# 1 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c"
# 1 "/home/chr1s/src/oxide/master/src/objdir-arm64/chromium//"
# 1 "<built-in>"
# 1 "<command-line>"
# 1 "/usr/aarch64-linux-gnu/include/stdc-predef.h" 1 3
# 1 "<command-line>" 2
# 1 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c"
# 11 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c"
# 1 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 1 3 4
# 30 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
#pragma GCC push_options
#pragma GCC target ("+nothing+simd")

# 1 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stdint.h" 1 3 4
# 9 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stdint.h" 3 4
# 1 "/usr/aarch64-linux-gnu/include/stdint.h" 1 3 4
# 25 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
# 1 "/usr/aarch64-linux-gnu/include/features.h" 1 3 4
# 367 "/usr/aarch64-linux-gnu/include/features.h" 3 4
# 1 "/usr/aarch64-linux-gnu/include/sys/cdefs.h" 1 3 4
# 410 "/usr/aarch64-linux-gnu/include/sys/cdefs.h" 3 4
# 1 "/usr/aarch64-linux-gnu/include/bits/wordsize.h" 1 3 4
# 411 "/usr/aarch64-linux-gnu/include/sys/cdefs.h" 2 3 4
# 368 "/usr/aarch64-linux-gnu/include/features.h" 2 3 4
# 391 "/usr/aarch64-linux-gnu/include/features.h" 3 4
# 1 "/usr/aarch64-linux-gnu/include/gnu/stubs.h" 1 3 4




# 1 "/usr/aarch64-linux-gnu/include/bits/wordsize.h" 1 3 4
# 6 "/usr/aarch64-linux-gnu/include/gnu/stubs.h" 2 3 4


# 1 "/usr/aarch64-linux-gnu/include/gnu/stubs-lp64.h" 1 3 4
# 9 "/usr/aarch64-linux-gnu/include/gnu/stubs.h" 2 3 4
# 392 "/usr/aarch64-linux-gnu/include/features.h" 2 3 4
# 26 "/usr/aarch64-linux-gnu/include/stdint.h" 2 3 4
# 1 "/usr/aarch64-linux-gnu/include/bits/wchar.h" 1 3 4
# 27 "/usr/aarch64-linux-gnu/include/stdint.h" 2 3 4
# 1 "/usr/aarch64-linux-gnu/include/bits/wordsize.h" 1 3 4
# 28 "/usr/aarch64-linux-gnu/include/stdint.h" 2 3 4
# 36 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4

# 36 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
typedef signed char int8_t;
typedef short int int16_t;
typedef int int32_t;

typedef long int int64_t;







typedef unsigned char uint8_t;
typedef unsigned short int uint16_t;

typedef unsigned int uint32_t;



typedef unsigned long int uint64_t;
# 65 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
typedef signed char int_least8_t;
typedef short int int_least16_t;
typedef int int_least32_t;

typedef long int int_least64_t;






typedef unsigned char uint_least8_t;
typedef unsigned short int uint_least16_t;
typedef unsigned int uint_least32_t;

typedef unsigned long int uint_least64_t;
# 90 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
typedef signed char int_fast8_t;

typedef long int int_fast16_t;
typedef long int int_fast32_t;
typedef long int int_fast64_t;
# 103 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
typedef unsigned char uint_fast8_t;

typedef unsigned long int uint_fast16_t;
typedef unsigned long int uint_fast32_t;
typedef unsigned long int uint_fast64_t;
# 119 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
typedef long int intptr_t;


typedef unsigned long int uintptr_t;
# 134 "/usr/aarch64-linux-gnu/include/stdint.h" 3 4
typedef long int intmax_t;
typedef unsigned long int uintmax_t;
# 10 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stdint.h" 2 3 4
# 34 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 2 3 4




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;
# 604 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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;
}



__extension__ static __inline float16_t __attribute__ ((__always_inline__))
vget_lane_f16 (float16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vget_lane_f32 (float32x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vget_lane_f64 (float64x1_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vget_lane_p8 (poly8x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vget_lane_p16 (poly16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vget_lane_s8 (int8x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vget_lane_s16 (int16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vget_lane_s32 (int32x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vget_lane_s64 (int64x1_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vget_lane_u8 (uint8x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vget_lane_u16 (uint16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vget_lane_u32 (uint32x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vget_lane_u64 (uint64x1_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}



