t) __a,
                                                   (int16x4_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsubl_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint64x2_t) __builtin_aarch64_usublv2si ((int32x2_t) __a,
                                                   (int32x2_t) __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsubl_high_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int16x8_t) __builtin_aarch64_ssubl2v16qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsubl_high_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int32x4_t) __builtin_aarch64_ssubl2v8hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsubl_high_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int64x2_t) __builtin_aarch64_ssubl2v4si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsubl_high_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint16x8_t) __builtin_aarch64_usubl2v16qi ((int8x16_t) __a,
                                                     (int8x16_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsubl_high_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint32x4_t) __builtin_aarch64_usubl2v8hi ((int16x8_t) __a,
                                                    (int16x8_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsubl_high_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint64x2_t) __builtin_aarch64_usubl2v4si ((int32x4_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsubw_s8 (int16x8_t __a, int8x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_ssubwv8qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsubw_s16 (int32x4_t __a, int16x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_ssubwv4hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsubw_s32 (int64x2_t __a, int32x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_ssubwv2si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsubw_u8 (uint16x8_t __a, uint8x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_usubwv8qi ((int16x8_t) __a,
                                                   (int8x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsubw_u16 (uint32x4_t __a, uint16x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_usubwv4hi ((int32x4_t) __a,
                                                   (int16x4_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsubw_u32 (uint64x2_t __a, uint32x2_t __b)
{
  return (uint64x2_t) __builtin_aarch64_usubwv2si ((int64x2_t) __a,
                                                   (int32x2_t) __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsubw_high_s8 (int16x8_t __a, int8x16_t __b)
{
  return (int16x8_t) __builtin_aarch64_ssubw2v16qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsubw_high_s16 (int32x4_t __a, int16x8_t __b)
{
  return (int32x4_t) __builtin_aarch64_ssubw2v8hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsubw_high_s32 (int64x2_t __a, int32x4_t __b)
{
  return (int64x2_t) __builtin_aarch64_ssubw2v4si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsubw_high_u8 (uint16x8_t __a, uint8x16_t __b)
{
  return (uint16x8_t) __builtin_aarch64_usubw2v16qi ((int16x8_t) __a,
                                                     (int8x16_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsubw_high_u16 (uint32x4_t __a, uint16x8_t __b)
{
  return (uint32x4_t) __builtin_aarch64_usubw2v8hi ((int32x4_t) __a,
                                                    (int16x8_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsubw_high_u32 (uint64x2_t __a, uint32x4_t __b)
{
  return (uint64x2_t) __builtin_aarch64_usubw2v4si ((int64x2_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqadd_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_sqaddv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqadd_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_sqaddv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqadd_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_sqaddv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqadd_s64 (int64x1_t __a, int64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_sqadddi (__a[0], __b[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqadd_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __builtin_aarch64_uqaddv8qi_uuu (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vhsub_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x8_t)__builtin_aarch64_shsubv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vhsub_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_shsubv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vhsub_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_shsubv2si (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vhsub_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_uhsubv8qi ((int8x8_t) __a,
                                                  (int8x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vhsub_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_uhsubv4hi ((int16x4_t) __a,
                                                   (int16x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vhsub_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_uhsubv2si ((int32x2_t) __a,
                                                   (int32x2_t) __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vhsubq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int8x16_t) __builtin_aarch64_shsubv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vhsubq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_shsubv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vhsubq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_shsubv4si (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vhsubq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint8x16_t) __builtin_aarch64_uhsubv16qi ((int8x16_t) __a,
                                                    (int8x16_t) __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vhsubq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uhsubv8hi ((int16x8_t) __a,
                                                   (int16x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vhsubq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uhsubv4si ((int32x4_t) __a,
                                                   (int32x4_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vsubhn_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_subhnv8hi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vsubhn_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_subhnv4si (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vsubhn_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_subhnv2di (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsubhn_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_subhnv8hi ((int16x8_t) __a,
                                                  (int16x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vsubhn_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_subhnv4si ((int32x4_t) __a,
                                                   (int32x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vsubhn_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_subhnv2di ((int64x2_t) __a,
                                                   (int64x2_t) __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrsubhn_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_rsubhnv8hi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrsubhn_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_rsubhnv4si (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vrsubhn_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_rsubhnv2di (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrsubhn_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_rsubhnv8hi ((int16x8_t) __a,
                                                   (int16x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrsubhn_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_rsubhnv4si ((int32x4_t) __a,
                                                    (int32x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrsubhn_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_rsubhnv2di ((int64x2_t) __a,
                                                    (int64x2_t) __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrsubhn_high_s16 (int8x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return (int8x16_t) __builtin_aarch64_rsubhn2v8hi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrsubhn_high_s32 (int16x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return (int16x8_t) __builtin_aarch64_rsubhn2v4si (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vrsubhn_high_s64 (int32x2_t __a, int64x2_t __b, int64x2_t __c)
{
  return (int32x4_t) __builtin_aarch64_rsubhn2v2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrsubhn_high_u16 (uint8x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
  return (uint8x16_t) __builtin_aarch64_rsubhn2v8hi ((int8x8_t) __a,
                                                     (int16x8_t) __b,
                                                     (int16x8_t) __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrsubhn_high_u32 (uint16x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
  return (uint16x8_t) __builtin_aarch64_rsubhn2v4si ((int16x4_t) __a,
                                                     (int32x4_t) __b,
                                                     (int32x4_t) __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrsubhn_high_u64 (uint32x2_t __a, uint64x2_t __b, uint64x2_t __c)
{
  return (uint32x4_t) __builtin_aarch64_rsubhn2v2di ((int32x2_t) __a,
                                                     (int64x2_t) __b,
                                                     (int64x2_t) __c);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsubhn_high_s16 (int8x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return (int8x16_t) __builtin_aarch64_subhn2v8hi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsubhn_high_s32 (int16x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return (int16x8_t) __builtin_aarch64_subhn2v4si (__a, __b, __c);;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsubhn_high_s64 (int32x2_t __a, int64x2_t __b, int64x2_t __c)
{
  return (int32x4_t) __builtin_aarch64_subhn2v2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsubhn_high_u16 (uint8x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
  return (uint8x16_t) __builtin_aarch64_subhn2v8hi ((int8x8_t) __a,
                                                    (int16x8_t) __b,
                                                    (int16x8_t) __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsubhn_high_u32 (uint16x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
  return (uint16x8_t) __builtin_aarch64_subhn2v4si ((int16x4_t) __a,
                                                    (int32x4_t) __b,
                                                    (int32x4_t) __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsubhn_high_u64 (uint32x2_t __a, uint64x2_t __b, uint64x2_t __c)
{
  return (uint32x4_t) __builtin_aarch64_subhn2v2di ((int32x2_t) __a,
                                                    (int64x2_t) __b,
                                                    (int64x2_t) __c);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqadd_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __builtin_aarch64_uqaddv4hi_uuu (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqadd_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __builtin_aarch64_uqaddv2si_uuu (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vqadd_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_uqadddi_uuu (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqaddq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int8x16_t) __builtin_aarch64_sqaddv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqaddq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_sqaddv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqaddq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_sqaddv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqaddq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_sqaddv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqaddq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __builtin_aarch64_uqaddv16qi_uuu (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqaddq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __builtin_aarch64_uqaddv8hi_uuu (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqaddq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __builtin_aarch64_uqaddv4si_uuu (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vqaddq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __builtin_aarch64_uqaddv2di_uuu (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqsub_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_sqsubv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqsub_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_sqsubv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqsub_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_sqsubv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqsub_s64 (int64x1_t __a, int64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_sqsubdi (__a[0], __b[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqsub_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return __builtin_aarch64_uqsubv8qi_uuu (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqsub_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return __builtin_aarch64_uqsubv4hi_uuu (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqsub_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return __builtin_aarch64_uqsubv2si_uuu (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vqsub_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_uqsubdi_uuu (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqsubq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int8x16_t) __builtin_aarch64_sqsubv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqsubq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_sqsubv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqsubq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_sqsubv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqsubq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_sqsubv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqsubq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return __builtin_aarch64_uqsubv16qi_uuu (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqsubq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return __builtin_aarch64_uqsubv8hi_uuu (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqsubq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return __builtin_aarch64_uqsubv4si_uuu (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vqsubq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return __builtin_aarch64_uqsubv2di_uuu (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqneg_s8 (int8x8_t __a)
{
  return (int8x8_t) __builtin_aarch64_sqnegv8qi (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqneg_s16 (int16x4_t __a)
{
  return (int16x4_t) __builtin_aarch64_sqnegv4hi (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqneg_s32 (int32x2_t __a)
{
  return (int32x2_t) __builtin_aarch64_sqnegv2si (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqneg_s64 (int64x1_t __a)
{
  return (int64x1_t) {__builtin_aarch64_sqnegdi (__a[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqnegq_s8 (int8x16_t __a)
{
  return (int8x16_t) __builtin_aarch64_sqnegv16qi (__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqnegq_s16 (int16x8_t __a)
{
  return (int16x8_t) __builtin_aarch64_sqnegv8hi (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqnegq_s32 (int32x4_t __a)
{
  return (int32x4_t) __builtin_aarch64_sqnegv4si (__a);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqabs_s8 (int8x8_t __a)
{
  return (int8x8_t) __builtin_aarch64_sqabsv8qi (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqabs_s16 (int16x4_t __a)
{
  return (int16x4_t) __builtin_aarch64_sqabsv4hi (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqabs_s32 (int32x2_t __a)
{
  return (int32x2_t) __builtin_aarch64_sqabsv2si (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqabs_s64 (int64x1_t __a)
{
  return (int64x1_t) {__builtin_aarch64_sqabsdi (__a[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqabsq_s8 (int8x16_t __a)
{
  return (int8x16_t) __builtin_aarch64_sqabsv16qi (__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqabsq_s16 (int16x8_t __a)
{
  return (int16x8_t) __builtin_aarch64_sqabsv8hi (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqabsq_s32 (int32x4_t __a)
{
  return (int32x4_t) __builtin_aarch64_sqabsv4si (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqdmulh_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_sqdmulhv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqdmulh_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_sqdmulhv2si (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqdmulhq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_sqdmulhv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmulhq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_sqdmulhv4si (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmulh_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_sqrdmulhv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmulh_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_sqrdmulhv2si (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmulhq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_sqrdmulhv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmulhq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_sqrdmulhv4si (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vcreate_s8 (uint64_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vcreate_s16 (uint64_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcreate_s32 (uint64_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vcreate_s64 (uint64_t __a)
{
  return (int64x1_t) {__a};
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vcreate_f16 (uint64_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vcreate_f32 (uint64_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcreate_u8 (uint64_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcreate_u16 (uint64_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcreate_u32 (uint64_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcreate_u64 (uint64_t __a)
{
  return (uint64x1_t) {__a};
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vcreate_f64 (uint64_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vcreate_p8 (uint64_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vcreate_p16 (uint64_t __a)
{
  return (poly16x4_t) __a;
}

/* vget_lane  */

__extension__ static __inline float16_t __attribute__ ((__always_inline__))
vget_lane_f16 (float16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vget_lane_f32 (float32x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vget_lane_f64 (float64x1_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vget_lane_p8 (poly8x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vget_lane_p16 (poly16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vget_lane_s8 (int8x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vget_lane_s16 (int16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vget_lane_s32 (int32x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vget_lane_s64 (int64x1_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vget_lane_u8 (uint8x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vget_lane_u16 (uint16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vget_lane_u32 (uint32x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vget_lane_u64 (uint64x1_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vgetq_lane  */

__extension__ static __inline float16_t __attribute__ ((__always_inline__))
vgetq_lane_f16 (float16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vgetq_lane_f32 (float32x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vgetq_lane_f64 (float64x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vgetq_lane_p8 (poly8x16_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vgetq_lane_p16 (poly16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vgetq_lane_s8 (int8x16_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vgetq_lane_s16 (int16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vgetq_lane_s32 (int32x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vgetq_lane_s64 (int64x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vgetq_lane_u8 (uint8x16_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vgetq_lane_u16 (uint16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vgetq_lane_u32 (uint32x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vgetq_lane_u64 (uint64x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vreinterpret  */

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_f16 (float16x4_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_f64 (float64x1_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_s8 (int8x8_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_s16 (int16x4_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_s32 (int32x2_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_s64 (int64x1_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_f32 (float32x2_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_u8 (uint8x8_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_u16 (uint16x4_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_u32 (uint32x2_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_u64 (uint64x1_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vreinterpret_p8_p16 (poly16x4_t __a)
{
  return (poly8x8_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_f64 (float64x2_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_s8 (int8x16_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_s16 (int16x8_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_s32 (int32x4_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_s64 (int64x2_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_f16 (float16x8_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_f32 (float32x4_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_u8 (uint8x16_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_u16 (uint16x8_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_u32 (uint32x4_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_u64 (uint64x2_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vreinterpretq_p8_p16 (poly16x8_t __a)
{
  return (poly8x16_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_f16 (float16x4_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_f64 (float64x1_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_s8 (int8x8_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_s16 (int16x4_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_s32 (int32x2_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_s64 (int64x1_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_f32 (float32x2_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_u8 (uint8x8_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_u16 (uint16x4_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_u32 (uint32x2_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_u64 (uint64x1_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vreinterpret_p16_p8 (poly8x8_t __a)
{
  return (poly16x4_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_f64 (float64x2_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_s8 (int8x16_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_s16 (int16x8_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_s32 (int32x4_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_s64 (int64x2_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_f16 (float16x8_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_f32 (float32x4_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_u8 (uint8x16_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_u16 (uint16x8_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_u32 (uint32x4_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_u64 (uint64x2_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vreinterpretq_p16_p8 (poly8x16_t __a)
{
  return (poly16x8_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_f64 (float64x1_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_s8 (int8x8_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_s16 (int16x4_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_s32 (int32x2_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_s64 (int64x1_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_f32 (float32x2_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_u8 (uint8x8_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_u16 (uint16x4_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_u32 (uint32x2_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_u64 (uint64x1_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_p8 (poly8x8_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vreinterpret_f16_p16 (poly16x4_t __a)
{
  return (float16x4_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_f64 (float64x2_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_s8 (int8x16_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_s16 (int16x8_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_s32 (int32x4_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_s64 (int64x2_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_f32 (float32x4_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_u8 (uint8x16_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_u16 (uint16x8_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_u32 (uint32x4_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_u64 (uint64x2_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_p8 (poly8x16_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vreinterpretq_f16_p16 (poly16x8_t __a)
{
  return (float16x8_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_f16 (float16x4_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_f64 (float64x1_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_s8 (int8x8_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_s16 (int16x4_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_s32 (int32x2_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_s64 (int64x1_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_u8 (uint8x8_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_u16 (uint16x4_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_u32 (uint32x2_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_u64 (uint64x1_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_p8 (poly8x8_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vreinterpret_f32_p16 (poly16x4_t __a)
{
  return (float32x2_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_f16 (float16x8_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_f64 (float64x2_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_s8 (int8x16_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_s16 (int16x8_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_s32 (int32x4_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_s64 (int64x2_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_u8 (uint8x16_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_u16 (uint16x8_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_u32 (uint32x4_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_u64 (uint64x2_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_p8 (poly8x16_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vreinterpretq_f32_p16 (poly16x8_t __a)
{
  return (float32x4_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_f16 (float16x4_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_f32 (float32x2_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_p8 (poly8x8_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_p16 (poly16x4_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_s8 (int8x8_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_s16 (int16x4_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_s32 (int32x2_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_s64 (int64x1_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_u8 (uint8x8_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_u16 (uint16x4_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_u32 (uint32x2_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x1_t __attribute__((__always_inline__))
vreinterpret_f64_u64 (uint64x1_t __a)
{
  return (float64x1_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_f16 (float16x8_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_f32 (float32x4_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_p8 (poly8x16_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_p16 (poly16x8_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_s8 (int8x16_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_s16 (int16x8_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_s32 (int32x4_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_s64 (int64x2_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_u8 (uint8x16_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_u16 (uint16x8_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_u32 (uint32x4_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline float64x2_t __attribute__((__always_inline__))
vreinterpretq_f64_u64 (uint64x2_t __a)
{
  return (float64x2_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_f16 (float16x4_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_f64 (float64x1_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_s8 (int8x8_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_s16 (int16x4_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_s32 (int32x2_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_f32 (float32x2_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_u8 (uint8x8_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_u16 (uint16x4_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_u32 (uint32x2_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_u64 (uint64x1_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_p8 (poly8x8_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vreinterpret_s64_p16 (poly16x4_t __a)
{
  return (int64x1_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_f64 (float64x2_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_s8 (int8x16_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_s16 (int16x8_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_s32 (int32x4_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_f16 (float16x8_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_f32 (float32x4_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_u8 (uint8x16_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_u16 (uint16x8_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_u32 (uint32x4_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_u64 (uint64x2_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_p8 (poly8x16_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vreinterpretq_s64_p16 (poly16x8_t __a)
{
  return (int64x2_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_f16 (float16x4_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_f64 (float64x1_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_s8 (int8x8_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_s16 (int16x4_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_s32 (int32x2_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_s64 (int64x1_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_f32 (float32x2_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_u8 (uint8x8_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_u16 (uint16x4_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_u32 (uint32x2_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_p8 (poly8x8_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vreinterpret_u64_p16 (poly16x4_t __a)
{
  return (uint64x1_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_f64 (float64x2_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_s8 (int8x16_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_s16 (int16x8_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_s32 (int32x4_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_s64 (int64x2_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_f16 (float16x8_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_f32 (float32x4_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_u8 (uint8x16_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_u16 (uint16x8_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_u32 (uint32x4_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_p8 (poly8x16_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vreinterpretq_u64_p16 (poly16x8_t __a)
{
  return (uint64x2_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_f16 (float16x4_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_f64 (float64x1_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_s16 (int16x4_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_s32 (int32x2_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_s64 (int64x1_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_f32 (float32x2_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_u8 (uint8x8_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_u16 (uint16x4_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_u32 (uint32x2_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_u64 (uint64x1_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_p8 (poly8x8_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vreinterpret_s8_p16 (poly16x4_t __a)
{
  return (int8x8_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_f64 (float64x2_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_s16 (int16x8_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_s32 (int32x4_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_s64 (int64x2_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_f16 (float16x8_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_f32 (float32x4_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_u8 (uint8x16_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_u16 (uint16x8_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_u32 (uint32x4_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_u64 (uint64x2_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_p8 (poly8x16_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vreinterpretq_s8_p16 (poly16x8_t __a)
{
  return (int8x16_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_f16 (float16x4_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_f64 (float64x1_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_s8 (int8x8_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_s32 (int32x2_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_s64 (int64x1_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_f32 (float32x2_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_u8 (uint8x8_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_u16 (uint16x4_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_u32 (uint32x2_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_u64 (uint64x1_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_p8 (poly8x8_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vreinterpret_s16_p16 (poly16x4_t __a)
{
  return (int16x4_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_f64 (float64x2_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_s8 (int8x16_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_s32 (int32x4_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_s64 (int64x2_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_f16 (float16x8_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_f32 (float32x4_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_u8 (uint8x16_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_u16 (uint16x8_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_u32 (uint32x4_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_u64 (uint64x2_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_p8 (poly8x16_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vreinterpretq_s16_p16 (poly16x8_t __a)
{
  return (int16x8_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_f16 (float16x4_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_f64 (float64x1_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_s8 (int8x8_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_s16 (int16x4_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_s64 (int64x1_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_f32 (float32x2_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_u8 (uint8x8_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_u16 (uint16x4_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_u32 (uint32x2_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_u64 (uint64x1_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_p8 (poly8x8_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vreinterpret_s32_p16 (poly16x4_t __a)
{
  return (int32x2_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_f64 (float64x2_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_s8 (int8x16_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_s16 (int16x8_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_s64 (int64x2_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_f16 (float16x8_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_f32 (float32x4_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_u8 (uint8x16_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_u16 (uint16x8_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_u32 (uint32x4_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_u64 (uint64x2_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_p8 (poly8x16_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vreinterpretq_s32_p16 (poly16x8_t __a)
{
  return (int32x4_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_f16 (float16x4_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_f64 (float64x1_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_s8 (int8x8_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_s16 (int16x4_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_s32 (int32x2_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_s64 (int64x1_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_f32 (float32x2_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_u16 (uint16x4_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_u32 (uint32x2_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_u64 (uint64x1_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_p8 (poly8x8_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vreinterpret_u8_p16 (poly16x4_t __a)
{
  return (uint8x8_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_f64 (float64x2_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_s8 (int8x16_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_s16 (int16x8_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_s32 (int32x4_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_s64 (int64x2_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_f16 (float16x8_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_f32 (float32x4_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_u16 (uint16x8_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_u32 (uint32x4_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_u64 (uint64x2_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_p8 (poly8x16_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vreinterpretq_u8_p16 (poly16x8_t __a)
{
  return (uint8x16_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_f16 (float16x4_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_f64 (float64x1_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_s8 (int8x8_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_s16 (int16x4_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_s32 (int32x2_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_s64 (int64x1_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_f32 (float32x2_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_u8 (uint8x8_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_u32 (uint32x2_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_u64 (uint64x1_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_p8 (poly8x8_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vreinterpret_u16_p16 (poly16x4_t __a)
{
  return (uint16x4_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_f64 (float64x2_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_s8 (int8x16_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_s16 (int16x8_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_s32 (int32x4_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_s64 (int64x2_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_f16 (float16x8_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_f32 (float32x4_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_u8 (uint8x16_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_u32 (uint32x4_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_u64 (uint64x2_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_p8 (poly8x16_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vreinterpretq_u16_p16 (poly16x8_t __a)
{
  return (uint16x8_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_f16 (float16x4_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_f64 (float64x1_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_s8 (int8x8_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_s16 (int16x4_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_s32 (int32x2_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_s64 (int64x1_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_f32 (float32x2_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_u8 (uint8x8_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_u16 (uint16x4_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_u64 (uint64x1_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_p8 (poly8x8_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vreinterpret_u32_p16 (poly16x4_t __a)
{
  return (uint32x2_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_f64 (float64x2_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_s8 (int8x16_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_s16 (int16x8_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_s32 (int32x4_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_s64 (int64x2_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_f16 (float16x8_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_f32 (float32x4_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_u8 (uint8x16_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_u16 (uint16x8_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_u64 (uint64x2_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_p8 (poly8x16_t __a)
{
  return (uint32x4_t) __a;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vreinterpretq_u32_p16 (poly16x8_t __a)
{
  return (uint32x4_t) __a;
}

/* vset_lane  */

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vset_lane_f16 (float16_t __elem, float16x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vset_lane_f32 (float32_t __elem, float32x2_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vset_lane_f64 (float64_t __elem, float64x1_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vset_lane_p8 (poly8_t __elem, poly8x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vset_lane_p16 (poly16_t __elem, poly16x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vset_lane_s8 (int8_t __elem, int8x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vset_lane_s16 (int16_t __elem, int16x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vset_lane_s32 (int32_t __elem, int32x2_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vset_lane_s64 (int64_t __elem, int64x1_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vset_lane_u8 (uint8_t __elem, uint8x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vset_lane_u16 (uint16_t __elem, uint16x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vset_lane_u32 (uint32_t __elem, uint32x2_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vset_lane_u64 (uint64_t __elem, uint64x1_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

/* vsetq_lane  */

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vsetq_lane_f16 (float16_t __elem, float16x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vsetq_lane_f32 (float32_t __elem, float32x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vsetq_lane_f64 (float64_t __elem, float64x2_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vsetq_lane_p8 (poly8_t __elem, poly8x16_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vsetq_lane_p16 (poly16_t __elem, poly16x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsetq_lane_s8 (int8_t __elem, int8x16_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsetq_lane_s16 (int16_t __elem, int16x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsetq_lane_s32 (int32_t __elem, int32x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsetq_lane_s64 (int64_t __elem, int64x2_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsetq_lane_u8 (uint8_t __elem, uint8x16_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsetq_lane_u16 (uint16_t __elem, uint16x8_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsetq_lane_u32 (uint32_t __elem, uint32x4_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsetq_lane_u64 (uint64_t __elem, uint64x2_t __vec, const int __index)
{
  return __aarch64_vset_lane_any (__elem, __vec, __index);
}

#define __GET_LOW(__TYPE) \
  uint64x2_t tmp = vreinterpretq_u64_##__TYPE (__a);  \
  uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0));  \
  return vreinterpret_##__TYPE##_u64 (lo);

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vget_low_f16 (float16x8_t __a)
{
  __GET_LOW (f16);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vget_low_f32 (float32x4_t __a)
{
  __GET_LOW (f32);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vget_low_f64 (float64x2_t __a)
{
  return (float64x1_t) {vgetq_lane_f64 (__a, 0)};
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vget_low_p8 (poly8x16_t __a)
{
  __GET_LOW (p8);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vget_low_p16 (poly16x8_t __a)
{
  __GET_LOW (p16);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vget_low_s8 (int8x16_t __a)
{
  __GET_LOW (s8);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vget_low_s16 (int16x8_t __a)
{
  __GET_LOW (s16);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vget_low_s32 (int32x4_t __a)
{
  __GET_LOW (s32);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vget_low_s64 (int64x2_t __a)
{
  __GET_LOW (s64);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vget_low_u8 (uint8x16_t __a)
{
  __GET_LOW (u8);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vget_low_u16 (uint16x8_t __a)
{
  __GET_LOW (u16);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vget_low_u32 (uint32x4_t __a)
{
  __GET_LOW (u32);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vget_low_u64 (uint64x2_t __a)
{
  return vcreate_u64 (vgetq_lane_u64 (__a, 0));
}

#undef __GET_LOW

#define __GET_HIGH(__TYPE)                                      \
  uint64x2_t tmp = vreinterpretq_u64_##__TYPE (__a);            \
  uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1));        \
  return vreinterpret_##__TYPE##_u64 (hi);

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vget_high_f16 (float16x8_t __a)
{
  __GET_HIGH (f16);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vget_high_f32 (float32x4_t __a)
{
  __GET_HIGH (f32);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vget_high_f64 (float64x2_t __a)
{
  __GET_HIGH (f64);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vget_high_p8 (poly8x16_t __a)
{
  __GET_HIGH (p8);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vget_high_p16 (poly16x8_t __a)
{
  __GET_HIGH (p16);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vget_high_s8 (int8x16_t __a)
{
  __GET_HIGH (s8);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vget_high_s16 (int16x8_t __a)
{
  __GET_HIGH (s16);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vget_high_s32 (int32x4_t __a)
{
  __GET_HIGH (s32);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vget_high_s64 (int64x2_t __a)
{
  __GET_HIGH (s64);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vget_high_u8 (uint8x16_t __a)
{
  __GET_HIGH (u8);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vget_high_u16 (uint16x8_t __a)
{
  __GET_HIGH (u16);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vget_high_u32 (uint32x4_t __a)
{
  __GET_HIGH (u32);
}

#undef __GET_HIGH

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vget_high_u64 (uint64x2_t __a)
{
  return vcreate_u64 (vgetq_lane_u64 (__a, 1));
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vcombine_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x16_t) __builtin_aarch64_combinev8qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vcombine_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x8_t) __builtin_aarch64_combinev4hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vcombine_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x4_t) __builtin_aarch64_combinev2si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vcombine_s64 (int64x1_t __a, int64x1_t __b)
{
  return __builtin_aarch64_combinedi (__a[0], __b[0]);
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vcombine_f16 (float16x4_t __a, float16x4_t __b)
{
  return __builtin_aarch64_combinev4hf (__a, __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcombine_f32 (float32x2_t __a, float32x2_t __b)
{
  return (float32x4_t) __builtin_aarch64_combinev2sf (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcombine_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x16_t) __builtin_aarch64_combinev8qi ((int8x8_t) __a,
                                                     (int8x8_t) __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcombine_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x8_t) __builtin_aarch64_combinev4hi ((int16x4_t) __a,
                                                     (int16x4_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcombine_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x4_t) __builtin_aarch64_combinev2si ((int32x2_t) __a,
                                                     (int32x2_t) __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcombine_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (uint64x2_t) __builtin_aarch64_combinedi (__a[0], __b[0]);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vcombine_f64 (float64x1_t __a, float64x1_t __b)
{
  return __builtin_aarch64_combinedf (__a[0], __b[0]);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vcombine_p8 (poly8x8_t __a, poly8x8_t __b)
{
  return (poly8x16_t) __builtin_aarch64_combinev8qi ((int8x8_t) __a,
                                                     (int8x8_t) __b);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vcombine_p16 (poly16x4_t __a, poly16x4_t __b)
{
  return (poly16x8_t) __builtin_aarch64_combinev4hi ((int16x4_t) __a,
                                                     (int16x4_t) __b);
}

/* Start of temporary inline asm implementations.  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vaba_s8 (int8x8_t a, int8x8_t b, int8x8_t c)
{
  int8x8_t result;
  __asm__ ("saba %0.8b,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vaba_s16 (int16x4_t a, int16x4_t b, int16x4_t c)
{
  int16x4_t result;
  __asm__ ("saba %0.4h,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vaba_s32 (int32x2_t a, int32x2_t b, int32x2_t c)
{
  int32x2_t result;
  __asm__ ("saba %0.2s,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vaba_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c)
{
  uint8x8_t result;
  __asm__ ("uaba %0.8b,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vaba_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c)
{
  uint16x4_t result;
  __asm__ ("uaba %0.4h,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vaba_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c)
{
  uint32x2_t result;
  __asm__ ("uaba %0.2s,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabal_high_s8 (int16x8_t a, int8x16_t b, int8x16_t c)
{
  int16x8_t result;
  __asm__ ("sabal2 %0.8h,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabal_high_s16 (int32x4_t a, int16x8_t b, int16x8_t c)
{
  int32x4_t result;
  __asm__ ("sabal2 %0.4s,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vabal_high_s32 (int64x2_t a, int32x4_t b, int32x4_t c)
{
  int64x2_t result;
  __asm__ ("sabal2 %0.2d,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vabal_high_u8 (uint16x8_t a, uint8x16_t b, uint8x16_t c)
{
  uint16x8_t result;
  __asm__ ("uabal2 %0.8h,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vabal_high_u16 (uint32x4_t a, uint16x8_t b, uint16x8_t c)
{
  uint32x4_t result;
  __asm__ ("uabal2 %0.4s,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vabal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c)
{
  uint64x2_t result;
  __asm__ ("uabal2 %0.2d,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabal_s8 (int16x8_t a, int8x8_t b, int8x8_t c)
{
  int16x8_t result;
  __asm__ ("sabal %0.8h,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabal_s16 (int32x4_t a, int16x4_t b, int16x4_t c)
{
  int32x4_t result;
  __asm__ ("sabal %0.4s,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vabal_s32 (int64x2_t a, int32x2_t b, int32x2_t c)
{
  int64x2_t result;
  __asm__ ("sabal %0.2d,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vabal_u8 (uint16x8_t a, uint8x8_t b, uint8x8_t c)
{
  uint16x8_t result;
  __asm__ ("uabal %0.8h,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vabal_u16 (uint32x4_t a, uint16x4_t b, uint16x4_t c)
{
  uint32x4_t result;
  __asm__ ("uabal %0.4s,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vabal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c)
{
  uint64x2_t result;
  __asm__ ("uabal %0.2d,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vabaq_s8 (int8x16_t a, int8x16_t b, int8x16_t c)
{
  int8x16_t result;
  __asm__ ("saba %0.16b,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabaq_s16 (int16x8_t a, int16x8_t b, int16x8_t c)
{
  int16x8_t result;
  __asm__ ("saba %0.8h,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabaq_s32 (int32x4_t a, int32x4_t b, int32x4_t c)
{
  int32x4_t result;
  __asm__ ("saba %0.4s,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vabaq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c)
{
  uint8x16_t result;
  __asm__ ("uaba %0.16b,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vabaq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c)
{
  uint16x8_t result;
  __asm__ ("uaba %0.8h,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vabaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c)
{
  uint32x4_t result;
  __asm__ ("uaba %0.4s,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vabd_f32 (float32x2_t a, float32x2_t b)
{
  float32x2_t result;
  __asm__ ("fabd %0.2s, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vabd_s8 (int8x8_t a, int8x8_t b)
{
  int8x8_t result;
  __asm__ ("sabd %0.8b, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vabd_s16 (int16x4_t a, int16x4_t b)
{
  int16x4_t result;
  __asm__ ("sabd %0.4h, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vabd_s32 (int32x2_t a, int32x2_t b)
{
  int32x2_t result;
  __asm__ ("sabd %0.2s, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vabd_u8 (uint8x8_t a, uint8x8_t b)
{
  uint8x8_t result;
  __asm__ ("uabd %0.8b, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vabd_u16 (uint16x4_t a, uint16x4_t b)
{
  uint16x4_t result;
  __asm__ ("uabd %0.4h, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vabd_u32 (uint32x2_t a, uint32x2_t b)
{
  uint32x2_t result;
  __asm__ ("uabd %0.2s, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vabdd_f64 (float64_t a, float64_t b)
{
  float64_t result;
  __asm__ ("fabd %d0, %d1, %d2"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabdl_high_s8 (int8x16_t a, int8x16_t b)
{
  int16x8_t result;
  __asm__ ("sabdl2 %0.8h,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabdl_high_s16 (int16x8_t a, int16x8_t b)
{
  int32x4_t result;
  __asm__ ("sabdl2 %0.4s,%1.8h,%2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vabdl_high_s32 (int32x4_t a, int32x4_t b)
{
  int64x2_t result;
  __asm__ ("sabdl2 %0.2d,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vabdl_high_u8 (uint8x16_t a, uint8x16_t b)
{
  uint16x8_t result;
  __asm__ ("uabdl2 %0.8h,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vabdl_high_u16 (uint16x8_t a, uint16x8_t b)
{
  uint32x4_t result;
  __asm__ ("uabdl2 %0.4s,%1.8h,%2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vabdl_high_u32 (uint32x4_t a, uint32x4_t b)
{
  uint64x2_t result;
  __asm__ ("uabdl2 %0.2d,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabdl_s8 (int8x8_t a, int8x8_t b)
{
  int16x8_t result;
  __asm__ ("sabdl %0.8h, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabdl_s16 (int16x4_t a, int16x4_t b)
{
  int32x4_t result;
  __asm__ ("sabdl %0.4s, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vabdl_s32 (int32x2_t a, int32x2_t b)
{
  int64x2_t result;
  __asm__ ("sabdl %0.2d, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vabdl_u8 (uint8x8_t a, uint8x8_t b)
{
  uint16x8_t result;
  __asm__ ("uabdl %0.8h, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vabdl_u16 (uint16x4_t a, uint16x4_t b)
{
  uint32x4_t result;
  __asm__ ("uabdl %0.4s, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vabdl_u32 (uint32x2_t a, uint32x2_t b)
{
  uint64x2_t result;
  __asm__ ("uabdl %0.2d, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vabdq_f32 (float32x4_t a, float32x4_t b)
{
  float32x4_t result;
  __asm__ ("fabd %0.4s, %1.4s, %2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vabdq_f64 (float64x2_t a, float64x2_t b)
{
  float64x2_t result;
  __asm__ ("fabd %0.2d, %1.2d, %2.2d"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vabdq_s8 (int8x16_t a, int8x16_t b)
{
  int8x16_t result;
  __asm__ ("sabd %0.16b, %1.16b, %2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabdq_s16 (int16x8_t a, int16x8_t b)
{
  int16x8_t result;
  __asm__ ("sabd %0.8h, %1.8h, %2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabdq_s32 (int32x4_t a, int32x4_t b)
{
  int32x4_t result;
  __asm__ ("sabd %0.4s, %1.4s, %2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vabdq_u8 (uint8x16_t a, uint8x16_t b)
{
  uint8x16_t result;
  __asm__ ("uabd %0.16b, %1.16b, %2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vabdq_u16 (uint16x8_t a, uint16x8_t b)
{
  uint16x8_t result;
  __asm__ ("uabd %0.8h, %1.8h, %2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vabdq_u32 (uint32x4_t a, uint32x4_t b)
{
  uint32x4_t result;
  __asm__ ("uabd %0.4s, %1.4s, %2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vabds_f32 (float32_t a, float32_t b)
{
  float32_t result;
  __asm__ ("fabd %s0, %s1, %s2"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vaddlv_s8 (int8x8_t a)
{
  int16_t result;
  __asm__ ("saddlv %h0,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vaddlv_s16 (int16x4_t a)
{
  int32_t result;
  __asm__ ("saddlv %s0,%1.4h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vaddlv_u8 (uint8x8_t a)
{
  uint16_t result;
  __asm__ ("uaddlv %h0,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vaddlv_u16 (uint16x4_t a)
{
  uint32_t result;
  __asm__ ("uaddlv %s0,%1.4h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vaddlvq_s8 (int8x16_t a)
{
  int16_t result;
  __asm__ ("saddlv %h0,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vaddlvq_s16 (int16x8_t a)
{
  int32_t result;
  __asm__ ("saddlv %s0,%1.8h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vaddlvq_s32 (int32x4_t a)
{
  int64_t result;
  __asm__ ("saddlv %d0,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vaddlvq_u8 (uint8x16_t a)
{
  uint16_t result;
  __asm__ ("uaddlv %h0,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vaddlvq_u16 (uint16x8_t a)
{
  uint32_t result;
  __asm__ ("uaddlv %s0,%1.8h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vaddlvq_u32 (uint32x4_t a)
{
  uint64_t result;
  __asm__ ("uaddlv %d0,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

#define vcopyq_lane_f32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       float32x4_t c_ = (c);                                            \
       float32x4_t a_ = (a);                                            \
       float32x4_t result;                                              \
       __asm__ ("ins %0.s[%2], %3.s[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_f64(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       float64x2_t c_ = (c);                                            \
       float64x2_t a_ = (a);                                            \
       float64x2_t result;                                              \
       __asm__ ("ins %0.d[%2], %3.d[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_p8(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       poly8x16_t c_ = (c);                                             \
       poly8x16_t a_ = (a);                                             \
       poly8x16_t result;                                               \
       __asm__ ("ins %0.b[%2], %3.b[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_p16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       poly16x8_t c_ = (c);                                             \
       poly16x8_t a_ = (a);                                             \
       poly16x8_t result;                                               \
       __asm__ ("ins %0.h[%2], %3.h[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_s8(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       int8x16_t c_ = (c);                                              \
       int8x16_t a_ = (a);                                              \
       int8x16_t result;                                                \
       __asm__ ("ins %0.b[%2], %3.b[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_s16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t c_ = (c);                                              \
       int16x8_t a_ = (a);                                              \
       int16x8_t result;                                                \
       __asm__ ("ins %0.h[%2], %3.h[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_s32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t c_ = (c);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("ins %0.s[%2], %3.s[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_s64(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t c_ = (c);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("ins %0.d[%2], %3.d[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_u8(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint8x16_t c_ = (c);                                             \
       uint8x16_t a_ = (a);                                             \
       uint8x16_t result;                                               \
       __asm__ ("ins %0.b[%2], %3.b[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_u16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t c_ = (c);                                             \
       uint16x8_t a_ = (a);                                             \
       uint16x8_t result;                                               \
       __asm__ ("ins %0.h[%2], %3.h[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_u32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t c_ = (c);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("ins %0.s[%2], %3.s[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcopyq_lane_u64(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t c_ = (c);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("ins %0.d[%2], %3.d[%4]"                                \
                : "=w"(result)                                          \
                : "0"(a_), "i"(b), "w"(c_), "i"(d)                      \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvt_n_f32_s32(a, b)                                            \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t a_ = (a);                                              \
       float32x2_t result;                                              \
       __asm__ ("scvtf %0.2s, %1.2s, #%2"                               \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvt_n_f32_u32(a, b)                                            \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t a_ = (a);                                             \
       float32x2_t result;                                              \
       __asm__ ("ucvtf %0.2s, %1.2s, #%2"                               \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvt_n_s32_f32(a, b)                                            \
  __extension__                                                         \
    ({                                                                  \
       float32x2_t a_ = (a);                                            \
       int32x2_t result;                                                \
       __asm__ ("fcvtzs %0.2s, %1.2s, #%2"                              \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvt_n_u32_f32(a, b)                                            \
  __extension__                                                         \
    ({                                                                  \
       float32x2_t a_ = (a);                                            \
       uint32x2_t result;                                               \
       __asm__ ("fcvtzu %0.2s, %1.2s, #%2"                              \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtd_n_f64_s64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       int64_t a_ = (a);                                                \
       float64_t result;                                                \
       __asm__ ("scvtf %d0,%d1,%2"                                      \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtd_n_f64_u64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       uint64_t a_ = (a);                                               \
       float64_t result;                                                \
       __asm__ ("ucvtf %d0,%d1,%2"                                      \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtd_n_s64_f64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float64_t a_ = (a);                                              \
       int64_t result;                                                  \
       __asm__ ("fcvtzs %d0,%d1,%2"                                     \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtd_n_u64_f64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float64_t a_ = (a);                                              \
       uint64_t result;                                                 \
       __asm__ ("fcvtzu %d0,%d1,%2"                                     \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_f32_s32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t a_ = (a);                                              \
       float32x4_t result;                                              \
       __asm__ ("scvtf %0.4s, %1.4s, #%2"                               \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_f32_u32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t a_ = (a);                                             \
       float32x4_t result;                                              \
       __asm__ ("ucvtf %0.4s, %1.4s, #%2"                               \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_f64_s64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t a_ = (a);                                              \
       float64x2_t result;                                              \
       __asm__ ("scvtf %0.2d, %1.2d, #%2"                               \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_f64_u64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t a_ = (a);                                             \
       float64x2_t result;                                              \
       __asm__ ("ucvtf %0.2d, %1.2d, #%2"                               \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_s32_f32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float32x4_t a_ = (a);                                            \
       int32x4_t result;                                                \
       __asm__ ("fcvtzs %0.4s, %1.4s, #%2"                              \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_s64_f64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float64x2_t a_ = (a);                                            \
       int64x2_t result;                                                \
       __asm__ ("fcvtzs %0.2d, %1.2d, #%2"                              \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_u32_f32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float32x4_t a_ = (a);                                            \
       uint32x4_t result;                                               \
       __asm__ ("fcvtzu %0.4s, %1.4s, #%2"                              \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvtq_n_u64_f64(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float64x2_t a_ = (a);                                            \
       uint64x2_t result;                                               \
       __asm__ ("fcvtzu %0.2d, %1.2d, #%2"                              \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvts_n_f32_s32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       int32_t a_ = (a);                                                \
       float32_t result;                                                \
       __asm__ ("scvtf %s0,%s1,%2"                                      \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvts_n_f32_u32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       uint32_t a_ = (a);                                               \
       float32_t result;                                                \
       __asm__ ("ucvtf %s0,%s1,%2"                                      \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvts_n_s32_f32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float32_t a_ = (a);                                              \
       int32_t result;                                                  \
       __asm__ ("fcvtzs %s0,%s1,%2"                                     \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vcvts_n_u32_f32(a, b)                                           \
  __extension__                                                         \
    ({                                                                  \
       float32_t a_ = (a);                                              \
       uint32_t result;                                                 \
       __asm__ ("fcvtzu %s0,%s1,%2"                                     \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vcvtx_f32_f64 (float64x2_t a)
{
  float32x2_t result;
  __asm__ ("fcvtxn %0.2s,%1.2d"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcvtx_high_f32_f64 (float32x2_t a, float64x2_t b)
{
  float32x4_t result;
  __asm__ ("fcvtxn2 %0.4s,%1.2d"
           : "=w"(result)
           : "w" (b), "0"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vcvtxd_f32_f64 (float64_t a)
{
  float32_t result;
  __asm__ ("fcvtxn %s0,%d1"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmla_n_f32 (float32x2_t a, float32x2_t b, float32_t c)
{
  float32x2_t result;
  float32x2_t t1;
  __asm__ ("fmul %1.2s, %3.2s, %4.s[0]; fadd %0.2s, %0.2s, %1.2s"
           : "=w"(result), "=w"(t1)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmla_n_s16 (int16x4_t a, int16x4_t b, int16_t c)
{
  int16x4_t result;
  __asm__ ("mla %0.4h,%2.4h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmla_n_s32 (int32x2_t a, int32x2_t b, int32_t c)
{
  int32x2_t result;
  __asm__ ("mla %0.2s,%2.2s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmla_n_u16 (uint16x4_t a, uint16x4_t b, uint16_t c)
{
  uint16x4_t result;
  __asm__ ("mla %0.4h,%2.4h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmla_n_u32 (uint32x2_t a, uint32x2_t b, uint32_t c)
{
  uint32x2_t result;
  __asm__ ("mla %0.2s,%2.2s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmla_s8 (int8x8_t a, int8x8_t b, int8x8_t c)
{
  int8x8_t result;
  __asm__ ("mla %0.8b, %2.8b, %3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmla_s16 (int16x4_t a, int16x4_t b, int16x4_t c)
{
  int16x4_t result;
  __asm__ ("mla %0.4h, %2.4h, %3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmla_s32 (int32x2_t a, int32x2_t b, int32x2_t c)
{
  int32x2_t result;
  __asm__ ("mla %0.2s, %2.2s, %3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmla_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c)
{
  uint8x8_t result;
  __asm__ ("mla %0.8b, %2.8b, %3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmla_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c)
{
  uint16x4_t result;
  __asm__ ("mla %0.4h, %2.4h, %3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmla_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c)
{
  uint32x2_t result;
  __asm__ ("mla %0.2s, %2.2s, %3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

#define vmlal_high_lane_s16(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       int16x4_t c_ = (c);                                              \
       int16x8_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlal2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_lane_s32(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t c_ = (c);                                              \
       int32x4_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlal2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_lane_u16(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       uint16x4_t c_ = (c);                                             \
       uint16x8_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlal2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_lane_u32(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t c_ = (c);                                             \
       uint32x4_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlal2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_laneq_s16(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t c_ = (c);                                              \
       int16x8_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlal2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_laneq_s32(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t c_ = (c);                                              \
       int32x4_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlal2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_laneq_u16(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t c_ = (c);                                             \
       uint16x8_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlal2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_high_laneq_u32(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t c_ = (c);                                             \
       uint32x4_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlal2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlal_high_n_s16 (int32x4_t a, int16x8_t b, int16_t c)
{
  int32x4_t result;
  __asm__ ("smlal2 %0.4s,%2.8h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlal_high_n_s32 (int64x2_t a, int32x4_t b, int32_t c)
{
  int64x2_t result;
  __asm__ ("smlal2 %0.2d,%2.4s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlal_high_n_u16 (uint32x4_t a, uint16x8_t b, uint16_t c)
{
  uint32x4_t result;
  __asm__ ("umlal2 %0.4s,%2.8h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlal_high_n_u32 (uint64x2_t a, uint32x4_t b, uint32_t c)
{
  uint64x2_t result;
  __asm__ ("umlal2 %0.2d,%2.4s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlal_high_s8 (int16x8_t a, int8x16_t b, int8x16_t c)
{
  int16x8_t result;
  __asm__ ("smlal2 %0.8h,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlal_high_s16 (int32x4_t a, int16x8_t b, int16x8_t c)
{
  int32x4_t result;
  __asm__ ("smlal2 %0.4s,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlal_high_s32 (int64x2_t a, int32x4_t b, int32x4_t c)
{
  int64x2_t result;
  __asm__ ("smlal2 %0.2d,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlal_high_u8 (uint16x8_t a, uint8x16_t b, uint8x16_t c)
{
  uint16x8_t result;
  __asm__ ("umlal2 %0.8h,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlal_high_u16 (uint32x4_t a, uint16x8_t b, uint16x8_t c)
{
  uint32x4_t result;
  __asm__ ("umlal2 %0.4s,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c)
{
  uint64x2_t result;
  __asm__ ("umlal2 %0.2d,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