__extension__ static __inline float16_t __attribute__ ((__always_inline__))
vgetq_lane_f16 (float16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vgetq_lane_f32 (float32x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vgetq_lane_f64 (float64x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vgetq_lane_p8 (poly8x16_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vgetq_lane_p16 (poly16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vgetq_lane_s8 (int8x16_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vgetq_lane_s16 (int16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vgetq_lane_s32 (int32x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vgetq_lane_s64 (int64x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vgetq_lane_u8 (uint8x16_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vgetq_lane_u16 (uint16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vgetq_lane_u32 (uint32x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vgetq_lane_u64 (uint64x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}



__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;
}



__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vset_lane_f16 (float16_t __elem, float16x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vset_lane_f32 (float32_t __elem, float32x2_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vset_lane_f64 (float64_t __elem, float64x1_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vset_lane_p8 (poly8_t __elem, poly8x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vset_lane_p16 (poly16_t __elem, poly16x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vset_lane_s8 (int8_t __elem, int8x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vset_lane_s16 (int16_t __elem, int16x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vset_lane_s32 (int32_t __elem, int32x2_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vset_lane_s64 (int64_t __elem, int64x1_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vset_lane_u8 (uint8_t __elem, uint8x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vset_lane_u16 (uint16_t __elem, uint16x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vset_lane_u32 (uint32_t __elem, uint32x2_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vset_lane_u64 (uint64_t __elem, uint64x1_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}



__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vsetq_lane_f16 (float16_t __elem, float16x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vsetq_lane_f32 (float32_t __elem, float32x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vsetq_lane_f64 (float64_t __elem, float64x2_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vsetq_lane_p8 (poly8_t __elem, poly8x16_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vsetq_lane_p16 (poly16_t __elem, poly16x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vsetq_lane_s8 (int8_t __elem, int8x16_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vsetq_lane_s16 (int16_t __elem, int16x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vsetq_lane_s32 (int32_t __elem, int32x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vsetq_lane_s64 (int64_t __elem, int64x2_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vsetq_lane_u8 (uint8_t __elem, uint8x16_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vsetq_lane_u16 (uint16_t __elem, uint16x8_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vsetq_lane_u32 (uint32_t __elem, uint32x4_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vsetq_lane_u64 (uint64_t __elem, uint64x2_t __vec, const int __index)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __index); __vec[__index] = __elem; __vec; });
}






__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vget_low_f16 (float16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_f16 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_f16_u64 (lo);;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vget_low_f32 (float32x4_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_f32 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_f32_u64 (lo);;
}

__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)
{
  uint64x2_t tmp = vreinterpretq_u64_p8 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_p8_u64 (lo);;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vget_low_p16 (poly16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_p16 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_p16_u64 (lo);;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vget_low_s8 (int8x16_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s8 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_s8_u64 (lo);;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vget_low_s16 (int16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s16 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_s16_u64 (lo);;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vget_low_s32 (int32x4_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s32 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_s32_u64 (lo);;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vget_low_s64 (int64x2_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s64 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_s64_u64 (lo);;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vget_low_u8 (uint8x16_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_u8 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_u8_u64 (lo);;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vget_low_u16 (uint16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_u16 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_u16_u64 (lo);;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vget_low_u32 (uint32x4_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_u32 (__a); uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); return vreinterpret_u32_u64 (lo);;
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vget_low_u64 (uint64x2_t __a)
{
  return vcreate_u64 (vgetq_lane_u64 (__a, 0));
}
# 5014 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vget_high_f16 (float16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_f16 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_f16_u64 (hi);;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vget_high_f32 (float32x4_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_f32 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_f32_u64 (hi);;
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vget_high_f64 (float64x2_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_f64 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_f64_u64 (hi);;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vget_high_p8 (poly8x16_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_p8 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_p8_u64 (hi);;
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vget_high_p16 (poly16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_p16 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_p16_u64 (hi);;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vget_high_s8 (int8x16_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s8 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_s8_u64 (hi);;
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vget_high_s16 (int16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s16 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_s16_u64 (hi);;
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vget_high_s32 (int32x4_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s32 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_s32_u64 (hi);;
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vget_high_s64 (int64x2_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_s64 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_s64_u64 (hi);;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vget_high_u8 (uint8x16_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_u8 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_u8_u64 (hi);;
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vget_high_u16 (uint16x8_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_u16 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_u16_u64 (hi);;
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vget_high_u32 (uint32x4_t __a)
{
  uint64x2_t tmp = vreinterpretq_u64_u32 (__a); uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); return vreinterpret_u32_u64 (hi);;
}