#define vmlal_lane_s16(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       int16x4_t c_ = (c);                                              \
       int16x4_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlal %0.4s,%2.4h,%3.h[%4]"                            \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_lane_s32(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t c_ = (c);                                              \
       int32x2_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlal %0.2d,%2.2s,%3.s[%4]"                            \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_lane_u16(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint16x4_t c_ = (c);                                             \
       uint16x4_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlal %0.4s,%2.4h,%3.h[%4]"                            \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_lane_u32(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t c_ = (c);                                             \
       uint32x2_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlal %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_laneq_s16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t c_ = (c);                                              \
       int16x4_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlal %0.4s, %2.4h, %3.h[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_laneq_s32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t c_ = (c);                                              \
       int32x2_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlal %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_laneq_u16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t c_ = (c);                                             \
       uint16x4_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlal %0.4s, %2.4h, %3.h[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlal_laneq_u32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t c_ = (c);                                             \
       uint32x2_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlal %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlal_n_s16 (int32x4_t a, int16x4_t b, int16_t c)
{
  int32x4_t result;
  __asm__ ("smlal %0.4s,%2.4h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlal_n_s32 (int64x2_t a, int32x2_t b, int32_t c)
{
  int64x2_t result;
  __asm__ ("smlal %0.2d,%2.2s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlal_n_u16 (uint32x4_t a, uint16x4_t b, uint16_t c)
{
  uint32x4_t result;
  __asm__ ("umlal %0.4s,%2.4h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlal_n_u32 (uint64x2_t a, uint32x2_t b, uint32_t c)
{
  uint64x2_t result;
  __asm__ ("umlal %0.2d,%2.2s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlal_s8 (int16x8_t a, int8x8_t b, int8x8_t c)
{
  int16x8_t result;
  __asm__ ("smlal %0.8h,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlal_s16 (int32x4_t a, int16x4_t b, int16x4_t c)
{
  int32x4_t result;
  __asm__ ("smlal %0.4s,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlal_s32 (int64x2_t a, int32x2_t b, int32x2_t c)
{
  int64x2_t result;
  __asm__ ("smlal %0.2d,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlal_u8 (uint16x8_t a, uint8x8_t b, uint8x8_t c)
{
  uint16x8_t result;
  __asm__ ("umlal %0.8h,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlal_u16 (uint32x4_t a, uint16x4_t b, uint16x4_t c)
{
  uint32x4_t result;
  __asm__ ("umlal %0.4s,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c)
{
  uint64x2_t result;
  __asm__ ("umlal %0.2d,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlaq_n_f32 (float32x4_t a, float32x4_t b, float32_t c)
{
  float32x4_t result;
  float32x4_t t1;
  __asm__ ("fmul %1.4s, %3.4s, %4.s[0]; fadd %0.4s, %0.4s, %1.4s"
           : "=w"(result), "=w"(t1)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlaq_n_s16 (int16x8_t a, int16x8_t b, int16_t c)
{
  int16x8_t result;
  __asm__ ("mla %0.8h,%2.8h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlaq_n_s32 (int32x4_t a, int32x4_t b, int32_t c)
{
  int32x4_t result;
  __asm__ ("mla %0.4s,%2.4s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlaq_n_u16 (uint16x8_t a, uint16x8_t b, uint16_t c)
{
  uint16x8_t result;
  __asm__ ("mla %0.8h,%2.8h,%3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlaq_n_u32 (uint32x4_t a, uint32x4_t b, uint32_t c)
{
  uint32x4_t result;
  __asm__ ("mla %0.4s,%2.4s,%3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmlaq_s8 (int8x16_t a, int8x16_t b, int8x16_t c)
{
  int8x16_t result;
  __asm__ ("mla %0.16b, %2.16b, %3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlaq_s16 (int16x8_t a, int16x8_t b, int16x8_t c)
{
  int16x8_t result;
  __asm__ ("mla %0.8h, %2.8h, %3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlaq_s32 (int32x4_t a, int32x4_t b, int32x4_t c)
{
  int32x4_t result;
  __asm__ ("mla %0.4s, %2.4s, %3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmlaq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c)
{
  uint8x16_t result;
  __asm__ ("mla %0.16b, %2.16b, %3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlaq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c)
{
  uint16x8_t result;
  __asm__ ("mla %0.8h, %2.8h, %3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c)
{
  uint32x4_t result;
  __asm__ ("mla %0.4s, %2.4s, %3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmls_n_f32 (float32x2_t a, float32x2_t b, float32_t c)
{
  float32x2_t result;
  float32x2_t t1;
  __asm__ ("fmul %1.2s, %3.2s, %4.s[0]; fsub %0.2s, %0.2s, %1.2s"
           : "=w"(result), "=w"(t1)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmls_n_s16 (int16x4_t a, int16x4_t b, int16_t c)
{
  int16x4_t result;
  __asm__ ("mls %0.4h, %2.4h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmls_n_s32 (int32x2_t a, int32x2_t b, int32_t c)
{
  int32x2_t result;
  __asm__ ("mls %0.2s, %2.2s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmls_n_u16 (uint16x4_t a, uint16x4_t b, uint16_t c)
{
  uint16x4_t result;
  __asm__ ("mls %0.4h, %2.4h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmls_n_u32 (uint32x2_t a, uint32x2_t b, uint32_t c)
{
  uint32x2_t result;
  __asm__ ("mls %0.2s, %2.2s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmls_s8 (int8x8_t a, int8x8_t b, int8x8_t c)
{
  int8x8_t result;
  __asm__ ("mls %0.8b,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmls_s16 (int16x4_t a, int16x4_t b, int16x4_t c)
{
  int16x4_t result;
  __asm__ ("mls %0.4h,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmls_s32 (int32x2_t a, int32x2_t b, int32x2_t c)
{
  int32x2_t result;
  __asm__ ("mls %0.2s,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmls_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c)
{
  uint8x8_t result;
  __asm__ ("mls %0.8b,%2.8b,%3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmls_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c)
{
  uint16x4_t result;
  __asm__ ("mls %0.4h,%2.4h,%3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmls_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c)
{
  uint32x2_t result;
  __asm__ ("mls %0.2s,%2.2s,%3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

#define vmlsl_high_lane_s16(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       int16x4_t c_ = (c);                                              \
       int16x8_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_lane_s32(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t c_ = (c);                                              \
       int32x4_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlsl2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_lane_u16(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       uint16x4_t c_ = (c);                                             \
       uint16x8_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_lane_u32(a, b, c, d)                                 \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t c_ = (c);                                             \
       uint32x4_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlsl2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_laneq_s16(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t c_ = (c);                                              \
       int16x8_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_laneq_s32(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t c_ = (c);                                              \
       int32x4_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlsl2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_laneq_u16(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t c_ = (c);                                             \
       uint16x8_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_high_laneq_u32(a, b, c, d)                                \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t c_ = (c);                                             \
       uint32x4_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlsl2 %0.2d, %2.4s, %3.s[%4]"                         \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsl_high_n_s16 (int32x4_t a, int16x8_t b, int16_t c)
{
  int32x4_t result;
  __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlsl_high_n_s32 (int64x2_t a, int32x4_t b, int32_t c)
{
  int64x2_t result;
  __asm__ ("smlsl2 %0.2d, %2.4s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsl_high_n_u16 (uint32x4_t a, uint16x8_t b, uint16_t c)
{
  uint32x4_t result;
  __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlsl_high_n_u32 (uint64x2_t a, uint32x4_t b, uint32_t c)
{
  uint64x2_t result;
  __asm__ ("umlsl2 %0.2d, %2.4s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlsl_high_s8 (int16x8_t a, int8x16_t b, int8x16_t c)
{
  int16x8_t result;
  __asm__ ("smlsl2 %0.8h,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsl_high_s16 (int32x4_t a, int16x8_t b, int16x8_t c)
{
  int32x4_t result;
  __asm__ ("smlsl2 %0.4s,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlsl_high_s32 (int64x2_t a, int32x4_t b, int32x4_t c)
{
  int64x2_t result;
  __asm__ ("smlsl2 %0.2d,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlsl_high_u8 (uint16x8_t a, uint8x16_t b, uint8x16_t c)
{
  uint16x8_t result;
  __asm__ ("umlsl2 %0.8h,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsl_high_u16 (uint32x4_t a, uint16x8_t b, uint16x8_t c)
{
  uint32x4_t result;
  __asm__ ("umlsl2 %0.4s,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlsl_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c)
{
  uint64x2_t result;
  __asm__ ("umlsl2 %0.2d,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

#define vmlsl_lane_s16(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       int16x4_t c_ = (c);                                              \
       int16x4_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlsl %0.4s, %2.4h, %3.h[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_lane_s32(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t c_ = (c);                                              \
       int32x2_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlsl %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_lane_u16(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint16x4_t c_ = (c);                                             \
       uint16x4_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlsl %0.4s, %2.4h, %3.h[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_lane_u32(a, b, c, d)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t c_ = (c);                                             \
       uint32x2_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlsl %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_laneq_s16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t c_ = (c);                                              \
       int16x4_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smlsl %0.4s, %2.4h, %3.h[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_laneq_s32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t c_ = (c);                                              \
       int32x2_t b_ = (b);                                              \
       int64x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smlsl %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_laneq_u16(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t c_ = (c);                                             \
       uint16x4_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umlsl %0.4s, %2.4h, %3.h[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "x"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmlsl_laneq_u32(a, b, c, d)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t c_ = (c);                                             \
       uint32x2_t b_ = (b);                                             \
       uint64x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umlsl %0.2d, %2.2s, %3.s[%4]"                          \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "w"(c_), "i"(d)                     \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsl_n_s16 (int32x4_t a, int16x4_t b, int16_t c)
{
  int32x4_t result;
  __asm__ ("smlsl %0.4s, %2.4h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlsl_n_s32 (int64x2_t a, int32x2_t b, int32_t c)
{
  int64x2_t result;
  __asm__ ("smlsl %0.2d, %2.2s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsl_n_u16 (uint32x4_t a, uint16x4_t b, uint16_t c)
{
  uint32x4_t result;
  __asm__ ("umlsl %0.4s, %2.4h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlsl_n_u32 (uint64x2_t a, uint32x2_t b, uint32_t c)
{
  uint64x2_t result;
  __asm__ ("umlsl %0.2d, %2.2s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlsl_s8 (int16x8_t a, int8x8_t b, int8x8_t c)
{
  int16x8_t result;
  __asm__ ("smlsl %0.8h, %2.8b, %3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsl_s16 (int32x4_t a, int16x4_t b, int16x4_t c)
{
  int32x4_t result;
  __asm__ ("smlsl %0.4s, %2.4h, %3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmlsl_s32 (int64x2_t a, int32x2_t b, int32x2_t c)
{
  int64x2_t result;
  __asm__ ("smlsl %0.2d, %2.2s, %3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlsl_u8 (uint16x8_t a, uint8x8_t b, uint8x8_t c)
{
  uint16x8_t result;
  __asm__ ("umlsl %0.8h, %2.8b, %3.8b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsl_u16 (uint32x4_t a, uint16x4_t b, uint16x4_t c)
{
  uint32x4_t result;
  __asm__ ("umlsl %0.4s, %2.4h, %3.4h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmlsl_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c)
{
  uint64x2_t result;
  __asm__ ("umlsl %0.2d, %2.2s, %3.2s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlsq_n_f32 (float32x4_t a, float32x4_t b, float32_t c)
{
  float32x4_t result;
  float32x4_t t1;
  __asm__ ("fmul %1.4s, %3.4s, %4.s[0]; fsub %0.4s, %0.4s, %1.4s"
           : "=w"(result), "=w"(t1)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlsq_n_s16 (int16x8_t a, int16x8_t b, int16_t c)
{
  int16x8_t result;
  __asm__ ("mls %0.8h, %2.8h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsq_n_s32 (int32x4_t a, int32x4_t b, int32_t c)
{
  int32x4_t result;
  __asm__ ("mls %0.4s, %2.4s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlsq_n_u16 (uint16x8_t a, uint16x8_t b, uint16_t c)
{
  uint16x8_t result;
  __asm__ ("mls %0.8h, %2.8h, %3.h[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "x"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsq_n_u32 (uint32x4_t a, uint32x4_t b, uint32_t c)
{
  uint32x4_t result;
  __asm__ ("mls %0.4s, %2.4s, %3.s[0]"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmlsq_s8 (int8x16_t a, int8x16_t b, int8x16_t c)
{
  int8x16_t result;
  __asm__ ("mls %0.16b,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlsq_s16 (int16x8_t a, int16x8_t b, int16x8_t c)
{
  int16x8_t result;
  __asm__ ("mls %0.8h,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsq_s32 (int32x4_t a, int32x4_t b, int32x4_t c)
{
  int32x4_t result;
  __asm__ ("mls %0.4s,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmlsq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c)
{
  uint8x16_t result;
  __asm__ ("mls %0.16b,%2.16b,%3.16b"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlsq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c)
{
  uint16x8_t result;
  __asm__ ("mls %0.8h,%2.8h,%3.8h"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c)
{
  uint32x4_t result;
  __asm__ ("mls %0.4s,%2.4s,%3.4s"
           : "=w"(result)
           : "0"(a), "w"(b), "w"(c)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmovl_high_s8 (int8x16_t a)
{
  int16x8_t result;
  __asm__ ("sshll2 %0.8h,%1.16b,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmovl_high_s16 (int16x8_t a)
{
  int32x4_t result;
  __asm__ ("sshll2 %0.4s,%1.8h,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmovl_high_s32 (int32x4_t a)
{
  int64x2_t result;
  __asm__ ("sshll2 %0.2d,%1.4s,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmovl_high_u8 (uint8x16_t a)
{
  uint16x8_t result;
  __asm__ ("ushll2 %0.8h,%1.16b,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmovl_high_u16 (uint16x8_t a)
{
  uint32x4_t result;
  __asm__ ("ushll2 %0.4s,%1.8h,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmovl_high_u32 (uint32x4_t a)
{
  uint64x2_t result;
  __asm__ ("ushll2 %0.2d,%1.4s,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmovl_s8 (int8x8_t a)
{
  int16x8_t result;
  __asm__ ("sshll %0.8h,%1.8b,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmovl_s16 (int16x4_t a)
{
  int32x4_t result;
  __asm__ ("sshll %0.4s,%1.4h,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmovl_s32 (int32x2_t a)
{
  int64x2_t result;
  __asm__ ("sshll %0.2d,%1.2s,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmovl_u8 (uint8x8_t a)
{
  uint16x8_t result;
  __asm__ ("ushll %0.8h,%1.8b,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmovl_u16 (uint16x4_t a)
{
  uint32x4_t result;
  __asm__ ("ushll %0.4s,%1.4h,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmovl_u32 (uint32x2_t a)
{
  uint64x2_t result;
  __asm__ ("ushll %0.2d,%1.2s,#0"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmovn_high_s16 (int8x8_t a, int16x8_t b)
{
  int8x16_t result = vcombine_s8 (a, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("xtn2 %0.16b,%1.8h"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmovn_high_s32 (int16x4_t a, int32x4_t b)
{
  int16x8_t result = vcombine_s16 (a, vcreate_s16 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("xtn2 %0.8h,%1.4s"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmovn_high_s64 (int32x2_t a, int64x2_t b)
{
  int32x4_t result = vcombine_s32 (a, vcreate_s32 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("xtn2 %0.4s,%1.2d"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmovn_high_u16 (uint8x8_t a, uint16x8_t b)
{
  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("xtn2 %0.16b,%1.8h"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmovn_high_u32 (uint16x4_t a, uint32x4_t b)
{
  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("xtn2 %0.8h,%1.4s"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmovn_high_u64 (uint32x2_t a, uint64x2_t b)
{
  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("xtn2 %0.4s,%1.2d"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmovn_s16 (int16x8_t a)
{
  int8x8_t result;
  __asm__ ("xtn %0.8b,%1.8h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmovn_s32 (int32x4_t a)
{
  int16x4_t result;
  __asm__ ("xtn %0.4h,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmovn_s64 (int64x2_t a)
{
  int32x2_t result;
  __asm__ ("xtn %0.2s,%1.2d"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmovn_u16 (uint16x8_t a)
{
  uint8x8_t result;
  __asm__ ("xtn %0.8b,%1.8h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmovn_u32 (uint32x4_t a)
{
  uint16x4_t result;
  __asm__ ("xtn %0.4h,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmovn_u64 (uint64x2_t a)
{
  uint32x2_t result;
  __asm__ ("xtn %0.2s,%1.2d"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_n_f32 (float32x2_t a, float32_t b)
{
  float32x2_t result;
  __asm__ ("fmul %0.2s,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmul_n_s16 (int16x4_t a, int16_t b)
{
  int16x4_t result;
  __asm__ ("mul %0.4h,%1.4h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmul_n_s32 (int32x2_t a, int32_t b)
{
  int32x2_t result;
  __asm__ ("mul %0.2s,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmul_n_u16 (uint16x4_t a, uint16_t b)
{
  uint16x4_t result;
  __asm__ ("mul %0.4h,%1.4h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmul_n_u32 (uint32x2_t a, uint32_t b)
{
  uint32x2_t result;
  __asm__ ("mul %0.2s,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

#define vmull_high_lane_s16(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       int16x4_t b_ = (b);                                              \
       int16x8_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smull2 %0.4s, %1.8h, %2.h[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_lane_s32(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smull2 %0.2d, %1.4s, %2.s[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_lane_u16(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       uint16x4_t b_ = (b);                                             \
       uint16x8_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umull2 %0.4s, %1.8h, %2.h[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_lane_u32(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umull2 %0.2d, %1.4s, %2.s[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_laneq_s16(a, b, c)                                   \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       int16x8_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smull2 %0.4s, %1.8h, %2.h[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_laneq_s32(a, b, c)                                   \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       int32x4_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smull2 %0.2d, %1.4s, %2.s[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_laneq_u16(a, b, c)                                   \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t b_ = (b);                                             \
       uint16x8_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umull2 %0.4s, %1.8h, %2.h[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_high_laneq_u32(a, b, c)                                   \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t b_ = (b);                                             \
       uint32x4_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umull2 %0.2d, %1.4s, %2.s[%3]"                         \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmull_high_n_s16 (int16x8_t a, int16_t b)
{
  int32x4_t result;
  __asm__ ("smull2 %0.4s,%1.8h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmull_high_n_s32 (int32x4_t a, int32_t b)
{
  int64x2_t result;
  __asm__ ("smull2 %0.2d,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmull_high_n_u16 (uint16x8_t a, uint16_t b)
{
  uint32x4_t result;
  __asm__ ("umull2 %0.4s,%1.8h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmull_high_n_u32 (uint32x4_t a, uint32_t b)
{
  uint64x2_t result;
  __asm__ ("umull2 %0.2d,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vmull_high_p8 (poly8x16_t a, poly8x16_t b)
{
  poly16x8_t result;
  __asm__ ("pmull2 %0.8h,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmull_high_s8 (int8x16_t a, int8x16_t b)
{
  int16x8_t result;
  __asm__ ("smull2 %0.8h,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmull_high_s16 (int16x8_t a, int16x8_t b)
{
  int32x4_t result;
  __asm__ ("smull2 %0.4s,%1.8h,%2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmull_high_s32 (int32x4_t a, int32x4_t b)
{
  int64x2_t result;
  __asm__ ("smull2 %0.2d,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmull_high_u8 (uint8x16_t a, uint8x16_t b)
{
  uint16x8_t result;
  __asm__ ("umull2 %0.8h,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmull_high_u16 (uint16x8_t a, uint16x8_t b)
{
  uint32x4_t result;
  __asm__ ("umull2 %0.4s,%1.8h,%2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmull_high_u32 (uint32x4_t a, uint32x4_t b)
{
  uint64x2_t result;
  __asm__ ("umull2 %0.2d,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

#define vmull_lane_s16(a, b, c)                                         \
  __extension__                                                         \
    ({                                                                  \
       int16x4_t b_ = (b);                                              \
       int16x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smull %0.4s,%1.4h,%2.h[%3]"                            \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_lane_s32(a, b, c)                                         \
  __extension__                                                         \
    ({                                                                  \
       int32x2_t b_ = (b);                                              \
       int32x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smull %0.2d,%1.2s,%2.s[%3]"                            \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_lane_u16(a, b, c)                                         \
  __extension__                                                         \
    ({                                                                  \
       uint16x4_t b_ = (b);                                             \
       uint16x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umull %0.4s,%1.4h,%2.h[%3]"                            \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_lane_u32(a, b, c)                                         \
  __extension__                                                         \
    ({                                                                  \
       uint32x2_t b_ = (b);                                             \
       uint32x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umull %0.2d, %1.2s, %2.s[%3]"                          \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_laneq_s16(a, b, c)                                        \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       int16x4_t a_ = (a);                                              \
       int32x4_t result;                                                \
       __asm__ ("smull %0.4s, %1.4h, %2.h[%3]"                          \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_laneq_s32(a, b, c)                                        \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       int32x2_t a_ = (a);                                              \
       int64x2_t result;                                                \
       __asm__ ("smull %0.2d, %1.2s, %2.s[%3]"                          \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_laneq_u16(a, b, c)                                        \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t b_ = (b);                                             \
       uint16x4_t a_ = (a);                                             \
       uint32x4_t result;                                               \
       __asm__ ("umull %0.4s, %1.4h, %2.h[%3]"                          \
                : "=w"(result)                                          \
                : "w"(a_), "x"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vmull_laneq_u32(a, b, c)                                        \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t b_ = (b);                                             \
       uint32x2_t a_ = (a);                                             \
       uint64x2_t result;                                               \
       __asm__ ("umull %0.2d, %1.2s, %2.s[%3]"                          \
                : "=w"(result)                                          \
                : "w"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmull_n_s16 (int16x4_t a, int16_t b)
{
  int32x4_t result;
  __asm__ ("smull %0.4s,%1.4h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmull_n_s32 (int32x2_t a, int32_t b)
{
  int64x2_t result;
  __asm__ ("smull %0.2d,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmull_n_u16 (uint16x4_t a, uint16_t b)
{
  uint32x4_t result;
  __asm__ ("umull %0.4s,%1.4h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmull_n_u32 (uint32x2_t a, uint32_t b)
{
  uint64x2_t result;
  __asm__ ("umull %0.2d,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vmull_p8 (poly8x8_t a, poly8x8_t b)
{
  poly16x8_t result;
  __asm__ ("pmull %0.8h, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmull_s8 (int8x8_t a, int8x8_t b)
{
  int16x8_t result;
  __asm__ ("smull %0.8h, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmull_s16 (int16x4_t a, int16x4_t b)
{
  int32x4_t result;
  __asm__ ("smull %0.4s, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmull_s32 (int32x2_t a, int32x2_t b)
{
  int64x2_t result;
  __asm__ ("smull %0.2d, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmull_u8 (uint8x8_t a, uint8x8_t b)
{
  uint16x8_t result;
  __asm__ ("umull %0.8h, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmull_u16 (uint16x4_t a, uint16x4_t b)
{
  uint32x4_t result;
  __asm__ ("umull %0.4s, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmull_u32 (uint32x2_t a, uint32x2_t b)
{
  uint64x2_t result;
  __asm__ ("umull %0.2d, %1.2s, %2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_n_f32 (float32x4_t a, float32_t b)
{
  float32x4_t result;
  __asm__ ("fmul %0.4s,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulq_n_f64 (float64x2_t a, float64_t b)
{
  float64x2_t result;
  __asm__ ("fmul %0.2d,%1.2d,%2.d[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmulq_n_s16 (int16x8_t a, int16_t b)
{
  int16x8_t result;
  __asm__ ("mul %0.8h,%1.8h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmulq_n_s32 (int32x4_t a, int32_t b)
{
  int32x4_t result;
  __asm__ ("mul %0.4s,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmulq_n_u16 (uint16x8_t a, uint16_t b)
{
  uint16x8_t result;
  __asm__ ("mul %0.8h,%1.8h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmulq_n_u32 (uint32x4_t a, uint32_t b)
{
  uint32x4_t result;
  __asm__ ("mul %0.4s,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vmvn_p8 (poly8x8_t a)
{
  poly8x8_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmvn_s8 (int8x8_t a)
{
  int8x8_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmvn_s16 (int16x4_t a)
{
  int16x4_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmvn_s32 (int32x2_t a)
{
  int32x2_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmvn_u8 (uint8x8_t a)
{
  uint8x8_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmvn_u16 (uint16x4_t a)
{
  uint16x4_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmvn_u32 (uint32x2_t a)
{
  uint32x2_t result;
  __asm__ ("mvn %0.8b,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vmvnq_p8 (poly8x16_t a)
{
  poly8x16_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmvnq_s8 (int8x16_t a)
{
  int8x16_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmvnq_s16 (int16x8_t a)
{
  int16x8_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmvnq_s32 (int32x4_t a)
{
  int32x4_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmvnq_u8 (uint8x16_t a)
{
  uint8x16_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmvnq_u16 (uint16x8_t a)
{
  uint16x8_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmvnq_u32 (uint32x4_t a)
{
  uint32x4_t result;
  __asm__ ("mvn %0.16b,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}


__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vpadal_s8 (int16x4_t a, int8x8_t b)
{
  int16x4_t result;
  __asm__ ("sadalp %0.4h,%2.8b"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vpadal_s16 (int32x2_t a, int16x4_t b)
{
  int32x2_t result;
  __asm__ ("sadalp %0.2s,%2.4h"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vpadal_s32 (int64x1_t a, int32x2_t b)
{
  int64x1_t result;
  __asm__ ("sadalp %0.1d,%2.2s"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vpadal_u8 (uint16x4_t a, uint8x8_t b)
{
  uint16x4_t result;
  __asm__ ("uadalp %0.4h,%2.8b"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vpadal_u16 (uint32x2_t a, uint16x4_t b)
{
  uint32x2_t result;
  __asm__ ("uadalp %0.2s,%2.4h"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vpadal_u32 (uint64x1_t a, uint32x2_t b)
{
  uint64x1_t result;
  __asm__ ("uadalp %0.1d,%2.2s"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vpadalq_s8 (int16x8_t a, int8x16_t b)
{
  int16x8_t result;
  __asm__ ("sadalp %0.8h,%2.16b"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vpadalq_s16 (int32x4_t a, int16x8_t b)
{
  int32x4_t result;
  __asm__ ("sadalp %0.4s,%2.8h"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vpadalq_s32 (int64x2_t a, int32x4_t b)
{
  int64x2_t result;
  __asm__ ("sadalp %0.2d,%2.4s"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vpadalq_u8 (uint16x8_t a, uint8x16_t b)
{
  uint16x8_t result;
  __asm__ ("uadalp %0.8h,%2.16b"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vpadalq_u16 (uint32x4_t a, uint16x8_t b)
{
  uint32x4_t result;
  __asm__ ("uadalp %0.4s,%2.8h"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vpadalq_u32 (uint64x2_t a, uint32x4_t b)
{
  uint64x2_t result;
  __asm__ ("uadalp %0.2d,%2.4s"
           : "=w"(result)
           : "0"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vpadd_f32 (float32x2_t a, float32x2_t b)
{
  float32x2_t result;
  __asm__ ("faddp %0.2s,%1.2s,%2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vpaddl_s8 (int8x8_t a)
{
  int16x4_t result;
  __asm__ ("saddlp %0.4h,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vpaddl_s16 (int16x4_t a)
{
  int32x2_t result;
  __asm__ ("saddlp %0.2s,%1.4h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vpaddl_s32 (int32x2_t a)
{
  int64x1_t result;
  __asm__ ("saddlp %0.1d,%1.2s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vpaddl_u8 (uint8x8_t a)
{
  uint16x4_t result;
  __asm__ ("uaddlp %0.4h,%1.8b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vpaddl_u16 (uint16x4_t a)
{
  uint32x2_t result;
  __asm__ ("uaddlp %0.2s,%1.4h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vpaddl_u32 (uint32x2_t a)
{
  uint64x1_t result;
  __asm__ ("uaddlp %0.1d,%1.2s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vpaddlq_s8 (int8x16_t a)
{
  int16x8_t result;
  __asm__ ("saddlp %0.8h,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vpaddlq_s16 (int16x8_t a)
{
  int32x4_t result;
  __asm__ ("saddlp %0.4s,%1.8h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vpaddlq_s32 (int32x4_t a)
{
  int64x2_t result;
  __asm__ ("saddlp %0.2d,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vpaddlq_u8 (uint8x16_t a)
{
  uint16x8_t result;
  __asm__ ("uaddlp %0.8h,%1.16b"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vpaddlq_u16 (uint16x8_t a)
{
  uint32x4_t result;
  __asm__ ("uaddlp %0.4s,%1.8h"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vpaddlq_u32 (uint32x4_t a)
{
  uint64x2_t result;
  __asm__ ("uaddlp %0.2d,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vpaddq_f32 (float32x4_t a, float32x4_t b)
{
  float32x4_t result;
  __asm__ ("faddp %0.4s,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vpaddq_f64 (float64x2_t a, float64x2_t b)
{
  float64x2_t result;
  __asm__ ("faddp %0.2d,%1.2d,%2.2d"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vpaddq_s8 (int8x16_t a, int8x16_t b)
{
  int8x16_t result;
  __asm__ ("addp %0.16b,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vpaddq_s16 (int16x8_t a, int16x8_t b)
{
  int16x8_t result;
  __asm__ ("addp %0.8h,%1.8h,%2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vpaddq_s32 (int32x4_t a, int32x4_t b)
{
  int32x4_t result;
  __asm__ ("addp %0.4s,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vpaddq_s64 (int64x2_t a, int64x2_t b)
{
  int64x2_t result;
  __asm__ ("addp %0.2d,%1.2d,%2.2d"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vpaddq_u8 (uint8x16_t a, uint8x16_t b)
{
  uint8x16_t result;
  __asm__ ("addp %0.16b,%1.16b,%2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vpaddq_u16 (uint16x8_t a, uint16x8_t b)
{
  uint16x8_t result;
  __asm__ ("addp %0.8h,%1.8h,%2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vpaddq_u32 (uint32x4_t a, uint32x4_t b)
{
  uint32x4_t result;
  __asm__ ("addp %0.4s,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vpaddq_u64 (uint64x2_t a, uint64x2_t b)
{
  uint64x2_t result;
  __asm__ ("addp %0.2d,%1.2d,%2.2d"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vpadds_f32 (float32x2_t a)
{
  float32_t result;
  __asm__ ("faddp %s0,%1.2s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqdmulh_n_s16 (int16x4_t a, int16_t b)
{
  int16x4_t result;
  __asm__ ("sqdmulh %0.4h,%1.4h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqdmulh_n_s32 (int32x2_t a, int32_t b)
{
  int32x2_t result;
  __asm__ ("sqdmulh %0.2s,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqdmulhq_n_s16 (int16x8_t a, int16_t b)
{
  int16x8_t result;
  __asm__ ("sqdmulh %0.8h,%1.8h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmulhq_n_s32 (int32x4_t a, int32_t b)
{
  int32x4_t result;
  __asm__ ("sqdmulh %0.4s,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqmovn_high_s16 (int8x8_t a, int16x8_t b)
{
  int8x16_t result = vcombine_s8 (a, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("sqxtn2 %0.16b, %1.8h"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqmovn_high_s32 (int16x4_t a, int32x4_t b)
{
  int16x8_t result = vcombine_s16 (a, vcreate_s16 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("sqxtn2 %0.8h, %1.4s"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqmovn_high_s64 (int32x2_t a, int64x2_t b)
{
  int32x4_t result = vcombine_s32 (a, vcreate_s32 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("sqxtn2 %0.4s, %1.2d"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqmovn_high_u16 (uint8x8_t a, uint16x8_t b)
{
  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("uqxtn2 %0.16b, %1.8h"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqmovn_high_u32 (uint16x4_t a, uint32x4_t b)
{
  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("uqxtn2 %0.8h, %1.4s"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqmovn_high_u64 (uint32x2_t a, uint64x2_t b)
{
  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("uqxtn2 %0.4s, %1.2d"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqmovun_high_s16 (uint8x8_t a, int16x8_t b)
{
  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("sqxtun2 %0.16b, %1.8h"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqmovun_high_s32 (uint16x4_t a, int32x4_t b)
{
  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("sqxtun2 %0.8h, %1.4s"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqmovun_high_s64 (uint32x2_t a, int64x2_t b)
{
  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("sqxtun2 %0.4s, %1.2d"
           : "+w"(result)
           : "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmulh_n_s16 (int16x4_t a, int16_t b)
{
  int16x4_t result;
  __asm__ ("sqrdmulh %0.4h,%1.4h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmulh_n_s32 (int32x2_t a, int32_t b)
{
  int32x2_t result;
  __asm__ ("sqrdmulh %0.2s,%1.2s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmulhq_n_s16 (int16x8_t a, int16_t b)
{
  int16x8_t result;
  __asm__ ("sqrdmulh %0.8h,%1.8h,%2.h[0]"
           : "=w"(result)
           : "w"(a), "x"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
{
  int32x4_t result;
  __asm__ ("sqrdmulh %0.4s,%1.4s,%2.s[0]"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

#define vqrshrn_high_n_s16(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       int8x8_t a_ = (a);                                               \
       int8x16_t result = vcombine_s8                                   \
                            (a_, vcreate_s8                             \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("sqrshrn2 %0.16b, %1.8h, #%2"                           \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrn_high_n_s32(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       int16x4_t a_ = (a);                                              \
       int16x8_t result = vcombine_s16                                  \
                            (a_, vcreate_s16                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("sqrshrn2 %0.8h, %1.4s, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrn_high_n_s64(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t b_ = (b);                                              \
       int32x2_t a_ = (a);                                              \
       int32x4_t result = vcombine_s32                                  \
                            (a_, vcreate_s32                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("sqrshrn2 %0.4s, %1.2d, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrn_high_n_u16(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t b_ = (b);                                             \
       uint8x8_t a_ = (a);                                              \
       uint8x16_t result = vcombine_u8                                  \
                             (a_, vcreate_u8                            \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("uqrshrn2 %0.16b, %1.8h, #%2"                           \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrn_high_n_u32(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t b_ = (b);                                             \
       uint16x4_t a_ = (a);                                             \
       uint16x8_t result = vcombine_u16                                 \
                             (a_, vcreate_u16                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("uqrshrn2 %0.8h, %1.4s, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrn_high_n_u64(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t b_ = (b);                                             \
       uint32x2_t a_ = (a);                                             \
       uint32x4_t result = vcombine_u32                                 \
                             (a_, vcreate_u32                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("uqrshrn2 %0.4s, %1.2d, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrun_high_n_s16(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       uint8x8_t a_ = (a);                                              \
       uint8x16_t result = vcombine_u8                                  \
                             (a_, vcreate_u8                            \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("sqrshrun2 %0.16b, %1.8h, #%2"                          \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrun_high_n_s32(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       uint16x4_t a_ = (a);                                             \
       uint16x8_t result = vcombine_u16                                 \
                             (a_, vcreate_u16                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("sqrshrun2 %0.8h, %1.4s, #%2"                           \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqrshrun_high_n_s64(a, b, c)                                    \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t b_ = (b);                                              \
       uint32x2_t a_ = (a);                                             \
       uint32x4_t result = vcombine_u32                                 \
                             (a_, vcreate_u32                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("sqrshrun2 %0.4s, %1.2d, #%2"                           \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrn_high_n_s16(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       int8x8_t a_ = (a);                                               \
       int8x16_t result = vcombine_s8                                   \
                            (a_, vcreate_s8                             \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("sqshrn2 %0.16b, %1.8h, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrn_high_n_s32(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       int16x4_t a_ = (a);                                              \
       int16x8_t result = vcombine_s16                                  \
                            (a_, vcreate_s16                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("sqshrn2 %0.8h, %1.4s, #%2"                             \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrn_high_n_s64(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t b_ = (b);                                              \
       int32x2_t a_ = (a);                                              \
       int32x4_t result = vcombine_s32                                  \
                            (a_, vcreate_s32                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("sqshrn2 %0.4s, %1.2d, #%2"                             \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrn_high_n_u16(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t b_ = (b);                                             \
       uint8x8_t a_ = (a);                                              \
       uint8x16_t result = vcombine_u8                                  \
                             (a_, vcreate_u8                            \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("uqshrn2 %0.16b, %1.8h, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrn_high_n_u32(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t b_ = (b);                                             \
       uint16x4_t a_ = (a);                                             \
       uint16x8_t result = vcombine_u16                                 \
                             (a_, vcreate_u16                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("uqshrn2 %0.8h, %1.4s, #%2"                             \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrn_high_n_u64(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t b_ = (b);                                             \
       uint32x2_t a_ = (a);                                             \
       uint32x4_t result = vcombine_u32                                 \
                             (a_, vcreate_u32                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("uqshrn2 %0.4s, %1.2d, #%2"                             \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrun_high_n_s16(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       uint8x8_t a_ = (a);                                              \
       uint8x16_t result = vcombine_u8                                  \
                             (a_, vcreate_u8                            \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("sqshrun2 %0.16b, %1.8h, #%2"                           \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrun_high_n_s32(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       uint16x4_t a_ = (a);                                             \
       uint16x8_t result = vcombine_u16                                 \
                             (a_, vcreate_u16                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("sqshrun2 %0.8h, %1.4s, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vqshrun_high_n_s64(a, b, c)                                     \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t b_ = (b);                                              \
       uint32x2_t a_ = (a);                                             \
       uint32x4_t result = vcombine_u32                                 \
                             (a_, vcreate_u32                           \
                                    (__AARCH64_UINT64_C (0x0)));        \
       __asm__ ("sqshrun2 %0.4s, %1.2d, #%2"                            \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_high_n_s16(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       int8x8_t a_ = (a);                                               \
       int8x16_t result = vcombine_s8                                   \
                            (a_, vcreate_s8                             \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("rshrn2 %0.16b,%1.8h,#%2"                               \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_high_n_s32(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       int16x4_t a_ = (a);                                              \
       int16x8_t result = vcombine_s16                                  \
                            (a_, vcreate_s16                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("rshrn2 %0.8h,%1.4s,#%2"                                \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_high_n_s64(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t b_ = (b);                                              \
       int32x2_t a_ = (a);                                              \
       int32x4_t result = vcombine_s32                                  \
                            (a_, vcreate_s32                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("rshrn2 %0.4s,%1.2d,#%2"                                \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_high_n_u16(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t b_ = (b);                                             \
       uint8x8_t a_ = (a);                                              \
       uint8x16_t result = vcombine_u8                                  \
                            (a_, vcreate_u8                             \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("rshrn2 %0.16b,%1.8h,#%2"                               \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_high_n_u32(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t b_ = (b);                                             \
       uint16x4_t a_ = (a);                                             \
       uint16x8_t result = vcombine_u16                                 \
                            (a_, vcreate_u16                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("rshrn2 %0.8h,%1.4s,#%2"                                \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_high_n_u64(a, b, c)                                      \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t b_ = (b);                                             \
       uint32x2_t a_ = (a);                                             \
       uint32x4_t result = vcombine_u32                                 \
                            (a_, vcreate_u32                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("rshrn2 %0.4s,%1.2d,#%2"                                \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_n_s16(a, b)                                              \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t a_ = (a);                                              \
       int8x8_t result;                                                 \
       __asm__ ("rshrn %0.8b,%1.8h,%2"                                  \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_n_s32(a, b)                                              \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t a_ = (a);                                              \
       int16x4_t result;                                                \
       __asm__ ("rshrn %0.4h,%1.4s,%2"                                  \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_n_s64(a, b)                                              \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t a_ = (a);                                              \
       int32x2_t result;                                                \
       __asm__ ("rshrn %0.2s,%1.2d,%2"                                  \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_n_u16(a, b)                                              \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t a_ = (a);                                             \
       uint8x8_t result;                                                \
       __asm__ ("rshrn %0.8b,%1.8h,%2"                                  \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_n_u32(a, b)                                              \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t a_ = (a);                                             \
       uint16x4_t result;                                               \
       __asm__ ("rshrn %0.4h,%1.4s,%2"                                  \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vrshrn_n_u64(a, b)                                              \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t a_ = (a);                                             \
       uint32x2_t result;                                               \
       __asm__ ("rshrn %0.2s,%1.2d,%2"                                  \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrsqrte_f32 (float32x2_t a)
{
  float32x2_t result;
  __asm__ ("frsqrte %0.2s,%1.2s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrsqrte_f64 (float64x1_t a)
{
  float64x1_t result;
  __asm__ ("frsqrte %d0,%d1"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrsqrte_u32 (uint32x2_t a)
{
  uint32x2_t result;
  __asm__ ("ursqrte %0.2s,%1.2s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vrsqrted_f64 (float64_t a)
{
  float64_t result;
  __asm__ ("frsqrte %d0,%d1"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrsqrteq_f32 (float32x4_t a)
{
  float32x4_t result;
  __asm__ ("frsqrte %0.4s,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrsqrteq_f64 (float64x2_t a)
{
  float64x2_t result;
  __asm__ ("frsqrte %0.2d,%1.2d"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrsqrteq_u32 (uint32x4_t a)
{
  uint32x4_t result;
  __asm__ ("ursqrte %0.4s,%1.4s"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vrsqrtes_f32 (float32_t a)
{
  float32_t result;
  __asm__ ("frsqrte %s0,%s1"
           : "=w"(result)
           : "w"(a)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrsqrts_f32 (float32x2_t a, float32x2_t b)
{
  float32x2_t result;
  __asm__ ("frsqrts %0.2s,%1.2s,%2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vrsqrtsd_f64 (float64_t a, float64_t b)
{
  float64_t result;
  __asm__ ("frsqrts %d0,%d1,%d2"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrsqrtsq_f32 (float32x4_t a, float32x4_t b)
{
  float32x4_t result;
  __asm__ ("frsqrts %0.4s,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrsqrtsq_f64 (float64x2_t a, float64x2_t b)
{
  float64x2_t result;
  __asm__ ("frsqrts %0.2d,%1.2d,%2.2d"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vrsqrtss_f32 (float32_t a, float32_t b)
{
  float32_t result;
  __asm__ ("frsqrts %s0,%s1,%s2"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

#define vshrn_high_n_s16(a, b, c)                                       \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t b_ = (b);                                              \
       int8x8_t a_ = (a);                                               \
       int8x16_t result = vcombine_s8                                   \
                            (a_, vcreate_s8                             \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("shrn2 %0.16b,%1.8h,#%2"                                \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_high_n_s32(a, b, c)                                       \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t b_ = (b);                                              \
       int16x4_t a_ = (a);                                              \
       int16x8_t result = vcombine_s16                                  \
                            (a_, vcreate_s16                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("shrn2 %0.8h,%1.4s,#%2"                                 \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_high_n_s64(a, b, c)                                       \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t b_ = (b);                                              \
       int32x2_t a_ = (a);                                              \
       int32x4_t result = vcombine_s32                                  \
                            (a_, vcreate_s32                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("shrn2 %0.4s,%1.2d,#%2"                                 \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_high_n_u16(a, b, c)                                       \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t b_ = (b);                                             \
       uint8x8_t a_ = (a);                                              \
       uint8x16_t result = vcombine_u8                                  \
                            (a_, vcreate_u8                             \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("shrn2 %0.16b,%1.8h,#%2"                                \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_high_n_u32(a, b, c)                                       \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t b_ = (b);                                             \
       uint16x4_t a_ = (a);                                             \
       uint16x8_t result = vcombine_u16                                 \
                            (a_, vcreate_u16                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("shrn2 %0.8h,%1.4s,#%2"                                 \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_high_n_u64(a, b, c)                                       \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t b_ = (b);                                             \
       uint32x2_t a_ = (a);                                             \
       uint32x4_t result = vcombine_u32                                 \
                            (a_, vcreate_u32                            \
                                   (__AARCH64_UINT64_C (0x0)));         \
       __asm__ ("shrn2 %0.4s,%1.2d,#%2"                                 \
                : "+w"(result)                                          \
                : "w"(b_), "i"(c)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_n_s16(a, b)                                               \
  __extension__                                                         \
    ({                                                                  \
       int16x8_t a_ = (a);                                              \
       int8x8_t result;                                                 \
       __asm__ ("shrn %0.8b,%1.8h,%2"                                   \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_n_s32(a, b)                                               \
  __extension__                                                         \
    ({                                                                  \
       int32x4_t a_ = (a);                                              \
       int16x4_t result;                                                \
       __asm__ ("shrn %0.4h,%1.4s,%2"                                   \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_n_s64(a, b)                                               \
  __extension__                                                         \
    ({                                                                  \
       int64x2_t a_ = (a);                                              \
       int32x2_t result;                                                \
       __asm__ ("shrn %0.2s,%1.2d,%2"                                   \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_n_u16(a, b)                                               \
  __extension__                                                         \
    ({                                                                  \
       uint16x8_t a_ = (a);                                             \
       uint8x8_t result;                                                \
       __asm__ ("shrn %0.8b,%1.8h,%2"                                   \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_n_u32(a, b)                                               \
  __extension__                                                         \
    ({                                                                  \
       uint32x4_t a_ = (a);                                             \
       uint16x4_t result;                                               \
       __asm__ ("shrn %0.4h,%1.4s,%2"                                   \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vshrn_n_u64(a, b)                                               \
  __extension__                                                         \
    ({                                                                  \
       uint64x2_t a_ = (a);                                             \
       uint32x2_t result;                                               \
       __asm__ ("shrn %0.2s,%1.2d,%2"                                   \
                : "=w"(result)                                          \
                : "w"(a_), "i"(b)                                       \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsli_n_p8(a, b, c)                                              \
  __extension__                                                         \
    ({                                                                  \
       poly8x8_t b_ = (b);                                              \
       poly8x8_t a_ = (a);                                              \
       poly8x8_t result;                                                \
       __asm__ ("sli %0.8b,%2.8b,%3"                                    \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsli_n_p16(a, b, c)                                             \
  __extension__                                                         \
    ({                                                                  \
       poly16x4_t b_ = (b);                                             \
       poly16x4_t a_ = (a);                                             \
       poly16x4_t result;                                               \
       __asm__ ("sli %0.4h,%2.4h,%3"                                    \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsliq_n_p8(a, b, c)                                             \
  __extension__                                                         \
    ({                                                                  \
       poly8x16_t b_ = (b);                                             \
       poly8x16_t a_ = (a);                                             \
       poly8x16_t result;                                               \
       __asm__ ("sli %0.16b,%2.16b,%3"                                  \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsliq_n_p16(a, b, c)                                            \
  __extension__                                                         \
    ({                                                                  \
       poly16x8_t b_ = (b);                                             \
       poly16x8_t a_ = (a);                                             \
       poly16x8_t result;                                               \
       __asm__ ("sli %0.8h,%2.8h,%3"                                    \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsri_n_p8(a, b, c)                                              \
  __extension__                                                         \
    ({                                                                  \
       poly8x8_t b_ = (b);                                              \
       poly8x8_t a_ = (a);                                              \
       poly8x8_t result;                                                \
       __asm__ ("sri %0.8b,%2.8b,%3"                                    \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsri_n_p16(a, b, c)                                             \
  __extension__                                                         \
    ({                                                                  \
       poly16x4_t b_ = (b);                                             \
       poly16x4_t a_ = (a);                                             \
       poly16x4_t result;                                               \
       __asm__ ("sri %0.4h,%2.4h,%3"                                    \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsriq_n_p8(a, b, c)                                             \
  __extension__                                                         \
    ({                                                                  \
       poly8x16_t b_ = (b);                                             \
       poly8x16_t a_ = (a);                                             \
       poly8x16_t result;                                               \
       __asm__ ("sri %0.16b,%2.16b,%3"                                  \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

#define vsriq_n_p16(a, b, c)                                            \
  __extension__                                                         \
    ({                                                                  \
       poly16x8_t b_ = (b);                                             \
       poly16x8_t a_ = (a);                                             \
       poly16x8_t result;                                               \
       __asm__ ("sri %0.8h,%2.8h,%3"                                    \
                : "=w"(result)                                          \
                : "0"(a_), "w"(b_), "i"(c)                              \
                : /* No clobbers */);                                   \
       result;                                                          \
     })

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtst_p8 (poly8x8_t a, poly8x8_t b)
{
  uint8x8_t result;
  __asm__ ("cmtst %0.8b, %1.8b, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtst_p16 (poly16x4_t a, poly16x4_t b)
{
  uint16x4_t result;
  __asm__ ("cmtst %0.4h, %1.4h, %2.4h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtstq_p8 (poly8x16_t a, poly8x16_t b)
{
  uint8x16_t result;
  __asm__ ("cmtst %0.16b, %1.16b, %2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtstq_p16 (poly16x8_t a, poly16x8_t b)
{
  uint16x8_t result;
  __asm__ ("cmtst %0.8h, %1.8h, %2.8h"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

/* End of temporary inline asm implementations.  */

/* Start of temporary inline asm for vldn, vstn and friends.  */

/* Create struct element types for duplicating loads.

   Create 2 element structures of:

   +------+----+----+----+----+
   |      | 8  | 16 | 32 | 64 |
   +------+----+----+----+----+
   |int   | Y  | Y  | N  | N  |
   +------+----+----+----+----+
   |uint  | Y  | Y  | N  | N  |
   +------+----+----+----+----+
   |float | -  | Y  | N  | N  |
   +------+----+----+----+----+
   |poly  | Y  | Y  | -  | -  |
   +------+----+----+----+----+

   Create 3 element structures of:

   +------+----+----+----+----+
   |      | 8  | 16 | 32 | 64 |
   +------+----+----+----+----+
   |int   | Y  | Y  | Y  | Y  |
   +------+----+----+----+----+
   |uint  | Y  | Y  | Y  | Y  |
   +------+----+----+----+----+
   |float | -  | Y  | Y  | Y  |
   +------+----+----+----+----+
   |poly  | Y  | Y  | -  | -  |
   +------+----+----+----+----+

   Create 4 element structures of:

   +------+----+----+----+----+
   |      | 8  | 16 | 32 | 64 |
   +------+----+----+----+----+
   |int   | Y  | N  | N  | Y  |
   +------+----+----+----+----+
   |uint  | Y  | N  | N  | Y  |
   +------+----+----+----+----+
   |float | -  | N  | N  | Y  |
   +------+----+----+----+----+
   |poly  | Y  | N  | -  | -  |
   +------+----+----+----+----+

  This is required for casting memory reference.  */
#define __STRUCTN(t, sz, nelem)                 \
  typedef struct t ## sz ## x ## nelem ## _t {  \
    t ## sz ## _t val[nelem];                   \
  }  t ## sz ## x ## nelem ## _t;

/* 2-element structs.  */
__STRUCTN (int, 8, 2)
__STRUCTN (int, 16, 2)
__STRUCTN (uint, 8, 2)
__STRUCTN (uint, 16, 2)
__STRUCTN (float, 16, 2)
__STRUCTN (poly, 8, 2)
__STRUCTN (poly, 16, 2)
/* 3-element structs.  */
__STRUCTN (int, 8, 3)
__STRUCTN (int, 16, 3)
__STRUCTN (int, 32, 3)
__STRUCTN (int, 64, 3)
__STRUCTN (uint, 8, 3)
__STRUCTN (uint, 16, 3)
__STRUCTN (uint, 32, 3)
__STRUCTN (uint, 64, 3)
__STRUCTN (float, 16, 3)
__STRUCTN (float, 32, 3)
__STRUCTN (float, 64, 3)
__STRUCTN (poly, 8, 3)
__STRUCTN (poly, 16, 3)
/* 4-element structs.  */
__STRUCTN (int, 8, 4)
__STRUCTN (int, 64, 4)
__STRUCTN (uint, 8, 4)
__STRUCTN (uint, 64, 4)
__STRUCTN (poly, 8, 4)
__STRUCTN (float, 64, 4)
#undef __STRUCTN


#define __ST2_LANE_FUNC(intype, largetype, ptrtype, mode,                    \
                        qmode, ptr_mode, funcsuffix, signedtype)             \
__extension__ static __inline void                                           \
__attribute__ ((__always_inline__))                                          \
vst2_lane_ ## funcsuffix (ptrtype *__ptr,                                    \
                          intype __b, const int __c)                         \
{                                                                            \
  __builtin_aarch64_simd_oi __o;                                             \
  largetype __temp;                                                          \
  __temp.val[0]                                                              \
    = vcombine_##funcsuffix (__b.val[0],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __temp.val[1]                                                              \
    = vcombine_##funcsuffix (__b.val[1],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __o = __builtin_aarch64_set_qregoi##qmode (__o,                            \
                                             (signedtype) __temp.val[0], 0); \
  __o = __builtin_aarch64_set_qregoi##qmode (__o,                            \
                                             (signedtype) __temp.val[1], 1); \
  __builtin_aarch64_st2_lane##mode ((__builtin_aarch64_simd_ ## ptr_mode *)  \
                                     __ptr, __o, __c);                       \
}

__ST2_LANE_FUNC (float16x4x2_t, float16x8x2_t, float16_t, v4hf, v8hf, hf, f16,
                 float16x8_t)
__ST2_LANE_FUNC (float32x2x2_t, float32x4x2_t, float32_t, v2sf, v4sf, sf, f32,
                 float32x4_t)
__ST2_LANE_FUNC (float64x1x2_t, float64x2x2_t, float64_t, df, v2df, df, f64,
                 float64x2_t)
__ST2_LANE_FUNC (poly8x8x2_t, poly8x16x2_t, poly8_t, v8qi, v16qi, qi, p8,
                 int8x16_t)
__ST2_LANE_FUNC (poly16x4x2_t, poly16x8x2_t, poly16_t, v4hi, v8hi, hi, p16,
                 int16x8_t)
__ST2_LANE_FUNC (int8x8x2_t, int8x16x2_t, int8_t, v8qi, v16qi, qi, s8,
                 int8x16_t)
__ST2_LANE_FUNC (int16x4x2_t, int16x8x2_t, int16_t, v4hi, v8hi, hi, s16,
                 int16x8_t)
__ST2_LANE_FUNC (int32x2x2_t, int32x4x2_t, int32_t, v2si, v4si, si, s32,
                 int32x4_t)
__ST2_LANE_FUNC (int64x1x2_t, int64x2x2_t, int64_t, di, v2di, di, s64,
                 int64x2_t)
__ST2_LANE_FUNC (uint8x8x2_t, uint8x16x2_t, uint8_t, v8qi, v16qi, qi, u8,
                 int8x16_t)
__ST2_LANE_FUNC (uint16x4x2_t, uint16x8x2_t, uint16_t, v4hi, v8hi, hi, u16,
                 int16x8_t)
__ST2_LANE_FUNC (uint32x2x2_t, uint32x4x2_t, uint32_t, v2si, v4si, si, u32,
                 int32x4_t)
__ST2_LANE_FUNC (uint64x1x2_t, uint64x2x2_t, uint64_t, di, v2di, di, u64,
                 int64x2_t)

#undef __ST2_LANE_FUNC
#define __ST2_LANE_FUNC(intype, ptrtype, mode, ptr_mode, funcsuffix)        \
__extension__ static __inline void                                          \
__attribute__ ((__always_inline__))                                         \
vst2q_lane_ ## funcsuffix (ptrtype *__ptr,                                  \
                           intype __b, const int __c)                       \
{                                                                           \
  union { intype __i;                                                       \
          __builtin_aarch64_simd_oi __o; } __temp = { __b };                \
  __builtin_aarch64_st2_lane##mode ((__builtin_aarch64_simd_ ## ptr_mode *) \
                                    __ptr, __temp.__o, __c);                \
}

__ST2_LANE_FUNC (float16x8x2_t, float16_t, v8hf, hf, f16)
__ST2_LANE_FUNC (float32x4x2_t, float32_t, v4sf, sf, f32)
__ST2_LANE_FUNC (float64x2x2_t, float64_t, v2df, df, f64)
__ST2_LANE_FUNC (poly8x16x2_t, poly8_t, v16qi, qi, p8)
__ST2_LANE_FUNC (poly16x8x2_t, poly16_t, v8hi, hi, p16)
__ST2_LANE_FUNC (int8x16x2_t, int8_t, v16qi, qi, s8)
__ST2_LANE_FUNC (int16x8x2_t, int16_t, v8hi, hi, s16)
__ST2_LANE_FUNC (int32x4x2_t, int32_t, v4si, si, s32)
__ST2_LANE_FUNC (int64x2x2_t, int64_t, v2di, di, s64)
__ST2_LANE_FUNC (uint8x16x2_t, uint8_t, v16qi, qi, u8)
__ST2_LANE_FUNC (uint16x8x2_t, uint16_t, v8hi, hi, u16)
__ST2_LANE_FUNC (uint32x4x2_t, uint32_t, v4si, si, u32)
__ST2_LANE_FUNC (uint64x2x2_t, uint64_t, v2di, di, u64)

#define __ST3_LANE_FUNC(intype, largetype, ptrtype, mode,                    \
                        qmode, ptr_mode, funcsuffix, signedtype)             \
__extension__ static __inline void                                           \
__attribute__ ((__always_inline__))                                          \
vst3_lane_ ## funcsuffix (ptrtype *__ptr,                                    \
                          intype __b, const int __c)                         \
{                                                                            \
  __builtin_aarch64_simd_ci __o;                                             \
  largetype __temp;                                                          \
  __temp.val[0]                                                              \
    = vcombine_##funcsuffix (__b.val[0],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __temp.val[1]                                                              \
    = vcombine_##funcsuffix (__b.val[1],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __temp.val[2]                                                              \
    = vcombine_##funcsuffix (__b.val[2],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __o = __builtin_aarch64_set_qregci##qmode (__o,                            \
                                             (signedtype) __temp.val[0], 0); \
  __o = __builtin_aarch64_set_qregci##qmode (__o,                            \
                                             (signedtype) __temp.val[1], 1); \
  __o = __builtin_aarch64_set_qregci##qmode (__o,                            \
                                             (signedtype) __temp.val[2], 2); \
  __builtin_aarch64_st3_lane##mode ((__builtin_aarch64_simd_ ## ptr_mode *)  \
                                     __ptr, __o, __c);                       \
}

__ST3_LANE_FUNC (float16x4x3_t, float16x8x3_t, float16_t, v4hf, v8hf, hf, f16,
                 float16x8_t)
__ST3_LANE_FUNC (float32x2x3_t, float32x4x3_t, float32_t, v2sf, v4sf, sf, f32,
                 float32x4_t)
__ST3_LANE_FUNC (float64x1x3_t, float64x2x3_t, float64_t, df, v2df, df, f64,
                 float64x2_t)
__ST3_LANE_FUNC (poly8x8x3_t, poly8x16x3_t, poly8_t, v8qi, v16qi, qi, p8,
                 int8x16_t)
__ST3_LANE_FUNC (poly16x4x3_t, poly16x8x3_t, poly16_t, v4hi, v8hi, hi, p16,
                 int16x8_t)
__ST3_LANE_FUNC (int8x8x3_t, int8x16x3_t, int8_t, v8qi, v16qi, qi, s8,
                 int8x16_t)
__ST3_LANE_FUNC (int16x4x3_t, int16x8x3_t, int16_t, v4hi, v8hi, hi, s16,
                 int16x8_t)
__ST3_LANE_FUNC (int32x2x3_t, int32x4x3_t, int32_t, v2si, v4si, si, s32,
                 int32x4_t)
__ST3_LANE_FUNC (int64x1x3_t, int64x2x3_t, int64_t, di, v2di, di, s64,
                 int64x2_t)
__ST3_LANE_FUNC (uint8x8x3_t, uint8x16x3_t, uint8_t, v8qi, v16qi, qi, u8,
                 int8x16_t)
__ST3_LANE_FUNC (uint16x4x3_t, uint16x8x3_t, uint16_t, v4hi, v8hi, hi, u16,
                 int16x8_t)
__ST3_LANE_FUNC (uint32x2x3_t, uint32x4x3_t, uint32_t, v2si, v4si, si, u32,
                 int32x4_t)
__ST3_LANE_FUNC (uint64x1x3_t, uint64x2x3_t, uint64_t, di, v2di, di, u64,
                 int64x2_t)

#undef __ST3_LANE_FUNC
#define __ST3_LANE_FUNC(intype, ptrtype, mode, ptr_mode, funcsuffix)        \
__extension__ static __inline void                                          \
__attribute__ ((__always_inline__))                                         \
vst3q_lane_ ## funcsuffix (ptrtype *__ptr,                                  \
                           intype __b, const int __c)                       \
{                                                                           \
  union { intype __i;                                                       \
          __builtin_aarch64_simd_ci __o; } __temp = { __b };                \
  __builtin_aarch64_st3_lane##mode ((__builtin_aarch64_simd_ ## ptr_mode *) \
                                    __ptr, __temp.__o, __c);                \
}

__ST3_LANE_FUNC (float16x8x3_t, float16_t, v8hf, hf, f16)
__ST3_LANE_FUNC (float32x4x3_t, float32_t, v4sf, sf, f32)
__ST3_LANE_FUNC (float64x2x3_t, float64_t, v2df, df, f64)
__ST3_LANE_FUNC (poly8x16x3_t, poly8_t, v16qi, qi, p8)
__ST3_LANE_FUNC (poly16x8x3_t, poly16_t, v8hi, hi, p16)
__ST3_LANE_FUNC (int8x16x3_t, int8_t, v16qi, qi, s8)
__ST3_LANE_FUNC (int16x8x3_t, int16_t, v8hi, hi, s16)
__ST3_LANE_FUNC (int32x4x3_t, int32_t, v4si, si, s32)
__ST3_LANE_FUNC (int64x2x3_t, int64_t, v2di, di, s64)
__ST3_LANE_FUNC (uint8x16x3_t, uint8_t, v16qi, qi, u8)
__ST3_LANE_FUNC (uint16x8x3_t, uint16_t, v8hi, hi, u16)
__ST3_LANE_FUNC (uint32x4x3_t, uint32_t, v4si, si, u32)
__ST3_LANE_FUNC (uint64x2x3_t, uint64_t, v2di, di, u64)

#define __ST4_LANE_FUNC(intype, largetype, ptrtype, mode,                    \
                        qmode, ptr_mode, funcsuffix, signedtype)             \
__extension__ static __inline void                                           \
__attribute__ ((__always_inline__))                                          \
vst4_lane_ ## funcsuffix (ptrtype *__ptr,                                    \
                          intype __b, const int __c)                         \
{                                                                            \
  __builtin_aarch64_simd_xi __o;                                             \
  largetype __temp;                                                          \
  __temp.val[0]                                                              \
    = vcombine_##funcsuffix (__b.val[0],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __temp.val[1]                                                              \
    = vcombine_##funcsuffix (__b.val[1],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __temp.val[2]                                                              \
    = vcombine_##funcsuffix (__b.val[2],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __temp.val[3]                                                              \
    = vcombine_##funcsuffix (__b.val[3],                                     \
                             vcreate_##funcsuffix (__AARCH64_UINT64_C (0))); \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                            \
                                             (signedtype) __temp.val[0], 0); \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                            \
                                             (signedtype) __temp.val[1], 1); \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                            \
                                             (signedtype) __temp.val[2], 2); \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                            \
                                             (signedtype) __temp.val[3], 3); \
  __builtin_aarch64_st4_lane##mode ((__builtin_aarch64_simd_ ## ptr_mode *)  \
                                     __ptr, __o, __c);                       \
}

__ST4_LANE_FUNC (float16x4x4_t, float16x8x4_t, float16_t, v4hf, v8hf, hf, f16,
                 float16x8_t)
__ST4_LANE_FUNC (float32x2x4_t, float32x4x4_t, float32_t, v2sf, v4sf, sf, f32,
                 float32x4_t)
__ST4_LANE_FUNC (float64x1x4_t, float64x2x4_t, float64_t, df, v2df, df, f64,
                 float64x2_t)
__ST4_LANE_FUNC (poly8x8x4_t, poly8x16x4_t, poly8_t, v8qi, v16qi, qi, p8,
                 int8x16_t)
__ST4_LANE_FUNC (poly16x4x4_t, poly16x8x4_t, poly16_t, v4hi, v8hi, hi, p16,
                 int16x8_t)
__ST4_LANE_FUNC (int8x8x4_t, int8x16x4_t, int8_t, v8qi, v16qi, qi, s8,
                 int8x16_t)
__ST4_LANE_FUNC (int16x4x4_t, int16x8x4_t, int16_t, v4hi, v8hi, hi, s16,
                 int16x8_t)
__ST4_LANE_FUNC (int32x2x4_t, int32x4x4_t, int32_t, v2si, v4si, si, s32,
                 int32x4_t)
__ST4_LANE_FUNC (int64x1x4_t, int64x2x4_t, int64_t, di, v2di, di, s64,
                 int64x2_t)
__ST4_LANE_FUNC (uint8x8x4_t, uint8x16x4_t, uint8_t, v8qi, v16qi, qi, u8,
                 int8x16_t)
__ST4_LANE_FUNC (uint16x4x4_t, uint16x8x4_t, uint16_t, v4hi, v8hi, hi, u16,
                 int16x8_t)
__ST4_LANE_FUNC (uint32x2x4_t, uint32x4x4_t, uint32_t, v2si, v4si, si, u32,
                 int32x4_t)
__ST4_LANE_FUNC (uint64x1x4_t, uint64x2x4_t, uint64_t, di, v2di, di, u64,
                 int64x2_t)

#undef __ST4_LANE_FUNC
#define __ST4_LANE_FUNC(intype, ptrtype, mode, ptr_mode, funcsuffix)        \
__extension__ static __inline void                                          \
__attribute__ ((__always_inline__))                                         \
vst4q_lane_ ## funcsuffix (ptrtype *__ptr,                                  \
                           intype __b, const int __c)                       \
{                                                                           \
  union { intype __i;                                                       \
          __builtin_aarch64_simd_xi __o; } __temp = { __b };                \
  __builtin_aarch64_st4_lane##mode ((__builtin_aarch64_simd_ ## ptr_mode *) \
                                    __ptr, __temp.__o, __c);                \
}

__ST4_LANE_FUNC (float16x8x4_t, float16_t, v8hf, hf, f16)
__ST4_LANE_FUNC (float32x4x4_t, float32_t, v4sf, sf, f32)
__ST4_LANE_FUNC (float64x2x4_t, float64_t, v2df, df, f64)
__ST4_LANE_FUNC (poly8x16x4_t, poly8_t, v16qi, qi, p8)
__ST4_LANE_FUNC (poly16x8x4_t, poly16_t, v8hi, hi, p16)
__ST4_LANE_FUNC (int8x16x4_t, int8_t, v16qi, qi, s8)
__ST4_LANE_FUNC (int16x8x4_t, int16_t, v8hi, hi, s16)
__ST4_LANE_FUNC (int32x4x4_t, int32_t, v4si, si, s32)
__ST4_LANE_FUNC (int64x2x4_t, int64_t, v2di, di, s64)
__ST4_LANE_FUNC (uint8x16x4_t, uint8_t, v16qi, qi, u8)
__ST4_LANE_FUNC (uint16x8x4_t, uint16_t, v8hi, hi, u16)
__ST4_LANE_FUNC (uint32x4x4_t, uint32_t, v4si, si, u32)
__ST4_LANE_FUNC (uint64x2x4_t, uint64_t, v2di, di, u64)

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vaddlv_s32 (int32x2_t a)
{
  int64_t result;
  __asm__ ("saddlp %0.1d, %1.2s" : "=w"(result) : "w"(a) : );
  return result;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vaddlv_u32 (uint32x2_t a)
{
  uint64_t result;
  __asm__ ("uaddlp %0.1d, %1.2s" : "=w"(result) : "w"(a) : );
  return result;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqdmulh_laneq_s16 (int16x4_t __a, int16x8_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_laneqv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqdmulh_laneq_s32 (int32x2_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_laneqv2si (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqdmulhq_laneq_s16 (int16x8_t __a, int16x8_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_laneqv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmulhq_laneq_s32 (int32x4_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_laneqv4si (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmulh_laneq_s16 (int16x4_t __a, int16x8_t __b, const int __c)
{
  return  __builtin_aarch64_sqrdmulh_laneqv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmulh_laneq_s32 (int32x2_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_laneqv2si (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmulhq_laneq_s16 (int16x8_t __a, int16x8_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_laneqv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmulhq_laneq_s32 (int32x4_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_laneqv4si (__a, __b, __c);
}

/* Table intrinsics.  */

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl1_p8 (poly8x16_t a, uint8x8_t b)
{
  poly8x8_t result;
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl1_s8 (int8x16_t a, uint8x8_t b)
{
  int8x8_t result;
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl1_u8 (uint8x16_t a, uint8x8_t b)
{
  uint8x8_t result;
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl1q_p8 (poly8x16_t a, uint8x16_t b)
{
  poly8x16_t result;
  __asm__ ("tbl %0.16b, {%1.16b}, %2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl1q_s8 (int8x16_t a, uint8x16_t b)
{
  int8x16_t result;
  __asm__ ("tbl %0.16b, {%1.16b}, %2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl1q_u8 (uint8x16_t a, uint8x16_t b)
{
  uint8x16_t result;
  __asm__ ("tbl %0.16b, {%1.16b}, %2.16b"
           : "=w"(result)
           : "w"(a), "w"(b)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx1_s8 (int8x8_t r, int8x16_t tab, uint8x8_t idx)
{
  int8x8_t result = r;
  __asm__ ("tbx %0.8b,{%1.16b},%2.8b"
           : "+w"(result)
           : "w"(tab), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx1_u8 (uint8x8_t r, uint8x16_t tab, uint8x8_t idx)
{
  uint8x8_t result = r;
  __asm__ ("tbx %0.8b,{%1.16b},%2.8b"
           : "+w"(result)
           : "w"(tab), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx1_p8 (poly8x8_t r, poly8x16_t tab, uint8x8_t idx)
{
  poly8x8_t result = r;
  __asm__ ("tbx %0.8b,{%1.16b},%2.8b"
           : "+w"(result)
           : "w"(tab), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx1q_s8 (int8x16_t r, int8x16_t tab, uint8x16_t idx)
{
  int8x16_t result = r;
  __asm__ ("tbx %0.16b,{%1.16b},%2.16b"
           : "+w"(result)
           : "w"(tab), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx1q_u8 (uint8x16_t r, uint8x16_t tab, uint8x16_t idx)
{
  uint8x16_t result = r;
  __asm__ ("tbx %0.16b,{%1.16b},%2.16b"
           : "+w"(result)
           : "w"(tab), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx1q_p8 (poly8x16_t r, poly8x16_t tab, uint8x16_t idx)
{
  poly8x16_t result = r;
  __asm__ ("tbx %0.16b,{%1.16b},%2.16b"
           : "+w"(result)
           : "w"(tab), "w"(idx)
           : /* No clobbers */);
  return result;
}

/* V7 legacy table intrinsics.  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbl1_s8 (int8x8_t tab, int8x8_t idx)
{
  int8x8_t result;
  int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbl1_u8 (uint8x8_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbl1_p8 (poly8x8_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (__AARCH64_UINT64_C (0x0)));
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbl2_s8 (int8x8x2_t tab, int8x8_t idx)
{
  int8x8_t result;
  int8x16_t temp = vcombine_s8 (tab.val[0], tab.val[1]);
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbl2_u8 (uint8x8x2_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  uint8x16_t temp = vcombine_u8 (tab.val[0], tab.val[1]);
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbl2_p8 (poly8x8x2_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  poly8x16_t temp = vcombine_p8 (tab.val[0], tab.val[1]);
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbl3_s8 (int8x8x3_t tab, int8x8_t idx)
{
  int8x8_t result;
  int8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]);
  temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (__AARCH64_UINT64_C (0x0)));
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = __builtin_aarch64_tbl3v8qi (__o, idx);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbl3_u8 (uint8x8x3_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  uint8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]);
  temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (__AARCH64_UINT64_C (0x0)));
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = (uint8x8_t)__builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbl3_p8 (poly8x8x3_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  poly8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]);
  temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (__AARCH64_UINT64_C (0x0)));
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = (poly8x8_t)__builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbl4_s8 (int8x8x4_t tab, int8x8_t idx)
{
  int8x8_t result;
  int8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]);
  temp.val[1] = vcombine_s8 (tab.val[2], tab.val[3]);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = __builtin_aarch64_tbl3v8qi (__o, idx);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbl4_u8 (uint8x8x4_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  uint8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]);
  temp.val[1] = vcombine_u8 (tab.val[2], tab.val[3]);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = (uint8x8_t)__builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbl4_p8 (poly8x8x4_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  poly8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]);
  temp.val[1] = vcombine_p8 (tab.val[2], tab.val[3]);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = (poly8x8_t)__builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbx2_s8 (int8x8_t r, int8x8x2_t tab, int8x8_t idx)
{
  int8x8_t result = r;
  int8x16_t temp = vcombine_s8 (tab.val[0], tab.val[1]);
  __asm__ ("tbx %0.8b, {%1.16b}, %2.8b"
           : "+w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbx2_u8 (uint8x8_t r, uint8x8x2_t tab, uint8x8_t idx)
{
  uint8x8_t result = r;
  uint8x16_t temp = vcombine_u8 (tab.val[0], tab.val[1]);
  __asm__ ("tbx %0.8b, {%1.16b}, %2.8b"
           : "+w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbx2_p8 (poly8x8_t r, poly8x8x2_t tab, uint8x8_t idx)
{
  poly8x8_t result = r;
  poly8x16_t temp = vcombine_p8 (tab.val[0], tab.val[1]);
  __asm__ ("tbx %0.8b, {%1.16b}, %2.8b"
           : "+w"(result)
           : "w"(temp), "w"(idx)
           : /* No clobbers */);
  return result;
}

/* End of temporary inline asm.  */

/* Start of optimal implementations in approved order.  */

/* vabs  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vabs_f32 (float32x2_t __a)
{
  return __builtin_aarch64_absv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vabs_f64 (float64x1_t __a)
{
  return (float64x1_t) {__builtin_fabs (__a[0])};
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vabs_s8 (int8x8_t __a)
{
  return __builtin_aarch64_absv8qi (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vabs_s16 (int16x4_t __a)
{
  return __builtin_aarch64_absv4hi (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vabs_s32 (int32x2_t __a)
{
  return __builtin_aarch64_absv2si (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vabs_s64 (int64x1_t __a)
{
  return (int64x1_t) {__builtin_aarch64_absdi (__a[0])};
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vabsq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_absv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vabsq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_absv2df (__a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vabsq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_absv16qi (__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vabsq_s16 (int16x8_t __a)
{
  return __builtin_aarch64_absv8hi (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vabsq_s32 (int32x4_t __a)
{
  return __builtin_aarch64_absv4si (__a);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vabsq_s64 (int64x2_t __a)
{
  return __builtin_aarch64_absv2di (__a);
}

/* vadd */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vaddd_s64 (int64_t __a, int64_t __b)
{
  return __a + __b;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vaddd_u64 (uint64_t __a, uint64_t __b)
{
  return __a + __b;
}

/* vaddv */

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vaddv_s8 (int8x8_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v8qi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vaddv_s16 (int16x4_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v4hi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vaddv_s32 (int32x2_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v2si (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vaddv_u8 (uint8x8_t __a)
{
  return (uint8_t) __builtin_aarch64_reduc_plus_scal_v8qi ((int8x8_t) __a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vaddv_u16 (uint16x4_t __a)
{
  return (uint16_t) __builtin_aarch64_reduc_plus_scal_v4hi ((int16x4_t) __a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vaddv_u32 (uint32x2_t __a)
{
  return (int32_t) __builtin_aarch64_reduc_plus_scal_v2si ((int32x2_t) __a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vaddvq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v16qi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vaddvq_s16 (int16x8_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v8hi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vaddvq_s32 (int32x4_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v4si (__a);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vaddvq_s64 (int64x2_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v2di (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vaddvq_u8 (uint8x16_t __a)
{
  return (uint8_t) __builtin_aarch64_reduc_plus_scal_v16qi ((int8x16_t) __a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vaddvq_u16 (uint16x8_t __a)
{
  return (uint16_t) __builtin_aarch64_reduc_plus_scal_v8hi ((int16x8_t) __a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vaddvq_u32 (uint32x4_t __a)
{
  return (uint32_t) __builtin_aarch64_reduc_plus_scal_v4si ((int32x4_t) __a);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vaddvq_u64 (uint64x2_t __a)
{
  return (uint64_t) __builtin_aarch64_reduc_plus_scal_v2di ((int64x2_t) __a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vaddv_f32 (float32x2_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v2sf (__a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vaddvq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v4sf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vaddvq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v2df (__a);
}

/* vbsl  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vbsl_f32 (uint32x2_t __a, float32x2_t __b, float32x2_t __c)
{
  return __builtin_aarch64_simd_bslv2sf_suss (__a, __b, __c);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vbsl_f64 (uint64x1_t __a, float64x1_t __b, float64x1_t __c)
{
  return (float64x1_t)
    { __builtin_aarch64_simd_bsldf_suss (__a[0], __b[0], __c[0]) };
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vbsl_p8 (uint8x8_t __a, poly8x8_t __b, poly8x8_t __c)
{
  return __builtin_aarch64_simd_bslv8qi_pupp (__a, __b, __c);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vbsl_p16 (uint16x4_t __a, poly16x4_t __b, poly16x4_t __c)
{
  return __builtin_aarch64_simd_bslv4hi_pupp (__a, __b, __c);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vbsl_s8 (uint8x8_t __a, int8x8_t __b, int8x8_t __c)
{
  return __builtin_aarch64_simd_bslv8qi_suss (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vbsl_s16 (uint16x4_t __a, int16x4_t __b, int16x4_t __c)
{
  return __builtin_aarch64_simd_bslv4hi_suss (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vbsl_s32 (uint32x2_t __a, int32x2_t __b, int32x2_t __c)
{
  return __builtin_aarch64_simd_bslv2si_suss (__a, __b, __c);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vbsl_s64 (uint64x1_t __a, int64x1_t __b, int64x1_t __c)
{
  return (int64x1_t)
      {__builtin_aarch64_simd_bsldi_suss (__a[0], __b[0], __c[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vbsl_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c)
{
  return __builtin_aarch64_simd_bslv8qi_uuuu (__a, __b, __c);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vbsl_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c)
{
  return __builtin_aarch64_simd_bslv4hi_uuuu (__a, __b, __c);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vbsl_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c)
{
  return __builtin_aarch64_simd_bslv2si_uuuu (__a, __b, __c);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vbsl_u64 (uint64x1_t __a, uint64x1_t __b, uint64x1_t __c)
{
  return (uint64x1_t)
      {__builtin_aarch64_simd_bsldi_uuuu (__a[0], __b[0], __c[0])};
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vbslq_f32 (uint32x4_t __a, float32x4_t __b, float32x4_t __c)
{
  return __builtin_aarch64_simd_bslv4sf_suss (__a, __b, __c);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vbslq_f64 (uint64x2_t __a, float64x2_t __b, float64x2_t __c)
{
  return __builtin_aarch64_simd_bslv2df_suss (__a, __b, __c);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vbslq_p8 (uint8x16_t __a, poly8x16_t __b, poly8x16_t __c)
{
  return __builtin_aarch64_simd_bslv16qi_pupp (__a, __b, __c);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vbslq_p16 (uint16x8_t __a, poly16x8_t __b, poly16x8_t __c)
{
  return __builtin_aarch64_simd_bslv8hi_pupp (__a, __b, __c);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vbslq_s8 (uint8x16_t __a, int8x16_t __b, int8x16_t __c)
{
  return __builtin_aarch64_simd_bslv16qi_suss (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vbslq_s16 (uint16x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return __builtin_aarch64_simd_bslv8hi_suss (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vbslq_s32 (uint32x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return __builtin_aarch64_simd_bslv4si_suss (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vbslq_s64 (uint64x2_t __a, int64x2_t __b, int64x2_t __c)
{
  return __builtin_aarch64_simd_bslv2di_suss (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vbslq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c)
{
  return __builtin_aarch64_simd_bslv16qi_uuuu (__a, __b, __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vbslq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
  return __builtin_aarch64_simd_bslv8hi_uuuu (__a, __b, __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vbslq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
  return __builtin_aarch64_simd_bslv4si_uuuu (__a, __b, __c);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vbslq_u64 (uint64x2_t __a, uint64x2_t __b, uint64x2_t __c)
{
  return __builtin_aarch64_simd_bslv2di_uuuu (__a, __b, __c);
}

/* ARMv8.1 instrinsics.  */
#pragma GCC push_options
#pragma GCC target ("arch=armv8.1-a")

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmlah_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c)
{
  return __builtin_aarch64_sqrdmlahv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmlah_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c)
{
  return __builtin_aarch64_sqrdmlahv2si (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmlahq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return __builtin_aarch64_sqrdmlahv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmlahq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return __builtin_aarch64_sqrdmlahv4si (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmlsh_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c)
{
  return __builtin_aarch64_sqrdmlshv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmlsh_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c)
{
  return __builtin_aarch64_sqrdmlshv2si (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmlshq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c)
{
  return __builtin_aarch64_sqrdmlshv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmlshq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c)
{
  return __builtin_aarch64_sqrdmlshv4si (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmlah_laneq_s16 (int16x4_t __a, int16x4_t __b, int16x8_t __c, const int __d)
{
  return  __builtin_aarch64_sqrdmlah_laneqv4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmlah_laneq_s32 (int32x2_t __a, int32x2_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_laneqv2si (__a, __b, __c, __d);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmlahq_laneq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_laneqv8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmlahq_laneq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_laneqv4si (__a, __b, __c, __d);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmlsh_laneq_s16 (int16x4_t __a, int16x4_t __b, int16x8_t __c, const int __d)
{
  return  __builtin_aarch64_sqrdmlsh_laneqv4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmlsh_laneq_s32 (int32x2_t __a, int32x2_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_laneqv2si (__a, __b, __c, __d);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmlshq_laneq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_laneqv8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmlshq_laneq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_laneqv4si (__a, __b, __c, __d);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmlah_lane_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c, const int __d)
{
  return  __builtin_aarch64_sqrdmlah_lanev4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmlah_lane_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_lanev2si (__a, __b, __c, __d);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmlahq_lane_s16 (int16x8_t __a, int16x8_t __b, int16x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_lanev8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmlahq_lane_s32 (int32x4_t __a, int32x4_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_lanev4si (__a, __b, __c, __d);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmlahh_s16 (int16_t __a, int16_t __b, int16_t __c)
{
  return (int16_t) __builtin_aarch64_sqrdmlahhi (__a, __b, __c);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmlahh_lane_s16 (int16_t __a, int16_t __b, int16x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_lanehi (__a, __b, __c, __d);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmlahh_laneq_s16 (int16_t __a, int16_t __b, int16x8_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_laneqhi (__a, __b, __c, __d);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmlahs_s32 (int32_t __a, int32_t __b, int32_t __c)
{
  return (int32_t) __builtin_aarch64_sqrdmlahsi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmlahs_lane_s32 (int32_t __a, int32_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_lanesi (__a, __b, __c, __d);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmlahs_laneq_s32 (int32_t __a, int32_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlah_laneqsi (__a, __b, __c, __d);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmlsh_lane_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c, const int __d)
{
  return  __builtin_aarch64_sqrdmlsh_lanev4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmlsh_lane_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_lanev2si (__a, __b, __c, __d);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmlshq_lane_s16 (int16x8_t __a, int16x8_t __b, int16x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_lanev8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmlshq_lane_s32 (int32x4_t __a, int32x4_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_lanev4si (__a, __b, __c, __d);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmlshh_s16 (int16_t __a, int16_t __b, int16_t __c)
{
  return (int16_t) __builtin_aarch64_sqrdmlshhi (__a, __b, __c);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmlshh_lane_s16 (int16_t __a, int16_t __b, int16x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_lanehi (__a, __b, __c, __d);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmlshh_laneq_s16 (int16_t __a, int16_t __b, int16x8_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_laneqhi (__a, __b, __c, __d);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmlshs_s32 (int32_t __a, int32_t __b, int32_t __c)
{
  return (int32_t) __builtin_aarch64_sqrdmlshsi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmlshs_lane_s32 (int32_t __a, int32_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_lanesi (__a, __b, __c, __d);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmlshs_laneq_s32 (int32_t __a, int32_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqrdmlsh_laneqsi (__a, __b, __c, __d);
}
#pragma GCC pop_options

#pragma GCC push_options
#pragma GCC target ("+nothing+crypto")
/* vaes  */

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vaeseq_u8 (uint8x16_t data, uint8x16_t key)
{
  return __builtin_aarch64_crypto_aesev16qi_uuu (data, key);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vaesdq_u8 (uint8x16_t data, uint8x16_t key)
{
  return __builtin_aarch64_crypto_aesdv16qi_uuu (data, key);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vaesmcq_u8 (uint8x16_t data)
{
  return __builtin_aarch64_crypto_aesmcv16qi_uu (data);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vaesimcq_u8 (uint8x16_t data)
{
  return __builtin_aarch64_crypto_aesimcv16qi_uu (data);
}
#pragma GCC pop_options

/* vcage  */

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcage_f64 (float64x1_t __a, float64x1_t __b)
{
  return vabs_f64 (__a) >= vabs_f64 (__b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcages_f32 (float32_t __a, float32_t __b)
{
  return __builtin_fabsf (__a) >= __builtin_fabsf (__b) ? -1 : 0;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcage_f32 (float32x2_t __a, float32x2_t __b)
{
  return vabs_f32 (__a) >= vabs_f32 (__b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcageq_f32 (float32x4_t __a, float32x4_t __b)
{
  return vabsq_f32 (__a) >= vabsq_f32 (__b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcaged_f64 (float64_t __a, float64_t __b)
{
  return __builtin_fabs (__a) >= __builtin_fabs (__b) ? -1 : 0;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcageq_f64 (float64x2_t __a, float64x2_t __b)
{
  return vabsq_f64 (__a) >= vabsq_f64 (__b);
}

/* vcagt  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcagts_f32 (float32_t __a, float32_t __b)
{
  return __builtin_fabsf (__a) > __builtin_fabsf (__b) ? -1 : 0;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcagt_f32 (float32x2_t __a, float32x2_t __b)
{
  return vabs_f32 (__a) > vabs_f32 (__b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcagt_f64 (float64x1_t __a, float64x1_t __b)
{
  return vabs_f64 (__a) > vabs_f64 (__b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcagtq_f32 (float32x4_t __a, float32x4_t __b)
{
  return vabsq_f32 (__a) > vabsq_f32 (__b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcagtd_f64 (float64_t __a, float64_t __b)
{
  return __builtin_fabs (__a) > __builtin_fabs (__b) ? -1 : 0;
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcagtq_f64 (float64x2_t __a, float64x2_t __b)
{
  return vabsq_f64 (__a) > vabsq_f64 (__b);
}

/* vcale  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcale_f32 (float32x2_t __a, float32x2_t __b)
{
  return vabs_f32 (__a) <= vabs_f32 (__b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcale_f64 (float64x1_t __a, float64x1_t __b)
{
  return vabs_f64 (__a) <= vabs_f64 (__b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcaled_f64 (float64_t __a, float64_t __b)
{
  return __builtin_fabs (__a) <= __builtin_fabs (__b) ? -1 : 0;
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcales_f32 (float32_t __a, float32_t __b)
{
  return __builtin_fabsf (__a) <= __builtin_fabsf (__b) ? -1 : 0;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcaleq_f32 (float32x4_t __a, float32x4_t __b)
{
  return vabsq_f32 (__a) <= vabsq_f32 (__b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcaleq_f64 (float64x2_t __a, float64x2_t __b)
{
  return vabsq_f64 (__a) <= vabsq_f64 (__b);
}

/* vcalt  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcalt_f32 (float32x2_t __a, float32x2_t __b)
{
  return vabs_f32 (__a) < vabs_f32 (__b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcalt_f64 (float64x1_t __a, float64x1_t __b)
{
  return vabs_f64 (__a) < vabs_f64 (__b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcaltd_f64 (float64_t __a, float64_t __b)
{
  return __builtin_fabs (__a) < __builtin_fabs (__b) ? -1 : 0;
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcaltq_f32 (float32x4_t __a, float32x4_t __b)
{
  return vabsq_f32 (__a) < vabsq_f32 (__b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcaltq_f64 (float64x2_t __a, float64x2_t __b)
{
  return vabsq_f64 (__a) < vabsq_f64 (__b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcalts_f32 (float32_t __a, float32_t __b)
{
  return __builtin_fabsf (__a) < __builtin_fabsf (__b) ? -1 : 0;
}

/* vceq - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vceq_f32 (float32x2_t __a, float32x2_t __b)
{
  return (uint32x2_t) (__a == __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vceq_f64 (float64x1_t __a, float64x1_t __b)
{
  return (uint64x1_t) (__a == __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vceq_p8 (poly8x8_t __a, poly8x8_t __b)
{
  return (uint8x8_t) (__a == __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vceq_s8 (int8x8_t __a, int8x8_t __b)
{
  return (uint8x8_t) (__a == __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vceq_s16 (int16x4_t __a, int16x4_t __b)
{
  return (uint16x4_t) (__a == __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vceq_s32 (int32x2_t __a, int32x2_t __b)
{
  return (uint32x2_t) (__a == __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vceq_s64 (int64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) (__a == __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vceq_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vceq_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vceq_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vceq_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vceqq_f32 (float32x4_t __a, float32x4_t __b)
{
  return (uint32x4_t) (__a == __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vceqq_f64 (float64x2_t __a, float64x2_t __b)
{
  return (uint64x2_t) (__a == __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vceqq_p8 (poly8x16_t __a, poly8x16_t __b)
{
  return (uint8x16_t) (__a == __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vceqq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (uint8x16_t) (__a == __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vceqq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (uint16x8_t) (__a == __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vceqq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (uint32x4_t) (__a == __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vceqq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (uint64x2_t) (__a == __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vceqq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vceqq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vceqq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (__a == __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vceqq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (__a == __b);
}

/* vceq - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vceqs_f32 (float32_t __a, float32_t __b)
{
  return __a == __b ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vceqd_s64 (int64_t __a, int64_t __b)
{
  return __a == __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vceqd_u64 (uint64_t __a, uint64_t __b)
{
  return __a == __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vceqd_f64 (float64_t __a, float64_t __b)
{
  return __a == __b ? -1ll : 0ll;
}

/* vceqz - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vceqz_f32 (float32x2_t __a)
{
  return (uint32x2_t) (__a == 0.0f);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vceqz_f64 (float64x1_t __a)
{
  return (uint64x1_t) (__a == (float64x1_t) {0.0});
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vceqz_p8 (poly8x8_t __a)
{
  return (uint8x8_t) (__a == 0);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vceqz_s8 (int8x8_t __a)
{
  return (uint8x8_t) (__a == 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vceqz_s16 (int16x4_t __a)
{
  return (uint16x4_t) (__a == 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vceqz_s32 (int32x2_t __a)
{
  return (uint32x2_t) (__a == 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vceqz_s64 (int64x1_t __a)
{
  return (uint64x1_t) (__a == __AARCH64_INT64_C (0));
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vceqz_u8 (uint8x8_t __a)
{
  return (__a == 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vceqz_u16 (uint16x4_t __a)
{
  return (__a == 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vceqz_u32 (uint32x2_t __a)
{
  return (__a == 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vceqz_u64 (uint64x1_t __a)
{
  return (__a == __AARCH64_UINT64_C (0));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vceqzq_f32 (float32x4_t __a)
{
  return (uint32x4_t) (__a == 0.0f);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vceqzq_f64 (float64x2_t __a)
{
  return (uint64x2_t) (__a == 0.0f);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vceqzq_p8 (poly8x16_t __a)
{
  return (uint8x16_t) (__a == 0);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vceqzq_s8 (int8x16_t __a)
{
  return (uint8x16_t) (__a == 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vceqzq_s16 (int16x8_t __a)
{
  return (uint16x8_t) (__a == 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vceqzq_s32 (int32x4_t __a)
{
  return (uint32x4_t) (__a == 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vceqzq_s64 (int64x2_t __a)
{
  return (uint64x2_t) (__a == __AARCH64_INT64_C (0));
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vceqzq_u8 (uint8x16_t __a)
{
  return (__a == 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vceqzq_u16 (uint16x8_t __a)
{
  return (__a == 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vceqzq_u32 (uint32x4_t __a)
{
  return (__a == 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vceqzq_u64 (uint64x2_t __a)
{
  return (__a == __AARCH64_UINT64_C (0));
}

/* vceqz - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vceqzs_f32 (float32_t __a)
{
  return __a == 0.0f ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vceqzd_s64 (int64_t __a)
{
  return __a == 0 ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vceqzd_u64 (uint64_t __a)
{
  return __a == 0 ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vceqzd_f64 (float64_t __a)
{
  return __a == 0.0 ? -1ll : 0ll;
}