__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);
}



__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 6268 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 6535 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 6757 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 7223 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 7445 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("xtn2 %0.16b,%1.8h"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("xtn2 %0.8h,%1.4s"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("xtn2 %0.4s,%1.2d"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("xtn2 %0.16b,%1.8h"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("xtn2 %0.8h,%1.4s"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("xtn2 %0.4s,%1.2d"
           : "+w"(result)
           : "w"(b)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 8100 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 8325 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmulx_f32 (float32x2_t a, float32x2_t b)
{
  float32x2_t result;
  __asm__ ("fmulx %0.2s,%1.2s,%2.2s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : );
  return result;
}
# 8536 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmulxd_f64 (float64_t a, float64_t b)
{
  float64_t result;
  __asm__ ("fmulx %d0, %d1, %d2"
           : "=w"(result)
           : "w"(a), "w"(b)
           : );
  return result;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulxq_f32 (float32x4_t a, float32x4_t b)
{
  float32x4_t result;
  __asm__ ("fmulx %0.4s,%1.4s,%2.4s"
           : "=w"(result)
           : "w"(a), "w"(b)
           : );
  return result;
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulxq_f64 (float64x2_t a, float64x2_t b)
{
  float64x2_t result;
  __asm__ ("fmulx %0.2d,%1.2d,%2.2d"
           : "=w"(result)
           : "w"(a), "w"(b)
           : );
  return result;
}
# 8595 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmulxs_f32 (float32_t a, float32_t b)
{
  float32_t result;
  __asm__ ("fmulx %s0, %s1, %s2"
           : "=w"(result)
           : "w"(a), "w"(b)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("sqxtn2 %0.16b, %1.8h"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("sqxtn2 %0.8h, %1.4s"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("sqxtn2 %0.4s, %1.2d"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("uqxtn2 %0.16b, %1.8h"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("uqxtn2 %0.8h, %1.4s"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("uqxtn2 %0.4s, %1.2d"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("sqxtun2 %0.16b, %1.8h"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("sqxtun2 %0.8h, %1.4s"
           : "+w"(result)
           : "w"(b)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("sqxtun2 %0.4s, %1.2d"
           : "+w"(result)
           : "w"(b)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 9776 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 10185 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}
# 10284 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
typedef struct int8x2_t { int8_t val[2]; } int8x2_t;
typedef struct int16x2_t { int16_t val[2]; } int16x2_t;
typedef struct uint8x2_t { uint8_t val[2]; } uint8x2_t;
typedef struct uint16x2_t { uint16_t val[2]; } uint16x2_t;
typedef struct float16x2_t { float16_t val[2]; } float16x2_t;
typedef struct poly8x2_t { poly8_t val[2]; } poly8x2_t;
typedef struct poly16x2_t { poly16_t val[2]; } poly16x2_t;

typedef struct int8x3_t { int8_t val[3]; } int8x3_t;
typedef struct int16x3_t { int16_t val[3]; } int16x3_t;
typedef struct int32x3_t { int32_t val[3]; } int32x3_t;
typedef struct int64x3_t { int64_t val[3]; } int64x3_t;
typedef struct uint8x3_t { uint8_t val[3]; } uint8x3_t;
typedef struct uint16x3_t { uint16_t val[3]; } uint16x3_t;
typedef struct uint32x3_t { uint32_t val[3]; } uint32x3_t;
typedef struct uint64x3_t { uint64_t val[3]; } uint64x3_t;
typedef struct float16x3_t { float16_t val[3]; } float16x3_t;
typedef struct float32x3_t { float32_t val[3]; } float32x3_t;
typedef struct float64x3_t { float64_t val[3]; } float64x3_t;
typedef struct poly8x3_t { poly8_t val[3]; } poly8x3_t;
typedef struct poly16x3_t { poly16_t val[3]; } poly16x3_t;

typedef struct int8x4_t { int8_t val[4]; } int8x4_t;
typedef struct int64x4_t { int64_t val[4]; } int64x4_t;
typedef struct uint8x4_t { uint8_t val[4]; } uint8x4_t;
typedef struct uint64x4_t { uint64_t val[4]; } uint64x4_t;
typedef struct poly8x4_t { poly8_t val[4]; } poly8x4_t;
typedef struct float64x4_t { float64_t val[4]; } float64x4_t;
# 10338 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_f16 (float16_t *__ptr, float16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float16x8x2_t __temp; __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (((uint64_t) 0))); __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (((uint64_t) 0))); __o = __builtin_aarch64_set_qregoiv8hf (__o, (float16x8_t) __temp.val[0], 0); __o = __builtin_aarch64_set_qregoiv8hf (__o, (float16x8_t) __temp.val[1], 1); __builtin_aarch64_st2_lanev4hf ((__builtin_aarch64_simd_hf *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_f32 (float32_t *__ptr, float32x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float32x4x2_t __temp; __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (((uint64_t) 0))); __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (((uint64_t) 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_st2_lanev2sf ((__builtin_aarch64_simd_sf *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_f64 (float64_t *__ptr, float64x1x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float64x2x2_t __temp; __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (((uint64_t) 0))); __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (((uint64_t) 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_st2_lanedf ((__builtin_aarch64_simd_df *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_p8 (poly8_t *__ptr, poly8x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; poly8x16x2_t __temp; __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (((uint64_t) 0))); __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (((uint64_t) 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_st2_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_p16 (poly16_t *__ptr, poly16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; poly16x8x2_t __temp; __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (((uint64_t) 0))); __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (((uint64_t) 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_st2_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_s8 (int8_t *__ptr, int8x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int8x16x2_t __temp; __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (((uint64_t) 0))); __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (((uint64_t) 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_st2_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_s16 (int16_t *__ptr, int16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int16x8x2_t __temp; __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (((uint64_t) 0))); __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (((uint64_t) 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_st2_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_s32 (int32_t *__ptr, int32x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int32x4x2_t __temp; __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (((uint64_t) 0))); __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (((uint64_t) 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_st2_lanev2si ((__builtin_aarch64_simd_si *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_s64 (int64_t *__ptr, int64x1x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int64x2x2_t __temp; __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (((uint64_t) 0))); __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (((uint64_t) 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_st2_lanedi ((__builtin_aarch64_simd_di *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_u8 (uint8_t *__ptr, uint8x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint8x16x2_t __temp; __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (((uint64_t) 0))); __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (((uint64_t) 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_st2_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_u16 (uint16_t *__ptr, uint16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint16x8x2_t __temp; __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (((uint64_t) 0))); __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (((uint64_t) 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_st2_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_u32 (uint32_t *__ptr, uint32x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint32x4x2_t __temp; __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (((uint64_t) 0))); __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (((uint64_t) 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_st2_lanev2si ((__builtin_aarch64_simd_si *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst2_lane_u64 (uint64_t *__ptr, uint64x1x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint64x2x2_t __temp; __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (((uint64_t) 0))); __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (((uint64_t) 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_st2_lanedi ((__builtin_aarch64_simd_di *) __ptr, __o, __c); }
# 10378 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_f16 (float16_t *__ptr, float16x8x2_t __b, const int __c) { union { float16x8x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev8hf ((__builtin_aarch64_simd_hf *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_f32 (float32_t *__ptr, float32x4x2_t __b, const int __c) { union { float32x4x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev4sf ((__builtin_aarch64_simd_sf *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_f64 (float64_t *__ptr, float64x2x2_t __b, const int __c) { union { float64x2x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev2df ((__builtin_aarch64_simd_df *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_p8 (poly8_t *__ptr, poly8x16x2_t __b, const int __c) { union { poly8x16x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_p16 (poly16_t *__ptr, poly16x8x2_t __b, const int __c) { union { poly16x8x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_s8 (int8_t *__ptr, int8x16x2_t __b, const int __c) { union { int8x16x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_s16 (int16_t *__ptr, int16x8x2_t __b, const int __c) { union { int16x8x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_s32 (int32_t *__ptr, int32x4x2_t __b, const int __c) { union { int32x4x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev4si ((__builtin_aarch64_simd_si *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_s64 (int64_t *__ptr, int64x2x2_t __b, const int __c) { union { int64x2x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev2di ((__builtin_aarch64_simd_di *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_u8 (uint8_t *__ptr, uint8x16x2_t __b, const int __c) { union { uint8x16x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_u16 (uint16_t *__ptr, uint16x8x2_t __b, const int __c) { union { uint16x8x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_u32 (uint32_t *__ptr, uint32x4x2_t __b, const int __c) { union { uint32x4x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev4si ((__builtin_aarch64_simd_si *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst2q_lane_u64 (uint64_t *__ptr, uint64x2x2_t __b, const int __c) { union { uint64x2x2_t __i; __builtin_aarch64_simd_oi __o; } __temp = { __b }; __builtin_aarch64_st2_lanev2di ((__builtin_aarch64_simd_di *) __ptr, __temp.