/* vcge - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcge_f32 (float32x2_t __a, float32x2_t __b)
{
  return (uint32x2_t) (__a >= __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcge_f64 (float64x1_t __a, float64x1_t __b)
{
  return (uint64x1_t) (__a >= __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcge_s8 (int8x8_t __a, int8x8_t __b)
{
  return (uint8x8_t) (__a >= __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcge_s16 (int16x4_t __a, int16x4_t __b)
{
  return (uint16x4_t) (__a >= __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcge_s32 (int32x2_t __a, int32x2_t __b)
{
  return (uint32x2_t) (__a >= __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcge_s64 (int64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) (__a >= __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcge_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcge_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcge_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcge_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgeq_f32 (float32x4_t __a, float32x4_t __b)
{
  return (uint32x4_t) (__a >= __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgeq_f64 (float64x2_t __a, float64x2_t __b)
{
  return (uint64x2_t) (__a >= __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcgeq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (uint8x16_t) (__a >= __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcgeq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (uint16x8_t) (__a >= __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgeq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (uint32x4_t) (__a >= __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgeq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (uint64x2_t) (__a >= __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcgeq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcgeq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgeq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (__a >= __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgeq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (__a >= __b);
}

/* vcge - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcges_f32 (float32_t __a, float32_t __b)
{
  return __a >= __b ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcged_s64 (int64_t __a, int64_t __b)
{
  return __a >= __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcged_u64 (uint64_t __a, uint64_t __b)
{
  return __a >= __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcged_f64 (float64_t __a, float64_t __b)
{
  return __a >= __b ? -1ll : 0ll;
}

/* vcgez - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgez_f32 (float32x2_t __a)
{
  return (uint32x2_t) (__a >= 0.0f);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgez_f64 (float64x1_t __a)
{
  return (uint64x1_t) (__a[0] >= (float64x1_t) {0.0});
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcgez_s8 (int8x8_t __a)
{
  return (uint8x8_t) (__a >= 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcgez_s16 (int16x4_t __a)
{
  return (uint16x4_t) (__a >= 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgez_s32 (int32x2_t __a)
{
  return (uint32x2_t) (__a >= 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgez_s64 (int64x1_t __a)
{
  return (uint64x1_t) (__a >= __AARCH64_INT64_C (0));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgezq_f32 (float32x4_t __a)
{
  return (uint32x4_t) (__a >= 0.0f);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgezq_f64 (float64x2_t __a)
{
  return (uint64x2_t) (__a >= 0.0);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcgezq_s8 (int8x16_t __a)
{
  return (uint8x16_t) (__a >= 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcgezq_s16 (int16x8_t __a)
{
  return (uint16x8_t) (__a >= 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgezq_s32 (int32x4_t __a)
{
  return (uint32x4_t) (__a >= 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgezq_s64 (int64x2_t __a)
{
  return (uint64x2_t) (__a >= __AARCH64_INT64_C (0));
}

/* vcgez - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcgezs_f32 (float32_t __a)
{
  return __a >= 0.0f ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgezd_s64 (int64_t __a)
{
  return __a >= 0 ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgezd_f64 (float64_t __a)
{
  return __a >= 0.0 ? -1ll : 0ll;
}

/* vcgt - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgt_f32 (float32x2_t __a, float32x2_t __b)
{
  return (uint32x2_t) (__a > __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgt_f64 (float64x1_t __a, float64x1_t __b)
{
  return (uint64x1_t) (__a > __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcgt_s8 (int8x8_t __a, int8x8_t __b)
{
  return (uint8x8_t) (__a > __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcgt_s16 (int16x4_t __a, int16x4_t __b)
{
  return (uint16x4_t) (__a > __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgt_s32 (int32x2_t __a, int32x2_t __b)
{
  return (uint32x2_t) (__a > __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgt_s64 (int64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) (__a > __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcgt_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcgt_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgt_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgt_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgtq_f32 (float32x4_t __a, float32x4_t __b)
{
  return (uint32x4_t) (__a > __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgtq_f64 (float64x2_t __a, float64x2_t __b)
{
  return (uint64x2_t) (__a > __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcgtq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (uint8x16_t) (__a > __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcgtq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (uint16x8_t) (__a > __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgtq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (uint32x4_t) (__a > __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgtq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (uint64x2_t) (__a > __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcgtq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcgtq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgtq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (__a > __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgtq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (__a > __b);
}

/* vcgt - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcgts_f32 (float32_t __a, float32_t __b)
{
  return __a > __b ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgtd_s64 (int64_t __a, int64_t __b)
{
  return __a > __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgtd_u64 (uint64_t __a, uint64_t __b)
{
  return __a > __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgtd_f64 (float64_t __a, float64_t __b)
{
  return __a > __b ? -1ll : 0ll;
}

/* vcgtz - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgtz_f32 (float32x2_t __a)
{
  return (uint32x2_t) (__a > 0.0f);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgtz_f64 (float64x1_t __a)
{
  return (uint64x1_t) (__a > (float64x1_t) {0.0});
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcgtz_s8 (int8x8_t __a)
{
  return (uint8x8_t) (__a > 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcgtz_s16 (int16x4_t __a)
{
  return (uint16x4_t) (__a > 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcgtz_s32 (int32x2_t __a)
{
  return (uint32x2_t) (__a > 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcgtz_s64 (int64x1_t __a)
{
  return (uint64x1_t) (__a > __AARCH64_INT64_C (0));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgtzq_f32 (float32x4_t __a)
{
  return (uint32x4_t) (__a > 0.0f);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgtzq_f64 (float64x2_t __a)
{
    return (uint64x2_t) (__a > 0.0);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcgtzq_s8 (int8x16_t __a)
{
  return (uint8x16_t) (__a > 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcgtzq_s16 (int16x8_t __a)
{
  return (uint16x8_t) (__a > 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcgtzq_s32 (int32x4_t __a)
{
  return (uint32x4_t) (__a > 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcgtzq_s64 (int64x2_t __a)
{
  return (uint64x2_t) (__a > __AARCH64_INT64_C (0));
}

/* vcgtz - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcgtzs_f32 (float32_t __a)
{
  return __a > 0.0f ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgtzd_s64 (int64_t __a)
{
  return __a > 0 ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcgtzd_f64 (float64_t __a)
{
  return __a > 0.0 ? -1ll : 0ll;
}

/* vcle - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcle_f32 (float32x2_t __a, float32x2_t __b)
{
  return (uint32x2_t) (__a <= __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcle_f64 (float64x1_t __a, float64x1_t __b)
{
  return (uint64x1_t) (__a <= __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcle_s8 (int8x8_t __a, int8x8_t __b)
{
  return (uint8x8_t) (__a <= __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcle_s16 (int16x4_t __a, int16x4_t __b)
{
  return (uint16x4_t) (__a <= __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcle_s32 (int32x2_t __a, int32x2_t __b)
{
  return (uint32x2_t) (__a <= __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcle_s64 (int64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) (__a <= __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcle_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcle_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcle_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcle_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcleq_f32 (float32x4_t __a, float32x4_t __b)
{
  return (uint32x4_t) (__a <= __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcleq_f64 (float64x2_t __a, float64x2_t __b)
{
  return (uint64x2_t) (__a <= __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcleq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (uint8x16_t) (__a <= __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcleq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (uint16x8_t) (__a <= __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcleq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (uint32x4_t) (__a <= __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcleq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (uint64x2_t) (__a <= __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcleq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcleq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcleq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (__a <= __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcleq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (__a <= __b);
}

/* vcle - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcles_f32 (float32_t __a, float32_t __b)
{
  return __a <= __b ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcled_s64 (int64_t __a, int64_t __b)
{
  return __a <= __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcled_u64 (uint64_t __a, uint64_t __b)
{
  return __a <= __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcled_f64 (float64_t __a, float64_t __b)
{
  return __a <= __b ? -1ll : 0ll;
}

/* vclez - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vclez_f32 (float32x2_t __a)
{
  return (uint32x2_t) (__a <= 0.0f);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vclez_f64 (float64x1_t __a)
{
  return (uint64x1_t) (__a <= (float64x1_t) {0.0});
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vclez_s8 (int8x8_t __a)
{
  return (uint8x8_t) (__a <= 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vclez_s16 (int16x4_t __a)
{
  return (uint16x4_t) (__a <= 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vclez_s32 (int32x2_t __a)
{
  return (uint32x2_t) (__a <= 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vclez_s64 (int64x1_t __a)
{
  return (uint64x1_t) (__a <= __AARCH64_INT64_C (0));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vclezq_f32 (float32x4_t __a)
{
  return (uint32x4_t) (__a <= 0.0f);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vclezq_f64 (float64x2_t __a)
{
  return (uint64x2_t) (__a <= 0.0);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vclezq_s8 (int8x16_t __a)
{
  return (uint8x16_t) (__a <= 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vclezq_s16 (int16x8_t __a)
{
  return (uint16x8_t) (__a <= 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vclezq_s32 (int32x4_t __a)
{
  return (uint32x4_t) (__a <= 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vclezq_s64 (int64x2_t __a)
{
  return (uint64x2_t) (__a <= __AARCH64_INT64_C (0));
}

/* vclez - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vclezs_f32 (float32_t __a)
{
  return __a <= 0.0f ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vclezd_s64 (int64_t __a)
{
  return __a <= 0 ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vclezd_f64 (float64_t __a)
{
  return __a <= 0.0 ? -1ll : 0ll;
}

/* vclt - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vclt_f32 (float32x2_t __a, float32x2_t __b)
{
  return (uint32x2_t) (__a < __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vclt_f64 (float64x1_t __a, float64x1_t __b)
{
  return (uint64x1_t) (__a < __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vclt_s8 (int8x8_t __a, int8x8_t __b)
{
  return (uint8x8_t) (__a < __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vclt_s16 (int16x4_t __a, int16x4_t __b)
{
  return (uint16x4_t) (__a < __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vclt_s32 (int32x2_t __a, int32x2_t __b)
{
  return (uint32x2_t) (__a < __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vclt_s64 (int64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) (__a < __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vclt_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vclt_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vclt_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vclt_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcltq_f32 (float32x4_t __a, float32x4_t __b)
{
  return (uint32x4_t) (__a < __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcltq_f64 (float64x2_t __a, float64x2_t __b)
{
  return (uint64x2_t) (__a < __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcltq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (uint8x16_t) (__a < __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcltq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (uint16x8_t) (__a < __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcltq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (uint32x4_t) (__a < __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcltq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (uint64x2_t) (__a < __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcltq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcltq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcltq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (__a < __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcltq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return (__a < __b);
}

/* vclt - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vclts_f32 (float32_t __a, float32_t __b)
{
  return __a < __b ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcltd_s64 (int64_t __a, int64_t __b)
{
  return __a < __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcltd_u64 (uint64_t __a, uint64_t __b)
{
  return __a < __b ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcltd_f64 (float64_t __a, float64_t __b)
{
  return __a < __b ? -1ll : 0ll;
}

/* vcltz - vector.  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcltz_f32 (float32x2_t __a)
{
  return (uint32x2_t) (__a < 0.0f);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcltz_f64 (float64x1_t __a)
{
  return (uint64x1_t) (__a < (float64x1_t) {0.0});
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcltz_s8 (int8x8_t __a)
{
  return (uint8x8_t) (__a < 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vcltz_s16 (int16x4_t __a)
{
  return (uint16x4_t) (__a < 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcltz_s32 (int32x2_t __a)
{
  return (uint32x2_t) (__a < 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcltz_s64 (int64x1_t __a)
{
  return (uint64x1_t) (__a < __AARCH64_INT64_C (0));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcltzq_f32 (float32x4_t __a)
{
  return (uint32x4_t) (__a < 0.0f);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcltzq_f64 (float64x2_t __a)
{
  return (uint64x2_t) (__a < 0.0);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcltzq_s8 (int8x16_t __a)
{
  return (uint8x16_t) (__a < 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vcltzq_s16 (int16x8_t __a)
{
  return (uint16x8_t) (__a < 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcltzq_s32 (int32x4_t __a)
{
  return (uint32x4_t) (__a < 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcltzq_s64 (int64x2_t __a)
{
  return (uint64x2_t) (__a < __AARCH64_INT64_C (0));
}

/* vcltz - scalar.  */

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcltzs_f32 (float32_t __a)
{
  return __a < 0.0f ? -1 : 0;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcltzd_s64 (int64_t __a)
{
  return __a < 0 ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcltzd_f64 (float64_t __a)
{
  return __a < 0.0 ? -1ll : 0ll;
}

/* vcls.  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vcls_s8 (int8x8_t __a)
{
  return __builtin_aarch64_clrsbv8qi (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vcls_s16 (int16x4_t __a)
{
  return __builtin_aarch64_clrsbv4hi (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcls_s32 (int32x2_t __a)
{
  return __builtin_aarch64_clrsbv2si (__a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vclsq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_clrsbv16qi (__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vclsq_s16 (int16x8_t __a)
{
  return __builtin_aarch64_clrsbv8hi (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vclsq_s32 (int32x4_t __a)
{
  return __builtin_aarch64_clrsbv4si (__a);
}

/* vclz.  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vclz_s8 (int8x8_t __a)
{
  return __builtin_aarch64_clzv8qi (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vclz_s16 (int16x4_t __a)
{
  return __builtin_aarch64_clzv4hi (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vclz_s32 (int32x2_t __a)
{
  return __builtin_aarch64_clzv2si (__a);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vclz_u8 (uint8x8_t __a)
{
  return (uint8x8_t)__builtin_aarch64_clzv8qi ((int8x8_t)__a);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vclz_u16 (uint16x4_t __a)
{
  return (uint16x4_t)__builtin_aarch64_clzv4hi ((int16x4_t)__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vclz_u32 (uint32x2_t __a)
{
  return (uint32x2_t)__builtin_aarch64_clzv2si ((int32x2_t)__a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vclzq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_clzv16qi (__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vclzq_s16 (int16x8_t __a)
{
  return __builtin_aarch64_clzv8hi (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vclzq_s32 (int32x4_t __a)
{
  return __builtin_aarch64_clzv4si (__a);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vclzq_u8 (uint8x16_t __a)
{
  return (uint8x16_t)__builtin_aarch64_clzv16qi ((int8x16_t)__a);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vclzq_u16 (uint16x8_t __a)
{
  return (uint16x8_t)__builtin_aarch64_clzv8hi ((int16x8_t)__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vclzq_u32 (uint32x4_t __a)
{
  return (uint32x4_t)__builtin_aarch64_clzv4si ((int32x4_t)__a);
}

/* vcnt.  */

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vcnt_p8 (poly8x8_t __a)
{
  return (poly8x8_t) __builtin_aarch64_popcountv8qi ((int8x8_t) __a);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vcnt_s8 (int8x8_t __a)
{
  return __builtin_aarch64_popcountv8qi (__a);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vcnt_u8 (uint8x8_t __a)
{
  return (uint8x8_t) __builtin_aarch64_popcountv8qi ((int8x8_t) __a);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vcntq_p8 (poly8x16_t __a)
{
  return (poly8x16_t) __builtin_aarch64_popcountv16qi ((int8x16_t) __a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vcntq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_popcountv16qi (__a);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vcntq_u8 (uint8x16_t __a)
{
  return (uint8x16_t) __builtin_aarch64_popcountv16qi ((int8x16_t) __a);
}

/* vcvt (double -> float).  */

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vcvt_f16_f32 (float32x4_t __a)
{
  return __builtin_aarch64_float_truncate_lo_v4hf (__a);
}

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vcvt_high_f16_f32 (float16x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_float_truncate_hi_v8hf (__a, __b);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vcvt_f32_f64 (float64x2_t __a)
{
  return __builtin_aarch64_float_truncate_lo_v2sf (__a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcvt_high_f32_f64 (float32x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_float_truncate_hi_v4sf (__a, __b);
}

/* vcvt (float -> double).  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcvt_f32_f16 (float16x4_t __a)
{
  return __builtin_aarch64_float_extend_lo_v4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vcvt_f64_f32 (float32x2_t __a)
{

  return __builtin_aarch64_float_extend_lo_v2df (__a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcvt_high_f32_f16 (float16x8_t __a)
{
  return __builtin_aarch64_vec_unpacks_hi_v8hf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vcvt_high_f64_f32 (float32x4_t __a)
{
  return __builtin_aarch64_vec_unpacks_hi_v4sf (__a);
}

/* vcvt  (<u>int -> float)  */

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vcvtd_f64_s64 (int64_t __a)
{
  return (float64_t) __a;
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vcvtd_f64_u64 (uint64_t __a)
{
  return (float64_t) __a;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vcvts_f32_s32 (int32_t __a)
{
  return (float32_t) __a;
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vcvts_f32_u32 (uint32_t __a)
{
  return (float32_t) __a;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vcvt_f32_s32 (int32x2_t __a)
{
  return __builtin_aarch64_floatv2siv2sf (__a);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vcvt_f32_u32 (uint32x2_t __a)
{
  return __builtin_aarch64_floatunsv2siv2sf ((int32x2_t) __a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcvtq_f32_s32 (int32x4_t __a)
{
  return __builtin_aarch64_floatv4siv4sf (__a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vcvtq_f32_u32 (uint32x4_t __a)
{
  return __builtin_aarch64_floatunsv4siv4sf ((int32x4_t) __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vcvtq_f64_s64 (int64x2_t __a)
{
  return __builtin_aarch64_floatv2div2df (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vcvtq_f64_u64 (uint64x2_t __a)
{
  return __builtin_aarch64_floatunsv2div2df ((int64x2_t) __a);
}

/* vcvt (float -> <u>int)  */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vcvtd_s64_f64 (float64_t __a)
{
  return (int64_t) __a;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcvtd_u64_f64 (float64_t __a)
{
  return (uint64_t) __a;
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vcvts_s32_f32 (float32_t __a)
{
  return (int32_t) __a;
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcvts_u32_f32 (float32_t __a)
{
  return (uint32_t) __a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcvt_s32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lbtruncv2sfv2si (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcvt_u32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lbtruncuv2sfv2si_us (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vcvtq_s32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lbtruncv4sfv4si (__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcvtq_u32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lbtruncuv4sfv4si_us (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vcvt_s64_f64 (float64x1_t __a)
{
  return (int64x1_t) {vcvtd_s64_f64 (__a[0])};
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcvt_u64_f64 (float64x1_t __a)
{
  return (uint64x1_t) {vcvtd_u64_f64 (__a[0])};
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vcvtq_s64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lbtruncv2dfv2di (__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcvtq_u64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lbtruncuv2dfv2di_us (__a);
}

/* vcvta  */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vcvtad_s64_f64 (float64_t __a)
{
  return __builtin_aarch64_lrounddfdi (__a);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcvtad_u64_f64 (float64_t __a)
{
  return __builtin_aarch64_lroundudfdi_us (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vcvtas_s32_f32 (float32_t __a)
{
  return __builtin_aarch64_lroundsfsi (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcvtas_u32_f32 (float32_t __a)
{
  return __builtin_aarch64_lroundusfsi_us (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcvta_s32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lroundv2sfv2si (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcvta_u32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lrounduv2sfv2si_us (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vcvtaq_s32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lroundv4sfv4si (__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcvtaq_u32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lrounduv4sfv4si_us (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vcvta_s64_f64 (float64x1_t __a)
{
  return (int64x1_t) {vcvtad_s64_f64 (__a[0])};
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcvta_u64_f64 (float64x1_t __a)
{
  return (uint64x1_t) {vcvtad_u64_f64 (__a[0])};
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vcvtaq_s64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lroundv2dfv2di (__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcvtaq_u64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lrounduv2dfv2di_us (__a);
}

/* vcvtm  */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vcvtmd_s64_f64 (float64_t __a)
{
  return __builtin_llfloor (__a);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcvtmd_u64_f64 (float64_t __a)
{
  return __builtin_aarch64_lfloorudfdi_us (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vcvtms_s32_f32 (float32_t __a)
{
  return __builtin_ifloorf (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcvtms_u32_f32 (float32_t __a)
{
  return __builtin_aarch64_lfloorusfsi_us (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcvtm_s32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lfloorv2sfv2si (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcvtm_u32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lflooruv2sfv2si_us (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vcvtmq_s32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lfloorv4sfv4si (__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcvtmq_u32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lflooruv4sfv4si_us (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vcvtm_s64_f64 (float64x1_t __a)
{
  return (int64x1_t) {vcvtmd_s64_f64 (__a[0])};
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcvtm_u64_f64 (float64x1_t __a)
{
  return (uint64x1_t) {vcvtmd_u64_f64 (__a[0])};
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vcvtmq_s64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lfloorv2dfv2di (__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcvtmq_u64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lflooruv2dfv2di_us (__a);
}

/* vcvtn  */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vcvtnd_s64_f64 (float64_t __a)
{
  return __builtin_aarch64_lfrintndfdi (__a);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcvtnd_u64_f64 (float64_t __a)
{
  return __builtin_aarch64_lfrintnudfdi_us (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vcvtns_s32_f32 (float32_t __a)
{
  return __builtin_aarch64_lfrintnsfsi (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcvtns_u32_f32 (float32_t __a)
{
  return __builtin_aarch64_lfrintnusfsi_us (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcvtn_s32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lfrintnv2sfv2si (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcvtn_u32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lfrintnuv2sfv2si_us (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vcvtnq_s32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lfrintnv4sfv4si (__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcvtnq_u32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lfrintnuv4sfv4si_us (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vcvtn_s64_f64 (float64x1_t __a)
{
  return (int64x1_t) {vcvtnd_s64_f64 (__a[0])};
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcvtn_u64_f64 (float64x1_t __a)
{
  return (uint64x1_t) {vcvtnd_u64_f64 (__a[0])};
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vcvtnq_s64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lfrintnv2dfv2di (__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcvtnq_u64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lfrintnuv2dfv2di_us (__a);
}

/* vcvtp  */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vcvtpd_s64_f64 (float64_t __a)
{
  return __builtin_llceil (__a);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vcvtpd_u64_f64 (float64_t __a)
{
  return __builtin_aarch64_lceiludfdi_us (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vcvtps_s32_f32 (float32_t __a)
{
  return __builtin_iceilf (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vcvtps_u32_f32 (float32_t __a)
{
  return __builtin_aarch64_lceilusfsi_us (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vcvtp_s32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lceilv2sfv2si (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vcvtp_u32_f32 (float32x2_t __a)
{
  return __builtin_aarch64_lceiluv2sfv2si_us (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vcvtpq_s32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lceilv4sfv4si (__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vcvtpq_u32_f32 (float32x4_t __a)
{
  return __builtin_aarch64_lceiluv4sfv4si_us (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vcvtp_s64_f64 (float64x1_t __a)
{
  return (int64x1_t) {vcvtpd_s64_f64 (__a[0])};
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vcvtp_u64_f64 (float64x1_t __a)
{
  return (uint64x1_t) {vcvtpd_u64_f64 (__a[0])};
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vcvtpq_s64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lceilv2dfv2di (__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vcvtpq_u64_f64 (float64x2_t __a)
{
  return __builtin_aarch64_lceiluv2dfv2di_us (__a);
}

/* vdup_n  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vdup_n_f32 (float32_t __a)
{
  return (float32x2_t) {__a, __a};
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vdup_n_f64 (float64_t __a)
{
  return (float64x1_t) {__a};
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vdup_n_p8 (poly8_t __a)
{
  return (poly8x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vdup_n_p16 (poly16_t __a)
{
  return (poly16x4_t) {__a, __a, __a, __a};
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vdup_n_s8 (int8_t __a)
{
  return (int8x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vdup_n_s16 (int16_t __a)
{
  return (int16x4_t) {__a, __a, __a, __a};
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vdup_n_s32 (int32_t __a)
{
  return (int32x2_t) {__a, __a};
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vdup_n_s64 (int64_t __a)
{
  return (int64x1_t) {__a};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vdup_n_u8 (uint8_t __a)
{
  return (uint8x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vdup_n_u16 (uint16_t __a)
{
  return (uint16x4_t) {__a, __a, __a, __a};
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vdup_n_u32 (uint32_t __a)
{
  return (uint32x2_t) {__a, __a};
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vdup_n_u64 (uint64_t __a)
{
  return (uint64x1_t) {__a};
}

/* vdupq_n  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vdupq_n_f32 (float32_t __a)
{
  return (float32x4_t) {__a, __a, __a, __a};
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vdupq_n_f64 (float64_t __a)
{
  return (float64x2_t) {__a, __a};
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vdupq_n_p8 (uint32_t __a)
{
  return (poly8x16_t) {__a, __a, __a, __a, __a, __a, __a, __a,
                       __a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vdupq_n_p16 (uint32_t __a)
{
  return (poly16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vdupq_n_s8 (int32_t __a)
{
  return (int8x16_t) {__a, __a, __a, __a, __a, __a, __a, __a,
                      __a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vdupq_n_s16 (int32_t __a)
{
  return (int16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vdupq_n_s32 (int32_t __a)
{
  return (int32x4_t) {__a, __a, __a, __a};
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vdupq_n_s64 (int64_t __a)
{
  return (int64x2_t) {__a, __a};
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vdupq_n_u8 (uint32_t __a)
{
  return (uint8x16_t) {__a, __a, __a, __a, __a, __a, __a, __a,
                       __a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vdupq_n_u16 (uint32_t __a)
{
  return (uint16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a};
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vdupq_n_u32 (uint32_t __a)
{
  return (uint32x4_t) {__a, __a, __a, __a};
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vdupq_n_u64 (uint64_t __a)
{
  return (uint64x2_t) {__a, __a};
}

/* vdup_lane  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vdup_lane_f32 (float32x2_t __a, const int __b)
{
  return __aarch64_vdup_lane_f32 (__a, __b);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vdup_lane_f64 (float64x1_t __a, const int __b)
{
  return __aarch64_vdup_lane_f64 (__a, __b);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vdup_lane_p8 (poly8x8_t __a, const int __b)
{
  return __aarch64_vdup_lane_p8 (__a, __b);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vdup_lane_p16 (poly16x4_t __a, const int __b)
{
  return __aarch64_vdup_lane_p16 (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vdup_lane_s8 (int8x8_t __a, const int __b)
{
  return __aarch64_vdup_lane_s8 (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vdup_lane_s16 (int16x4_t __a, const int __b)
{
  return __aarch64_vdup_lane_s16 (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vdup_lane_s32 (int32x2_t __a, const int __b)
{
  return __aarch64_vdup_lane_s32 (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vdup_lane_s64 (int64x1_t __a, const int __b)
{
  return __aarch64_vdup_lane_s64 (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vdup_lane_u8 (uint8x8_t __a, const int __b)
{
  return __aarch64_vdup_lane_u8 (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vdup_lane_u16 (uint16x4_t __a, const int __b)
{
  return __aarch64_vdup_lane_u16 (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vdup_lane_u32 (uint32x2_t __a, const int __b)
{
  return __aarch64_vdup_lane_u32 (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vdup_lane_u64 (uint64x1_t __a, const int __b)
{
  return __aarch64_vdup_lane_u64 (__a, __b);
}

/* vdup_laneq  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vdup_laneq_f32 (float32x4_t __a, const int __b)
{
  return __aarch64_vdup_laneq_f32 (__a, __b);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vdup_laneq_f64 (float64x2_t __a, const int __b)
{
  return __aarch64_vdup_laneq_f64 (__a, __b);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vdup_laneq_p8 (poly8x16_t __a, const int __b)
{
  return __aarch64_vdup_laneq_p8 (__a, __b);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vdup_laneq_p16 (poly16x8_t __a, const int __b)
{
  return __aarch64_vdup_laneq_p16 (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vdup_laneq_s8 (int8x16_t __a, const int __b)
{
  return __aarch64_vdup_laneq_s8 (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vdup_laneq_s16 (int16x8_t __a, const int __b)
{
  return __aarch64_vdup_laneq_s16 (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vdup_laneq_s32 (int32x4_t __a, const int __b)
{
  return __aarch64_vdup_laneq_s32 (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vdup_laneq_s64 (int64x2_t __a, const int __b)
{
  return __aarch64_vdup_laneq_s64 (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vdup_laneq_u8 (uint8x16_t __a, const int __b)
{
  return __aarch64_vdup_laneq_u8 (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vdup_laneq_u16 (uint16x8_t __a, const int __b)
{
  return __aarch64_vdup_laneq_u16 (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vdup_laneq_u32 (uint32x4_t __a, const int __b)
{
  return __aarch64_vdup_laneq_u32 (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vdup_laneq_u64 (uint64x2_t __a, const int __b)
{
  return __aarch64_vdup_laneq_u64 (__a, __b);
}

/* vdupq_lane  */
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vdupq_lane_f32 (float32x2_t __a, const int __b)
{
  return __aarch64_vdupq_lane_f32 (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vdupq_lane_f64 (float64x1_t __a, const int __b)
{
  return __aarch64_vdupq_lane_f64 (__a, __b);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vdupq_lane_p8 (poly8x8_t __a, const int __b)
{
  return __aarch64_vdupq_lane_p8 (__a, __b);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vdupq_lane_p16 (poly16x4_t __a, const int __b)
{
  return __aarch64_vdupq_lane_p16 (__a, __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vdupq_lane_s8 (int8x8_t __a, const int __b)
{
  return __aarch64_vdupq_lane_s8 (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vdupq_lane_s16 (int16x4_t __a, const int __b)
{
  return __aarch64_vdupq_lane_s16 (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vdupq_lane_s32 (int32x2_t __a, const int __b)
{
  return __aarch64_vdupq_lane_s32 (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vdupq_lane_s64 (int64x1_t __a, const int __b)
{
  return __aarch64_vdupq_lane_s64 (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vdupq_lane_u8 (uint8x8_t __a, const int __b)
{
  return __aarch64_vdupq_lane_u8 (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vdupq_lane_u16 (uint16x4_t __a, const int __b)
{
  return __aarch64_vdupq_lane_u16 (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vdupq_lane_u32 (uint32x2_t __a, const int __b)
{
  return __aarch64_vdupq_lane_u32 (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vdupq_lane_u64 (uint64x1_t __a, const int __b)
{
  return __aarch64_vdupq_lane_u64 (__a, __b);
}

/* vdupq_laneq  */
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vdupq_laneq_f32 (float32x4_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_f32 (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vdupq_laneq_f64 (float64x2_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_f64 (__a, __b);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vdupq_laneq_p8 (poly8x16_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_p8 (__a, __b);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vdupq_laneq_p16 (poly16x8_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_p16 (__a, __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vdupq_laneq_s8 (int8x16_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_s8 (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vdupq_laneq_s16 (int16x8_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_s16 (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vdupq_laneq_s32 (int32x4_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_s32 (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vdupq_laneq_s64 (int64x2_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_s64 (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vdupq_laneq_u8 (uint8x16_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_u8 (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vdupq_laneq_u16 (uint16x8_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_u16 (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vdupq_laneq_u32 (uint32x4_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_u32 (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vdupq_laneq_u64 (uint64x2_t __a, const int __b)
{
  return __aarch64_vdupq_laneq_u64 (__a, __b);
}

/* vdupb_lane  */
__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vdupb_lane_p8 (poly8x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vdupb_lane_s8 (int8x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vdupb_lane_u8 (uint8x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vduph_lane  */
__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vduph_lane_p16 (poly16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vduph_lane_s16 (int16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vduph_lane_u16 (uint16x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vdups_lane  */
__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vdups_lane_f32 (float32x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vdups_lane_s32 (int32x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vdups_lane_u32 (uint32x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vdupd_lane  */
__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vdupd_lane_f64 (float64x1_t __a, const int __b)
{
  __AARCH64_LANE_CHECK (__a, __b);
  return __a[0];
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vdupd_lane_s64 (int64x1_t __a, const int __b)
{
  __AARCH64_LANE_CHECK (__a, __b);
  return __a[0];
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vdupd_lane_u64 (uint64x1_t __a, const int __b)
{
  __AARCH64_LANE_CHECK (__a, __b);
  return __a[0];
}

/* vdupb_laneq  */
__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vdupb_laneq_p8 (poly8x16_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vdupb_laneq_s8 (int8x16_t __a, const int __attribute__ ((unused)) __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vdupb_laneq_u8 (uint8x16_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vduph_laneq  */
__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vduph_laneq_p16 (poly16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vduph_laneq_s16 (int16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vduph_laneq_u16 (uint16x8_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vdups_laneq  */
__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vdups_laneq_f32 (float32x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vdups_laneq_s32 (int32x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vdups_laneq_u32 (uint32x4_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vdupd_laneq  */
__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vdupd_laneq_f64 (float64x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vdupd_laneq_s64 (int64x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vdupd_laneq_u64 (uint64x2_t __a, const int __b)
{
  return __aarch64_vget_lane_any (__a, __b);
}

/* vext  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vext_f32 (float32x2_t __a, float32x2_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint32x2_t) {2-__c, 3-__c});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {__c, __c+1});
#endif
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vext_f64 (float64x1_t __a, float64x1_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
  /* The only possible index to the assembler instruction returns element 0.  */
  return __a;
}
__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vext_p8 (poly8x8_t __a, poly8x8_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint8x8_t)
      {8-__c, 9-__c, 10-__c, 11-__c, 12-__c, 13-__c, 14-__c, 15-__c});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vext_p16 (poly16x4_t __a, poly16x4_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a,
      (uint16x4_t) {4-__c, 5-__c, 6-__c, 7-__c});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {__c, __c+1, __c+2, __c+3});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vext_s8 (int8x8_t __a, int8x8_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint8x8_t)
      {8-__c, 9-__c, 10-__c, 11-__c, 12-__c, 13-__c, 14-__c, 15-__c});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vext_s16 (int16x4_t __a, int16x4_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a,
      (uint16x4_t) {4-__c, 5-__c, 6-__c, 7-__c});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {__c, __c+1, __c+2, __c+3});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vext_s32 (int32x2_t __a, int32x2_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint32x2_t) {2-__c, 3-__c});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {__c, __c+1});
#endif
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vext_s64 (int64x1_t __a, int64x1_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
  /* The only possible index to the assembler instruction returns element 0.  */
  return __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vext_u8 (uint8x8_t __a, uint8x8_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint8x8_t)
      {8-__c, 9-__c, 10-__c, 11-__c, 12-__c, 13-__c, 14-__c, 15-__c});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vext_u16 (uint16x4_t __a, uint16x4_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a,
      (uint16x4_t) {4-__c, 5-__c, 6-__c, 7-__c});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {__c, __c+1, __c+2, __c+3});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vext_u32 (uint32x2_t __a, uint32x2_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint32x2_t) {2-__c, 3-__c});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {__c, __c+1});
#endif
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vext_u64 (uint64x1_t __a, uint64x1_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
  /* The only possible index to the assembler instruction returns element 0.  */
  return __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vextq_f32 (float32x4_t __a, float32x4_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a,
      (uint32x4_t) {4-__c, 5-__c, 6-__c, 7-__c});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {__c, __c+1, __c+2, __c+3});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vextq_f64 (float64x2_t __a, float64x2_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint64x2_t) {2-__c, 3-__c});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {__c, __c+1});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vextq_p8 (poly8x16_t __a, poly8x16_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint8x16_t)
      {16-__c, 17-__c, 18-__c, 19-__c, 20-__c, 21-__c, 22-__c, 23-__c,
       24-__c, 25-__c, 26-__c, 27-__c, 28-__c, 29-__c, 30-__c, 31-__c});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7,
       __c+8, __c+9, __c+10, __c+11, __c+12, __c+13, __c+14, __c+15});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vextq_p16 (poly16x8_t __a, poly16x8_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint16x8_t)
      {8-__c, 9-__c, 10-__c, 11-__c, 12-__c, 13-__c, 14-__c, 15-__c});
#else
  return __builtin_shuffle (__a, __b,
      (uint16x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vextq_s8 (int8x16_t __a, int8x16_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint8x16_t)
      {16-__c, 17-__c, 18-__c, 19-__c, 20-__c, 21-__c, 22-__c, 23-__c,
       24-__c, 25-__c, 26-__c, 27-__c, 28-__c, 29-__c, 30-__c, 31-__c});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7,
       __c+8, __c+9, __c+10, __c+11, __c+12, __c+13, __c+14, __c+15});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vextq_s16 (int16x8_t __a, int16x8_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint16x8_t)
      {8-__c, 9-__c, 10-__c, 11-__c, 12-__c, 13-__c, 14-__c, 15-__c});
#else
  return __builtin_shuffle (__a, __b,
      (uint16x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vextq_s32 (int32x4_t __a, int32x4_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a,
      (uint32x4_t) {4-__c, 5-__c, 6-__c, 7-__c});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {__c, __c+1, __c+2, __c+3});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vextq_s64 (int64x2_t __a, int64x2_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint64x2_t) {2-__c, 3-__c});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {__c, __c+1});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vextq_u8 (uint8x16_t __a, uint8x16_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint8x16_t)
      {16-__c, 17-__c, 18-__c, 19-__c, 20-__c, 21-__c, 22-__c, 23-__c,
       24-__c, 25-__c, 26-__c, 27-__c, 28-__c, 29-__c, 30-__c, 31-__c});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7,
       __c+8, __c+9, __c+10, __c+11, __c+12, __c+13, __c+14, __c+15});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vextq_u16 (uint16x8_t __a, uint16x8_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint16x8_t)
      {8-__c, 9-__c, 10-__c, 11-__c, 12-__c, 13-__c, 14-__c, 15-__c});
#else
  return __builtin_shuffle (__a, __b,
      (uint16x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vextq_u32 (uint32x4_t __a, uint32x4_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a,
      (uint32x4_t) {4-__c, 5-__c, 6-__c, 7-__c});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {__c, __c+1, __c+2, __c+3});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vextq_u64 (uint64x2_t __a, uint64x2_t __b, __const int __c)
{
  __AARCH64_LANE_CHECK (__a, __c);
#ifdef __AARCH64EB__
  return __builtin_shuffle (__b, __a, (uint64x2_t) {2-__c, 3-__c});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {__c, __c+1});
#endif
}

/* vfma  */

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vfma_f64 (float64x1_t __a, float64x1_t __b, float64x1_t __c)
{
  return (float64x1_t) {__builtin_fma (__b[0], __c[0], __a[0])};
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfma_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c)
{
  return __builtin_aarch64_fmav2sf (__b, __c, __a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmaq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
{
  return __builtin_aarch64_fmav4sf (__b, __c, __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmaq_f64 (float64x2_t __a, float64x2_t __b, float64x2_t __c)
{
  return __builtin_aarch64_fmav2df (__b, __c, __a);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfma_n_f32 (float32x2_t __a, float32x2_t __b, float32_t __c)
{
  return __builtin_aarch64_fmav2sf (__b, vdup_n_f32 (__c), __a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmaq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c)
{
  return __builtin_aarch64_fmav4sf (__b, vdupq_n_f32 (__c), __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmaq_n_f64 (float64x2_t __a, float64x2_t __b, float64_t __c)
{
  return __builtin_aarch64_fmav2df (__b, vdupq_n_f64 (__c), __a);
}

/* vfma_lane  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfma_lane_f32 (float32x2_t __a, float32x2_t __b,
               float32x2_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2sf (__b,
                                    __aarch64_vdup_lane_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vfma_lane_f64 (float64x1_t __a, float64x1_t __b,
               float64x1_t __c, const int __lane)
{
  return (float64x1_t) {__builtin_fma (__b[0], __c[0], __a[0])};
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vfmad_lane_f64 (float64_t __a, float64_t __b,
                float64x1_t __c, const int __lane)
{
  return __builtin_fma (__b, __c[0], __a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vfmas_lane_f32 (float32_t __a, float32_t __b,
                float32x2_t __c, const int __lane)
{
  return __builtin_fmaf (__b, __aarch64_vget_lane_any (__c, __lane), __a);
}

/* vfma_laneq  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfma_laneq_f32 (float32x2_t __a, float32x2_t __b,
                float32x4_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2sf (__b,
                                    __aarch64_vdup_laneq_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vfma_laneq_f64 (float64x1_t __a, float64x1_t __b,
                float64x2_t __c, const int __lane)
{
  float64_t __c0 = __aarch64_vget_lane_any (__c, __lane);
  return (float64x1_t) {__builtin_fma (__b[0], __c0, __a[0])};
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vfmad_laneq_f64 (float64_t __a, float64_t __b,
                 float64x2_t __c, const int __lane)
{
  return __builtin_fma (__b, __aarch64_vget_lane_any (__c, __lane), __a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vfmas_laneq_f32 (float32_t __a, float32_t __b,
                 float32x4_t __c, const int __lane)
{
  return __builtin_fmaf (__b, __aarch64_vget_lane_any (__c, __lane), __a);
}

/* vfmaq_lane  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmaq_lane_f32 (float32x4_t __a, float32x4_t __b,
                float32x2_t __c, const int __lane)
{
  return __builtin_aarch64_fmav4sf (__b,
                                    __aarch64_vdupq_lane_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmaq_lane_f64 (float64x2_t __a, float64x2_t __b,
                float64x1_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2df (__b, vdupq_n_f64 (__c[0]), __a);
}

/* vfmaq_laneq  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmaq_laneq_f32 (float32x4_t __a, float32x4_t __b,
                 float32x4_t __c, const int __lane)
{
  return __builtin_aarch64_fmav4sf (__b,
                                    __aarch64_vdupq_laneq_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmaq_laneq_f64 (float64x2_t __a, float64x2_t __b,
                 float64x2_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2df (__b,
                                    __aarch64_vdupq_laneq_f64 (__c, __lane),
                                    __a);
}

/* vfms  */

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vfms_f64 (float64x1_t __a, float64x1_t __b, float64x1_t __c)
{
  return (float64x1_t) {__builtin_fma (-__b[0], __c[0], __a[0])};
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfms_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c)
{
  return __builtin_aarch64_fmav2sf (-__b, __c, __a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmsq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
{
  return __builtin_aarch64_fmav4sf (-__b, __c, __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmsq_f64 (float64x2_t __a, float64x2_t __b, float64x2_t __c)
{
  return __builtin_aarch64_fmav2df (-__b, __c, __a);
}


/* vfms_lane  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfms_lane_f32 (float32x2_t __a, float32x2_t __b,
               float32x2_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2sf (-__b,
                                    __aarch64_vdup_lane_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vfms_lane_f64 (float64x1_t __a, float64x1_t __b,
               float64x1_t __c, const int __lane)
{
  return (float64x1_t) {__builtin_fma (-__b[0], __c[0], __a[0])};
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vfmsd_lane_f64 (float64_t __a, float64_t __b,
                float64x1_t __c, const int __lane)
{
  return __builtin_fma (-__b, __c[0], __a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vfmss_lane_f32 (float32_t __a, float32_t __b,
                float32x2_t __c, const int __lane)
{
  return __builtin_fmaf (-__b, __aarch64_vget_lane_any (__c, __lane), __a);
}

/* vfms_laneq  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vfms_laneq_f32 (float32x2_t __a, float32x2_t __b,
                float32x4_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2sf (-__b,
                                    __aarch64_vdup_laneq_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vfms_laneq_f64 (float64x1_t __a, float64x1_t __b,
                float64x2_t __c, const int __lane)
{
  float64_t __c0 = __aarch64_vget_lane_any (__c, __lane);
  return (float64x1_t) {__builtin_fma (-__b[0], __c0, __a[0])};
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vfmsd_laneq_f64 (float64_t __a, float64_t __b,
                 float64x2_t __c, const int __lane)
{
  return __builtin_fma (-__b, __aarch64_vget_lane_any (__c, __lane), __a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vfmss_laneq_f32 (float32_t __a, float32_t __b,
                 float32x4_t __c, const int __lane)
{
  return __builtin_fmaf (-__b, __aarch64_vget_lane_any (__c, __lane), __a);
}

/* vfmsq_lane  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmsq_lane_f32 (float32x4_t __a, float32x4_t __b,
                float32x2_t __c, const int __lane)
{
  return __builtin_aarch64_fmav4sf (-__b,
                                    __aarch64_vdupq_lane_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmsq_lane_f64 (float64x2_t __a, float64x2_t __b,
                float64x1_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2df (-__b, vdupq_n_f64 (__c[0]), __a);
}

/* vfmsq_laneq  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vfmsq_laneq_f32 (float32x4_t __a, float32x4_t __b,
                 float32x4_t __c, const int __lane)
{
  return __builtin_aarch64_fmav4sf (-__b,
                                    __aarch64_vdupq_laneq_f32 (__c, __lane),
                                    __a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vfmsq_laneq_f64 (float64x2_t __a, float64x2_t __b,
                 float64x2_t __c, const int __lane)
{
  return __builtin_aarch64_fmav2df (-__b,
                                    __aarch64_vdupq_laneq_f64 (__c, __lane),
                                    __a);
}

/* vld1 */

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vld1_f16 (const float16_t *__a)
{
  return __builtin_aarch64_ld1v4hf (__a);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vld1_f32 (const float32_t *a)
{
  return __builtin_aarch64_ld1v2sf ((const __builtin_aarch64_simd_sf *) a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vld1_f64 (const float64_t *a)
{
  return (float64x1_t) {*a};
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vld1_p8 (const poly8_t *a)
{
  return (poly8x8_t)
    __builtin_aarch64_ld1v8qi ((const __builtin_aarch64_simd_qi *) a);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vld1_p16 (const poly16_t *a)
{
  return (poly16x4_t)
    __builtin_aarch64_ld1v4hi ((const __builtin_aarch64_simd_hi *) a);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vld1_s8 (const int8_t *a)
{
  return __builtin_aarch64_ld1v8qi ((const __builtin_aarch64_simd_qi *) a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vld1_s16 (const int16_t *a)
{
  return __builtin_aarch64_ld1v4hi ((const __builtin_aarch64_simd_hi *) a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vld1_s32 (const int32_t *a)
{
  return __builtin_aarch64_ld1v2si ((const __builtin_aarch64_simd_si *) a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vld1_s64 (const int64_t *a)
{
  return (int64x1_t) {*a};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vld1_u8 (const uint8_t *a)
{
  return (uint8x8_t)
    __builtin_aarch64_ld1v8qi ((const __builtin_aarch64_simd_qi *) a);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vld1_u16 (const uint16_t *a)
{
  return (uint16x4_t)
    __builtin_aarch64_ld1v4hi ((const __builtin_aarch64_simd_hi *) a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vld1_u32 (const uint32_t *a)
{
  return (uint32x2_t)
    __builtin_aarch64_ld1v2si ((const __builtin_aarch64_simd_si *) a);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vld1_u64 (const uint64_t *a)
{
  return (uint64x1_t) {*a};
}