__o, __c); }
# 10420 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_f16 (float16_t *__ptr, float16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float16x8x3_t __temp; __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (((uint64_t) 0))); __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (((uint64_t) 0))); __temp.val[2] = vcombine_f16 (__b.val[2], vcreate_f16 (((uint64_t) 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_st3_lanev4hf ((__builtin_aarch64_simd_hf *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_f32 (float32_t *__ptr, float32x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float32x4x3_t __temp; __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (((uint64_t) 0))); __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (((uint64_t) 0))); __temp.val[2] = vcombine_f32 (__b.val[2], vcreate_f32 (((uint64_t) 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_st3_lanev2sf ((__builtin_aarch64_simd_sf *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_f64 (float64_t *__ptr, float64x1x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float64x2x3_t __temp; __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (((uint64_t) 0))); __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (((uint64_t) 0))); __temp.val[2] = vcombine_f64 (__b.val[2], vcreate_f64 (((uint64_t) 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_st3_lanedf ((__builtin_aarch64_simd_df *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_p8 (poly8_t *__ptr, poly8x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; poly8x16x3_t __temp; __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (((uint64_t) 0))); __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (((uint64_t) 0))); __temp.val[2] = vcombine_p8 (__b.val[2], vcreate_p8 (((uint64_t) 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_st3_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_p16 (poly16_t *__ptr, poly16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; poly16x8x3_t __temp; __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (((uint64_t) 0))); __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (((uint64_t) 0))); __temp.val[2] = vcombine_p16 (__b.val[2], vcreate_p16 (((uint64_t) 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_st3_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_s8 (int8_t *__ptr, int8x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int8x16x3_t __temp; __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (((uint64_t) 0))); __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (((uint64_t) 0))); __temp.val[2] = vcombine_s8 (__b.val[2], vcreate_s8 (((uint64_t) 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_st3_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_s16 (int16_t *__ptr, int16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int16x8x3_t __temp; __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (((uint64_t) 0))); __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (((uint64_t) 0))); __temp.val[2] = vcombine_s16 (__b.val[2], vcreate_s16 (((uint64_t) 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_st3_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_s32 (int32_t *__ptr, int32x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int32x4x3_t __temp; __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (((uint64_t) 0))); __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (((uint64_t) 0))); __temp.val[2] = vcombine_s32 (__b.val[2], vcreate_s32 (((uint64_t) 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_st3_lanev2si ((__builtin_aarch64_simd_si *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_s64 (int64_t *__ptr, int64x1x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int64x2x3_t __temp; __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (((uint64_t) 0))); __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (((uint64_t) 0))); __temp.val[2] = vcombine_s64 (__b.val[2], vcreate_s64 (((uint64_t) 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_st3_lanedi ((__builtin_aarch64_simd_di *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_u8 (uint8_t *__ptr, uint8x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint8x16x3_t __temp; __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (((uint64_t) 0))); __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (((uint64_t) 0))); __temp.val[2] = vcombine_u8 (__b.val[2], vcreate_u8 (((uint64_t) 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_st3_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_u16 (uint16_t *__ptr, uint16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint16x8x3_t __temp; __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (((uint64_t) 0))); __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (((uint64_t) 0))); __temp.val[2] = vcombine_u16 (__b.val[2], vcreate_u16 (((uint64_t) 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_st3_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_u32 (uint32_t *__ptr, uint32x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint32x4x3_t __temp; __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (((uint64_t) 0))); __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (((uint64_t) 0))); __temp.val[2] = vcombine_u32 (__b.val[2], vcreate_u32 (((uint64_t) 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_st3_lanev2si ((__builtin_aarch64_simd_si *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst3_lane_u64 (uint64_t *__ptr, uint64x1x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint64x2x3_t __temp; __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (((uint64_t) 0))); __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (((uint64_t) 0))); __temp.val[2] = vcombine_u64 (__b.val[2], vcreate_u64 (((uint64_t) 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_st3_lanedi ((__builtin_aarch64_simd_di *) __ptr, __o, __c); }
# 10460 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_f16 (float16_t *__ptr, float16x8x3_t __b, const int __c) { union { float16x8x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev8hf ((__builtin_aarch64_simd_hf *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_f32 (float32_t *__ptr, float32x4x3_t __b, const int __c) { union { float32x4x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev4sf ((__builtin_aarch64_simd_sf *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_f64 (float64_t *__ptr, float64x2x3_t __b, const int __c) { union { float64x2x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev2df ((__builtin_aarch64_simd_df *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_p8 (poly8_t *__ptr, poly8x16x3_t __b, const int __c) { union { poly8x16x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_p16 (poly16_t *__ptr, poly16x8x3_t __b, const int __c) { union { poly16x8x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_s8 (int8_t *__ptr, int8x16x3_t __b, const int __c) { union { int8x16x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_s16 (int16_t *__ptr, int16x8x3_t __b, const int __c) { union { int16x8x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_s32 (int32_t *__ptr, int32x4x3_t __b, const int __c) { union { int32x4x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev4si ((__builtin_aarch64_simd_si *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_s64 (int64_t *__ptr, int64x2x3_t __b, const int __c) { union { int64x2x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev2di ((__builtin_aarch64_simd_di *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_u8 (uint8_t *__ptr, uint8x16x3_t __b, const int __c) { union { uint8x16x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_u16 (uint16_t *__ptr, uint16x8x3_t __b, const int __c) { union { uint16x8x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_u32 (uint32_t *__ptr, uint32x4x3_t __b, const int __c) { union { uint32x4x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev4si ((__builtin_aarch64_simd_si *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst3q_lane_u64 (uint64_t *__ptr, uint64x2x3_t __b, const int __c) { union { uint64x2x3_t __i; __builtin_aarch64_simd_ci __o; } __temp = { __b }; __builtin_aarch64_st3_lanev2di ((__builtin_aarch64_simd_di *) __ptr, __temp.__o, __c); }
# 10507 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_f16 (float16_t *__ptr, float16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float16x8x4_t __temp; __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (((uint64_t) 0))); __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (((uint64_t) 0))); __temp.val[2] = vcombine_f16 (__b.val[2], vcreate_f16 (((uint64_t) 0))); __temp.val[3] = vcombine_f16 (__b.val[3], vcreate_f16 (((uint64_t) 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_st4_lanev4hf ((__builtin_aarch64_simd_hf *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_f32 (float32_t *__ptr, float32x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float32x4x4_t __temp; __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (((uint64_t) 0))); __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (((uint64_t) 0))); __temp.val[2] = vcombine_f32 (__b.val[2], vcreate_f32 (((uint64_t) 0))); __temp.val[3] = vcombine_f32 (__b.val[3], vcreate_f32 (((uint64_t) 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_st4_lanev2sf ((__builtin_aarch64_simd_sf *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_f64 (float64_t *__ptr, float64x1x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float64x2x4_t __temp; __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (((uint64_t) 0))); __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (((uint64_t) 0))); __temp.val[2] = vcombine_f64 (__b.val[2], vcreate_f64 (((uint64_t) 0))); __temp.val[3] = vcombine_f64 (__b.val[3], vcreate_f64 (((uint64_t) 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_st4_lanedf ((__builtin_aarch64_simd_df *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_p8 (poly8_t *__ptr, poly8x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; poly8x16x4_t __temp; __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (((uint64_t) 0))); __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (((uint64_t) 0))); __temp.val[2] = vcombine_p8 (__b.val[2], vcreate_p8 (((uint64_t) 0))); __temp.val[3] = vcombine_p8 (__b.val[3], vcreate_p8 (((uint64_t) 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_st4_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_p16 (poly16_t *__ptr, poly16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; poly16x8x4_t __temp; __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (((uint64_t) 0))); __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (((uint64_t) 0))); __temp.val[2] = vcombine_p16 (__b.val[2], vcreate_p16 (((uint64_t) 0))); __temp.val[3] = vcombine_p16 (__b.val[3], vcreate_p16 (((uint64_t) 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_st4_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_s8 (int8_t *__ptr, int8x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int8x16x4_t __temp; __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (((uint64_t) 0))); __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (((uint64_t) 0))); __temp.val[2] = vcombine_s8 (__b.val[2], vcreate_s8 (((uint64_t) 0))); __temp.val[3] = vcombine_s8 (__b.val[3], vcreate_s8 (((uint64_t) 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_st4_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_s16 (int16_t *__ptr, int16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int16x8x4_t __temp; __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (((uint64_t) 0))); __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (((uint64_t) 0))); __temp.val[2] = vcombine_s16 (__b.val[2], vcreate_s16 (((uint64_t) 0))); __temp.val[3] = vcombine_s16 (__b.val[3], vcreate_s16 (((uint64_t) 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_st4_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_s32 (int32_t *__ptr, int32x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int32x4x4_t __temp; __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (((uint64_t) 0))); __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (((uint64_t) 0))); __temp.val[2] = vcombine_s32 (__b.val[2], vcreate_s32 (((uint64_t) 0))); __temp.val[3] = vcombine_s32 (__b.val[3], vcreate_s32 (((uint64_t) 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_st4_lanev2si ((__builtin_aarch64_simd_si *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_s64 (int64_t *__ptr, int64x1x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int64x2x4_t __temp; __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (((uint64_t) 0))); __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (((uint64_t) 0))); __temp.val[2] = vcombine_s64 (__b.val[2], vcreate_s64 (((uint64_t) 0))); __temp.val[3] = vcombine_s64 (__b.val[3], vcreate_s64 (((uint64_t) 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_st4_lanedi ((__builtin_aarch64_simd_di *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_u8 (uint8_t *__ptr, uint8x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint8x16x4_t __temp; __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (((uint64_t) 0))); __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (((uint64_t) 0))); __temp.val[2] = vcombine_u8 (__b.val[2], vcreate_u8 (((uint64_t) 0))); __temp.val[3] = vcombine_u8 (__b.val[3], vcreate_u8 (((uint64_t) 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_st4_lanev8qi ((__builtin_aarch64_simd_qi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_u16 (uint16_t *__ptr, uint16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint16x8x4_t __temp; __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (((uint64_t) 0))); __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (((uint64_t) 0))); __temp.val[2] = vcombine_u16 (__b.val[2], vcreate_u16 (((uint64_t) 0))); __temp.val[3] = vcombine_u16 (__b.val[3], vcreate_u16 (((uint64_t) 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_st4_lanev4hi ((__builtin_aarch64_simd_hi *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_u32 (uint32_t *__ptr, uint32x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint32x4x4_t __temp; __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (((uint64_t) 0))); __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (((uint64_t) 0))); __temp.val[2] = vcombine_u32 (__b.val[2], vcreate_u32 (((uint64_t) 0))); __temp.val[3] = vcombine_u32 (__b.val[3], vcreate_u32 (((uint64_t) 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_st4_lanev2si ((__builtin_aarch64_simd_si *) __ptr, __o, __c); }