/* vld1q */

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vld1q_f16 (const float16_t *__a)
{
  return __builtin_aarch64_ld1v8hf (__a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vld1q_f32 (const float32_t *a)
{
  return __builtin_aarch64_ld1v4sf ((const __builtin_aarch64_simd_sf *) a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vld1q_f64 (const float64_t *a)
{
  return __builtin_aarch64_ld1v2df ((const __builtin_aarch64_simd_df *) a);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vld1q_p8 (const poly8_t *a)
{
  return (poly8x16_t)
    __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vld1q_p16 (const poly16_t *a)
{
  return (poly16x8_t)
    __builtin_aarch64_ld1v8hi ((const __builtin_aarch64_simd_hi *) a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vld1q_s8 (const int8_t *a)
{
  return __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vld1q_s16 (const int16_t *a)
{
  return __builtin_aarch64_ld1v8hi ((const __builtin_aarch64_simd_hi *) a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vld1q_s32 (const int32_t *a)
{
  return __builtin_aarch64_ld1v4si ((const __builtin_aarch64_simd_si *) a);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vld1q_s64 (const int64_t *a)
{
  return __builtin_aarch64_ld1v2di ((const __builtin_aarch64_simd_di *) a);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vld1q_u8 (const uint8_t *a)
{
  return (uint8x16_t)
    __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vld1q_u16 (const uint16_t *a)
{
  return (uint16x8_t)
    __builtin_aarch64_ld1v8hi ((const __builtin_aarch64_simd_hi *) a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vld1q_u32 (const uint32_t *a)
{
  return (uint32x4_t)
    __builtin_aarch64_ld1v4si ((const __builtin_aarch64_simd_si *) a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vld1q_u64 (const uint64_t *a)
{
  return (uint64x2_t)
    __builtin_aarch64_ld1v2di ((const __builtin_aarch64_simd_di *) a);
}

/* vld1_dup  */

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vld1_dup_f16 (const float16_t* __a)
{
  float16_t __f = *__a;
  return (float16x4_t) { __f, __f, __f, __f };
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vld1_dup_f32 (const float32_t* __a)
{
  return vdup_n_f32 (*__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vld1_dup_f64 (const float64_t* __a)
{
  return vdup_n_f64 (*__a);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vld1_dup_p8 (const poly8_t* __a)
{
  return vdup_n_p8 (*__a);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vld1_dup_p16 (const poly16_t* __a)
{
  return vdup_n_p16 (*__a);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vld1_dup_s8 (const int8_t* __a)
{
  return vdup_n_s8 (*__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vld1_dup_s16 (const int16_t* __a)
{
  return vdup_n_s16 (*__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vld1_dup_s32 (const int32_t* __a)
{
  return vdup_n_s32 (*__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vld1_dup_s64 (const int64_t* __a)
{
  return vdup_n_s64 (*__a);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vld1_dup_u8 (const uint8_t* __a)
{
  return vdup_n_u8 (*__a);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vld1_dup_u16 (const uint16_t* __a)
{
  return vdup_n_u16 (*__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vld1_dup_u32 (const uint32_t* __a)
{
  return vdup_n_u32 (*__a);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vld1_dup_u64 (const uint64_t* __a)
{
  return vdup_n_u64 (*__a);
}

/* vld1q_dup  */

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vld1q_dup_f16 (const float16_t* __a)
{
  float16_t __f = *__a;
  return (float16x8_t) { __f, __f, __f, __f, __f, __f, __f, __f };
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vld1q_dup_f32 (const float32_t* __a)
{
  return vdupq_n_f32 (*__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vld1q_dup_f64 (const float64_t* __a)
{
  return vdupq_n_f64 (*__a);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vld1q_dup_p8 (const poly8_t* __a)
{
  return vdupq_n_p8 (*__a);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vld1q_dup_p16 (const poly16_t* __a)
{
  return vdupq_n_p16 (*__a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vld1q_dup_s8 (const int8_t* __a)
{
  return vdupq_n_s8 (*__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vld1q_dup_s16 (const int16_t* __a)
{
  return vdupq_n_s16 (*__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vld1q_dup_s32 (const int32_t* __a)
{
  return vdupq_n_s32 (*__a);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vld1q_dup_s64 (const int64_t* __a)
{
  return vdupq_n_s64 (*__a);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vld1q_dup_u8 (const uint8_t* __a)
{
  return vdupq_n_u8 (*__a);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vld1q_dup_u16 (const uint16_t* __a)
{
  return vdupq_n_u16 (*__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vld1q_dup_u32 (const uint32_t* __a)
{
  return vdupq_n_u32 (*__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vld1q_dup_u64 (const uint64_t* __a)
{
  return vdupq_n_u64 (*__a);
}

/* vld1_lane  */

__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vld1_lane_f16 (const float16_t *__src, float16x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vld1_lane_f32 (const float32_t *__src, float32x2_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vld1_lane_f64 (const float64_t *__src, float64x1_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vld1_lane_p8 (const poly8_t *__src, poly8x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vld1_lane_p16 (const poly16_t *__src, poly16x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vld1_lane_s8 (const int8_t *__src, int8x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vld1_lane_s16 (const int16_t *__src, int16x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vld1_lane_s32 (const int32_t *__src, int32x2_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vld1_lane_s64 (const int64_t *__src, int64x1_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vld1_lane_u8 (const uint8_t *__src, uint8x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vld1_lane_u16 (const uint16_t *__src, uint16x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vld1_lane_u32 (const uint32_t *__src, uint32x2_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vld1_lane_u64 (const uint64_t *__src, uint64x1_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

/* vld1q_lane  */

__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vld1q_lane_f16 (const float16_t *__src, float16x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vld1q_lane_f32 (const float32_t *__src, float32x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vld1q_lane_f64 (const float64_t *__src, float64x2_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vld1q_lane_p8 (const poly8_t *__src, poly8x16_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vld1q_lane_p16 (const poly16_t *__src, poly16x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vld1q_lane_s8 (const int8_t *__src, int8x16_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vld1q_lane_s16 (const int16_t *__src, int16x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vld1q_lane_s32 (const int32_t *__src, int32x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vld1q_lane_s64 (const int64_t *__src, int64x2_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vld1q_lane_u8 (const uint8_t *__src, uint8x16_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vld1q_lane_u16 (const uint16_t *__src, uint16x8_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vld1q_lane_u32 (const uint32_t *__src, uint32x4_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vld1q_lane_u64 (const uint64_t *__src, uint64x2_t __vec, const int __lane)
{
  return __aarch64_vset_lane_any (*__src, __vec, __lane);
}

/* vldn */

__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__))
vld2_s64 (const int64_t * __a)
{
  int64x1x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
  return ret;
}

__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__))
vld2_u64 (const uint64_t * __a)
{
  uint64x1x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
  return ret;
}

__extension__ static __inline float64x1x2_t __attribute__ ((__always_inline__))
vld2_f64 (const float64_t * __a)
{
  float64x1x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 0)};
  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 1)};
  return ret;
}

__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
vld2_s8 (const int8_t * __a)
{
  int8x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
  return ret;
}

__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
vld2_p8 (const poly8_t * __a)
{
  poly8x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
  return ret;
}

__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
vld2_s16 (const int16_t * __a)
{
  int16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
  return ret;
}

__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
vld2_p16 (const poly16_t * __a)
{
  poly16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
  return ret;
}

__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
vld2_s32 (const int32_t * __a)
{
  int32x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
  return ret;
}

__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
vld2_u8 (const uint8_t * __a)
{
  uint8x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
  return ret;
}

__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
vld2_u16 (const uint16_t * __a)
{
  uint16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
  return ret;
}

__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
vld2_u32 (const uint32_t * __a)
{
  uint32x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
  return ret;
}

__extension__ static __inline float16x4x2_t __attribute__ ((__always_inline__))
vld2_f16 (const float16_t * __a)
{
  float16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4hf (__a);
  ret.val[0] = __builtin_aarch64_get_dregoiv4hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_dregoiv4hf (__o, 1);
  return ret;
}

__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
vld2_f32 (const float32_t * __a)
{
  float32x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v2sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 0);
  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 1);
  return ret;
}

__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
vld2q_s8 (const int8_t * __a)
{
  int8x16x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
  return ret;
}

__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
vld2q_p8 (const poly8_t * __a)
{
  poly8x16x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
  return ret;
}

__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
vld2q_s16 (const int16_t * __a)
{
  int16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
  return ret;
}

__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
vld2q_p16 (const poly16_t * __a)
{
  poly16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
  return ret;
}

__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
vld2q_s32 (const int32_t * __a)
{
  int32x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
  return ret;
}

__extension__ static __inline int64x2x2_t __attribute__ ((__always_inline__))
vld2q_s64 (const int64_t * __a)
{
  int64x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
  return ret;
}

__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
vld2q_u8 (const uint8_t * __a)
{
  uint8x16x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
  return ret;
}

__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
vld2q_u16 (const uint16_t * __a)
{
  uint16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
  return ret;
}

__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
vld2q_u32 (const uint32_t * __a)
{
  uint32x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
  return ret;
}

__extension__ static __inline uint64x2x2_t __attribute__ ((__always_inline__))
vld2q_u64 (const uint64_t * __a)
{
  uint64x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
  return ret;
}

__extension__ static __inline float16x8x2_t __attribute__ ((__always_inline__))
vld2q_f16 (const float16_t * __a)
{
  float16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v8hf (__a);
  ret.val[0] = __builtin_aarch64_get_qregoiv8hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_qregoiv8hf (__o, 1);
  return ret;
}

__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
vld2q_f32 (const float32_t * __a)
{
  float32x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v4sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 0);
  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 1);
  return ret;
}

__extension__ static __inline float64x2x2_t __attribute__ ((__always_inline__))
vld2q_f64 (const float64_t * __a)
{
  float64x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2v2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 0);
  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 1);
  return ret;
}

__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__))
vld3_s64 (const int64_t * __a)
{
  int64x1x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 0);
  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 1);
  ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 2);
  return ret;
}

__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__))
vld3_u64 (const uint64_t * __a)
{
  uint64x1x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 0);
  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 1);
  ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 2);
  return ret;
}

__extension__ static __inline float64x1x3_t __attribute__ ((__always_inline__))
vld3_f64 (const float64_t * __a)
{
  float64x1x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 0)};
  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 1)};
  ret.val[2] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 2)};
  return ret;
}

__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__))
vld3_s8 (const int8_t * __a)
{
  int8x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
  ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
  return ret;
}

__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__))
vld3_p8 (const poly8_t * __a)
{
  poly8x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
  ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
  return ret;
}

__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__))
vld3_s16 (const int16_t * __a)
{
  int16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
  ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
  return ret;
}

__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__))
vld3_p16 (const poly16_t * __a)
{
  poly16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
  ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
  return ret;
}

__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__))
vld3_s32 (const int32_t * __a)
{
  int32x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0);
  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1);
  ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2);
  return ret;
}

__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__))
vld3_u8 (const uint8_t * __a)
{
  uint8x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
  ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
  return ret;
}

__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__))
vld3_u16 (const uint16_t * __a)
{
  uint16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
  ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
  return ret;
}

__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__))
vld3_u32 (const uint32_t * __a)
{
  uint32x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0);
  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1);
  ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2);
  return ret;
}

__extension__ static __inline float16x4x3_t __attribute__ ((__always_inline__))
vld3_f16 (const float16_t * __a)
{
  float16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4hf (__a);
  ret.val[0] = __builtin_aarch64_get_dregciv4hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_dregciv4hf (__o, 1);
  ret.val[2] = __builtin_aarch64_get_dregciv4hf (__o, 2);
  return ret;
}

__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__))
vld3_f32 (const float32_t * __a)
{
  float32x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v2sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 0);
  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 1);
  ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 2);
  return ret;
}

__extension__ static __inline int8x16x3_t __attribute__ ((__always_inline__))
vld3q_s8 (const int8_t * __a)
{
  int8x16x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
  ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
  return ret;
}

__extension__ static __inline poly8x16x3_t __attribute__ ((__always_inline__))
vld3q_p8 (const poly8_t * __a)
{
  poly8x16x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
  ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
  return ret;
}

__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__))
vld3q_s16 (const int16_t * __a)
{
  int16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
  ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
  return ret;
}

__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__))
vld3q_p16 (const poly16_t * __a)
{
  poly16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
  ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
  return ret;
}

__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__))
vld3q_s32 (const int32_t * __a)
{
  int32x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0);
  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1);
  ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2);
  return ret;
}

__extension__ static __inline int64x2x3_t __attribute__ ((__always_inline__))
vld3q_s64 (const int64_t * __a)
{
  int64x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0);
  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1);
  ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2);
  return ret;
}

__extension__ static __inline uint8x16x3_t __attribute__ ((__always_inline__))
vld3q_u8 (const uint8_t * __a)
{
  uint8x16x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
  ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
  return ret;
}

__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__))
vld3q_u16 (const uint16_t * __a)
{
  uint16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
  ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
  return ret;
}

__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__))
vld3q_u32 (const uint32_t * __a)
{
  uint32x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0);
  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1);
  ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2);
  return ret;
}

__extension__ static __inline uint64x2x3_t __attribute__ ((__always_inline__))
vld3q_u64 (const uint64_t * __a)
{
  uint64x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0);
  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1);
  ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2);
  return ret;
}

__extension__ static __inline float16x8x3_t __attribute__ ((__always_inline__))
vld3q_f16 (const float16_t * __a)
{
  float16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v8hf (__a);
  ret.val[0] = __builtin_aarch64_get_qregciv8hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_qregciv8hf (__o, 1);
  ret.val[2] = __builtin_aarch64_get_qregciv8hf (__o, 2);
  return ret;
}

__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__))
vld3q_f32 (const float32_t * __a)
{
  float32x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v4sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 0);
  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 1);
  ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 2);
  return ret;
}

__extension__ static __inline float64x2x3_t __attribute__ ((__always_inline__))
vld3q_f64 (const float64_t * __a)
{
  float64x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3v2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 0);
  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 1);
  ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 2);
  return ret;
}

__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__))
vld4_s64 (const int64_t * __a)
{
  int64x1x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
  ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
  ret.val[3] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
  return ret;
}

__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__))
vld4_u64 (const uint64_t * __a)
{
  uint64x1x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
  ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
  ret.val[3] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
  return ret;
}

__extension__ static __inline float64x1x4_t __attribute__ ((__always_inline__))
vld4_f64 (const float64_t * __a)
{
  float64x1x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 0)};
  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 1)};
  ret.val[2] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 2)};
  ret.val[3] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 3)};
  return ret;
}

__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__))
vld4_s8 (const int8_t * __a)
{
  int8x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
  ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
  ret.val[3] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
  return ret;
}

__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__))
vld4_p8 (const poly8_t * __a)
{
  poly8x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
  ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
  ret.val[3] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
  return ret;
}

__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__))
vld4_s16 (const int16_t * __a)
{
  int16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
  ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
  ret.val[3] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
  return ret;
}

__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__))
vld4_p16 (const poly16_t * __a)
{
  poly16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
  ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
  ret.val[3] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
  return ret;
}

__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__))
vld4_s32 (const int32_t * __a)
{
  int32x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0);
  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1);
  ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2);
  ret.val[3] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3);
  return ret;
}

__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__))
vld4_u8 (const uint8_t * __a)
{
  uint8x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
  ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
  ret.val[3] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
  return ret;
}

__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__))
vld4_u16 (const uint16_t * __a)
{
  uint16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
  ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
  ret.val[3] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
  return ret;
}

__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__))
vld4_u32 (const uint32_t * __a)
{
  uint32x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0);
  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1);
  ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2);
  ret.val[3] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3);
  return ret;
}

__extension__ static __inline float16x4x4_t __attribute__ ((__always_inline__))
vld4_f16 (const float16_t * __a)
{
  float16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4hf (__a);
  ret.val[0] = __builtin_aarch64_get_dregxiv4hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_dregxiv4hf (__o, 1);
  ret.val[2] = __builtin_aarch64_get_dregxiv4hf (__o, 2);
  ret.val[3] = __builtin_aarch64_get_dregxiv4hf (__o, 3);
  return ret;
}

__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__))
vld4_f32 (const float32_t * __a)
{
  float32x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v2sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 0);
  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 1);
  ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 2);
  ret.val[3] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 3);
  return ret;
}

__extension__ static __inline int8x16x4_t __attribute__ ((__always_inline__))
vld4q_s8 (const int8_t * __a)
{
  int8x16x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
  ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
  ret.val[3] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
  return ret;
}

__extension__ static __inline poly8x16x4_t __attribute__ ((__always_inline__))
vld4q_p8 (const poly8_t * __a)
{
  poly8x16x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
  ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
  ret.val[3] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
  return ret;
}

__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__))
vld4q_s16 (const int16_t * __a)
{
  int16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
  ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
  ret.val[3] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
  return ret;
}

__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__))
vld4q_p16 (const poly16_t * __a)
{
  poly16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
  ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
  ret.val[3] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
  return ret;
}

__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__))
vld4q_s32 (const int32_t * __a)
{
  int32x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
  ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
  ret.val[3] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
  return ret;
}

__extension__ static __inline int64x2x4_t __attribute__ ((__always_inline__))
vld4q_s64 (const int64_t * __a)
{
  int64x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0);
  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1);
  ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2);
  ret.val[3] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3);
  return ret;
}

__extension__ static __inline uint8x16x4_t __attribute__ ((__always_inline__))
vld4q_u8 (const uint8_t * __a)
{
  uint8x16x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
  ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
  ret.val[3] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
  return ret;
}

__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__))
vld4q_u16 (const uint16_t * __a)
{
  uint16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
  ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
  ret.val[3] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
  return ret;
}

__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__))
vld4q_u32 (const uint32_t * __a)
{
  uint32x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
  ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
  ret.val[3] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
  return ret;
}

__extension__ static __inline uint64x2x4_t __attribute__ ((__always_inline__))
vld4q_u64 (const uint64_t * __a)
{
  uint64x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0);
  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1);
  ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2);
  ret.val[3] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3);
  return ret;
}

__extension__ static __inline float16x8x4_t __attribute__ ((__always_inline__))
vld4q_f16 (const float16_t * __a)
{
  float16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v8hf (__a);
  ret.val[0] = __builtin_aarch64_get_qregxiv8hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_qregxiv8hf (__o, 1);
  ret.val[2] = __builtin_aarch64_get_qregxiv8hf (__o, 2);
  ret.val[3] = __builtin_aarch64_get_qregxiv8hf (__o, 3);
  return ret;
}

__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__))
vld4q_f32 (const float32_t * __a)
{
  float32x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v4sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 0);
  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 1);
  ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 2);
  ret.val[3] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 3);
  return ret;
}

__extension__ static __inline float64x2x4_t __attribute__ ((__always_inline__))
vld4q_f64 (const float64_t * __a)
{
  float64x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4v2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 0);
  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 1);
  ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 2);
  ret.val[3] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 3);
  return ret;
}

/* vldn_dup */

__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
vld2_dup_s8 (const int8_t * __a)
{
  int8x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
  return ret;
}

__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_s16 (const int16_t * __a)
{
  int16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
  return ret;
}

__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
vld2_dup_s32 (const int32_t * __a)
{
  int32x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
  return ret;
}

__extension__ static __inline float16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_f16 (const float16_t * __a)
{
  float16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4hf ((const __builtin_aarch64_simd_hf *) __a);
  ret.val[0] = __builtin_aarch64_get_dregoiv4hf (__o, 0);
  ret.val[1] = (float16x4_t) __builtin_aarch64_get_dregoiv4hf (__o, 1);
  return ret;
}

__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
vld2_dup_f32 (const float32_t * __a)
{
  float32x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv2sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 0);
  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 1);
  return ret;
}

__extension__ static __inline float64x1x2_t __attribute__ ((__always_inline__))
vld2_dup_f64 (const float64_t * __a)
{
  float64x1x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rdf ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 0)};
  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 1)};
  return ret;
}

__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
vld2_dup_u8 (const uint8_t * __a)
{
  uint8x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
  return ret;
}

__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_u16 (const uint16_t * __a)
{
  uint16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
  return ret;
}

__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
vld2_dup_u32 (const uint32_t * __a)
{
  uint32x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
  return ret;
}

__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
vld2_dup_p8 (const poly8_t * __a)
{
  poly8x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
  return ret;
}

__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_p16 (const poly16_t * __a)
{
  poly16x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
  return ret;
}

__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__))
vld2_dup_s64 (const int64_t * __a)
{
  int64x1x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rdi ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
  return ret;
}

__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__))
vld2_dup_u64 (const uint64_t * __a)
{
  uint64x1x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rdi ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
  return ret;
}

__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
vld2q_dup_s8 (const int8_t * __a)
{
  int8x16x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
  return ret;
}

__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
vld2q_dup_p8 (const poly8_t * __a)
{
  poly8x16x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
  return ret;
}

__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_s16 (const int16_t * __a)
{
  int16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
  return ret;
}

__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_p16 (const poly16_t * __a)
{
  poly16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
  return ret;
}

__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
vld2q_dup_s32 (const int32_t * __a)
{
  int32x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
  return ret;
}

__extension__ static __inline int64x2x2_t __attribute__ ((__always_inline__))
vld2q_dup_s64 (const int64_t * __a)
{
  int64x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
  return ret;
}

__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
vld2q_dup_u8 (const uint8_t * __a)
{
  uint8x16x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
  return ret;
}

__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_u16 (const uint16_t * __a)
{
  uint16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
  return ret;
}

__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
vld2q_dup_u32 (const uint32_t * __a)
{
  uint32x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
  return ret;
}

__extension__ static __inline uint64x2x2_t __attribute__ ((__always_inline__))
vld2q_dup_u64 (const uint64_t * __a)
{
  uint64x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
  return ret;
}

__extension__ static __inline float16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_f16 (const float16_t * __a)
{
  float16x8x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv8hf ((const __builtin_aarch64_simd_hf *) __a);
  ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregoiv8hf (__o, 0);
  ret.val[1] = __builtin_aarch64_get_qregoiv8hf (__o, 1);
  return ret;
}

__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
vld2q_dup_f32 (const float32_t * __a)
{
  float32x4x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv4sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 0);
  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 1);
  return ret;
}

__extension__ static __inline float64x2x2_t __attribute__ ((__always_inline__))
vld2q_dup_f64 (const float64_t * __a)
{
  float64x2x2_t ret;
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_ld2rv2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 0);
  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 1);
  return ret;
}

__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__))
vld3_dup_s64 (const int64_t * __a)
{
  int64x1x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rdi ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 0);
  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 1);
  ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 2);
  return ret;
}

__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__))
vld3_dup_u64 (const uint64_t * __a)
{
  uint64x1x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rdi ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 0);
  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 1);
  ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 2);
  return ret;
}

__extension__ static __inline float64x1x3_t __attribute__ ((__always_inline__))
vld3_dup_f64 (const float64_t * __a)
{
  float64x1x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rdf ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 0)};
  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 1)};
  ret.val[2] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 2)};
  return ret;
}

__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__))
vld3_dup_s8 (const int8_t * __a)
{
  int8x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
  ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
  return ret;
}

__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__))
vld3_dup_p8 (const poly8_t * __a)
{
  poly8x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
  ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
  return ret;
}

__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_s16 (const int16_t * __a)
{
  int16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
  ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
  return ret;
}

__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_p16 (const poly16_t * __a)
{
  poly16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
  ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
  return ret;
}

__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__))
vld3_dup_s32 (const int32_t * __a)
{
  int32x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0);
  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1);
  ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2);
  return ret;
}

__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__))
vld3_dup_u8 (const uint8_t * __a)
{
  uint8x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
  ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
  return ret;
}

__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_u16 (const uint16_t * __a)
{
  uint16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
  ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
  return ret;
}

__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__))
vld3_dup_u32 (const uint32_t * __a)
{
  uint32x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0);
  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1);
  ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2);
  return ret;
}

__extension__ static __inline float16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_f16 (const float16_t * __a)
{
  float16x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4hf ((const __builtin_aarch64_simd_hf *) __a);
  ret.val[0] = (float16x4_t) __builtin_aarch64_get_dregciv4hf (__o, 0);
  ret.val[1] = (float16x4_t) __builtin_aarch64_get_dregciv4hf (__o, 1);
  ret.val[2] = (float16x4_t) __builtin_aarch64_get_dregciv4hf (__o, 2);
  return ret;
}

__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__))
vld3_dup_f32 (const float32_t * __a)
{
  float32x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv2sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 0);
  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 1);
  ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 2);
  return ret;
}

__extension__ static __inline int8x16x3_t __attribute__ ((__always_inline__))
vld3q_dup_s8 (const int8_t * __a)
{
  int8x16x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
  ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
  return ret;
}

__extension__ static __inline poly8x16x3_t __attribute__ ((__always_inline__))
vld3q_dup_p8 (const poly8_t * __a)
{
  poly8x16x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
  ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
  return ret;
}

__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_s16 (const int16_t * __a)
{
  int16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
  ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
  return ret;
}

__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_p16 (const poly16_t * __a)
{
  poly16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
  ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
  return ret;
}

__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__))
vld3q_dup_s32 (const int32_t * __a)
{
  int32x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0);
  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1);
  ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2);
  return ret;
}

__extension__ static __inline int64x2x3_t __attribute__ ((__always_inline__))
vld3q_dup_s64 (const int64_t * __a)
{
  int64x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0);
  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1);
  ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2);
  return ret;
}

__extension__ static __inline uint8x16x3_t __attribute__ ((__always_inline__))
vld3q_dup_u8 (const uint8_t * __a)
{
  uint8x16x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
  ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
  return ret;
}

__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_u16 (const uint16_t * __a)
{
  uint16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
  ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
  return ret;
}

__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__))
vld3q_dup_u32 (const uint32_t * __a)
{
  uint32x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0);
  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1);
  ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2);
  return ret;
}

__extension__ static __inline uint64x2x3_t __attribute__ ((__always_inline__))
vld3q_dup_u64 (const uint64_t * __a)
{
  uint64x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0);
  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1);
  ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2);
  return ret;
}

__extension__ static __inline float16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_f16 (const float16_t * __a)
{
  float16x8x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv8hf ((const __builtin_aarch64_simd_hf *) __a);
  ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregciv8hf (__o, 0);
  ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregciv8hf (__o, 1);
  ret.val[2] = (float16x8_t) __builtin_aarch64_get_qregciv8hf (__o, 2);
  return ret;
}

__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__))
vld3q_dup_f32 (const float32_t * __a)
{
  float32x4x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv4sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 0);
  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 1);
  ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 2);
  return ret;
}

__extension__ static __inline float64x2x3_t __attribute__ ((__always_inline__))
vld3q_dup_f64 (const float64_t * __a)
{
  float64x2x3_t ret;
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_ld3rv2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 0);
  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 1);
  ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 2);
  return ret;
}

__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__))
vld4_dup_s64 (const int64_t * __a)
{
  int64x1x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rdi ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
  ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
  ret.val[3] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
  return ret;
}

__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__))
vld4_dup_u64 (const uint64_t * __a)
{
  uint64x1x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rdi ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
  ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
  ret.val[3] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
  return ret;
}

__extension__ static __inline float64x1x4_t __attribute__ ((__always_inline__))
vld4_dup_f64 (const float64_t * __a)
{
  float64x1x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rdf ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 0)};
  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 1)};
  ret.val[2] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 2)};
  ret.val[3] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 3)};
  return ret;
}

__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__))
vld4_dup_s8 (const int8_t * __a)
{
  int8x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
  ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
  ret.val[3] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
  return ret;
}

__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__))
vld4_dup_p8 (const poly8_t * __a)
{
  poly8x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
  ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
  ret.val[3] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
  return ret;
}

__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_s16 (const int16_t * __a)
{
  int16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
  ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
  ret.val[3] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
  return ret;
}

__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_p16 (const poly16_t * __a)
{
  poly16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
  ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
  ret.val[3] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
  return ret;
}

__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__))
vld4_dup_s32 (const int32_t * __a)
{
  int32x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0);
  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1);
  ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2);
  ret.val[3] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3);
  return ret;
}

__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__))
vld4_dup_u8 (const uint8_t * __a)
{
  uint8x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
  ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
  ret.val[3] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
  return ret;
}

__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_u16 (const uint16_t * __a)
{
  uint16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
  ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
  ret.val[3] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
  return ret;
}

__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__))
vld4_dup_u32 (const uint32_t * __a)
{
  uint32x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv2si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0);
  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1);
  ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2);
  ret.val[3] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3);
  return ret;
}

__extension__ static __inline float16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_f16 (const float16_t * __a)
{
  float16x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4hf ((const __builtin_aarch64_simd_hf *) __a);
  ret.val[0] = (float16x4_t) __builtin_aarch64_get_dregxiv4hf (__o, 0);
  ret.val[1] = (float16x4_t) __builtin_aarch64_get_dregxiv4hf (__o, 1);
  ret.val[2] = (float16x4_t) __builtin_aarch64_get_dregxiv4hf (__o, 2);
  ret.val[3] = (float16x4_t) __builtin_aarch64_get_dregxiv4hf (__o, 3);
  return ret;
}

__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__))
vld4_dup_f32 (const float32_t * __a)
{
  float32x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv2sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 0);
  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 1);
  ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 2);
  ret.val[3] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 3);
  return ret;
}

__extension__ static __inline int8x16x4_t __attribute__ ((__always_inline__))
vld4q_dup_s8 (const int8_t * __a)
{
  int8x16x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
  ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
  ret.val[3] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
  return ret;
}

__extension__ static __inline poly8x16x4_t __attribute__ ((__always_inline__))
vld4q_dup_p8 (const poly8_t * __a)
{
  poly8x16x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
  ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
  ret.val[3] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
  return ret;
}

__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_s16 (const int16_t * __a)
{
  int16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
  ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
  ret.val[3] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
  return ret;
}

__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_p16 (const poly16_t * __a)
{
  poly16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
  ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
  ret.val[3] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
  return ret;
}

__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__))
vld4q_dup_s32 (const int32_t * __a)
{
  int32x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
  ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
  ret.val[3] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
  return ret;
}

__extension__ static __inline int64x2x4_t __attribute__ ((__always_inline__))
vld4q_dup_s64 (const int64_t * __a)
{
  int64x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0);
  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1);
  ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2);
  ret.val[3] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3);
  return ret;
}

__extension__ static __inline uint8x16x4_t __attribute__ ((__always_inline__))
vld4q_dup_u8 (const uint8_t * __a)
{
  uint8x16x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv16qi ((const __builtin_aarch64_simd_qi *) __a);
  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
  ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
  ret.val[3] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
  return ret;
}

__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_u16 (const uint16_t * __a)
{
  uint16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8hi ((const __builtin_aarch64_simd_hi *) __a);
  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
  ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
  ret.val[3] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
  return ret;
}

__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__))
vld4q_dup_u32 (const uint32_t * __a)
{
  uint32x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4si ((const __builtin_aarch64_simd_si *) __a);
  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
  ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
  ret.val[3] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
  return ret;
}

__extension__ static __inline uint64x2x4_t __attribute__ ((__always_inline__))
vld4q_dup_u64 (const uint64_t * __a)
{
  uint64x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv2di ((const __builtin_aarch64_simd_di *) __a);
  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0);
  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1);
  ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2);
  ret.val[3] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3);
  return ret;
}

__extension__ static __inline float16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_f16 (const float16_t * __a)
{
  float16x8x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv8hf ((const __builtin_aarch64_simd_hf *) __a);
  ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregxiv8hf (__o, 0);
  ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregxiv8hf (__o, 1);
  ret.val[2] = (float16x8_t) __builtin_aarch64_get_qregxiv8hf (__o, 2);
  ret.val[3] = (float16x8_t) __builtin_aarch64_get_qregxiv8hf (__o, 3);
  return ret;
}

__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__))
vld4q_dup_f32 (const float32_t * __a)
{
  float32x4x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv4sf ((const __builtin_aarch64_simd_sf *) __a);
  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 0);
  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 1);
  ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 2);
  ret.val[3] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 3);
  return ret;
}

__extension__ static __inline float64x2x4_t __attribute__ ((__always_inline__))
vld4q_dup_f64 (const float64_t * __a)
{
  float64x2x4_t ret;
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_ld4rv2df ((const __builtin_aarch64_simd_df *) __a);
  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 0);
  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 1);
  ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 2);
  ret.val[3] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 3);
  return ret;
}

/* vld2_lane */

#define __LD2_LANE_FUNC(intype, vectype, largetype, ptrtype, mode,         \
                         qmode, ptrmode, funcsuffix, signedtype)           \
__extension__ static __inline intype __attribute__ ((__always_inline__))   \
vld2_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c)  \
{                                                                          \
  __builtin_aarch64_simd_oi __o;                                           \
  largetype __temp;                                                        \
  __temp.val[0] =                                                          \
    vcombine_##funcsuffix (__b.val[0], vcreate_##funcsuffix (0));          \
  __temp.val[1] =                                                          \
    vcombine_##funcsuffix (__b.val[1], vcreate_##funcsuffix (0));          \
  __o = __builtin_aarch64_set_qregoi##qmode (__o,                          \
                                            (signedtype) __temp.val[0],    \
                                            0);                            \
  __o = __builtin_aarch64_set_qregoi##qmode (__o,                          \
                                            (signedtype) __temp.val[1],    \
                                            1);                            \
  __o = __builtin_aarch64_ld2_lane##mode (                                 \
          (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c);           \
  __b.val[0] = (vectype) __builtin_aarch64_get_dregoidi (__o, 0);          \
  __b.val[1] = (vectype) __builtin_aarch64_get_dregoidi (__o, 1);          \
  return __b;                                                              \
}

__LD2_LANE_FUNC (float16x4x2_t, float16x4_t, float16x8x2_t, float16_t, v4hf,
                 v8hf, hf, f16, float16x8_t)
__LD2_LANE_FUNC (float32x2x2_t, float32x2_t, float32x4x2_t, float32_t, v2sf, v4sf,
                 sf, f32, float32x4_t)
__LD2_LANE_FUNC (float64x1x2_t, float64x1_t, float64x2x2_t, float64_t, df, v2df,
                 df, f64, float64x2_t)
__LD2_LANE_FUNC (poly8x8x2_t, poly8x8_t, poly8x16x2_t, poly8_t, v8qi, v16qi, qi, p8,
                 int8x16_t)
__LD2_LANE_FUNC (poly16x4x2_t, poly16x4_t, poly16x8x2_t, poly16_t, v4hi, v8hi, hi,
                 p16, int16x8_t)
__LD2_LANE_FUNC (int8x8x2_t, int8x8_t, int8x16x2_t, int8_t, v8qi, v16qi, qi, s8,
                 int8x16_t)
__LD2_LANE_FUNC (int16x4x2_t, int16x4_t, int16x8x2_t, int16_t, v4hi, v8hi, hi, s16,
                 int16x8_t)
__LD2_LANE_FUNC (int32x2x2_t, int32x2_t, int32x4x2_t, int32_t, v2si, v4si, si, s32,
                 int32x4_t)
__LD2_LANE_FUNC (int64x1x2_t, int64x1_t, int64x2x2_t, int64_t, di, v2di, di, s64,
                 int64x2_t)
__LD2_LANE_FUNC (uint8x8x2_t, uint8x8_t, uint8x16x2_t, uint8_t, v8qi, v16qi, qi, u8,
                 int8x16_t)
__LD2_LANE_FUNC (uint16x4x2_t, uint16x4_t, uint16x8x2_t, uint16_t, v4hi, v8hi, hi,
                 u16, int16x8_t)
__LD2_LANE_FUNC (uint32x2x2_t, uint32x2_t, uint32x4x2_t, uint32_t, v2si, v4si, si,
                 u32, int32x4_t)
__LD2_LANE_FUNC (uint64x1x2_t, uint64x1_t, uint64x2x2_t, uint64_t, di, v2di, di,
                 u64, int64x2_t)

#undef __LD2_LANE_FUNC

/* vld2q_lane */

#define __LD2_LANE_FUNC(intype, vtype, ptrtype, mode, ptrmode, funcsuffix) \
__extension__ static __inline intype __attribute__ ((__always_inline__))   \
vld2q_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c) \
{                                                                          \
  __builtin_aarch64_simd_oi __o;                                           \
  intype ret;                                                              \
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) __b.val[0], 0); \
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) __b.val[1], 1); \
  __o = __builtin_aarch64_ld2_lane##mode (                                 \
        (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c);             \
  ret.val[0] = (vtype) __builtin_aarch64_get_qregoiv4si (__o, 0);          \
  ret.val[1] = (vtype) __builtin_aarch64_get_qregoiv4si (__o, 1);          \
  return ret;                                                              \
}

__LD2_LANE_FUNC (float16x8x2_t, float16x8_t, float16_t, v8hf, hf, f16)
__LD2_LANE_FUNC (float32x4x2_t, float32x4_t, float32_t, v4sf, sf, f32)
__LD2_LANE_FUNC (float64x2x2_t, float64x2_t, float64_t, v2df, df, f64)
__LD2_LANE_FUNC (poly8x16x2_t, poly8x16_t, poly8_t, v16qi, qi, p8)
__LD2_LANE_FUNC (poly16x8x2_t, poly16x8_t, poly16_t, v8hi, hi, p16)
__LD2_LANE_FUNC (int8x16x2_t, int8x16_t, int8_t, v16qi, qi, s8)
__LD2_LANE_FUNC (int16x8x2_t, int16x8_t, int16_t, v8hi, hi, s16)
__LD2_LANE_FUNC (int32x4x2_t, int32x4_t, int32_t, v4si, si, s32)
__LD2_LANE_FUNC (int64x2x2_t, int64x2_t, int64_t, v2di, di, s64)
__LD2_LANE_FUNC (uint8x16x2_t, uint8x16_t, uint8_t, v16qi, qi, u8)
__LD2_LANE_FUNC (uint16x8x2_t, uint16x8_t, uint16_t, v8hi, hi, u16)
__LD2_LANE_FUNC (uint32x4x2_t, uint32x4_t, uint32_t, v4si, si, u32)
__LD2_LANE_FUNC (uint64x2x2_t, uint64x2_t, uint64_t, v2di, di, u64)

#undef __LD2_LANE_FUNC

/* vld3_lane */

#define __LD3_LANE_FUNC(intype, vectype, largetype, ptrtype, mode,         \
                         qmode, ptrmode, funcsuffix, signedtype)           \
__extension__ static __inline intype __attribute__ ((__always_inline__))   \
vld3_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c)  \
{                                                                          \
  __builtin_aarch64_simd_ci __o;                                           \
  largetype __temp;                                                        \
  __temp.val[0] =                                                          \
    vcombine_##funcsuffix (__b.val[0], vcreate_##funcsuffix (0));          \
  __temp.val[1] =                                                          \
    vcombine_##funcsuffix (__b.val[1], vcreate_##funcsuffix (0));          \
  __temp.val[2] =                                                          \
    vcombine_##funcsuffix (__b.val[2], vcreate_##funcsuffix (0));          \
  __o = __builtin_aarch64_set_qregci##qmode (__o,                          \
                                            (signedtype) __temp.val[0],    \
                                            0);                            \
  __o = __builtin_aarch64_set_qregci##qmode (__o,                          \
                                            (signedtype) __temp.val[1],    \
                                            1);                            \
  __o = __builtin_aarch64_set_qregci##qmode (__o,                          \
                                            (signedtype) __temp.val[2],    \
                                            2);                            \
  __o = __builtin_aarch64_ld3_lane##mode (                                 \
          (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c);           \
  __b.val[0] = (vectype) __builtin_aarch64_get_dregcidi (__o, 0);          \
  __b.val[1] = (vectype) __builtin_aarch64_get_dregcidi (__o, 1);          \
  __b.val[2] = (vectype) __builtin_aarch64_get_dregcidi (__o, 2);          \
  return __b;                                                              \
}

__LD3_LANE_FUNC (float16x4x3_t, float16x4_t, float16x8x3_t, float16_t, v4hf,
                 v8hf, hf, f16, float16x8_t)
__LD3_LANE_FUNC (float32x2x3_t, float32x2_t, float32x4x3_t, float32_t, v2sf, v4sf,
                 sf, f32, float32x4_t)
__LD3_LANE_FUNC (float64x1x3_t, float64x1_t, float64x2x3_t, float64_t, df, v2df,
                 df, f64, float64x2_t)
__LD3_LANE_FUNC (poly8x8x3_t, poly8x8_t, poly8x16x3_t, poly8_t, v8qi, v16qi, qi, p8,
                 int8x16_t)
__LD3_LANE_FUNC (poly16x4x3_t, poly16x4_t, poly16x8x3_t, poly16_t, v4hi, v8hi, hi,
                 p16, int16x8_t)
__LD3_LANE_FUNC (int8x8x3_t, int8x8_t, int8x16x3_t, int8_t, v8qi, v16qi, qi, s8,
                 int8x16_t)
__LD3_LANE_FUNC (int16x4x3_t, int16x4_t, int16x8x3_t, int16_t, v4hi, v8hi, hi, s16,
                 int16x8_t)
__LD3_LANE_FUNC (int32x2x3_t, int32x2_t, int32x4x3_t, int32_t, v2si, v4si, si, s32,
                 int32x4_t)
__LD3_LANE_FUNC (int64x1x3_t, int64x1_t, int64x2x3_t, int64_t, di, v2di, di, s64,
                 int64x2_t)
__LD3_LANE_FUNC (uint8x8x3_t, uint8x8_t, uint8x16x3_t, uint8_t, v8qi, v16qi, qi, u8,
                 int8x16_t)
__LD3_LANE_FUNC (uint16x4x3_t, uint16x4_t, uint16x8x3_t, uint16_t, v4hi, v8hi, hi,
                 u16, int16x8_t)
__LD3_LANE_FUNC (uint32x2x3_t, uint32x2_t, uint32x4x3_t, uint32_t, v2si, v4si, si,
                 u32, int32x4_t)
__LD3_LANE_FUNC (uint64x1x3_t, uint64x1_t, uint64x2x3_t, uint64_t, di, v2di, di,
                 u64, int64x2_t)

#undef __LD3_LANE_FUNC

/* vld3q_lane */

#define __LD3_LANE_FUNC(intype, vtype, ptrtype, mode, ptrmode, funcsuffix) \
__extension__ static __inline intype __attribute__ ((__always_inline__))   \
vld3q_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c) \
{                                                                          \
  __builtin_aarch64_simd_ci __o;                                           \
  intype ret;                                                              \
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) __b.val[0], 0); \
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) __b.val[1], 1); \
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) __b.val[2], 2); \
  __o = __builtin_aarch64_ld3_lane##mode (                                 \
        (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c);             \
  ret.val[0] = (vtype) __builtin_aarch64_get_qregciv4si (__o, 0);          \
  ret.val[1] = (vtype) __builtin_aarch64_get_qregciv4si (__o, 1);          \
  ret.val[2] = (vtype) __builtin_aarch64_get_qregciv4si (__o, 2);          \
  return ret;                                                              \
}

__LD3_LANE_FUNC (float16x8x3_t, float16x8_t, float16_t, v8hf, hf, f16)
__LD3_LANE_FUNC (float32x4x3_t, float32x4_t, float32_t, v4sf, sf, f32)
__LD3_LANE_FUNC (float64x2x3_t, float64x2_t, float64_t, v2df, df, f64)
__LD3_LANE_FUNC (poly8x16x3_t, poly8x16_t, poly8_t, v16qi, qi, p8)
__LD3_LANE_FUNC (poly16x8x3_t, poly16x8_t, poly16_t, v8hi, hi, p16)
__LD3_LANE_FUNC (int8x16x3_t, int8x16_t, int8_t, v16qi, qi, s8)
__LD3_LANE_FUNC (int16x8x3_t, int16x8_t, int16_t, v8hi, hi, s16)
__LD3_LANE_FUNC (int32x4x3_t, int32x4_t, int32_t, v4si, si, s32)
__LD3_LANE_FUNC (int64x2x3_t, int64x2_t, int64_t, v2di, di, s64)
__LD3_LANE_FUNC (uint8x16x3_t, uint8x16_t, uint8_t, v16qi, qi, u8)
__LD3_LANE_FUNC (uint16x8x3_t, uint16x8_t, uint16_t, v8hi, hi, u16)
__LD3_LANE_FUNC (uint32x4x3_t, uint32x4_t, uint32_t, v4si, si, u32)
__LD3_LANE_FUNC (uint64x2x3_t, uint64x2_t, uint64_t, v2di, di, u64)

#undef __LD3_LANE_FUNC

/* vld4_lane */

#define __LD4_LANE_FUNC(intype, vectype, largetype, ptrtype, mode,         \
                         qmode, ptrmode, funcsuffix, signedtype)           \
__extension__ static __inline intype __attribute__ ((__always_inline__))   \
vld4_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c)  \
{                                                                          \
  __builtin_aarch64_simd_xi __o;                                           \
  largetype __temp;                                                        \
  __temp.val[0] =                                                          \
    vcombine_##funcsuffix (__b.val[0], vcreate_##funcsuffix (0));          \
  __temp.val[1] =                                                          \
    vcombine_##funcsuffix (__b.val[1], vcreate_##funcsuffix (0));          \
  __temp.val[2] =                                                          \
    vcombine_##funcsuffix (__b.val[2], vcreate_##funcsuffix (0));          \
  __temp.val[3] =                                                          \
    vcombine_##funcsuffix (__b.val[3], vcreate_##funcsuffix (0));          \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                          \
                                            (signedtype) __temp.val[0],    \
                                            0);                            \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                          \
                                            (signedtype) __temp.val[1],    \
                                            1);                            \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                          \
                                            (signedtype) __temp.val[2],    \
                                            2);                            \
  __o = __builtin_aarch64_set_qregxi##qmode (__o,                          \
                                            (signedtype) __temp.val[3],    \
                                            3);                            \
  __o = __builtin_aarch64_ld4_lane##mode (                                 \
          (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c);           \
  __b.val[0] = (vectype) __builtin_aarch64_get_dregxidi (__o, 0);          \
  __b.val[1] = (vectype) __builtin_aarch64_get_dregxidi (__o, 1);          \
  __b.val[2] = (vectype) __builtin_aarch64_get_dregxidi (__o, 2);          \
  __b.val[3] = (vectype) __builtin_aarch64_get_dregxidi (__o, 3);          \
  return __b;                                                              \
}

/* vld4q_lane */

__LD4_LANE_FUNC (float16x4x4_t, float16x4_t, float16x8x4_t, float16_t, v4hf,
                 v8hf, hf, f16, float16x8_t)
__LD4_LANE_FUNC (float32x2x4_t, float32x2_t, float32x4x4_t, float32_t, v2sf, v4sf,
                 sf, f32, float32x4_t)
__LD4_LANE_FUNC (float64x1x4_t, float64x1_t, float64x2x4_t, float64_t, df, v2df,
                 df, f64, float64x2_t)
__LD4_LANE_FUNC (poly8x8x4_t, poly8x8_t, poly8x16x4_t, poly8_t, v8qi, v16qi, qi, p8,
                 int8x16_t)
__LD4_LANE_FUNC (poly16x4x4_t, poly16x4_t, poly16x8x4_t, poly16_t, v4hi, v8hi, hi,
                 p16, int16x8_t)
__LD4_LANE_FUNC (int8x8x4_t, int8x8_t, int8x16x4_t, int8_t, v8qi, v16qi, qi, s8,
                 int8x16_t)
__LD4_LANE_FUNC (int16x4x4_t, int16x4_t, int16x8x4_t, int16_t, v4hi, v8hi, hi, s16,
                 int16x8_t)
__LD4_LANE_FUNC (int32x2x4_t, int32x2_t, int32x4x4_t, int32_t, v2si, v4si, si, s32,
                 int32x4_t)
__LD4_LANE_FUNC (int64x1x4_t, int64x1_t, int64x2x4_t, int64_t, di, v2di, di, s64,
                 int64x2_t)
__LD4_LANE_FUNC (uint8x8x4_t, uint8x8_t, uint8x16x4_t, uint8_t, v8qi, v16qi, qi, u8,
                 int8x16_t)
__LD4_LANE_FUNC (uint16x4x4_t, uint16x4_t, uint16x8x4_t, uint16_t, v4hi, v8hi, hi,
                 u16, int16x8_t)
__LD4_LANE_FUNC (uint32x2x4_t, uint32x2_t, uint32x4x4_t, uint32_t, v2si, v4si, si,
                 u32, int32x4_t)
__LD4_LANE_FUNC (uint64x1x4_t, uint64x1_t, uint64x2x4_t, uint64_t, di, v2di, di,
                 u64, int64x2_t)