__extension__ static __inline void __attribute__ ((__always_inline__)) vst4_lane_u64 (uint64_t *__ptr, uint64x1x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint64x2x4_t __temp; __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (((uint64_t) 0))); __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (((uint64_t) 0))); __temp.val[2] = vcombine_u64 (__b.val[2], vcreate_u64 (((uint64_t) 0))); __temp.val[3] = vcombine_u64 (__b.val[3], vcreate_u64 (((uint64_t) 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_st4_lanedi ((__builtin_aarch64_simd_di *) __ptr, __o, __c); }
# 10547 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_f16 (float16_t *__ptr, float16x8x4_t __b, const int __c) { union { float16x8x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev8hf ((__builtin_aarch64_simd_hf *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_f32 (float32_t *__ptr, float32x4x4_t __b, const int __c) { union { float32x4x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev4sf ((__builtin_aarch64_simd_sf *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_f64 (float64_t *__ptr, float64x2x4_t __b, const int __c) { union { float64x2x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev2df ((__builtin_aarch64_simd_df *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_p8 (poly8_t *__ptr, poly8x16x4_t __b, const int __c) { union { poly8x16x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_p16 (poly16_t *__ptr, poly16x8x4_t __b, const int __c) { union { poly16x8x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_s8 (int8_t *__ptr, int8x16x4_t __b, const int __c) { union { int8x16x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_s16 (int16_t *__ptr, int16x8x4_t __b, const int __c) { union { int16x8x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_s32 (int32_t *__ptr, int32x4x4_t __b, const int __c) { union { int32x4x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev4si ((__builtin_aarch64_simd_si *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_s64 (int64_t *__ptr, int64x2x4_t __b, const int __c) { union { int64x2x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev2di ((__builtin_aarch64_simd_di *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_u8 (uint8_t *__ptr, uint8x16x4_t __b, const int __c) { union { uint8x16x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev16qi ((__builtin_aarch64_simd_qi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_u16 (uint16_t *__ptr, uint16x8x4_t __b, const int __c) { union { uint16x8x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev8hi ((__builtin_aarch64_simd_hi *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_u32 (uint32_t *__ptr, uint32x4x4_t __b, const int __c) { union { uint32x4x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev4si ((__builtin_aarch64_simd_si *) __ptr, __temp.__o, __c); }
__extension__ static __inline void __attribute__ ((__always_inline__)) vst4q_lane_u64 (uint64_t *__ptr, uint64x2x4_t __b, const int __c) { union { uint64x2x4_t __i; __builtin_aarch64_simd_xi __o; } __temp = { __b }; __builtin_aarch64_st4_lanev2di ((__builtin_aarch64_simd_di *) __ptr, __temp.__o, __c); }