#undef __LD4_LANE_FUNC

/* vld4q_lane */

#define __LD4_LANE_FUNC(intype, vtype, ptrtype, mode, ptrmode, funcsuffix) \
__extension__ static __inline intype __attribute__ ((__always_inline__))   \
vld4q_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c) \
{                                                                          \
  __builtin_aarch64_simd_xi __o;                                           \
  intype ret;                                                              \
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0); \
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1); \
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2); \
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3); \
  __o = __builtin_aarch64_ld4_lane##mode (                                 \
        (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c);             \
  ret.val[0] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 0);          \
  ret.val[1] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 1);          \
  ret.val[2] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 2);          \
  ret.val[3] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 3);          \
  return ret;                                                              \
}

__LD4_LANE_FUNC (float16x8x4_t, float16x8_t, float16_t, v8hf, hf, f16)
__LD4_LANE_FUNC (float32x4x4_t, float32x4_t, float32_t, v4sf, sf, f32)
__LD4_LANE_FUNC (float64x2x4_t, float64x2_t, float64_t, v2df, df, f64)
__LD4_LANE_FUNC (poly8x16x4_t, poly8x16_t, poly8_t, v16qi, qi, p8)
__LD4_LANE_FUNC (poly16x8x4_t, poly16x8_t, poly16_t, v8hi, hi, p16)
__LD4_LANE_FUNC (int8x16x4_t, int8x16_t, int8_t, v16qi, qi, s8)
__LD4_LANE_FUNC (int16x8x4_t, int16x8_t, int16_t, v8hi, hi, s16)
__LD4_LANE_FUNC (int32x4x4_t, int32x4_t, int32_t, v4si, si, s32)
__LD4_LANE_FUNC (int64x2x4_t, int64x2_t, int64_t, v2di, di, s64)
__LD4_LANE_FUNC (uint8x16x4_t, uint8x16_t, uint8_t, v16qi, qi, u8)
__LD4_LANE_FUNC (uint16x8x4_t, uint16x8_t, uint16_t, v8hi, hi, u16)
__LD4_LANE_FUNC (uint32x4x4_t, uint32x4_t, uint32_t, v4si, si, u32)
__LD4_LANE_FUNC (uint64x2x4_t, uint64x2_t, uint64_t, v2di, di, u64)

#undef __LD4_LANE_FUNC

/* vmax */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmax_f32 (float32x2_t __a, float32x2_t __b)
{
  return __builtin_aarch64_smax_nanv2sf (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmax_s8 (int8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_smaxv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmax_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_smaxv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmax_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_smaxv2si (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmax_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_umaxv8qi ((int8x8_t) __a,
                                                 (int8x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmax_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_umaxv4hi ((int16x4_t) __a,
                                                  (int16x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmax_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_umaxv2si ((int32x2_t) __a,
                                                  (int32x2_t) __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmaxq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_smax_nanv4sf (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmaxq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_smax_nanv2df (__a, __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmaxq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_smaxv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmaxq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_smaxv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmaxq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_smaxv4si (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmaxq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint8x16_t) __builtin_aarch64_umaxv16qi ((int8x16_t) __a,
                                                   (int8x16_t) __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmaxq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_umaxv8hi ((int16x8_t) __a,
                                                  (int16x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmaxq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_umaxv4si ((int32x4_t) __a,
                                                  (int32x4_t) __b);
}
/* vmulx */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmulx_f32 (float32x2_t __a, float32x2_t __b)
{
  return __builtin_aarch64_fmulxv2sf (__a, __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulxq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_fmulxv4sf (__a, __b);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmulx_f64 (float64x1_t __a, float64x1_t __b)
{
  return (float64x1_t) {__builtin_aarch64_fmulxdf (__a[0], __b[0])};
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulxq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_fmulxv2df (__a, __b);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmulxs_f32 (float32_t __a, float32_t __b)
{
  return __builtin_aarch64_fmulxsf (__a, __b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmulxd_f64 (float64_t __a, float64_t __b)
{
  return __builtin_aarch64_fmulxdf (__a, __b);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmulx_lane_f32 (float32x2_t __a, float32x2_t __v, const int __lane)
{
  return vmulx_f32 (__a, __aarch64_vdup_lane_f32 (__v, __lane));
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmulx_lane_f64 (float64x1_t __a, float64x1_t __v, const int __lane)
{
  return vmulx_f64 (__a, __aarch64_vdup_lane_f64 (__v, __lane));
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulxq_lane_f32 (float32x4_t __a, float32x2_t __v, const int __lane)
{
  return vmulxq_f32 (__a, __aarch64_vdupq_lane_f32 (__v, __lane));
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulxq_lane_f64 (float64x2_t __a, float64x1_t __v, const int __lane)
{
  return vmulxq_f64 (__a, __aarch64_vdupq_lane_f64 (__v, __lane));
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmulx_laneq_f32 (float32x2_t __a, float32x4_t __v, const int __lane)
{
  return vmulx_f32 (__a, __aarch64_vdup_laneq_f32 (__v, __lane));
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmulx_laneq_f64 (float64x1_t __a, float64x2_t __v, const int __lane)
{
  return vmulx_f64 (__a, __aarch64_vdup_laneq_f64 (__v, __lane));
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulxq_laneq_f32 (float32x4_t __a, float32x4_t __v, const int __lane)
{
  return vmulxq_f32 (__a, __aarch64_vdupq_laneq_f32 (__v, __lane));
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulxq_laneq_f64 (float64x2_t __a, float64x2_t __v, const int __lane)
{
  return vmulxq_f64 (__a, __aarch64_vdupq_laneq_f64 (__v, __lane));
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmulxs_lane_f32 (float32_t __a, float32x2_t __v, const int __lane)
{
  return vmulxs_f32 (__a, __aarch64_vget_lane_any (__v, __lane));
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmulxs_laneq_f32 (float32_t __a, float32x4_t __v, const int __lane)
{
  return vmulxs_f32 (__a, __aarch64_vget_lane_any (__v, __lane));
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmulxd_lane_f64 (float64_t __a, float64x1_t __v, const int __lane)
{
  return vmulxd_f64 (__a, __aarch64_vget_lane_any (__v, __lane));
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmulxd_laneq_f64 (float64_t __a, float64x2_t __v, const int __lane)
{
  return vmulxd_f64 (__a, __aarch64_vget_lane_any (__v, __lane));
}

/* vpmax  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vpmax_s8 (int8x8_t a, int8x8_t b)
{
  return __builtin_aarch64_smaxpv8qi (a, b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vpmax_s16 (int16x4_t a, int16x4_t b)
{
  return __builtin_aarch64_smaxpv4hi (a, b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vpmax_s32 (int32x2_t a, int32x2_t b)
{
  return __builtin_aarch64_smaxpv2si (a, b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vpmax_u8 (uint8x8_t a, uint8x8_t b)
{
  return (uint8x8_t) __builtin_aarch64_umaxpv8qi ((int8x8_t) a,
                                                  (int8x8_t) b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vpmax_u16 (uint16x4_t a, uint16x4_t b)
{
  return (uint16x4_t) __builtin_aarch64_umaxpv4hi ((int16x4_t) a,
                                                   (int16x4_t) b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vpmax_u32 (uint32x2_t a, uint32x2_t b)
{
  return (uint32x2_t) __builtin_aarch64_umaxpv2si ((int32x2_t) a,
                                                   (int32x2_t) b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vpmaxq_s8 (int8x16_t a, int8x16_t b)
{
  return __builtin_aarch64_smaxpv16qi (a, b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vpmaxq_s16 (int16x8_t a, int16x8_t b)
{
  return __builtin_aarch64_smaxpv8hi (a, b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vpmaxq_s32 (int32x4_t a, int32x4_t b)
{
  return __builtin_aarch64_smaxpv4si (a, b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vpmaxq_u8 (uint8x16_t a, uint8x16_t b)
{
  return (uint8x16_t) __builtin_aarch64_umaxpv16qi ((int8x16_t) a,
                                                    (int8x16_t) b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vpmaxq_u16 (uint16x8_t a, uint16x8_t b)
{
  return (uint16x8_t) __builtin_aarch64_umaxpv8hi ((int16x8_t) a,
                                                   (int16x8_t) b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vpmaxq_u32 (uint32x4_t a, uint32x4_t b)
{
  return (uint32x4_t) __builtin_aarch64_umaxpv4si ((int32x4_t) a,
                                                   (int32x4_t) b);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vpmax_f32 (float32x2_t a, float32x2_t b)
{
  return __builtin_aarch64_smax_nanpv2sf (a, b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vpmaxq_f32 (float32x4_t a, float32x4_t b)
{
  return __builtin_aarch64_smax_nanpv4sf (a, b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vpmaxq_f64 (float64x2_t a, float64x2_t b)
{
  return __builtin_aarch64_smax_nanpv2df (a, b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vpmaxqd_f64 (float64x2_t a)
{
  return __builtin_aarch64_reduc_smax_nan_scal_v2df (a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vpmaxs_f32 (float32x2_t a)
{
  return __builtin_aarch64_reduc_smax_nan_scal_v2sf (a);
}

/* vpmaxnm  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vpmaxnm_f32 (float32x2_t a, float32x2_t b)
{
  return __builtin_aarch64_smaxpv2sf (a, b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vpmaxnmq_f32 (float32x4_t a, float32x4_t b)
{
  return __builtin_aarch64_smaxpv4sf (a, b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vpmaxnmq_f64 (float64x2_t a, float64x2_t b)
{
  return __builtin_aarch64_smaxpv2df (a, b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vpmaxnmqd_f64 (float64x2_t a)
{
  return __builtin_aarch64_reduc_smax_scal_v2df (a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vpmaxnms_f32 (float32x2_t a)
{
  return __builtin_aarch64_reduc_smax_scal_v2sf (a);
}

/* vpmin  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vpmin_s8 (int8x8_t a, int8x8_t b)
{
  return __builtin_aarch64_sminpv8qi (a, b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vpmin_s16 (int16x4_t a, int16x4_t b)
{
  return __builtin_aarch64_sminpv4hi (a, b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vpmin_s32 (int32x2_t a, int32x2_t b)
{
  return __builtin_aarch64_sminpv2si (a, b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vpmin_u8 (uint8x8_t a, uint8x8_t b)
{
  return (uint8x8_t) __builtin_aarch64_uminpv8qi ((int8x8_t) a,
                                                  (int8x8_t) b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vpmin_u16 (uint16x4_t a, uint16x4_t b)
{
  return (uint16x4_t) __builtin_aarch64_uminpv4hi ((int16x4_t) a,
                                                   (int16x4_t) b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vpmin_u32 (uint32x2_t a, uint32x2_t b)
{
  return (uint32x2_t) __builtin_aarch64_uminpv2si ((int32x2_t) a,
                                                   (int32x2_t) b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vpminq_s8 (int8x16_t a, int8x16_t b)
{
  return __builtin_aarch64_sminpv16qi (a, b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vpminq_s16 (int16x8_t a, int16x8_t b)
{
  return __builtin_aarch64_sminpv8hi (a, b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vpminq_s32 (int32x4_t a, int32x4_t b)
{
  return __builtin_aarch64_sminpv4si (a, b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vpminq_u8 (uint8x16_t a, uint8x16_t b)
{
  return (uint8x16_t) __builtin_aarch64_uminpv16qi ((int8x16_t) a,
                                                    (int8x16_t) b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vpminq_u16 (uint16x8_t a, uint16x8_t b)
{
  return (uint16x8_t) __builtin_aarch64_uminpv8hi ((int16x8_t) a,
                                                   (int16x8_t) b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vpminq_u32 (uint32x4_t a, uint32x4_t b)
{
  return (uint32x4_t) __builtin_aarch64_uminpv4si ((int32x4_t) a,
                                                   (int32x4_t) b);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vpmin_f32 (float32x2_t a, float32x2_t b)
{
  return __builtin_aarch64_smin_nanpv2sf (a, b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vpminq_f32 (float32x4_t a, float32x4_t b)
{
  return __builtin_aarch64_smin_nanpv4sf (a, b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vpminq_f64 (float64x2_t a, float64x2_t b)
{
  return __builtin_aarch64_smin_nanpv2df (a, b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vpminqd_f64 (float64x2_t a)
{
  return __builtin_aarch64_reduc_smin_nan_scal_v2df (a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vpmins_f32 (float32x2_t a)
{
  return __builtin_aarch64_reduc_smin_nan_scal_v2sf (a);
}

/* vpminnm  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vpminnm_f32 (float32x2_t a, float32x2_t b)
{
  return __builtin_aarch64_sminpv2sf (a, b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vpminnmq_f32 (float32x4_t a, float32x4_t b)
{
  return __builtin_aarch64_sminpv4sf (a, b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vpminnmq_f64 (float64x2_t a, float64x2_t b)
{
  return __builtin_aarch64_sminpv2df (a, b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vpminnmqd_f64 (float64x2_t a)
{
  return __builtin_aarch64_reduc_smin_scal_v2df (a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vpminnms_f32 (float32x2_t a)
{
  return __builtin_aarch64_reduc_smin_scal_v2sf (a);
}

/* vmaxnm  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmaxnm_f32 (float32x2_t __a, float32x2_t __b)
{
  return __builtin_aarch64_smaxv2sf (__a, __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmaxnmq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_smaxv4sf (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmaxnmq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_smaxv2df (__a, __b);
}

/* vmaxv  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmaxv_f32 (float32x2_t __a)
{
  return __builtin_aarch64_reduc_smax_nan_scal_v2sf (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vmaxv_s8 (int8x8_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v8qi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vmaxv_s16 (int16x4_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v4hi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vmaxv_s32 (int32x2_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v2si (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vmaxv_u8 (uint8x8_t __a)
{
  return __builtin_aarch64_reduc_umax_scal_v8qi_uu (__a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vmaxv_u16 (uint16x4_t __a)
{
  return __builtin_aarch64_reduc_umax_scal_v4hi_uu (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vmaxv_u32 (uint32x2_t __a)
{
  return __builtin_aarch64_reduc_umax_scal_v2si_uu (__a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmaxvq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_reduc_smax_nan_scal_v4sf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmaxvq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_reduc_smax_nan_scal_v2df (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vmaxvq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v16qi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vmaxvq_s16 (int16x8_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v8hi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vmaxvq_s32 (int32x4_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v4si (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vmaxvq_u8 (uint8x16_t __a)
{
  return __builtin_aarch64_reduc_umax_scal_v16qi_uu (__a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vmaxvq_u16 (uint16x8_t __a)
{
  return __builtin_aarch64_reduc_umax_scal_v8hi_uu (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vmaxvq_u32 (uint32x4_t __a)
{
  return __builtin_aarch64_reduc_umax_scal_v4si_uu (__a);
}

/* vmaxnmv  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmaxnmv_f32 (float32x2_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v2sf (__a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmaxnmvq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v4sf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmaxnmvq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_reduc_smax_scal_v2df (__a);
}

/* vmin  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmin_f32 (float32x2_t __a, float32x2_t __b)
{
  return __builtin_aarch64_smin_nanv2sf (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmin_s8 (int8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_sminv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmin_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_sminv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmin_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_sminv2si (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmin_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_uminv8qi ((int8x8_t) __a,
                                                 (int8x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmin_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_uminv4hi ((int16x4_t) __a,
                                                  (int16x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmin_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_uminv2si ((int32x2_t) __a,
                                                  (int32x2_t) __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vminq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_smin_nanv4sf (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vminq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_smin_nanv2df (__a, __b);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vminq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_sminv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vminq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_sminv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vminq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_sminv4si (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vminq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return (uint8x16_t) __builtin_aarch64_uminv16qi ((int8x16_t) __a,
                                                   (int8x16_t) __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vminq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return (uint16x8_t) __builtin_aarch64_uminv8hi ((int16x8_t) __a,
                                                  (int16x8_t) __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vminq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return (uint32x4_t) __builtin_aarch64_uminv4si ((int32x4_t) __a,
                                                  (int32x4_t) __b);
}

/* vminnm  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vminnm_f32 (float32x2_t __a, float32x2_t __b)
{
  return __builtin_aarch64_sminv2sf (__a, __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vminnmq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_sminv4sf (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vminnmq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_sminv2df (__a, __b);
}

/* vminv  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vminv_f32 (float32x2_t __a)
{
  return __builtin_aarch64_reduc_smin_nan_scal_v2sf (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vminv_s8 (int8x8_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v8qi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vminv_s16 (int16x4_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v4hi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vminv_s32 (int32x2_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v2si (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vminv_u8 (uint8x8_t __a)
{
  return __builtin_aarch64_reduc_umin_scal_v8qi_uu (__a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vminv_u16 (uint16x4_t __a)
{
  return __builtin_aarch64_reduc_umin_scal_v4hi_uu (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vminv_u32 (uint32x2_t __a)
{
  return __builtin_aarch64_reduc_umin_scal_v2si_uu (__a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vminvq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_reduc_smin_nan_scal_v4sf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vminvq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_reduc_smin_nan_scal_v2df (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vminvq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v16qi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vminvq_s16 (int16x8_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v8hi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vminvq_s32 (int32x4_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v4si (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vminvq_u8 (uint8x16_t __a)
{
  return __builtin_aarch64_reduc_umin_scal_v16qi_uu (__a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vminvq_u16 (uint16x8_t __a)
{
  return __builtin_aarch64_reduc_umin_scal_v8hi_uu (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vminvq_u32 (uint32x4_t __a)
{
  return __builtin_aarch64_reduc_umin_scal_v4si_uu (__a);
}

/* vminnmv  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vminnmv_f32 (float32x2_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v2sf (__a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vminnmvq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v4sf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vminnmvq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_reduc_smin_scal_v2df (__a);
}

/* vmla */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmla_f32 (float32x2_t a, float32x2_t b, float32x2_t c)
{
  return a + b * c;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmla_f64 (float64x1_t __a, float64x1_t __b, float64x1_t __c)
{
  return __a + __b * __c;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlaq_f32 (float32x4_t a, float32x4_t b, float32x4_t c)
{
  return a + b * c;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmlaq_f64 (float64x2_t a, float64x2_t b, float64x2_t c)
{
  return a + b * c;
}

/* vmla_lane  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmla_lane_f32 (float32x2_t __a, float32x2_t __b,
               float32x2_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmla_lane_s16 (int16x4_t __a, int16x4_t __b,
                int16x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmla_lane_s32 (int32x2_t __a, int32x2_t __b,
                int32x2_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmla_lane_u16 (uint16x4_t __a, uint16x4_t __b,
                uint16x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmla_lane_u32 (uint32x2_t __a, uint32x2_t __b,
               uint32x2_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

/* vmla_laneq  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmla_laneq_f32 (float32x2_t __a, float32x2_t __b,
                float32x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmla_laneq_s16 (int16x4_t __a, int16x4_t __b,
                int16x8_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmla_laneq_s32 (int32x2_t __a, int32x2_t __b,
                int32x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmla_laneq_u16 (uint16x4_t __a, uint16x4_t __b,
                uint16x8_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmla_laneq_u32 (uint32x2_t __a, uint32x2_t __b,
                uint32x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

/* vmlaq_lane  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlaq_lane_f32 (float32x4_t __a, float32x4_t __b,
                float32x2_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlaq_lane_s16 (int16x8_t __a, int16x8_t __b,
                int16x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlaq_lane_s32 (int32x4_t __a, int32x4_t __b,
                int32x2_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlaq_lane_u16 (uint16x8_t __a, uint16x8_t __b,
                uint16x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlaq_lane_u32 (uint32x4_t __a, uint32x4_t __b,
                uint32x2_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

  /* vmlaq_laneq  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlaq_laneq_f32 (float32x4_t __a, float32x4_t __b,
                 float32x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlaq_laneq_s16 (int16x8_t __a, int16x8_t __b,
                int16x8_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlaq_laneq_s32 (int32x4_t __a, int32x4_t __b,
                int32x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlaq_laneq_u16 (uint16x8_t __a, uint16x8_t __b,
                uint16x8_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlaq_laneq_u32 (uint32x4_t __a, uint32x4_t __b,
                uint32x4_t __c, const int __lane)
{
  return (__a + (__b * __aarch64_vget_lane_any (__c, __lane)));
}

/* vmls  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmls_f32 (float32x2_t a, float32x2_t b, float32x2_t c)
{
  return a - b * c;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmls_f64 (float64x1_t __a, float64x1_t __b, float64x1_t __c)
{
  return __a - __b * __c;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlsq_f32 (float32x4_t a, float32x4_t b, float32x4_t c)
{
  return a - b * c;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmlsq_f64 (float64x2_t a, float64x2_t b, float64x2_t c)
{
  return a - b * c;
}

/* vmls_lane  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmls_lane_f32 (float32x2_t __a, float32x2_t __b,
               float32x2_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmls_lane_s16 (int16x4_t __a, int16x4_t __b,
                int16x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmls_lane_s32 (int32x2_t __a, int32x2_t __b,
                int32x2_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmls_lane_u16 (uint16x4_t __a, uint16x4_t __b,
                uint16x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmls_lane_u32 (uint32x2_t __a, uint32x2_t __b,
               uint32x2_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

/* vmls_laneq  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmls_laneq_f32 (float32x2_t __a, float32x2_t __b,
               float32x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmls_laneq_s16 (int16x4_t __a, int16x4_t __b,
                int16x8_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmls_laneq_s32 (int32x2_t __a, int32x2_t __b,
                int32x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmls_laneq_u16 (uint16x4_t __a, uint16x4_t __b,
                uint16x8_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmls_laneq_u32 (uint32x2_t __a, uint32x2_t __b,
                uint32x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

/* vmlsq_lane  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlsq_lane_f32 (float32x4_t __a, float32x4_t __b,
                float32x2_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlsq_lane_s16 (int16x8_t __a, int16x8_t __b,
                int16x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsq_lane_s32 (int32x4_t __a, int32x4_t __b,
                int32x2_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlsq_lane_u16 (uint16x8_t __a, uint16x8_t __b,
                uint16x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsq_lane_u32 (uint32x4_t __a, uint32x4_t __b,
                uint32x2_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

  /* vmlsq_laneq  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmlsq_laneq_f32 (float32x4_t __a, float32x4_t __b,
                float32x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmlsq_laneq_s16 (int16x8_t __a, int16x8_t __b,
                int16x8_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmlsq_laneq_s32 (int32x4_t __a, int32x4_t __b,
                int32x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}
__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmlsq_laneq_u16 (uint16x8_t __a, uint16x8_t __b,
                uint16x8_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmlsq_laneq_u32 (uint32x4_t __a, uint32x4_t __b,
                uint32x4_t __c, const int __lane)
{
  return (__a - (__b * __aarch64_vget_lane_any (__c, __lane)));
}

/* vmov_n_  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmov_n_f32 (float32_t __a)
{
  return vdup_n_f32 (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmov_n_f64 (float64_t __a)
{
  return (float64x1_t) {__a};
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vmov_n_p8 (poly8_t __a)
{
  return vdup_n_p8 (__a);
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vmov_n_p16 (poly16_t __a)
{
  return vdup_n_p16 (__a);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vmov_n_s8 (int8_t __a)
{
  return vdup_n_s8 (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmov_n_s16 (int16_t __a)
{
  return vdup_n_s16 (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmov_n_s32 (int32_t __a)
{
  return vdup_n_s32 (__a);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vmov_n_s64 (int64_t __a)
{
  return (int64x1_t) {__a};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vmov_n_u8 (uint8_t __a)
{
  return vdup_n_u8 (__a);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmov_n_u16 (uint16_t __a)
{
    return vdup_n_u16 (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmov_n_u32 (uint32_t __a)
{
   return vdup_n_u32 (__a);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vmov_n_u64 (uint64_t __a)
{
  return (uint64x1_t) {__a};
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmovq_n_f32 (float32_t __a)
{
  return vdupq_n_f32 (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmovq_n_f64 (float64_t __a)
{
  return vdupq_n_f64 (__a);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vmovq_n_p8 (poly8_t __a)
{
  return vdupq_n_p8 (__a);
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vmovq_n_p16 (poly16_t __a)
{
  return vdupq_n_p16 (__a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vmovq_n_s8 (int8_t __a)
{
  return vdupq_n_s8 (__a);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmovq_n_s16 (int16_t __a)
{
  return vdupq_n_s16 (__a);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmovq_n_s32 (int32_t __a)
{
  return vdupq_n_s32 (__a);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vmovq_n_s64 (int64_t __a)
{
  return vdupq_n_s64 (__a);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vmovq_n_u8 (uint8_t __a)
{
  return vdupq_n_u8 (__a);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmovq_n_u16 (uint16_t __a)
{
  return vdupq_n_u16 (__a);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmovq_n_u32 (uint32_t __a)
{
  return vdupq_n_u32 (__a);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vmovq_n_u64 (uint64_t __a)
{
  return vdupq_n_u64 (__a);
}

/* vmul_lane  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_lane_f32 (float32x2_t __a, float32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmul_lane_f64 (float64x1_t __a, float64x1_t __b, const int __lane)
{
  return __a * __b;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmul_lane_s16 (int16x4_t __a, int16x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmul_lane_s32 (int32x2_t __a, int32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmul_lane_u16 (uint16x4_t __a, uint16x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmul_lane_u32 (uint32x2_t __a, uint32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

/* vmuld_lane  */

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmuld_lane_f64 (float64_t __a, float64x1_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmuld_laneq_f64 (float64_t __a, float64x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

/* vmuls_lane  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmuls_lane_f32 (float32_t __a, float32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmuls_laneq_f32 (float32_t __a, float32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

/* vmul_laneq  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_laneq_f32 (float32x2_t __a, float32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmul_laneq_f64 (float64x1_t __a, float64x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmul_laneq_s16 (int16x4_t __a, int16x8_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmul_laneq_s32 (int32x2_t __a, int32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmul_laneq_u16 (uint16x4_t __a, uint16x8_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmul_laneq_u32 (uint32x2_t __a, uint32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

/* vmul_n  */

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmul_n_f64  (float64x1_t __a, float64_t __b)
{
  return (float64x1_t) { vget_lane_f64 (__a, 0) * __b };
}

/* vmulq_lane  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_lane_f32 (float32x4_t __a, float32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulq_lane_f64 (float64x2_t __a, float64x1_t __b, const int __lane)
{
  __AARCH64_LANE_CHECK (__a, __lane);
  return __a * __b[0];
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmulq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmulq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmulq_lane_u16 (uint16x8_t __a, uint16x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmulq_lane_u32 (uint32x4_t __a, uint32x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

/* vmulq_laneq  */

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_laneq_f32 (float32x4_t __a, float32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulq_laneq_f64 (float64x2_t __a, float64x2_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmulq_laneq_s16 (int16x8_t __a, int16x8_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmulq_laneq_s32 (int32x4_t __a, int32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmulq_laneq_u16 (uint16x8_t __a, uint16x8_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmulq_laneq_u32 (uint32x4_t __a, uint32x4_t __b, const int __lane)
{
  return __a * __aarch64_vget_lane_any (__b, __lane);
}

/* vneg  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vneg_f32 (float32x2_t __a)
{
  return -__a;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vneg_f64 (float64x1_t __a)
{
  return -__a;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vneg_s8 (int8x8_t __a)
{
  return -__a;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vneg_s16 (int16x4_t __a)
{
  return -__a;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vneg_s32 (int32x2_t __a)
{
  return -__a;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vneg_s64 (int64x1_t __a)
{
  return -__a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vnegq_f32 (float32x4_t __a)
{
  return -__a;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vnegq_f64 (float64x2_t __a)
{
  return -__a;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vnegq_s8 (int8x16_t __a)
{
  return -__a;
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vnegq_s16 (int16x8_t __a)
{
  return -__a;
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vnegq_s32 (int32x4_t __a)
{
  return -__a;
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vnegq_s64 (int64x2_t __a)
{
  return -__a;
}

/* vpadd  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vpadd_s8 (int8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_addpv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vpadd_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_addpv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vpadd_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_addpv2si (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vpadd_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return (uint8x8_t) __builtin_aarch64_addpv8qi ((int8x8_t) __a,
                                                 (int8x8_t) __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vpadd_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return (uint16x4_t) __builtin_aarch64_addpv4hi ((int16x4_t) __a,
                                                  (int16x4_t) __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vpadd_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return (uint32x2_t) __builtin_aarch64_addpv2si ((int32x2_t) __a,
                                                  (int32x2_t) __b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vpaddd_f64 (float64x2_t __a)
{
  return __builtin_aarch64_reduc_plus_scal_v2df (__a);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vpaddd_s64 (int64x2_t __a)
{
  return __builtin_aarch64_addpdi (__a);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vpaddd_u64 (uint64x2_t __a)
{
  return __builtin_aarch64_addpdi ((int64x2_t) __a);
}

/* vqabs */

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqabsq_s64 (int64x2_t __a)
{
  return (int64x2_t) __builtin_aarch64_sqabsv2di (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqabsb_s8 (int8_t __a)
{
  return (int8_t) __builtin_aarch64_sqabsqi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqabsh_s16 (int16_t __a)
{
  return (int16_t) __builtin_aarch64_sqabshi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqabss_s32 (int32_t __a)
{
  return (int32_t) __builtin_aarch64_sqabssi (__a);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqabsd_s64 (int64_t __a)
{
  return __builtin_aarch64_sqabsdi (__a);
}

/* vqadd */

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqaddb_s8 (int8_t __a, int8_t __b)
{
  return (int8_t) __builtin_aarch64_sqaddqi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqaddh_s16 (int16_t __a, int16_t __b)
{
  return (int16_t) __builtin_aarch64_sqaddhi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqadds_s32 (int32_t __a, int32_t __b)
{
  return (int32_t) __builtin_aarch64_sqaddsi (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqaddd_s64 (int64_t __a, int64_t __b)
{
  return __builtin_aarch64_sqadddi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqaddb_u8 (uint8_t __a, uint8_t __b)
{
  return (uint8_t) __builtin_aarch64_uqaddqi_uuu (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqaddh_u16 (uint16_t __a, uint16_t __b)
{
  return (uint16_t) __builtin_aarch64_uqaddhi_uuu (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqadds_u32 (uint32_t __a, uint32_t __b)
{
  return (uint32_t) __builtin_aarch64_uqaddsi_uuu (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vqaddd_u64 (uint64_t __a, uint64_t __b)
{
  return __builtin_aarch64_uqadddi_uuu (__a, __b);
}

/* vqdmlal */

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c)
{
  return __builtin_aarch64_sqdmlalv4hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_high_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c)
{
  return __builtin_aarch64_sqdmlal2v8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_high_lane_s16 (int32x4_t __a, int16x8_t __b, int16x4_t __c,
                       int const __d)
{
  return __builtin_aarch64_sqdmlal2_lanev8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_high_laneq_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c,
                        int const __d)
{
  return __builtin_aarch64_sqdmlal2_laneqv8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_high_n_s16 (int32x4_t __a, int16x8_t __b, int16_t __c)
{
  return __builtin_aarch64_sqdmlal2_nv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlal_lanev4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_laneq_s16 (int32x4_t __a, int16x4_t __b, int16x8_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlal_laneqv4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlal_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c)
{
  return __builtin_aarch64_sqdmlal_nv4hi (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c)
{
  return __builtin_aarch64_sqdmlalv2si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_high_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c)
{
  return __builtin_aarch64_sqdmlal2v4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_high_lane_s32 (int64x2_t __a, int32x4_t __b, int32x2_t __c,
                       int const __d)
{
  return __builtin_aarch64_sqdmlal2_lanev4si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_high_laneq_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c,
                        int const __d)
{
  return __builtin_aarch64_sqdmlal2_laneqv4si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_high_n_s32 (int64x2_t __a, int32x4_t __b, int32_t __c)
{
  return __builtin_aarch64_sqdmlal2_nv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlal_lanev2si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_laneq_s32 (int64x2_t __a, int32x2_t __b, int32x4_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlal_laneqv2si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlal_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c)
{
  return __builtin_aarch64_sqdmlal_nv2si (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmlalh_s16 (int32_t __a, int16_t __b, int16_t __c)
{
  return __builtin_aarch64_sqdmlalhi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmlalh_lane_s16 (int32_t __a, int16_t __b, int16x4_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlal_lanehi (__a, __b, __c, __d);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmlalh_laneq_s16 (int32_t __a, int16_t __b, int16x8_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlal_laneqhi (__a, __b, __c, __d);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmlals_s32 (int64_t __a, int32_t __b, int32_t __c)
{
  return __builtin_aarch64_sqdmlalsi (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmlals_lane_s32 (int64_t __a, int32_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlal_lanesi (__a, __b, __c, __d);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmlals_laneq_s32 (int64_t __a, int32_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlal_laneqsi (__a, __b, __c, __d);
}

/* vqdmlsl */

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c)
{
  return __builtin_aarch64_sqdmlslv4hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_high_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c)
{
  return __builtin_aarch64_sqdmlsl2v8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_high_lane_s16 (int32x4_t __a, int16x8_t __b, int16x4_t __c,
                       int const __d)
{
  return __builtin_aarch64_sqdmlsl2_lanev8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_high_laneq_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c,
                        int const __d)
{
  return __builtin_aarch64_sqdmlsl2_laneqv8hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_high_n_s16 (int32x4_t __a, int16x8_t __b, int16_t __c)
{
  return __builtin_aarch64_sqdmlsl2_nv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlsl_lanev4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_laneq_s16 (int32x4_t __a, int16x4_t __b, int16x8_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlsl_laneqv4hi (__a, __b, __c, __d);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmlsl_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c)
{
  return __builtin_aarch64_sqdmlsl_nv4hi (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c)
{
  return __builtin_aarch64_sqdmlslv2si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_high_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c)
{
  return __builtin_aarch64_sqdmlsl2v4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_high_lane_s32 (int64x2_t __a, int32x4_t __b, int32x2_t __c,
                       int const __d)
{
  return __builtin_aarch64_sqdmlsl2_lanev4si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_high_laneq_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c,
                        int const __d)
{
  return __builtin_aarch64_sqdmlsl2_laneqv4si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_high_n_s32 (int64x2_t __a, int32x4_t __b, int32_t __c)
{
  return __builtin_aarch64_sqdmlsl2_nv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlsl_lanev2si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_laneq_s32 (int64x2_t __a, int32x2_t __b, int32x4_t __c, int const __d)
{
  return __builtin_aarch64_sqdmlsl_laneqv2si (__a, __b, __c, __d);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmlsl_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c)
{
  return __builtin_aarch64_sqdmlsl_nv2si (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmlslh_s16 (int32_t __a, int16_t __b, int16_t __c)
{
  return __builtin_aarch64_sqdmlslhi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmlslh_lane_s16 (int32_t __a, int16_t __b, int16x4_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlsl_lanehi (__a, __b, __c, __d);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmlslh_laneq_s16 (int32_t __a, int16_t __b, int16x8_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlsl_laneqhi (__a, __b, __c, __d);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmlsls_s32 (int64_t __a, int32_t __b, int32_t __c)
{
  return __builtin_aarch64_sqdmlslsi (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmlsls_lane_s32 (int64_t __a, int32_t __b, int32x2_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlsl_lanesi (__a, __b, __c, __d);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmlsls_laneq_s32 (int64_t __a, int32_t __b, int32x4_t __c, const int __d)
{
  return __builtin_aarch64_sqdmlsl_laneqsi (__a, __b, __c, __d);
}

/* vqdmulh */

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqdmulh_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_lanev4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_lanev2si (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqdmulhq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_lanev8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmulhq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_lanev4si (__a, __b, __c);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqdmulhh_s16 (int16_t __a, int16_t __b)
{
  return (int16_t) __builtin_aarch64_sqdmulhhi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqdmulhh_lane_s16 (int16_t __a, int16x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_lanehi (__a, __b, __c);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqdmulhh_laneq_s16 (int16_t __a, int16x8_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_laneqhi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmulhs_s32 (int32_t __a, int32_t __b)
{
  return (int32_t) __builtin_aarch64_sqdmulhsi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmulhs_lane_s32 (int32_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_lanesi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmulhs_laneq_s32 (int32_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmulh_laneqsi (__a, __b, __c);
}

/* vqdmull */

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_sqdmullv4hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_high_s16 (int16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_sqdmull2v8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_high_lane_s16 (int16x8_t __a, int16x4_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull2_lanev8hi (__a, __b,__c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_high_laneq_s16 (int16x8_t __a, int16x8_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull2_laneqv8hi (__a, __b,__c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_high_n_s16 (int16x8_t __a, int16_t __b)
{
  return __builtin_aarch64_sqdmull2_nv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_lane_s16 (int16x4_t __a, int16x4_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull_lanev4hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_laneq_s16 (int16x4_t __a, int16x8_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull_laneqv4hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqdmull_n_s16 (int16x4_t __a, int16_t __b)
{
  return __builtin_aarch64_sqdmull_nv4hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_sqdmullv2si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_high_s32 (int32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_sqdmull2v4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_high_lane_s32 (int32x4_t __a, int32x2_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull2_lanev4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_high_laneq_s32 (int32x4_t __a, int32x4_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull2_laneqv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_high_n_s32 (int32x4_t __a, int32_t __b)
{
  return __builtin_aarch64_sqdmull2_nv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_lane_s32 (int32x2_t __a, int32x2_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull_lanev2si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_laneq_s32 (int32x2_t __a, int32x4_t __b, int const __c)
{
  return __builtin_aarch64_sqdmull_laneqv2si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqdmull_n_s32 (int32x2_t __a, int32_t __b)
{
  return __builtin_aarch64_sqdmull_nv2si (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmullh_s16 (int16_t __a, int16_t __b)
{
  return (int32_t) __builtin_aarch64_sqdmullhi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmullh_lane_s16 (int16_t __a, int16x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmull_lanehi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqdmullh_laneq_s16 (int16_t __a, int16x8_t __b, const int __c)
{
  return __builtin_aarch64_sqdmull_laneqhi (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmulls_s32 (int32_t __a, int32_t __b)
{
  return __builtin_aarch64_sqdmullsi (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmulls_lane_s32 (int32_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqdmull_lanesi (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqdmulls_laneq_s32 (int32_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqdmull_laneqsi (__a, __b, __c);
}

/* vqmovn */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqmovn_s16 (int16x8_t __a)
{
  return (int8x8_t) __builtin_aarch64_sqmovnv8hi (__a);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqmovn_s32 (int32x4_t __a)
{
  return (int16x4_t) __builtin_aarch64_sqmovnv4si (__a);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqmovn_s64 (int64x2_t __a)
{
  return (int32x2_t) __builtin_aarch64_sqmovnv2di (__a);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqmovn_u16 (uint16x8_t __a)
{
  return (uint8x8_t) __builtin_aarch64_uqmovnv8hi ((int16x8_t) __a);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqmovn_u32 (uint32x4_t __a)
{
  return (uint16x4_t) __builtin_aarch64_uqmovnv4si ((int32x4_t) __a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqmovn_u64 (uint64x2_t __a)
{
  return (uint32x2_t) __builtin_aarch64_uqmovnv2di ((int64x2_t) __a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqmovnh_s16 (int16_t __a)
{
  return (int8_t) __builtin_aarch64_sqmovnhi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqmovns_s32 (int32_t __a)
{
  return (int16_t) __builtin_aarch64_sqmovnsi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqmovnd_s64 (int64_t __a)
{
  return (int32_t) __builtin_aarch64_sqmovndi (__a);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqmovnh_u16 (uint16_t __a)
{
  return (uint8_t) __builtin_aarch64_uqmovnhi (__a);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqmovns_u32 (uint32_t __a)
{
  return (uint16_t) __builtin_aarch64_uqmovnsi (__a);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqmovnd_u64 (uint64_t __a)
{
  return (uint32_t) __builtin_aarch64_uqmovndi (__a);
}

/* vqmovun */

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqmovun_s16 (int16x8_t __a)
{
  return (uint8x8_t) __builtin_aarch64_sqmovunv8hi (__a);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqmovun_s32 (int32x4_t __a)
{
  return (uint16x4_t) __builtin_aarch64_sqmovunv4si (__a);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqmovun_s64 (int64x2_t __a)
{
  return (uint32x2_t) __builtin_aarch64_sqmovunv2di (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqmovunh_s16 (int16_t __a)
{
  return (int8_t) __builtin_aarch64_sqmovunhi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqmovuns_s32 (int32_t __a)
{
  return (int16_t) __builtin_aarch64_sqmovunsi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqmovund_s64 (int64_t __a)
{
  return (int32_t) __builtin_aarch64_sqmovundi (__a);
}

/* vqneg */

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqnegq_s64 (int64x2_t __a)
{
  return (int64x2_t) __builtin_aarch64_sqnegv2di (__a);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqnegb_s8 (int8_t __a)
{
  return (int8_t) __builtin_aarch64_sqnegqi (__a);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqnegh_s16 (int16_t __a)
{
  return (int16_t) __builtin_aarch64_sqneghi (__a);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqnegs_s32 (int32_t __a)
{
  return (int32_t) __builtin_aarch64_sqnegsi (__a);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqnegd_s64 (int64_t __a)
{
  return __builtin_aarch64_sqnegdi (__a);
}

/* vqrdmulh */

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrdmulh_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c)
{
  return  __builtin_aarch64_sqrdmulh_lanev4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_lanev2si (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrdmulhq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_lanev8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrdmulhq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_lanev4si (__a, __b, __c);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmulhh_s16 (int16_t __a, int16_t __b)
{
  return (int16_t) __builtin_aarch64_sqrdmulhhi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmulhh_lane_s16 (int16_t __a, int16x4_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_lanehi (__a, __b, __c);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrdmulhh_laneq_s16 (int16_t __a, int16x8_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_laneqhi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmulhs_s32 (int32_t __a, int32_t __b)
{
  return (int32_t) __builtin_aarch64_sqrdmulhsi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmulhs_lane_s32 (int32_t __a, int32x2_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_lanesi (__a, __b, __c);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrdmulhs_laneq_s32 (int32_t __a, int32x4_t __b, const int __c)
{
  return __builtin_aarch64_sqrdmulh_laneqsi (__a, __b, __c);
}

/* vqrshl */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqrshl_s8 (int8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_sqrshlv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrshl_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_sqrshlv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrshl_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_sqrshlv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqrshl_s64 (int64x1_t __a, int64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_sqrshldi (__a[0], __b[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqrshl_u8 (uint8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_uqrshlv8qi_uus ( __a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqrshl_u16 (uint16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_uqrshlv4hi_uus ( __a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqrshl_u32 (uint32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_uqrshlv2si_uus ( __a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vqrshl_u64 (uint64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_uqrshldi_uus (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqrshlq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_sqrshlv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqrshlq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_sqrshlv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqrshlq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_sqrshlv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqrshlq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_sqrshlv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqrshlq_u8 (uint8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_uqrshlv16qi_uus ( __a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqrshlq_u16 (uint16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_uqrshlv8hi_uus ( __a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqrshlq_u32 (uint32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_uqrshlv4si_uus ( __a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vqrshlq_u64 (uint64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_uqrshlv2di_uus ( __a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqrshlb_s8 (int8_t __a, int8_t __b)
{
  return __builtin_aarch64_sqrshlqi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrshlh_s16 (int16_t __a, int16_t __b)
{
  return __builtin_aarch64_sqrshlhi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrshls_s32 (int32_t __a, int32_t __b)
{
  return __builtin_aarch64_sqrshlsi (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqrshld_s64 (int64_t __a, int64_t __b)
{
  return __builtin_aarch64_sqrshldi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqrshlb_u8 (uint8_t __a, uint8_t __b)
{
  return __builtin_aarch64_uqrshlqi_uus (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqrshlh_u16 (uint16_t __a, uint16_t __b)
{
  return __builtin_aarch64_uqrshlhi_uus (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqrshls_u32 (uint32_t __a, uint32_t __b)
{
  return __builtin_aarch64_uqrshlsi_uus (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vqrshld_u64 (uint64_t __a, uint64_t __b)
{
  return __builtin_aarch64_uqrshldi_uus (__a, __b);
}

/* vqrshrn */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqrshrn_n_s16 (int16x8_t __a, const int __b)
{
  return (int8x8_t) __builtin_aarch64_sqrshrn_nv8hi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqrshrn_n_s32 (int32x4_t __a, const int __b)
{
  return (int16x4_t) __builtin_aarch64_sqrshrn_nv4si (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqrshrn_n_s64 (int64x2_t __a, const int __b)
{
  return (int32x2_t) __builtin_aarch64_sqrshrn_nv2di (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqrshrn_n_u16 (uint16x8_t __a, const int __b)
{
  return __builtin_aarch64_uqrshrn_nv8hi_uus ( __a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqrshrn_n_u32 (uint32x4_t __a, const int __b)
{
  return __builtin_aarch64_uqrshrn_nv4si_uus ( __a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqrshrn_n_u64 (uint64x2_t __a, const int __b)
{
  return __builtin_aarch64_uqrshrn_nv2di_uus ( __a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqrshrnh_n_s16 (int16_t __a, const int __b)
{
  return (int8_t) __builtin_aarch64_sqrshrn_nhi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrshrns_n_s32 (int32_t __a, const int __b)
{
  return (int16_t) __builtin_aarch64_sqrshrn_nsi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrshrnd_n_s64 (int64_t __a, const int __b)
{
  return (int32_t) __builtin_aarch64_sqrshrn_ndi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqrshrnh_n_u16 (uint16_t __a, const int __b)
{
  return __builtin_aarch64_uqrshrn_nhi_uus (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqrshrns_n_u32 (uint32_t __a, const int __b)
{
  return __builtin_aarch64_uqrshrn_nsi_uus (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqrshrnd_n_u64 (uint64_t __a, const int __b)
{
  return __builtin_aarch64_uqrshrn_ndi_uus (__a, __b);
}

/* vqrshrun */

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqrshrun_n_s16 (int16x8_t __a, const int __b)
{
  return (uint8x8_t) __builtin_aarch64_sqrshrun_nv8hi (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqrshrun_n_s32 (int32x4_t __a, const int __b)
{
  return (uint16x4_t) __builtin_aarch64_sqrshrun_nv4si (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqrshrun_n_s64 (int64x2_t __a, const int __b)
{
  return (uint32x2_t) __builtin_aarch64_sqrshrun_nv2di (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqrshrunh_n_s16 (int16_t __a, const int __b)
{
  return (int8_t) __builtin_aarch64_sqrshrun_nhi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqrshruns_n_s32 (int32_t __a, const int __b)
{
  return (int16_t) __builtin_aarch64_sqrshrun_nsi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqrshrund_n_s64 (int64_t __a, const int __b)
{
  return (int32_t) __builtin_aarch64_sqrshrun_ndi (__a, __b);
}

/* vqshl */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqshl_s8 (int8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_sqshlv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqshl_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_sqshlv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqshl_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_sqshlv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqshl_s64 (int64x1_t __a, int64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_sqshldi (__a[0], __b[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqshl_u8 (uint8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_uqshlv8qi_uus ( __a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqshl_u16 (uint16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_uqshlv4hi_uus ( __a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqshl_u32 (uint32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_uqshlv2si_uus ( __a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vqshl_u64 (uint64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_uqshldi_uus (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqshlq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_sqshlv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqshlq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_sqshlv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqshlq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_sqshlv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqshlq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_sqshlv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqshlq_u8 (uint8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_uqshlv16qi_uus ( __a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqshlq_u16 (uint16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_uqshlv8hi_uus ( __a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqshlq_u32 (uint32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_uqshlv4si_uus ( __a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vqshlq_u64 (uint64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_uqshlv2di_uus ( __a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqshlb_s8 (int8_t __a, int8_t __b)
{
  return __builtin_aarch64_sqshlqi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqshlh_s16 (int16_t __a, int16_t __b)
{
  return __builtin_aarch64_sqshlhi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqshls_s32 (int32_t __a, int32_t __b)
{
  return __builtin_aarch64_sqshlsi (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqshld_s64 (int64_t __a, int64_t __b)
{
  return __builtin_aarch64_sqshldi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqshlb_u8 (uint8_t __a, uint8_t __b)
{
  return __builtin_aarch64_uqshlqi_uus (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqshlh_u16 (uint16_t __a, uint16_t __b)
{
  return __builtin_aarch64_uqshlhi_uus (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqshls_u32 (uint32_t __a, uint32_t __b)
{
  return __builtin_aarch64_uqshlsi_uus (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vqshld_u64 (uint64_t __a, uint64_t __b)
{
  return __builtin_aarch64_uqshldi_uus (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqshl_n_s8 (int8x8_t __a, const int __b)
{
  return (int8x8_t) __builtin_aarch64_sqshl_nv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqshl_n_s16 (int16x4_t __a, const int __b)
{
  return (int16x4_t) __builtin_aarch64_sqshl_nv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqshl_n_s32 (int32x2_t __a, const int __b)
{
  return (int32x2_t) __builtin_aarch64_sqshl_nv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vqshl_n_s64 (int64x1_t __a, const int __b)
{
  return (int64x1_t) {__builtin_aarch64_sqshl_ndi (__a[0], __b)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqshl_n_u8 (uint8x8_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv8qi_uus (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqshl_n_u16 (uint16x4_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv4hi_uus (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqshl_n_u32 (uint32x2_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv2si_uus (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vqshl_n_u64 (uint64x1_t __a, const int __b)
{
  return (uint64x1_t) {__builtin_aarch64_uqshl_ndi_uus (__a[0], __b)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqshlq_n_s8 (int8x16_t __a, const int __b)
{
  return (int8x16_t) __builtin_aarch64_sqshl_nv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vqshlq_n_s16 (int16x8_t __a, const int __b)
{
  return (int16x8_t) __builtin_aarch64_sqshl_nv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vqshlq_n_s32 (int32x4_t __a, const int __b)
{
  return (int32x4_t) __builtin_aarch64_sqshl_nv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vqshlq_n_s64 (int64x2_t __a, const int __b)
{
  return (int64x2_t) __builtin_aarch64_sqshl_nv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqshlq_n_u8 (uint8x16_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv16qi_uus (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqshlq_n_u16 (uint16x8_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv8hi_uus (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqshlq_n_u32 (uint32x4_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv4si_uus (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vqshlq_n_u64 (uint64x2_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nv2di_uus (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqshlb_n_s8 (int8_t __a, const int __b)
{
  return (int8_t) __builtin_aarch64_sqshl_nqi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqshlh_n_s16 (int16_t __a, const int __b)
{
  return (int16_t) __builtin_aarch64_sqshl_nhi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqshls_n_s32 (int32_t __a, const int __b)
{
  return (int32_t) __builtin_aarch64_sqshl_nsi (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqshld_n_s64 (int64_t __a, const int __b)
{
  return __builtin_aarch64_sqshl_ndi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqshlb_n_u8 (uint8_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nqi_uus (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqshlh_n_u16 (uint16_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nhi_uus (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqshls_n_u32 (uint32_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_nsi_uus (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vqshld_n_u64 (uint64_t __a, const int __b)
{
  return __builtin_aarch64_uqshl_ndi_uus (__a, __b);
}

/* vqshlu */

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqshlu_n_s8 (int8x8_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv8qi_uss (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqshlu_n_s16 (int16x4_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv4hi_uss (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqshlu_n_s32 (int32x2_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv2si_uss (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vqshlu_n_s64 (int64x1_t __a, const int __b)
{
  return (uint64x1_t) {__builtin_aarch64_sqshlu_ndi_uss (__a[0], __b)};
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqshluq_n_s8 (int8x16_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv16qi_uss (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vqshluq_n_s16 (int16x8_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv8hi_uss (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vqshluq_n_s32 (int32x4_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv4si_uss (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vqshluq_n_s64 (int64x2_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_nv2di_uss (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqshlub_n_s8 (int8_t __a, const int __b)
{
  return (int8_t) __builtin_aarch64_sqshlu_nqi_uss (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqshluh_n_s16 (int16_t __a, const int __b)
{
  return (int16_t) __builtin_aarch64_sqshlu_nhi_uss (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqshlus_n_s32 (int32_t __a, const int __b)
{
  return (int32_t) __builtin_aarch64_sqshlu_nsi_uss (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vqshlud_n_s64 (int64_t __a, const int __b)
{
  return __builtin_aarch64_sqshlu_ndi_uss (__a, __b);
}

/* vqshrn */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqshrn_n_s16 (int16x8_t __a, const int __b)
{
  return (int8x8_t) __builtin_aarch64_sqshrn_nv8hi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vqshrn_n_s32 (int32x4_t __a, const int __b)
{
  return (int16x4_t) __builtin_aarch64_sqshrn_nv4si (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vqshrn_n_s64 (int64x2_t __a, const int __b)
{
  return (int32x2_t) __builtin_aarch64_sqshrn_nv2di (__a, __b);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqshrn_n_u16 (uint16x8_t __a, const int __b)
{
  return __builtin_aarch64_uqshrn_nv8hi_uus ( __a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqshrn_n_u32 (uint32x4_t __a, const int __b)
{
  return __builtin_aarch64_uqshrn_nv4si_uus ( __a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqshrn_n_u64 (uint64x2_t __a, const int __b)
{
  return __builtin_aarch64_uqshrn_nv2di_uus ( __a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqshrnh_n_s16 (int16_t __a, const int __b)
{
  return (int8_t) __builtin_aarch64_sqshrn_nhi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqshrns_n_s32 (int32_t __a, const int __b)
{
  return (int16_t) __builtin_aarch64_sqshrn_nsi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqshrnd_n_s64 (int64_t __a, const int __b)
{
  return (int32_t) __builtin_aarch64_sqshrn_ndi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqshrnh_n_u16 (uint16_t __a, const int __b)
{
  return __builtin_aarch64_uqshrn_nhi_uus (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqshrns_n_u32 (uint32_t __a, const int __b)
{
  return __builtin_aarch64_uqshrn_nsi_uus (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqshrnd_n_u64 (uint64_t __a, const int __b)
{
  return __builtin_aarch64_uqshrn_ndi_uus (__a, __b);
}

/* vqshrun */

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqshrun_n_s16 (int16x8_t __a, const int __b)
{
  return (uint8x8_t) __builtin_aarch64_sqshrun_nv8hi (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vqshrun_n_s32 (int32x4_t __a, const int __b)
{
  return (uint16x4_t) __builtin_aarch64_sqshrun_nv4si (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vqshrun_n_s64 (int64x2_t __a, const int __b)
{
  return (uint32x2_t) __builtin_aarch64_sqshrun_nv2di (__a, __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqshrunh_n_s16 (int16_t __a, const int __b)
{
  return (int8_t) __builtin_aarch64_sqshrun_nhi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqshruns_n_s32 (int32_t __a, const int __b)
{
  return (int16_t) __builtin_aarch64_sqshrun_nsi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqshrund_n_s64 (int64_t __a, const int __b)
{
  return (int32_t) __builtin_aarch64_sqshrun_ndi (__a, __b);
}

/* vqsub */

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vqsubb_s8 (int8_t __a, int8_t __b)
{
  return (int8_t) __builtin_aarch64_sqsubqi (__a, __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vqsubh_s16 (int16_t __a, int16_t __b)
{
  return (int16_t) __builtin_aarch64_sqsubhi (__a, __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vqsubs_s32 (int32_t __a, int32_t __b)
{
  return (int32_t) __builtin_aarch64_sqsubsi (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vqsubd_s64 (int64_t __a, int64_t __b)
{
  return __builtin_aarch64_sqsubdi (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vqsubb_u8 (uint8_t __a, uint8_t __b)
{
  return (uint8_t) __builtin_aarch64_uqsubqi_uuu (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vqsubh_u16 (uint16_t __a, uint16_t __b)
{
  return (uint16_t) __builtin_aarch64_uqsubhi_uuu (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vqsubs_u32 (uint32_t __a, uint32_t __b)
{
  return (uint32_t) __builtin_aarch64_uqsubsi_uuu (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vqsubd_u64 (uint64_t __a, uint64_t __b)
{
  return __builtin_aarch64_uqsubdi_uuu (__a, __b);
}

/* vqtbl2 */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl2_s8 (int8x16x2_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, tab.val[1], 1);
  return __builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl2_u8 (uint8x16x2_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (uint8x8_t)__builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl2_p8 (poly8x16x2_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (poly8x8_t)__builtin_aarch64_tbl3v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl2q_s8 (int8x16x2_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return __builtin_aarch64_tbl3v16qi (__o, (int8x16_t)idx);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl2q_u8 (uint8x16x2_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (uint8x16_t)__builtin_aarch64_tbl3v16qi (__o, (int8x16_t)idx);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl2q_p8 (poly8x16x2_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (poly8x16_t)__builtin_aarch64_tbl3v16qi (__o, (int8x16_t)idx);
}

/* vqtbl3 */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl3_s8 (int8x16x3_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return __builtin_aarch64_qtbl3v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl3_u8 (uint8x16x3_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (uint8x8_t)__builtin_aarch64_qtbl3v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl3_p8 (poly8x16x3_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (poly8x8_t)__builtin_aarch64_qtbl3v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl3q_s8 (int8x16x3_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return __builtin_aarch64_qtbl3v16qi (__o, (int8x16_t)idx);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl3q_u8 (uint8x16x3_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (uint8x16_t)__builtin_aarch64_qtbl3v16qi (__o, (int8x16_t)idx);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl3q_p8 (poly8x16x3_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (poly8x16_t)__builtin_aarch64_qtbl3v16qi (__o, (int8x16_t)idx);
}

/* vqtbl4 */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl4_s8 (int8x16x4_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return __builtin_aarch64_qtbl4v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl4_u8 (uint8x16x4_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (uint8x8_t)__builtin_aarch64_qtbl4v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl4_p8 (poly8x16x4_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (poly8x8_t)__builtin_aarch64_qtbl4v8qi (__o, (int8x8_t)idx);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl4q_s8 (int8x16x4_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return __builtin_aarch64_qtbl4v16qi (__o, (int8x16_t)idx);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl4q_u8 (uint8x16x4_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (uint8x16_t)__builtin_aarch64_qtbl4v16qi (__o, (int8x16_t)idx);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl4q_p8 (poly8x16x4_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (poly8x16_t)__builtin_aarch64_qtbl4v16qi (__o, (int8x16_t)idx);
}


/* vqtbx2 */
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx2_s8 (int8x8_t r, int8x16x2_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, tab.val[1], 1);
  return __builtin_aarch64_tbx4v8qi (r, __o, (int8x8_t)idx);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx2_u8 (uint8x8_t r, uint8x16x2_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (uint8x8_t)__builtin_aarch64_tbx4v8qi ((int8x8_t)r, __o,
                                                (int8x8_t)idx);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx2_p8 (poly8x8_t r, poly8x16x2_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (poly8x8_t)__builtin_aarch64_tbx4v8qi ((int8x8_t)r, __o,
                                                (int8x8_t)idx);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx2q_s8 (int8x16_t r, int8x16x2_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, tab.val[1], 1);
  return __builtin_aarch64_tbx4v16qi (r, __o, (int8x16_t)idx);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx2q_u8 (uint8x16_t r, uint8x16x2_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (uint8x16_t)__builtin_aarch64_tbx4v16qi ((int8x16_t)r, __o,
                                                  (int8x16_t)idx);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx2q_p8 (poly8x16_t r, poly8x16x2_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t)tab.val[1], 1);
  return (poly8x16_t)__builtin_aarch64_tbx4v16qi ((int8x16_t)r, __o,
                                                  (int8x16_t)idx);
}

/* vqtbx3 */
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx3_s8 (int8x8_t r, int8x16x3_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, tab.val[2], 2);
  return __builtin_aarch64_qtbx3v8qi (r, __o, (int8x8_t)idx);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx3_u8 (uint8x8_t r, uint8x16x3_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (uint8x8_t)__builtin_aarch64_qtbx3v8qi ((int8x8_t)r, __o,
                                                 (int8x8_t)idx);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx3_p8 (poly8x8_t r, poly8x16x3_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (poly8x8_t)__builtin_aarch64_qtbx3v8qi ((int8x8_t)r, __o,
                                                 (int8x8_t)idx);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx3q_s8 (int8x16_t r, int8x16x3_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, tab.val[2], 2);
  return __builtin_aarch64_qtbx3v16qi (r, __o, (int8x16_t)idx);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx3q_u8 (uint8x16_t r, uint8x16x3_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (uint8x16_t)__builtin_aarch64_qtbx3v16qi ((int8x16_t)r, __o,
                                                   (int8x16_t)idx);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx3q_p8 (poly8x16_t r, poly8x16x3_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t)tab.val[2], 2);
  return (poly8x16_t)__builtin_aarch64_qtbx3v16qi ((int8x16_t)r, __o,
                                                   (int8x16_t)idx);
}

/* vqtbx4 */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx4_s8 (int8x8_t r, int8x16x4_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[3], 3);
  return __builtin_aarch64_qtbx4v8qi (r, __o, (int8x8_t)idx);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx4_u8 (uint8x8_t r, uint8x16x4_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (uint8x8_t)__builtin_aarch64_qtbx4v8qi ((int8x8_t)r, __o,
                                                 (int8x8_t)idx);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx4_p8 (poly8x8_t r, poly8x16x4_t tab, uint8x8_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (poly8x8_t)__builtin_aarch64_qtbx4v8qi ((int8x8_t)r, __o,
                                                 (int8x8_t)idx);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx4q_s8 (int8x16_t r, int8x16x4_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, tab.val[3], 3);
  return __builtin_aarch64_qtbx4v16qi (r, __o, (int8x16_t)idx);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx4q_u8 (uint8x16_t r, uint8x16x4_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (uint8x16_t)__builtin_aarch64_qtbx4v16qi ((int8x16_t)r, __o,
                                                   (int8x16_t)idx);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx4q_p8 (poly8x16_t r, poly8x16x4_t tab, uint8x16_t idx)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t)tab.val[3], 3);
  return (poly8x16_t)__builtin_aarch64_qtbx4v16qi ((int8x16_t)r, __o,
                                                   (int8x16_t)idx);
}

/* vrbit  */

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vrbit_p8 (poly8x8_t __a)
{
  return (poly8x8_t) __builtin_aarch64_rbitv8qi ((int8x8_t) __a);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrbit_s8 (int8x8_t __a)
{
  return __builtin_aarch64_rbitv8qi (__a);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrbit_u8 (uint8x8_t __a)
{
  return (uint8x8_t) __builtin_aarch64_rbitv8qi ((int8x8_t) __a);
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vrbitq_p8 (poly8x16_t __a)
{
  return (poly8x16_t) __builtin_aarch64_rbitv16qi ((int8x16_t)__a);
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrbitq_s8 (int8x16_t __a)
{
  return __builtin_aarch64_rbitv16qi (__a);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrbitq_u8 (uint8x16_t __a)
{
  return (uint8x16_t) __builtin_aarch64_rbitv16qi ((int8x16_t) __a);
}

/* vrecpe  */

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrecpe_u32 (uint32x2_t __a)
{
  return (uint32x2_t) __builtin_aarch64_urecpev2si ((int32x2_t) __a);
}
 
__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrecpeq_u32 (uint32x4_t __a)
{
  return (uint32x4_t) __builtin_aarch64_urecpev4si ((int32x4_t) __a);
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vrecpes_f32 (float32_t __a)
{
  return __builtin_aarch64_frecpesf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vrecped_f64 (float64_t __a)
{
  return __builtin_aarch64_frecpedf (__a);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrecpe_f32 (float32x2_t __a)
{
  return __builtin_aarch64_frecpev2sf (__a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrecpeq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_frecpev4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrecpeq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_frecpev2df (__a);
}

/* vrecps  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vrecpss_f32 (float32_t __a, float32_t __b)
{
  return __builtin_aarch64_frecpssf (__a, __b);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vrecpsd_f64 (float64_t __a, float64_t __b)
{
  return __builtin_aarch64_frecpsdf (__a, __b);
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrecps_f32 (float32x2_t __a, float32x2_t __b)
{
  return __builtin_aarch64_frecpsv2sf (__a, __b);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrecpsq_f32 (float32x4_t __a, float32x4_t __b)
{
  return __builtin_aarch64_frecpsv4sf (__a, __b);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrecpsq_f64 (float64x2_t __a, float64x2_t __b)
{
  return __builtin_aarch64_frecpsv2df (__a, __b);
}

/* vrecpx  */

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vrecpxs_f32 (float32_t __a)
{
  return __builtin_aarch64_frecpxsf (__a);
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vrecpxd_f64 (float64_t __a)
{
  return __builtin_aarch64_frecpxdf (__a);
}


/* vrev  */

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vrev16_p8 (poly8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrev16_s8 (int8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrev16_u8 (uint8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vrev16q_p8 (poly8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 });
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrev16q_s8 (int8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 });
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrev16q_u8 (uint8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 });
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vrev32_p8 (poly8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vrev32_p16 (poly16x4_t a)
{
  return __builtin_shuffle (a, (uint16x4_t) { 1, 0, 3, 2 });
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrev32_s8 (int8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrev32_s16 (int16x4_t a)
{
  return __builtin_shuffle (a, (uint16x4_t) { 1, 0, 3, 2 });
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrev32_u8 (uint8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrev32_u16 (uint16x4_t a)
{
  return __builtin_shuffle (a, (uint16x4_t) { 1, 0, 3, 2 });
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vrev32q_p8 (poly8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 });
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vrev32q_p16 (poly16x8_t a)
{
  return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrev32q_s8 (int8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 });
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrev32q_s16 (int16x8_t a)
{
  return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrev32q_u8 (uint8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 });
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrev32q_u16 (uint16x8_t a)
{
  return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrev64_f32 (float32x2_t a)
{
  return __builtin_shuffle (a, (uint32x2_t) { 1, 0 });
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vrev64_p8 (poly8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 });
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vrev64_p16 (poly16x4_t a)
{
  return __builtin_shuffle (a, (uint16x4_t) { 3, 2, 1, 0 });
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrev64_s8 (int8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 });
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrev64_s16 (int16x4_t a)
{
  return __builtin_shuffle (a, (uint16x4_t) { 3, 2, 1, 0 });
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vrev64_s32 (int32x2_t a)
{
  return __builtin_shuffle (a, (uint32x2_t) { 1, 0 });
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrev64_u8 (uint8x8_t a)
{
  return __builtin_shuffle (a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 });
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrev64_u16 (uint16x4_t a)
{
  return __builtin_shuffle (a, (uint16x4_t) { 3, 2, 1, 0 });
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrev64_u32 (uint32x2_t a)
{
  return __builtin_shuffle (a, (uint32x2_t) { 1, 0 });
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrev64q_f32 (float32x4_t a)
{
  return __builtin_shuffle (a, (uint32x4_t) { 1, 0, 3, 2 });
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vrev64q_p8 (poly8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 });
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vrev64q_p16 (poly16x8_t a)
{
  return __builtin_shuffle (a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrev64q_s8 (int8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 });
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrev64q_s16 (int16x8_t a)
{
  return __builtin_shuffle (a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vrev64q_s32 (int32x4_t a)
{
  return __builtin_shuffle (a, (uint32x4_t) { 1, 0, 3, 2 });
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrev64q_u8 (uint8x16_t a)
{
  return __builtin_shuffle (a,
      (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 });
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrev64q_u16 (uint16x8_t a)
{
  return __builtin_shuffle (a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrev64q_u32 (uint32x4_t a)
{
  return __builtin_shuffle (a, (uint32x4_t) { 1, 0, 3, 2 });
}

/* vrnd  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrnd_f32 (float32x2_t __a)
{
  return __builtin_aarch64_btruncv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrnd_f64 (float64x1_t __a)
{
  return vset_lane_f64 (__builtin_trunc (vget_lane_f64 (__a, 0)), __a, 0);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_btruncv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_btruncv2df (__a);
}

/* vrnda  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrnda_f32 (float32x2_t __a)
{
  return __builtin_aarch64_roundv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrnda_f64 (float64x1_t __a)
{
  return vset_lane_f64 (__builtin_round (vget_lane_f64 (__a, 0)), __a, 0);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndaq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_roundv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndaq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_roundv2df (__a);
}

/* vrndi  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndi_f32 (float32x2_t __a)
{
  return __builtin_aarch64_nearbyintv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrndi_f64 (float64x1_t __a)
{
  return vset_lane_f64 (__builtin_nearbyint (vget_lane_f64 (__a, 0)), __a, 0);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndiq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_nearbyintv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndiq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_nearbyintv2df (__a);
}

/* vrndm  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndm_f32 (float32x2_t __a)
{
  return __builtin_aarch64_floorv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrndm_f64 (float64x1_t __a)
{
  return vset_lane_f64 (__builtin_floor (vget_lane_f64 (__a, 0)), __a, 0);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndmq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_floorv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndmq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_floorv2df (__a);
}

/* vrndn  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndn_f32 (float32x2_t __a)
{
  return __builtin_aarch64_frintnv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrndn_f64 (float64x1_t __a)
{
  return (float64x1_t) {__builtin_aarch64_frintndf (__a[0])};
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndnq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_frintnv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndnq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_frintnv2df (__a);
}

/* vrndp  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndp_f32 (float32x2_t __a)
{
  return __builtin_aarch64_ceilv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrndp_f64 (float64x1_t __a)
{
  return vset_lane_f64 (__builtin_ceil (vget_lane_f64 (__a, 0)), __a, 0);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndpq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_ceilv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndpq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_ceilv2df (__a);
}

/* vrndx  */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndx_f32 (float32x2_t __a)
{
  return __builtin_aarch64_rintv2sf (__a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vrndx_f64 (float64x1_t __a)
{
  return vset_lane_f64 (__builtin_rint (vget_lane_f64 (__a, 0)), __a, 0);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndxq_f32 (float32x4_t __a)
{
  return __builtin_aarch64_rintv4sf (__a);
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndxq_f64 (float64x2_t __a)
{
  return __builtin_aarch64_rintv2df (__a);
}

/* vrshl */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrshl_s8 (int8x8_t __a, int8x8_t __b)
{
  return (int8x8_t) __builtin_aarch64_srshlv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrshl_s16 (int16x4_t __a, int16x4_t __b)
{
  return (int16x4_t) __builtin_aarch64_srshlv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vrshl_s32 (int32x2_t __a, int32x2_t __b)
{
  return (int32x2_t) __builtin_aarch64_srshlv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vrshl_s64 (int64x1_t __a, int64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_srshldi (__a[0], __b[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrshl_u8 (uint8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_urshlv8qi_uus (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrshl_u16 (uint16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_urshlv4hi_uus (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrshl_u32 (uint32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_urshlv2si_uus (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vrshl_u64 (uint64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_urshldi_uus (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrshlq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (int8x16_t) __builtin_aarch64_srshlv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrshlq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (int16x8_t) __builtin_aarch64_srshlv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vrshlq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (int32x4_t) __builtin_aarch64_srshlv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vrshlq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (int64x2_t) __builtin_aarch64_srshlv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrshlq_u8 (uint8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_urshlv16qi_uus (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrshlq_u16 (uint16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_urshlv8hi_uus (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrshlq_u32 (uint32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_urshlv4si_uus (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vrshlq_u64 (uint64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_urshlv2di_uus (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vrshld_s64 (int64_t __a, int64_t __b)
{
  return __builtin_aarch64_srshldi (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vrshld_u64 (uint64_t __a, int64_t __b)
{
  return __builtin_aarch64_urshldi_uus (__a, __b);
}

/* vrshr */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrshr_n_s8 (int8x8_t __a, const int __b)
{
  return (int8x8_t) __builtin_aarch64_srshr_nv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrshr_n_s16 (int16x4_t __a, const int __b)
{
  return (int16x4_t) __builtin_aarch64_srshr_nv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vrshr_n_s32 (int32x2_t __a, const int __b)
{
  return (int32x2_t) __builtin_aarch64_srshr_nv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vrshr_n_s64 (int64x1_t __a, const int __b)
{
  return (int64x1_t) {__builtin_aarch64_srshr_ndi (__a[0], __b)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrshr_n_u8 (uint8x8_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv8qi_uus (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrshr_n_u16 (uint16x4_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv4hi_uus (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrshr_n_u32 (uint32x2_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv2si_uus (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vrshr_n_u64 (uint64x1_t __a, const int __b)
{
  return (uint64x1_t) {__builtin_aarch64_urshr_ndi_uus (__a[0], __b)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrshrq_n_s8 (int8x16_t __a, const int __b)
{
  return (int8x16_t) __builtin_aarch64_srshr_nv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrshrq_n_s16 (int16x8_t __a, const int __b)
{
  return (int16x8_t) __builtin_aarch64_srshr_nv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vrshrq_n_s32 (int32x4_t __a, const int __b)
{
  return (int32x4_t) __builtin_aarch64_srshr_nv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vrshrq_n_s64 (int64x2_t __a, const int __b)
{
  return (int64x2_t) __builtin_aarch64_srshr_nv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrshrq_n_u8 (uint8x16_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv16qi_uus (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrshrq_n_u16 (uint16x8_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv8hi_uus (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrshrq_n_u32 (uint32x4_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv4si_uus (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vrshrq_n_u64 (uint64x2_t __a, const int __b)
{
  return __builtin_aarch64_urshr_nv2di_uus (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vrshrd_n_s64 (int64_t __a, const int __b)
{
  return __builtin_aarch64_srshr_ndi (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vrshrd_n_u64 (uint64_t __a, const int __b)
{
  return __builtin_aarch64_urshr_ndi_uus (__a, __b);
}

/* vrsra */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vrsra_n_s8 (int8x8_t __a, int8x8_t __b, const int __c)
{
  return (int8x8_t) __builtin_aarch64_srsra_nv8qi (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vrsra_n_s16 (int16x4_t __a, int16x4_t __b, const int __c)
{
  return (int16x4_t) __builtin_aarch64_srsra_nv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vrsra_n_s32 (int32x2_t __a, int32x2_t __b, const int __c)
{
  return (int32x2_t) __builtin_aarch64_srsra_nv2si (__a, __b, __c);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vrsra_n_s64 (int64x1_t __a, int64x1_t __b, const int __c)
{
  return (int64x1_t) {__builtin_aarch64_srsra_ndi (__a[0], __b[0], __c)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vrsra_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv8qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vrsra_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv4hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vrsra_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv2si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vrsra_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c)
{
  return (uint64x1_t) {__builtin_aarch64_ursra_ndi_uuus (__a[0], __b[0], __c)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vrsraq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c)
{
  return (int8x16_t) __builtin_aarch64_srsra_nv16qi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vrsraq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c)
{
  return (int16x8_t) __builtin_aarch64_srsra_nv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vrsraq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c)
{
  return (int32x4_t) __builtin_aarch64_srsra_nv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vrsraq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c)
{
  return (int64x2_t) __builtin_aarch64_srsra_nv2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vrsraq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv16qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vrsraq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv8hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vrsraq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv4si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vrsraq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c)
{
  return __builtin_aarch64_ursra_nv2di_uuus (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vrsrad_n_s64 (int64_t __a, int64_t __b, const int __c)
{
  return __builtin_aarch64_srsra_ndi (__a, __b, __c);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vrsrad_n_u64 (uint64_t __a, uint64_t __b, const int __c)
{
  return __builtin_aarch64_ursra_ndi_uuus (__a, __b, __c);
}

#pragma GCC push_options
#pragma GCC target ("+nothing+crypto")

/* vsha1  */

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha1cq_u32 (uint32x4_t hash_abcd, uint32_t hash_e, uint32x4_t wk)
{
  return __builtin_aarch64_crypto_sha1cv4si_uuuu (hash_abcd, hash_e, wk);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha1mq_u32 (uint32x4_t hash_abcd, uint32_t hash_e, uint32x4_t wk)
{
  return __builtin_aarch64_crypto_sha1mv4si_uuuu (hash_abcd, hash_e, wk);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha1pq_u32 (uint32x4_t hash_abcd, uint32_t hash_e, uint32x4_t wk)
{
  return __builtin_aarch64_crypto_sha1pv4si_uuuu (hash_abcd, hash_e, wk);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vsha1h_u32 (uint32_t hash_e)
{
  return __builtin_aarch64_crypto_sha1hsi_uu (hash_e);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha1su0q_u32 (uint32x4_t w0_3, uint32x4_t w4_7, uint32x4_t w8_11)
{
  return __builtin_aarch64_crypto_sha1su0v4si_uuuu (w0_3, w4_7, w8_11);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha1su1q_u32 (uint32x4_t tw0_3, uint32x4_t w12_15)
{
  return __builtin_aarch64_crypto_sha1su1v4si_uuu (tw0_3, w12_15);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha256hq_u32 (uint32x4_t hash_abcd, uint32x4_t hash_efgh, uint32x4_t wk)
{
  return __builtin_aarch64_crypto_sha256hv4si_uuuu (hash_abcd, hash_efgh, wk);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha256h2q_u32 (uint32x4_t hash_efgh, uint32x4_t hash_abcd, uint32x4_t wk)
{
  return __builtin_aarch64_crypto_sha256h2v4si_uuuu (hash_efgh, hash_abcd, wk);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha256su0q_u32 (uint32x4_t w0_3, uint32x4_t w4_7)
{
  return __builtin_aarch64_crypto_sha256su0v4si_uuu (w0_3, w4_7);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsha256su1q_u32 (uint32x4_t tw0_3, uint32x4_t w8_11, uint32x4_t w12_15)
{
  return __builtin_aarch64_crypto_sha256su1v4si_uuuu (tw0_3, w8_11, w12_15);
}

__extension__ static __inline poly128_t __attribute__ ((__always_inline__))
vmull_p64 (poly64_t a, poly64_t b)
{
  return
    __builtin_aarch64_crypto_pmulldi_ppp (a, b);
}

__extension__ static __inline poly128_t __attribute__ ((__always_inline__))
vmull_high_p64 (poly64x2_t a, poly64x2_t b)
{
  return __builtin_aarch64_crypto_pmullv2di_ppp (a, b);
}

#pragma GCC pop_options

/* vshl */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vshl_n_s8 (int8x8_t __a, const int __b)
{
  return (int8x8_t) __builtin_aarch64_ashlv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vshl_n_s16 (int16x4_t __a, const int __b)
{
  return (int16x4_t) __builtin_aarch64_ashlv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vshl_n_s32 (int32x2_t __a, const int __b)
{
  return (int32x2_t) __builtin_aarch64_ashlv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vshl_n_s64 (int64x1_t __a, const int __b)
{
  return (int64x1_t) {__builtin_aarch64_ashldi (__a[0], __b)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vshl_n_u8 (uint8x8_t __a, const int __b)
{
  return (uint8x8_t) __builtin_aarch64_ashlv8qi ((int8x8_t) __a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vshl_n_u16 (uint16x4_t __a, const int __b)
{
  return (uint16x4_t) __builtin_aarch64_ashlv4hi ((int16x4_t) __a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vshl_n_u32 (uint32x2_t __a, const int __b)
{
  return (uint32x2_t) __builtin_aarch64_ashlv2si ((int32x2_t) __a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vshl_n_u64 (uint64x1_t __a, const int __b)
{
  return (uint64x1_t) {__builtin_aarch64_ashldi ((int64_t) __a[0], __b)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vshlq_n_s8 (int8x16_t __a, const int __b)
{
  return (int8x16_t) __builtin_aarch64_ashlv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vshlq_n_s16 (int16x8_t __a, const int __b)
{
  return (int16x8_t) __builtin_aarch64_ashlv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vshlq_n_s32 (int32x4_t __a, const int __b)
{
  return (int32x4_t) __builtin_aarch64_ashlv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vshlq_n_s64 (int64x2_t __a, const int __b)
{
  return (int64x2_t) __builtin_aarch64_ashlv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vshlq_n_u8 (uint8x16_t __a, const int __b)
{
  return (uint8x16_t) __builtin_aarch64_ashlv16qi ((int8x16_t) __a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vshlq_n_u16 (uint16x8_t __a, const int __b)
{
  return (uint16x8_t) __builtin_aarch64_ashlv8hi ((int16x8_t) __a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vshlq_n_u32 (uint32x4_t __a, const int __b)
{
  return (uint32x4_t) __builtin_aarch64_ashlv4si ((int32x4_t) __a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vshlq_n_u64 (uint64x2_t __a, const int __b)
{
  return (uint64x2_t) __builtin_aarch64_ashlv2di ((int64x2_t) __a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vshld_n_s64 (int64_t __a, const int __b)
{
  return __builtin_aarch64_ashldi (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vshld_n_u64 (uint64_t __a, const int __b)
{
  return (uint64_t) __builtin_aarch64_ashldi (__a, __b);
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vshl_s8 (int8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_sshlv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vshl_s16 (int16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_sshlv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vshl_s32 (int32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_sshlv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vshl_s64 (int64x1_t __a, int64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_sshldi (__a[0], __b[0])};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vshl_u8 (uint8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_ushlv8qi_uus (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vshl_u16 (uint16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_ushlv4hi_uus (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vshl_u32 (uint32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_ushlv2si_uus (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vshl_u64 (uint64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_ushldi_uus (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vshlq_s8 (int8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_sshlv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vshlq_s16 (int16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_sshlv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vshlq_s32 (int32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_sshlv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vshlq_s64 (int64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_sshlv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vshlq_u8 (uint8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_ushlv16qi_uus (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vshlq_u16 (uint16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_ushlv8hi_uus (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vshlq_u32 (uint32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_ushlv4si_uus (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vshlq_u64 (uint64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_ushlv2di_uus (__a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vshld_s64 (int64_t __a, int64_t __b)
{
  return __builtin_aarch64_sshldi (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vshld_u64 (uint64_t __a, uint64_t __b)
{
  return __builtin_aarch64_ushldi_uus (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vshll_high_n_s8 (int8x16_t __a, const int __b)
{
  return __builtin_aarch64_sshll2_nv16qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vshll_high_n_s16 (int16x8_t __a, const int __b)
{
  return __builtin_aarch64_sshll2_nv8hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vshll_high_n_s32 (int32x4_t __a, const int __b)
{
  return __builtin_aarch64_sshll2_nv4si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vshll_high_n_u8 (uint8x16_t __a, const int __b)
{
  return (uint16x8_t) __builtin_aarch64_ushll2_nv16qi ((int8x16_t) __a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vshll_high_n_u16 (uint16x8_t __a, const int __b)
{
  return (uint32x4_t) __builtin_aarch64_ushll2_nv8hi ((int16x8_t) __a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vshll_high_n_u32 (uint32x4_t __a, const int __b)
{
  return (uint64x2_t) __builtin_aarch64_ushll2_nv4si ((int32x4_t) __a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vshll_n_s8 (int8x8_t __a, const int __b)
{
  return __builtin_aarch64_sshll_nv8qi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vshll_n_s16 (int16x4_t __a, const int __b)
{
  return __builtin_aarch64_sshll_nv4hi (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vshll_n_s32 (int32x2_t __a, const int __b)
{
  return __builtin_aarch64_sshll_nv2si (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vshll_n_u8 (uint8x8_t __a, const int __b)
{
  return __builtin_aarch64_ushll_nv8qi_uus (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vshll_n_u16 (uint16x4_t __a, const int __b)
{
  return __builtin_aarch64_ushll_nv4hi_uus (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vshll_n_u32 (uint32x2_t __a, const int __b)
{
  return __builtin_aarch64_ushll_nv2si_uus (__a, __b);
}

/* vshr */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vshr_n_s8 (int8x8_t __a, const int __b)
{
  return (int8x8_t) __builtin_aarch64_ashrv8qi (__a, __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vshr_n_s16 (int16x4_t __a, const int __b)
{
  return (int16x4_t) __builtin_aarch64_ashrv4hi (__a, __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vshr_n_s32 (int32x2_t __a, const int __b)
{
  return (int32x2_t) __builtin_aarch64_ashrv2si (__a, __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vshr_n_s64 (int64x1_t __a, const int __b)
{
  return (int64x1_t) {__builtin_aarch64_ashr_simddi (__a[0], __b)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vshr_n_u8 (uint8x8_t __a, const int __b)
{
  return (uint8x8_t) __builtin_aarch64_lshrv8qi ((int8x8_t) __a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vshr_n_u16 (uint16x4_t __a, const int __b)
{
  return (uint16x4_t) __builtin_aarch64_lshrv4hi ((int16x4_t) __a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vshr_n_u32 (uint32x2_t __a, const int __b)
{
  return (uint32x2_t) __builtin_aarch64_lshrv2si ((int32x2_t) __a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vshr_n_u64 (uint64x1_t __a, const int __b)
{
  return (uint64x1_t) {__builtin_aarch64_lshr_simddi_uus ( __a[0], __b)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vshrq_n_s8 (int8x16_t __a, const int __b)
{
  return (int8x16_t) __builtin_aarch64_ashrv16qi (__a, __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vshrq_n_s16 (int16x8_t __a, const int __b)
{
  return (int16x8_t) __builtin_aarch64_ashrv8hi (__a, __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vshrq_n_s32 (int32x4_t __a, const int __b)
{
  return (int32x4_t) __builtin_aarch64_ashrv4si (__a, __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vshrq_n_s64 (int64x2_t __a, const int __b)
{
  return (int64x2_t) __builtin_aarch64_ashrv2di (__a, __b);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vshrq_n_u8 (uint8x16_t __a, const int __b)
{
  return (uint8x16_t) __builtin_aarch64_lshrv16qi ((int8x16_t) __a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vshrq_n_u16 (uint16x8_t __a, const int __b)
{
  return (uint16x8_t) __builtin_aarch64_lshrv8hi ((int16x8_t) __a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vshrq_n_u32 (uint32x4_t __a, const int __b)
{
  return (uint32x4_t) __builtin_aarch64_lshrv4si ((int32x4_t) __a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vshrq_n_u64 (uint64x2_t __a, const int __b)
{
  return (uint64x2_t) __builtin_aarch64_lshrv2di ((int64x2_t) __a, __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vshrd_n_s64 (int64_t __a, const int __b)
{
  return __builtin_aarch64_ashr_simddi (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vshrd_n_u64 (uint64_t __a, const int __b)
{
  return __builtin_aarch64_lshr_simddi_uus (__a, __b);
}

/* vsli */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vsli_n_s8 (int8x8_t __a, int8x8_t __b, const int __c)
{
  return (int8x8_t) __builtin_aarch64_ssli_nv8qi (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vsli_n_s16 (int16x4_t __a, int16x4_t __b, const int __c)
{
  return (int16x4_t) __builtin_aarch64_ssli_nv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vsli_n_s32 (int32x2_t __a, int32x2_t __b, const int __c)
{
  return (int32x2_t) __builtin_aarch64_ssli_nv2si (__a, __b, __c);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vsli_n_s64 (int64x1_t __a, int64x1_t __b, const int __c)
{
  return (int64x1_t) {__builtin_aarch64_ssli_ndi (__a[0], __b[0], __c)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsli_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv8qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vsli_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv4hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vsli_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv2si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vsli_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c)
{
  return (uint64x1_t) {__builtin_aarch64_usli_ndi_uuus (__a[0], __b[0], __c)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsliq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c)
{
  return (int8x16_t) __builtin_aarch64_ssli_nv16qi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsliq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c)
{
  return (int16x8_t) __builtin_aarch64_ssli_nv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsliq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c)
{
  return (int32x4_t) __builtin_aarch64_ssli_nv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsliq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c)
{
  return (int64x2_t) __builtin_aarch64_ssli_nv2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsliq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv16qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsliq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv8hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsliq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv4si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsliq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c)
{
  return __builtin_aarch64_usli_nv2di_uuus (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vslid_n_s64 (int64_t __a, int64_t __b, const int __c)
{
  return __builtin_aarch64_ssli_ndi (__a, __b, __c);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vslid_n_u64 (uint64_t __a, uint64_t __b, const int __c)
{
  return __builtin_aarch64_usli_ndi_uuus (__a, __b, __c);
}

/* vsqadd */

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsqadd_u8 (uint8x8_t __a, int8x8_t __b)
{
  return __builtin_aarch64_usqaddv8qi_uus (__a, __b);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vsqadd_u16 (uint16x4_t __a, int16x4_t __b)
{
  return __builtin_aarch64_usqaddv4hi_uus (__a, __b);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vsqadd_u32 (uint32x2_t __a, int32x2_t __b)
{
  return __builtin_aarch64_usqaddv2si_uus (__a, __b);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vsqadd_u64 (uint64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) {__builtin_aarch64_usqadddi_uus (__a[0], __b[0])};
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsqaddq_u8 (uint8x16_t __a, int8x16_t __b)
{
  return __builtin_aarch64_usqaddv16qi_uus (__a, __b);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsqaddq_u16 (uint16x8_t __a, int16x8_t __b)
{
  return __builtin_aarch64_usqaddv8hi_uus (__a, __b);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsqaddq_u32 (uint32x4_t __a, int32x4_t __b)
{
  return __builtin_aarch64_usqaddv4si_uus (__a, __b);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsqaddq_u64 (uint64x2_t __a, int64x2_t __b)
{
  return __builtin_aarch64_usqaddv2di_uus (__a, __b);
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vsqaddb_u8 (uint8_t __a, int8_t __b)
{
  return __builtin_aarch64_usqaddqi_uus (__a, __b);
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vsqaddh_u16 (uint16_t __a, int16_t __b)
{
  return __builtin_aarch64_usqaddhi_uus (__a, __b);
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vsqadds_u32 (uint32_t __a, int32_t __b)
{
  return __builtin_aarch64_usqaddsi_uus (__a, __b);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vsqaddd_u64 (uint64_t __a, int64_t __b)
{
  return __builtin_aarch64_usqadddi_uus (__a, __b);
}

/* vsqrt */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vsqrt_f32 (float32x2_t a)
{
  return __builtin_aarch64_sqrtv2sf (a);
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vsqrtq_f32 (float32x4_t a)
{
  return __builtin_aarch64_sqrtv4sf (a);
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vsqrt_f64 (float64x1_t a)
{
  return (float64x1_t) { __builtin_aarch64_sqrtdf (a[0]) };
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vsqrtq_f64 (float64x2_t a)
{
  return __builtin_aarch64_sqrtv2df (a);
}

/* vsra */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vsra_n_s8 (int8x8_t __a, int8x8_t __b, const int __c)
{
  return (int8x8_t) __builtin_aarch64_ssra_nv8qi (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vsra_n_s16 (int16x4_t __a, int16x4_t __b, const int __c)
{
  return (int16x4_t) __builtin_aarch64_ssra_nv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vsra_n_s32 (int32x2_t __a, int32x2_t __b, const int __c)
{
  return (int32x2_t) __builtin_aarch64_ssra_nv2si (__a, __b, __c);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vsra_n_s64 (int64x1_t __a, int64x1_t __b, const int __c)
{
  return (int64x1_t) {__builtin_aarch64_ssra_ndi (__a[0], __b[0], __c)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsra_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv8qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vsra_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv4hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vsra_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv2si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vsra_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c)
{
  return (uint64x1_t) {__builtin_aarch64_usra_ndi_uuus (__a[0], __b[0], __c)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsraq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c)
{
  return (int8x16_t) __builtin_aarch64_ssra_nv16qi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsraq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c)
{
  return (int16x8_t) __builtin_aarch64_ssra_nv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsraq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c)
{
  return (int32x4_t) __builtin_aarch64_ssra_nv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsraq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c)
{
  return (int64x2_t) __builtin_aarch64_ssra_nv2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsraq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv16qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsraq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv8hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsraq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv4si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsraq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c)
{
  return __builtin_aarch64_usra_nv2di_uuus (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vsrad_n_s64 (int64_t __a, int64_t __b, const int __c)
{
  return __builtin_aarch64_ssra_ndi (__a, __b, __c);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vsrad_n_u64 (uint64_t __a, uint64_t __b, const int __c)
{
  return __builtin_aarch64_usra_ndi_uuus (__a, __b, __c);
}

/* vsri */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vsri_n_s8 (int8x8_t __a, int8x8_t __b, const int __c)
{
  return (int8x8_t) __builtin_aarch64_ssri_nv8qi (__a, __b, __c);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vsri_n_s16 (int16x4_t __a, int16x4_t __b, const int __c)
{
  return (int16x4_t) __builtin_aarch64_ssri_nv4hi (__a, __b, __c);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vsri_n_s32 (int32x2_t __a, int32x2_t __b, const int __c)
{
  return (int32x2_t) __builtin_aarch64_ssri_nv2si (__a, __b, __c);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vsri_n_s64 (int64x1_t __a, int64x1_t __b, const int __c)
{
  return (int64x1_t) {__builtin_aarch64_ssri_ndi (__a[0], __b[0], __c)};
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vsri_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv8qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vsri_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv4hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vsri_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv2si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vsri_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c)
{
  return (uint64x1_t) {__builtin_aarch64_usri_ndi_uuus (__a[0], __b[0], __c)};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsriq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c)
{
  return (int8x16_t) __builtin_aarch64_ssri_nv16qi (__a, __b, __c);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsriq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c)
{
  return (int16x8_t) __builtin_aarch64_ssri_nv8hi (__a, __b, __c);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsriq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c)
{
  return (int32x4_t) __builtin_aarch64_ssri_nv4si (__a, __b, __c);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsriq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c)
{
  return (int64x2_t) __builtin_aarch64_ssri_nv2di (__a, __b, __c);
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsriq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv16qi_uuus (__a, __b, __c);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsriq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv8hi_uuus (__a, __b, __c);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsriq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv4si_uuus (__a, __b, __c);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsriq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c)
{
  return __builtin_aarch64_usri_nv2di_uuus (__a, __b, __c);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vsrid_n_s64 (int64_t __a, int64_t __b, const int __c)
{
  return __builtin_aarch64_ssri_ndi (__a, __b, __c);
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vsrid_n_u64 (uint64_t __a, uint64_t __b, const int __c)
{
  return __builtin_aarch64_usri_ndi_uuus (__a, __b, __c);
}

/* vst1 */

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_f16 (float16_t *__a, float16x4_t __b)
{
  __builtin_aarch64_st1v4hf (__a, __b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_f32 (float32_t *a, float32x2_t b)
{
  __builtin_aarch64_st1v2sf ((__builtin_aarch64_simd_sf *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_f64 (float64_t *a, float64x1_t b)
{
  *a = b[0];
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_p8 (poly8_t *a, poly8x8_t b)
{
  __builtin_aarch64_st1v8qi ((__builtin_aarch64_simd_qi *) a,
                             (int8x8_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_p16 (poly16_t *a, poly16x4_t b)
{
  __builtin_aarch64_st1v4hi ((__builtin_aarch64_simd_hi *) a,
                             (int16x4_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_s8 (int8_t *a, int8x8_t b)
{
  __builtin_aarch64_st1v8qi ((__builtin_aarch64_simd_qi *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_s16 (int16_t *a, int16x4_t b)
{
  __builtin_aarch64_st1v4hi ((__builtin_aarch64_simd_hi *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_s32 (int32_t *a, int32x2_t b)
{
  __builtin_aarch64_st1v2si ((__builtin_aarch64_simd_si *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_s64 (int64_t *a, int64x1_t b)
{
  *a = b[0];
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_u8 (uint8_t *a, uint8x8_t b)
{
  __builtin_aarch64_st1v8qi ((__builtin_aarch64_simd_qi *) a,
                             (int8x8_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_u16 (uint16_t *a, uint16x4_t b)
{
  __builtin_aarch64_st1v4hi ((__builtin_aarch64_simd_hi *) a,
                             (int16x4_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_u32 (uint32_t *a, uint32x2_t b)
{
  __builtin_aarch64_st1v2si ((__builtin_aarch64_simd_si *) a,
                             (int32x2_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_u64 (uint64_t *a, uint64x1_t b)
{
  *a = b[0];
}

/* vst1q */

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_f16 (float16_t *__a, float16x8_t __b)
{
  __builtin_aarch64_st1v8hf (__a, __b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_f32 (float32_t *a, float32x4_t b)
{
  __builtin_aarch64_st1v4sf ((__builtin_aarch64_simd_sf *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_f64 (float64_t *a, float64x2_t b)
{
  __builtin_aarch64_st1v2df ((__builtin_aarch64_simd_df *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_p8 (poly8_t *a, poly8x16_t b)
{
  __builtin_aarch64_st1v16qi ((__builtin_aarch64_simd_qi *) a,
                              (int8x16_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_p16 (poly16_t *a, poly16x8_t b)
{
  __builtin_aarch64_st1v8hi ((__builtin_aarch64_simd_hi *) a,
                             (int16x8_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_s8 (int8_t *a, int8x16_t b)
{
  __builtin_aarch64_st1v16qi ((__builtin_aarch64_simd_qi *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_s16 (int16_t *a, int16x8_t b)
{
  __builtin_aarch64_st1v8hi ((__builtin_aarch64_simd_hi *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_s32 (int32_t *a, int32x4_t b)
{
  __builtin_aarch64_st1v4si ((__builtin_aarch64_simd_si *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_s64 (int64_t *a, int64x2_t b)
{
  __builtin_aarch64_st1v2di ((__builtin_aarch64_simd_di *) a, b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_u8 (uint8_t *a, uint8x16_t b)
{
  __builtin_aarch64_st1v16qi ((__builtin_aarch64_simd_qi *) a,
                              (int8x16_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_u16 (uint16_t *a, uint16x8_t b)
{
  __builtin_aarch64_st1v8hi ((__builtin_aarch64_simd_hi *) a,
                             (int16x8_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_u32 (uint32_t *a, uint32x4_t b)
{
  __builtin_aarch64_st1v4si ((__builtin_aarch64_simd_si *) a,
                             (int32x4_t) b);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_u64 (uint64_t *a, uint64x2_t b)
{
  __builtin_aarch64_st1v2di ((__builtin_aarch64_simd_di *) a,
                             (int64x2_t) b);
}

/* vst1_lane */

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_f16 (float16_t *__a, float16x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_f32 (float32_t *__a, float32x2_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_f64 (float64_t *__a, float64x1_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_p8 (poly8_t *__a, poly8x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_p16 (poly16_t *__a, poly16x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s8 (int8_t *__a, int8x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s16 (int16_t *__a, int16x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s32 (int32_t *__a, int32x2_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s64 (int64_t *__a, int64x1_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u8 (uint8_t *__a, uint8x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u16 (uint16_t *__a, uint16x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u32 (uint32_t *__a, uint32x2_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u64 (uint64_t *__a, uint64x1_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

/* vst1q_lane */

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_f16 (float16_t *__a, float16x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_f32 (float32_t *__a, float32x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_f64 (float64_t *__a, float64x2_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_p8 (poly8_t *__a, poly8x16_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_p16 (poly16_t *__a, poly16x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s8 (int8_t *__a, int8x16_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s16 (int16_t *__a, int16x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s32 (int32_t *__a, int32x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s64 (int64_t *__a, int64x2_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u8 (uint8_t *__a, uint8x16_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u16 (uint16_t *__a, uint16x8_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u32 (uint32_t *__a, uint32x4_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u64 (uint64_t *__a, uint64x2_t __b, const int __lane)
{
  *__a = __aarch64_vget_lane_any (__b, __lane);
}

/* vstn */

__extension__ static __inline void
vst2_s64 (int64_t * __a, int64x1x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  int64x2x2_t temp;
  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[1], 1);
  __builtin_aarch64_st2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void
vst2_u64 (uint64_t * __a, uint64x1x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  uint64x2x2_t temp;
  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[1], 1);
  __builtin_aarch64_st2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void
vst2_f64 (float64_t * __a, float64x1x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  float64x2x2_t temp;
  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) temp.val[1], 1);
  __builtin_aarch64_st2df ((__builtin_aarch64_simd_df *) __a, __o);
}

__extension__ static __inline void
vst2_s8 (int8_t * __a, int8x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  int8x16x2_t temp;
  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1);
  __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_p8 (poly8_t * __a, poly8x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  poly8x16x2_t temp;
  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1);
  __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_s16 (int16_t * __a, int16x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  int16x8x2_t temp;
  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1);
  __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_p16 (poly16_t * __a, poly16x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  poly16x8x2_t temp;
  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1);
  __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_s32 (int32_t * __a, int32x2x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  int32x4x2_t temp;
  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[1], 1);
  __builtin_aarch64_st2v2si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_u8 (uint8_t * __a, uint8x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  uint8x16x2_t temp;
  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1);
  __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_u16 (uint16_t * __a, uint16x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  uint16x8x2_t temp;
  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1);
  __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_u32 (uint32_t * __a, uint32x2x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  uint32x4x2_t temp;
  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[1], 1);
  __builtin_aarch64_st2v2si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_f16 (float16_t * __a, float16x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  float16x8x2_t temp;
  temp.val[0] = vcombine_f16 (val.val[0], vcreate_f16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f16 (val.val[1], vcreate_f16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv8hf (__o, temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hf (__o, temp.val[1], 1);
  __builtin_aarch64_st2v4hf (__a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2_f32 (float32_t * __a, float32x2x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  float32x4x2_t temp;
  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) temp.val[1], 1);
  __builtin_aarch64_st2v2sf ((__builtin_aarch64_simd_sf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_s8 (int8_t * __a, int8x16x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[1], 1);
  __builtin_aarch64_st2v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_p8 (poly8_t * __a, poly8x16x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[1], 1);
  __builtin_aarch64_st2v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_s16 (int16_t * __a, int16x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[1], 1);
  __builtin_aarch64_st2v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_p16 (poly16_t * __a, poly16x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[1], 1);
  __builtin_aarch64_st2v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_s32 (int32_t * __a, int32x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[1], 1);
  __builtin_aarch64_st2v4si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_s64 (int64_t * __a, int64x2x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[1], 1);
  __builtin_aarch64_st2v2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_u8 (uint8_t * __a, uint8x16x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[1], 1);
  __builtin_aarch64_st2v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_u16 (uint16_t * __a, uint16x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[1], 1);
  __builtin_aarch64_st2v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_u32 (uint32_t * __a, uint32x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[1], 1);
  __builtin_aarch64_st2v4si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_u64 (uint64_t * __a, uint64x2x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[1], 1);
  __builtin_aarch64_st2v2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_f16 (float16_t * __a, float16x8x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv8hf (__o, val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv8hf (__o, val.val[1], 1);
  __builtin_aarch64_st2v8hf (__a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_f32 (float32_t * __a, float32x4x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) val.val[1], 1);
  __builtin_aarch64_st2v4sf ((__builtin_aarch64_simd_sf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst2q_f64 (float64_t * __a, float64x2x2_t val)
{
  __builtin_aarch64_simd_oi __o;
  __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) val.val[1], 1);
  __builtin_aarch64_st2v2df ((__builtin_aarch64_simd_df *) __a, __o);
}

__extension__ static __inline void
vst3_s64 (int64_t * __a, int64x1x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  int64x2x3_t temp;
  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[2], 2);
  __builtin_aarch64_st3di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void
vst3_u64 (uint64_t * __a, uint64x1x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  uint64x2x3_t temp;
  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[2], 2);
  __builtin_aarch64_st3di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void
vst3_f64 (float64_t * __a, float64x1x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  float64x2x3_t temp;
  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[2], 2);
  __builtin_aarch64_st3df ((__builtin_aarch64_simd_df *) __a, __o);
}

__extension__ static __inline void
vst3_s8 (int8_t * __a, int8x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  int8x16x3_t temp;
  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2);
  __builtin_aarch64_st3v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_p8 (poly8_t * __a, poly8x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  poly8x16x3_t temp;
  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2);
  __builtin_aarch64_st3v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_s16 (int16_t * __a, int16x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  int16x8x3_t temp;
  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2);
  __builtin_aarch64_st3v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_p16 (poly16_t * __a, poly16x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  poly16x8x3_t temp;
  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2);
  __builtin_aarch64_st3v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_s32 (int32_t * __a, int32x2x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  int32x4x3_t temp;
  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[2], 2);
  __builtin_aarch64_st3v2si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_u8 (uint8_t * __a, uint8x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  uint8x16x3_t temp;
  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2);
  __builtin_aarch64_st3v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_u16 (uint16_t * __a, uint16x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  uint16x8x3_t temp;
  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2);
  __builtin_aarch64_st3v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_u32 (uint32_t * __a, uint32x2x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  uint32x4x3_t temp;
  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[2], 2);
  __builtin_aarch64_st3v2si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_f16 (float16_t * __a, float16x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  float16x8x3_t temp;
  temp.val[0] = vcombine_f16 (val.val[0], vcreate_f16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f16 (val.val[1], vcreate_f16 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_f16 (val.val[2], vcreate_f16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv8hf (__o, (float16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hf (__o, (float16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hf (__o, (float16x8_t) temp.val[2], 2);
  __builtin_aarch64_st3v4hf ((__builtin_aarch64_simd_hf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3_f32 (float32_t * __a, float32x2x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  float32x4x3_t temp;
  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[2], 2);
  __builtin_aarch64_st3v2sf ((__builtin_aarch64_simd_sf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_s8 (int8_t * __a, int8x16x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[2], 2);
  __builtin_aarch64_st3v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_p8 (poly8_t * __a, poly8x16x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[2], 2);
  __builtin_aarch64_st3v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_s16 (int16_t * __a, int16x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[2], 2);
  __builtin_aarch64_st3v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_p16 (poly16_t * __a, poly16x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[2], 2);
  __builtin_aarch64_st3v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_s32 (int32_t * __a, int32x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[2], 2);
  __builtin_aarch64_st3v4si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_s64 (int64_t * __a, int64x2x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[2], 2);
  __builtin_aarch64_st3v2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_u8 (uint8_t * __a, uint8x16x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[2], 2);
  __builtin_aarch64_st3v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_u16 (uint16_t * __a, uint16x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[2], 2);
  __builtin_aarch64_st3v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_u32 (uint32_t * __a, uint32x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[2], 2);
  __builtin_aarch64_st3v4si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_u64 (uint64_t * __a, uint64x2x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[2], 2);
  __builtin_aarch64_st3v2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_f16 (float16_t * __a, float16x8x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv8hf (__o, (float16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv8hf (__o, (float16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv8hf (__o, (float16x8_t) val.val[2], 2);
  __builtin_aarch64_st3v8hf ((__builtin_aarch64_simd_hf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_f32 (float32_t * __a, float32x4x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) val.val[2], 2);
  __builtin_aarch64_st3v4sf ((__builtin_aarch64_simd_sf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst3q_f64 (float64_t * __a, float64x2x3_t val)
{
  __builtin_aarch64_simd_ci __o;
  __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) val.val[2], 2);
  __builtin_aarch64_st3v2df ((__builtin_aarch64_simd_df *) __a, __o);
}

__extension__ static __inline void
vst4_s64 (int64_t * __a, int64x1x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  int64x2x4_t temp;
  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (__AARCH64_INT64_C (0)));
  temp.val[3] = vcombine_s64 (val.val[3], vcreate_s64 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[3], 3);
  __builtin_aarch64_st4di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void
vst4_u64 (uint64_t * __a, uint64x1x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  uint64x2x4_t temp;
  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_u64 (val.val[3], vcreate_u64 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[3], 3);
  __builtin_aarch64_st4di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void
vst4_f64 (float64_t * __a, float64x1x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  float64x2x4_t temp;
  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_f64 (val.val[3], vcreate_f64 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[3], 3);
  __builtin_aarch64_st4df ((__builtin_aarch64_simd_df *) __a, __o);
}

__extension__ static __inline void
vst4_s8 (int8_t * __a, int8x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  int8x16x4_t temp;
  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (__AARCH64_INT64_C (0)));
  temp.val[3] = vcombine_s8 (val.val[3], vcreate_s8 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[3], 3);
  __builtin_aarch64_st4v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_p8 (poly8_t * __a, poly8x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  poly8x16x4_t temp;
  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_p8 (val.val[3], vcreate_p8 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[3], 3);
  __builtin_aarch64_st4v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_s16 (int16_t * __a, int16x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  int16x8x4_t temp;
  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (__AARCH64_INT64_C (0)));
  temp.val[3] = vcombine_s16 (val.val[3], vcreate_s16 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[3], 3);
  __builtin_aarch64_st4v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_p16 (poly16_t * __a, poly16x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  poly16x8x4_t temp;
  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_p16 (val.val[3], vcreate_p16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[3], 3);
  __builtin_aarch64_st4v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_s32 (int32_t * __a, int32x2x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  int32x4x4_t temp;
  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (__AARCH64_INT64_C (0)));
  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (__AARCH64_INT64_C (0)));
  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (__AARCH64_INT64_C (0)));
  temp.val[3] = vcombine_s32 (val.val[3], vcreate_s32 (__AARCH64_INT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[3], 3);
  __builtin_aarch64_st4v2si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_u8 (uint8_t * __a, uint8x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  uint8x16x4_t temp;
  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_u8 (val.val[3], vcreate_u8 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[3], 3);
  __builtin_aarch64_st4v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_u16 (uint16_t * __a, uint16x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  uint16x8x4_t temp;
  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_u16 (val.val[3], vcreate_u16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[3], 3);
  __builtin_aarch64_st4v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_u32 (uint32_t * __a, uint32x2x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  uint32x4x4_t temp;
  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_u32 (val.val[3], vcreate_u32 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[3], 3);
  __builtin_aarch64_st4v2si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_f16 (float16_t * __a, float16x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  float16x8x4_t temp;
  temp.val[0] = vcombine_f16 (val.val[0], vcreate_f16 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f16 (val.val[1], vcreate_f16 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_f16 (val.val[2], vcreate_f16 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_f16 (val.val[3], vcreate_f16 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) temp.val[3], 3);
  __builtin_aarch64_st4v4hf ((__builtin_aarch64_simd_hf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4_f32 (float32_t * __a, float32x2x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  float32x4x4_t temp;
  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (__AARCH64_UINT64_C (0)));
  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (__AARCH64_UINT64_C (0)));
  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (__AARCH64_UINT64_C (0)));
  temp.val[3] = vcombine_f32 (val.val[3], vcreate_f32 (__AARCH64_UINT64_C (0)));
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[3], 3);
  __builtin_aarch64_st4v2sf ((__builtin_aarch64_simd_sf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_s8 (int8_t * __a, int8x16x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[3], 3);
  __builtin_aarch64_st4v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_p8 (poly8_t * __a, poly8x16x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[3], 3);
  __builtin_aarch64_st4v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_s16 (int16_t * __a, int16x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[3], 3);
  __builtin_aarch64_st4v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_p16 (poly16_t * __a, poly16x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[3], 3);
  __builtin_aarch64_st4v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_s32 (int32_t * __a, int32x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[3], 3);
  __builtin_aarch64_st4v4si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_s64 (int64_t * __a, int64x2x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[3], 3);
  __builtin_aarch64_st4v2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_u8 (uint8_t * __a, uint8x16x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[3], 3);
  __builtin_aarch64_st4v16qi ((__builtin_aarch64_simd_qi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_u16 (uint16_t * __a, uint16x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[3], 3);
  __builtin_aarch64_st4v8hi ((__builtin_aarch64_simd_hi *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_u32 (uint32_t * __a, uint32x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[3], 3);
  __builtin_aarch64_st4v4si ((__builtin_aarch64_simd_si *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_u64 (uint64_t * __a, uint64x2x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[3], 3);
  __builtin_aarch64_st4v2di ((__builtin_aarch64_simd_di *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_f16 (float16_t * __a, float16x8x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) val.val[3], 3);
  __builtin_aarch64_st4v8hf ((__builtin_aarch64_simd_hf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_f32 (float32_t * __a, float32x4x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[3], 3);
  __builtin_aarch64_st4v4sf ((__builtin_aarch64_simd_sf *) __a, __o);
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst4q_f64 (float64_t * __a, float64x2x4_t val)
{
  __builtin_aarch64_simd_xi __o;
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[0], 0);
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[1], 1);
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[2], 2);
  __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[3], 3);
  __builtin_aarch64_st4v2df ((__builtin_aarch64_simd_df *) __a, __o);
}

/* vsub */

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vsubd_s64 (int64_t __a, int64_t __b)
{
  return __a - __b;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vsubd_u64 (uint64_t __a, uint64_t __b)
{
  return __a - __b;
}

/* vtbx1  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbx1_s8 (int8x8_t __r, int8x8_t __tab, int8x8_t __idx)
{
  uint8x8_t __mask = vclt_u8 (vreinterpret_u8_s8 (__idx),
                              vmov_n_u8 (8));
  int8x8_t __tbl = vtbl1_s8 (__tab, __idx);

  return vbsl_s8 (__mask, __tbl, __r);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbx1_u8 (uint8x8_t __r, uint8x8_t __tab, uint8x8_t __idx)
{
  uint8x8_t __mask = vclt_u8 (__idx, vmov_n_u8 (8));
  uint8x8_t __tbl = vtbl1_u8 (__tab, __idx);

  return vbsl_u8 (__mask, __tbl, __r);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbx1_p8 (poly8x8_t __r, poly8x8_t __tab, uint8x8_t __idx)
{
  uint8x8_t __mask = vclt_u8 (__idx, vmov_n_u8 (8));
  poly8x8_t __tbl = vtbl1_p8 (__tab, __idx);

  return vbsl_p8 (__mask, __tbl, __r);
}

/* vtbx3  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbx3_s8 (int8x8_t __r, int8x8x3_t __tab, int8x8_t __idx)
{
  uint8x8_t __mask = vclt_u8 (vreinterpret_u8_s8 (__idx),
                              vmov_n_u8 (24));
  int8x8_t __tbl = vtbl3_s8 (__tab, __idx);

  return vbsl_s8 (__mask, __tbl, __r);
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbx3_u8 (uint8x8_t __r, uint8x8x3_t __tab, uint8x8_t __idx)
{
  uint8x8_t __mask = vclt_u8 (__idx, vmov_n_u8 (24));
  uint8x8_t __tbl = vtbl3_u8 (__tab, __idx);

  return vbsl_u8 (__mask, __tbl, __r);
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbx3_p8 (poly8x8_t __r, poly8x8x3_t __tab, uint8x8_t __idx)
{
  uint8x8_t __mask = vclt_u8 (__idx, vmov_n_u8 (24));
  poly8x8_t __tbl = vtbl3_p8 (__tab, __idx);

  return vbsl_p8 (__mask, __tbl, __r);
}

/* vtbx4  */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtbx4_s8 (int8x8_t __r, int8x8x4_t __tab, int8x8_t __idx)
{
  int8x8_t result;
  int8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_s8 (__tab.val[0], __tab.val[1]);
  temp.val[1] = vcombine_s8 (__tab.val[2], __tab.val[3]);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = __builtin_aarch64_tbx4v8qi (__r, __o, __idx);
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtbx4_u8 (uint8x8_t __r, uint8x8x4_t __tab, uint8x8_t __idx)
{
  uint8x8_t result;
  uint8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_u8 (__tab.val[0], __tab.val[1]);
  temp.val[1] = vcombine_u8 (__tab.val[2], __tab.val[3]);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = (uint8x8_t)__builtin_aarch64_tbx4v8qi ((int8x8_t)__r, __o,
                                                  (int8x8_t)__idx);
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtbx4_p8 (poly8x8_t __r, poly8x8x4_t __tab, uint8x8_t __idx)
{
  poly8x8_t result;
  poly8x16x2_t temp;
  __builtin_aarch64_simd_oi __o;
  temp.val[0] = vcombine_p8 (__tab.val[0], __tab.val[1]);
  temp.val[1] = vcombine_p8 (__tab.val[2], __tab.val[3]);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[0], 0);
  __o = __builtin_aarch64_set_qregoiv16qi (__o,
                                           (int8x16_t) temp.val[1], 1);
  result = (poly8x8_t)__builtin_aarch64_tbx4v8qi ((int8x8_t)__r, __o,
                                                  (int8x8_t)__idx);
  return result;
}

/* vtrn */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vtrn1_f32 (float32x2_t __a, float32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtrn1_p8 (poly8x8_t __a, poly8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {9, 1, 11, 3, 13, 5, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 2, 10, 4, 12, 6, 14});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vtrn1_p16 (poly16x4_t __a, poly16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 1, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtrn1_s8 (int8x8_t __a, int8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {9, 1, 11, 3, 13, 5, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 2, 10, 4, 12, 6, 14});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vtrn1_s16 (int16x4_t __a, int16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 1, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vtrn1_s32 (int32x2_t __a, int32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtrn1_u8 (uint8x8_t __a, uint8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {9, 1, 11, 3, 13, 5, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 2, 10, 4, 12, 6, 14});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtrn1_u16 (uint16x4_t __a, uint16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 1, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vtrn1_u32 (uint32x2_t __a, uint32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vtrn1q_f32 (float32x4_t __a, float32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {5, 1, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 2, 6});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vtrn1q_f64 (float64x2_t __a, float64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vtrn1q_p8 (poly8x16_t __a, poly8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vtrn1q_p16 (poly16x8_t __a, poly16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 1, 11, 3, 13, 5, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vtrn1q_s8 (int8x16_t __a, int8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vtrn1q_s16 (int16x8_t __a, int16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 1, 11, 3, 13, 5, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vtrn1q_s32 (int32x4_t __a, int32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {5, 1, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 2, 6});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vtrn1q_s64 (int64x2_t __a, int64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtrn1q_u8 (uint8x16_t __a, uint8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtrn1q_u16 (uint16x8_t __a, uint16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 1, 11, 3, 13, 5, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vtrn1q_u32 (uint32x4_t __a, uint32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {5, 1, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 2, 6});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vtrn1q_u64 (uint64x2_t __a, uint64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vtrn2_f32 (float32x2_t __a, float32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtrn2_p8 (poly8x8_t __a, poly8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 0, 10, 2, 12, 4, 14, 6});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 9, 3, 11, 5, 13, 7, 15});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vtrn2_p16 (poly16x4_t __a, poly16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 6, 2});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtrn2_s8 (int8x8_t __a, int8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 0, 10, 2, 12, 4, 14, 6});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 9, 3, 11, 5, 13, 7, 15});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vtrn2_s16 (int16x4_t __a, int16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 6, 2});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vtrn2_s32 (int32x2_t __a, int32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtrn2_u8 (uint8x8_t __a, uint8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 0, 10, 2, 12, 4, 14, 6});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 9, 3, 11, 5, 13, 7, 15});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtrn2_u16 (uint16x4_t __a, uint16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 6, 2});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vtrn2_u32 (uint32x2_t __a, uint32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vtrn2q_f32 (float32x4_t __a, float32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 0, 6, 2});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 5, 3, 7});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vtrn2q_f64 (float64x2_t __a, float64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vtrn2q_p8 (poly8x16_t __a, poly8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vtrn2q_p16 (poly16x8_t __a, poly16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 10, 2, 12, 4, 14, 6});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vtrn2q_s8 (int8x16_t __a, int8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vtrn2q_s16 (int16x8_t __a, int16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 10, 2, 12, 4, 14, 6});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vtrn2q_s32 (int32x4_t __a, int32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 0, 6, 2});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 5, 3, 7});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vtrn2q_s64 (int64x2_t __a, int64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtrn2q_u8 (uint8x16_t __a, uint8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtrn2q_u16 (uint16x8_t __a, uint16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 10, 2, 12, 4, 14, 6});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vtrn2q_u32 (uint32x4_t __a, uint32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 0, 6, 2});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 5, 3, 7});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vtrn2q_u64 (uint64x2_t __a, uint64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
vtrn_f32 (float32x2_t a, float32x2_t b)
{
  return (float32x2x2_t) {vtrn1_f32 (a, b), vtrn2_f32 (a, b)};
}

__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
vtrn_p8 (poly8x8_t a, poly8x8_t b)
{
  return (poly8x8x2_t) {vtrn1_p8 (a, b), vtrn2_p8 (a, b)};
}

__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
vtrn_p16 (poly16x4_t a, poly16x4_t b)
{
  return (poly16x4x2_t) {vtrn1_p16 (a, b), vtrn2_p16 (a, b)};
}

__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
vtrn_s8 (int8x8_t a, int8x8_t b)
{
  return (int8x8x2_t) {vtrn1_s8 (a, b), vtrn2_s8 (a, b)};
}

__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
vtrn_s16 (int16x4_t a, int16x4_t b)
{
  return (int16x4x2_t) {vtrn1_s16 (a, b), vtrn2_s16 (a, b)};
}

__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
vtrn_s32 (int32x2_t a, int32x2_t b)
{
  return (int32x2x2_t) {vtrn1_s32 (a, b), vtrn2_s32 (a, b)};
}

__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
vtrn_u8 (uint8x8_t a, uint8x8_t b)
{
  return (uint8x8x2_t) {vtrn1_u8 (a, b), vtrn2_u8 (a, b)};
}

__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
vtrn_u16 (uint16x4_t a, uint16x4_t b)
{
  return (uint16x4x2_t) {vtrn1_u16 (a, b), vtrn2_u16 (a, b)};
}

__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
vtrn_u32 (uint32x2_t a, uint32x2_t b)
{
  return (uint32x2x2_t) {vtrn1_u32 (a, b), vtrn2_u32 (a, b)};
}

__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
vtrnq_f32 (float32x4_t a, float32x4_t b)
{
  return (float32x4x2_t) {vtrn1q_f32 (a, b), vtrn2q_f32 (a, b)};
}

__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
vtrnq_p8 (poly8x16_t a, poly8x16_t b)
{
  return (poly8x16x2_t) {vtrn1q_p8 (a, b), vtrn2q_p8 (a, b)};
}

__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
vtrnq_p16 (poly16x8_t a, poly16x8_t b)
{
  return (poly16x8x2_t) {vtrn1q_p16 (a, b), vtrn2q_p16 (a, b)};
}

__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
vtrnq_s8 (int8x16_t a, int8x16_t b)
{
  return (int8x16x2_t) {vtrn1q_s8 (a, b), vtrn2q_s8 (a, b)};
}

__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
vtrnq_s16 (int16x8_t a, int16x8_t b)
{
  return (int16x8x2_t) {vtrn1q_s16 (a, b), vtrn2q_s16 (a, b)};
}

__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
vtrnq_s32 (int32x4_t a, int32x4_t b)
{
  return (int32x4x2_t) {vtrn1q_s32 (a, b), vtrn2q_s32 (a, b)};
}

__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
vtrnq_u8 (uint8x16_t a, uint8x16_t b)
{
  return (uint8x16x2_t) {vtrn1q_u8 (a, b), vtrn2q_u8 (a, b)};
}

__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
vtrnq_u16 (uint16x8_t a, uint16x8_t b)
{
  return (uint16x8x2_t) {vtrn1q_u16 (a, b), vtrn2q_u16 (a, b)};
}

__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
vtrnq_u32 (uint32x4_t a, uint32x4_t b)
{
  return (uint32x4x2_t) {vtrn1q_u32 (a, b), vtrn2q_u32 (a, b)};
}

/* vtst */

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtst_s8 (int8x8_t __a, int8x8_t __b)
{
  return (uint8x8_t) ((__a & __b) != 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtst_s16 (int16x4_t __a, int16x4_t __b)
{
  return (uint16x4_t) ((__a & __b) != 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vtst_s32 (int32x2_t __a, int32x2_t __b)
{
  return (uint32x2_t) ((__a & __b) != 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vtst_s64 (int64x1_t __a, int64x1_t __b)
{
  return (uint64x1_t) ((__a & __b) != __AARCH64_INT64_C (0));
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtst_u8 (uint8x8_t __a, uint8x8_t __b)
{
  return ((__a & __b) != 0);
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtst_u16 (uint16x4_t __a, uint16x4_t __b)
{
  return ((__a & __b) != 0);
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vtst_u32 (uint32x2_t __a, uint32x2_t __b)
{
  return ((__a & __b) != 0);
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vtst_u64 (uint64x1_t __a, uint64x1_t __b)
{
  return ((__a & __b) != __AARCH64_UINT64_C (0));
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtstq_s8 (int8x16_t __a, int8x16_t __b)
{
  return (uint8x16_t) ((__a & __b) != 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtstq_s16 (int16x8_t __a, int16x8_t __b)
{
  return (uint16x8_t) ((__a & __b) != 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vtstq_s32 (int32x4_t __a, int32x4_t __b)
{
  return (uint32x4_t) ((__a & __b) != 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vtstq_s64 (int64x2_t __a, int64x2_t __b)
{
  return (uint64x2_t) ((__a & __b) != __AARCH64_INT64_C (0));
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtstq_u8 (uint8x16_t __a, uint8x16_t __b)
{
  return ((__a & __b) != 0);
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtstq_u16 (uint16x8_t __a, uint16x8_t __b)
{
  return ((__a & __b) != 0);
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vtstq_u32 (uint32x4_t __a, uint32x4_t __b)
{
  return ((__a & __b) != 0);
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vtstq_u64 (uint64x2_t __a, uint64x2_t __b)
{
  return ((__a & __b) != __AARCH64_UINT64_C (0));
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vtstd_s64 (int64_t __a, int64_t __b)
{
  return (__a & __b) ? -1ll : 0ll;
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vtstd_u64 (uint64_t __a, uint64_t __b)
{
  return (__a & __b) ? -1ll : 0ll;
}

/* vuqadd */

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vuqadd_s8 (int8x8_t __a, uint8x8_t __b)
{
  return __builtin_aarch64_suqaddv8qi_ssu (__a,  __b);
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vuqadd_s16 (int16x4_t __a, uint16x4_t __b)
{
  return __builtin_aarch64_suqaddv4hi_ssu (__a,  __b);
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vuqadd_s32 (int32x2_t __a, uint32x2_t __b)
{
  return __builtin_aarch64_suqaddv2si_ssu (__a,  __b);
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vuqadd_s64 (int64x1_t __a, uint64x1_t __b)
{
  return (int64x1_t) {__builtin_aarch64_suqadddi_ssu (__a[0], __b[0])};
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vuqaddq_s8 (int8x16_t __a, uint8x16_t __b)
{
  return __builtin_aarch64_suqaddv16qi_ssu (__a,  __b);
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vuqaddq_s16 (int16x8_t __a, uint16x8_t __b)
{
  return __builtin_aarch64_suqaddv8hi_ssu (__a,  __b);
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vuqaddq_s32 (int32x4_t __a, uint32x4_t __b)
{
  return __builtin_aarch64_suqaddv4si_ssu (__a,  __b);
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vuqaddq_s64 (int64x2_t __a, uint64x2_t __b)
{
  return __builtin_aarch64_suqaddv2di_ssu (__a,  __b);
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vuqaddb_s8 (int8_t __a, uint8_t __b)
{
  return __builtin_aarch64_suqaddqi_ssu (__a,  __b);
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vuqaddh_s16 (int16_t __a, uint16_t __b)
{
  return __builtin_aarch64_suqaddhi_ssu (__a,  __b);
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vuqadds_s32 (int32_t __a, uint32_t __b)
{
  return __builtin_aarch64_suqaddsi_ssu (__a,  __b);
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vuqaddd_s64 (int64_t __a, uint64_t __b)
{
  return __builtin_aarch64_suqadddi_ssu (__a,  __b);
}

#define __DEFINTERLEAVE(op, rettype, intype, funcsuffix, Q)             \
  __extension__ static __inline rettype                                 \
  __attribute__ ((__always_inline__))                                   \
  v ## op ## Q ## _ ## funcsuffix (intype a, intype b)                  \
  {                                                                     \
    return (rettype) {v ## op ## 1 ## Q ## _ ## funcsuffix (a, b),      \
                      v ## op ## 2 ## Q ## _ ## funcsuffix (a, b)};     \
  }

#define __INTERLEAVE_LIST(op)                                   \
  __DEFINTERLEAVE (op, float32x2x2_t, float32x2_t, f32,)        \
  __DEFINTERLEAVE (op, poly8x8x2_t, poly8x8_t, p8,)             \
  __DEFINTERLEAVE (op, poly16x4x2_t, poly16x4_t, p16,)          \
  __DEFINTERLEAVE (op, int8x8x2_t, int8x8_t, s8,)               \
  __DEFINTERLEAVE (op, int16x4x2_t, int16x4_t, s16,)            \
  __DEFINTERLEAVE (op, int32x2x2_t, int32x2_t, s32,)            \
  __DEFINTERLEAVE (op, uint8x8x2_t, uint8x8_t, u8,)             \
  __DEFINTERLEAVE (op, uint16x4x2_t, uint16x4_t, u16,)          \
  __DEFINTERLEAVE (op, uint32x2x2_t, uint32x2_t, u32,)          \
  __DEFINTERLEAVE (op, float32x4x2_t, float32x4_t, f32, q)      \
  __DEFINTERLEAVE (op, poly8x16x2_t, poly8x16_t, p8, q)         \
  __DEFINTERLEAVE (op, poly16x8x2_t, poly16x8_t, p16, q)        \
  __DEFINTERLEAVE (op, int8x16x2_t, int8x16_t, s8, q)           \
  __DEFINTERLEAVE (op, int16x8x2_t, int16x8_t, s16, q)          \
  __DEFINTERLEAVE (op, int32x4x2_t, int32x4_t, s32, q)          \
  __DEFINTERLEAVE (op, uint8x16x2_t, uint8x16_t, u8, q)         \
  __DEFINTERLEAVE (op, uint16x8x2_t, uint16x8_t, u16, q)        \
  __DEFINTERLEAVE (op, uint32x4x2_t, uint32x4_t, u32, q)

/* vuzp */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vuzp1_f32 (float32x2_t __a, float32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vuzp1_p8 (poly8x8_t __a, poly8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {9, 11, 13, 15, 1, 3, 5, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 2, 4, 6, 8, 10, 12, 14});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vuzp1_p16 (poly16x4_t __a, poly16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 7, 1, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vuzp1_s8 (int8x8_t __a, int8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {9, 11, 13, 15, 1, 3, 5, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 2, 4, 6, 8, 10, 12, 14});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vuzp1_s16 (int16x4_t __a, int16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 7, 1, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vuzp1_s32 (int32x2_t __a, int32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vuzp1_u8 (uint8x8_t __a, uint8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {9, 11, 13, 15, 1, 3, 5, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 2, 4, 6, 8, 10, 12, 14});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vuzp1_u16 (uint16x4_t __a, uint16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 7, 1, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vuzp1_u32 (uint32x2_t __a, uint32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vuzp1q_f32 (float32x4_t __a, float32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {5, 7, 1, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 2, 4, 6});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vuzp1q_f64 (float64x2_t __a, float64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vuzp1q_p8 (poly8x16_t __a, poly8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vuzp1q_p16 (poly16x8_t __a, poly16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 11, 13, 15, 1, 3, 5, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vuzp1q_s8 (int8x16_t __a, int8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vuzp1q_s16 (int16x8_t __a, int16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 11, 13, 15, 1, 3, 5, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vuzp1q_s32 (int32x4_t __a, int32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {5, 7, 1, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 2, 4, 6});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vuzp1q_s64 (int64x2_t __a, int64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vuzp1q_u8 (uint8x16_t __a, uint8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vuzp1q_u16 (uint16x8_t __a, uint16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 11, 13, 15, 1, 3, 5, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vuzp1q_u32 (uint32x4_t __a, uint32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {5, 7, 1, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 2, 4, 6});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vuzp1q_u64 (uint64x2_t __a, uint64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vuzp2_f32 (float32x2_t __a, float32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vuzp2_p8 (poly8x8_t __a, poly8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 10, 12, 14, 0, 2, 4, 6});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 3, 5, 7, 9, 11, 13, 15});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vuzp2_p16 (poly16x4_t __a, poly16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 6, 0, 2});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vuzp2_s8 (int8x8_t __a, int8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 10, 12, 14, 0, 2, 4, 6});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 3, 5, 7, 9, 11, 13, 15});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vuzp2_s16 (int16x4_t __a, int16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 6, 0, 2});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vuzp2_s32 (int32x2_t __a, int32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vuzp2_u8 (uint8x8_t __a, uint8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 10, 12, 14, 0, 2, 4, 6});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 3, 5, 7, 9, 11, 13, 15});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vuzp2_u16 (uint16x4_t __a, uint16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 6, 0, 2});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vuzp2_u32 (uint32x2_t __a, uint32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vuzp2q_f32 (float32x4_t __a, float32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 6, 0, 2});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 3, 5, 7});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vuzp2q_f64 (float64x2_t __a, float64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vuzp2q_p8 (poly8x16_t __a, poly8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vuzp2q_p16 (poly16x8_t __a, poly16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 10, 12, 14, 0, 2, 4, 6});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vuzp2q_s8 (int8x16_t __a, int8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14});
#else
  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vuzp2q_s16 (int16x8_t __a, int16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 10, 12, 14, 0, 2, 4, 6});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vuzp2q_s32 (int32x4_t __a, int32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 6, 0, 2});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 3, 5, 7});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vuzp2q_s64 (int64x2_t __a, int64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vuzp2q_u8 (uint8x16_t __a, uint8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vuzp2q_u16 (uint16x8_t __a, uint16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 10, 12, 14, 0, 2, 4, 6});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vuzp2q_u32 (uint32x4_t __a, uint32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 6, 0, 2});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 3, 5, 7});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vuzp2q_u64 (uint64x2_t __a, uint64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__INTERLEAVE_LIST (uzp)

/* vzip */

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vzip1_f32 (float32x2_t __a, float32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vzip1_p8 (poly8x8_t __a, poly8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {12, 4, 13, 5, 14, 6, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 1, 9, 2, 10, 3, 11});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vzip1_p16 (poly16x4_t __a, poly16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {6, 2, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vzip1_s8 (int8x8_t __a, int8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {12, 4, 13, 5, 14, 6, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 1, 9, 2, 10, 3, 11});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vzip1_s16 (int16x4_t __a, int16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {6, 2, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vzip1_s32 (int32x2_t __a, int32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vzip1_u8 (uint8x8_t __a, uint8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {12, 4, 13, 5, 14, 6, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 1, 9, 2, 10, 3, 11});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vzip1_u16 (uint16x4_t __a, uint16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {6, 2, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vzip1_u32 (uint32x2_t __a, uint32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});
#endif
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vzip1q_f32 (float32x4_t __a, float32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {6, 2, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 1, 5});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vzip1q_f64 (float64x2_t __a, float64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vzip1q_p8 (poly8x16_t __a, poly8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vzip1q_p16 (poly16x8_t __a, poly16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {12, 4, 13, 5, 14, 6, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vzip1q_s8 (int8x16_t __a, int8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vzip1q_s16 (int16x8_t __a, int16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {12, 4, 13, 5, 14, 6, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vzip1q_s32 (int32x4_t __a, int32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {6, 2, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 1, 5});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vzip1q_s64 (int64x2_t __a, int64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vzip1q_u8 (uint8x16_t __a, uint8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vzip1q_u16 (uint16x8_t __a, uint16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {12, 4, 13, 5, 14, 6, 15, 7});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vzip1q_u32 (uint32x4_t __a, uint32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {6, 2, 7, 3});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 1, 5});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vzip1q_u64 (uint64x2_t __a, uint64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {3, 1});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});
#endif
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vzip2_f32 (float32x2_t __a, float32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vzip2_p8 (poly8x8_t __a, poly8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 0, 9, 1, 10, 2, 11, 3});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {4, 12, 5, 13, 6, 14, 7, 15});
#endif
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vzip2_p16 (poly16x4_t __a, poly16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 5, 1});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7});
#endif
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vzip2_s8 (int8x8_t __a, int8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 0, 9, 1, 10, 2, 11, 3});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {4, 12, 5, 13, 6, 14, 7, 15});
#endif
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vzip2_s16 (int16x4_t __a, int16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 5, 1});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7});
#endif
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vzip2_s32 (int32x2_t __a, int32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vzip2_u8 (uint8x8_t __a, uint8x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x8_t) {8, 0, 9, 1, 10, 2, 11, 3});
#else
  return __builtin_shuffle (__a, __b, (uint8x8_t) {4, 12, 5, 13, 6, 14, 7, 15});
#endif
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vzip2_u16 (uint16x4_t __a, uint16x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 5, 1});
#else
  return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7});
#endif
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vzip2_u32 (uint32x2_t __a, uint32x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});
#endif
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vzip2q_f32 (float32x4_t __a, float32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 0, 5, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {2, 6, 3, 7});
#endif
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vzip2q_f64 (float64x2_t __a, float64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vzip2q_p8 (poly8x16_t __a, poly8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31});
#endif
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vzip2q_p16 (poly16x8_t __a, poly16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 9, 1, 10, 2, 11, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {4, 12, 5, 13, 6, 14, 7, 15});
#endif
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vzip2q_s8 (int8x16_t __a, int8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31});
#endif
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vzip2q_s16 (int16x8_t __a, int16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 9, 1, 10, 2, 11, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {4, 12, 5, 13, 6, 14, 7, 15});
#endif
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vzip2q_s32 (int32x4_t __a, int32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 0, 5, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {2, 6, 3, 7});
#endif
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vzip2q_s64 (int64x2_t __a, int64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vzip2q_u8 (uint8x16_t __a, uint8x16_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7});
#else
  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31});
#endif
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vzip2q_u16 (uint16x8_t __a, uint16x8_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 9, 1, 10, 2, 11, 3});
#else
  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {4, 12, 5, 13, 6, 14, 7, 15});
#endif
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vzip2q_u32 (uint32x4_t __a, uint32x4_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint32x4_t) {4, 0, 5, 1});
#else
  return __builtin_shuffle (__a, __b, (uint32x4_t) {2, 6, 3, 7});
#endif
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vzip2q_u64 (uint64x2_t __a, uint64x2_t __b)
{
#ifdef __AARCH64EB__
  return __builtin_shuffle (__a, __b, (uint64x2_t) {2, 0});
#else
  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});
#endif
}

__INTERLEAVE_LIST (zip)

#undef __INTERLEAVE_LIST
#undef __DEFINTERLEAVE

/* End of optimal implementations in approved order.  */

#undef __aarch64_vget_lane_any

#undef __aarch64_vdup_lane_any
#undef __aarch64_vdup_lane_f32
#undef __aarch64_vdup_lane_f64
#undef __aarch64_vdup_lane_p8
#undef __aarch64_vdup_lane_p16
#undef __aarch64_vdup_lane_s8
#undef __aarch64_vdup_lane_s16
#undef __aarch64_vdup_lane_s32
#undef __aarch64_vdup_lane_s64
#undef __aarch64_vdup_lane_u8
#undef __aarch64_vdup_lane_u16
#undef __aarch64_vdup_lane_u32
#undef __aarch64_vdup_lane_u64
#undef __aarch64_vdup_laneq_f32
#undef __aarch64_vdup_laneq_f64
#undef __aarch64_vdup_laneq_p8
#undef __aarch64_vdup_laneq_p16
#undef __aarch64_vdup_laneq_s8
#undef __aarch64_vdup_laneq_s16
#undef __aarch64_vdup_laneq_s32
#undef __aarch64_vdup_laneq_s64
#undef __aarch64_vdup_laneq_u8
#undef __aarch64_vdup_laneq_u16
#undef __aarch64_vdup_laneq_u32
#undef __aarch64_vdup_laneq_u64
#undef __aarch64_vdupq_lane_f32
#undef __aarch64_vdupq_lane_f64
#undef __aarch64_vdupq_lane_p8
#undef __aarch64_vdupq_lane_p16
#undef __aarch64_vdupq_lane_s8
#undef __aarch64_vdupq_lane_s16
#undef __aarch64_vdupq_lane_s32
#undef __aarch64_vdupq_lane_s64
#undef __aarch64_vdupq_lane_u8
#undef __aarch64_vdupq_lane_u16
#undef __aarch64_vdupq_lane_u32
#undef __aarch64_vdupq_lane_u64
#undef __aarch64_vdupq_laneq_f32
#undef __aarch64_vdupq_laneq_f64
#undef __aarch64_vdupq_laneq_p8
#undef __aarch64_vdupq_laneq_p16
#undef __aarch64_vdupq_laneq_s8
#undef __aarch64_vdupq_laneq_s16
#undef __aarch64_vdupq_laneq_s32
#undef __aarch64_vdupq_laneq_s64
#undef __aarch64_vdupq_laneq_u8
#undef __aarch64_vdupq_laneq_u16
#undef __aarch64_vdupq_laneq_u32
#undef __aarch64_vdupq_laneq_u64

#pragma GCC pop_options

#endif