__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);
}



__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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl2_s8 (int8x16x2_t tab, uint8x8_t idx)
{
  int8x8_t result;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b, v17.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl2_u8 (uint8x16x2_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b, v17.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl2_p8 (poly8x16x2_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b, v17.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl2q_s8 (int8x16x2_t tab, uint8x16_t idx)
{
  int8x16_t result;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b, v17.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl2q_u8 (uint8x16x2_t tab, uint8x16_t idx)
{
  uint8x16_t result;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b, v17.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl2q_p8 (poly8x16x2_t tab, uint8x16_t idx)
{
  poly8x16_t result;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b, v17.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl3_s8 (int8x16x3_t tab, uint8x8_t idx)
{
  int8x8_t result;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b - v18.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl3_u8 (uint8x16x3_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b - v18.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl3_p8 (poly8x16x3_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b - v18.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl3q_s8 (int8x16x3_t tab, uint8x16_t idx)
{
  int8x16_t result;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b - v18.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl3q_u8 (uint8x16x3_t tab, uint8x16_t idx)
{
  uint8x16_t result;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b - v18.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl3q_p8 (poly8x16x3_t tab, uint8x16_t idx)
{
  poly8x16_t result;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b - v18.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbl4_s8 (int8x16x4_t tab, uint8x8_t idx)
{
  int8x8_t result;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b - v19.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbl4_u8 (uint8x16x4_t tab, uint8x8_t idx)
{
  uint8x8_t result;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b - v19.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbl4_p8 (poly8x16x4_t tab, uint8x8_t idx)
{
  poly8x8_t result;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbl %0.8b, {v16.16b - v19.16b}, %2.8b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}


__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbl4q_s8 (int8x16x4_t tab, uint8x16_t idx)
{
  int8x16_t result;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b - v19.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbl4q_u8 (uint8x16x4_t tab, uint8x16_t idx)
{
  uint8x16_t result;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b - v19.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbl4q_p8 (poly8x16x4_t tab, uint8x16_t idx)
{
  poly8x16_t result;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbl %0.16b, {v16.16b - v19.16b}, %2.16b\n\t"
    :"=w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  return result;
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx2_s8 (int8x8_t r, int8x16x2_t tab, uint8x8_t idx)
{
  int8x8_t result = r;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b, v17.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx2_u8 (uint8x8_t r, uint8x16x2_t tab, uint8x8_t idx)
{
  uint8x8_t result = r;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b, v17.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx2_p8 (poly8x8_t r, poly8x16x2_t tab, uint8x8_t idx)
{
  poly8x8_t result = r;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b, v17.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}


__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx2q_s8 (int8x16_t r, int8x16x2_t tab, uint8x16_t idx)
{
  int8x16_t result = r;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b, v17.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx2q_u8 (uint8x16_t r, uint8x16x2_t tab, uint8x16_t idx)
{
  uint8x16_t result = r;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b, v17.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx2q_p8 (poly8x16_t r, poly8x16x2_t tab, uint8x16_t idx)
{
  poly8x16_t result = r;
  __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b, v17.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17");
  return result;
}


__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx3_s8 (int8x8_t r, int8x16x3_t tab, uint8x8_t idx)
{
  int8x8_t result = r;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b - v18.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx3_u8 (uint8x8_t r, uint8x16x3_t tab, uint8x8_t idx)
{
  uint8x8_t result = r;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b - v18.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx3_p8 (poly8x8_t r, poly8x16x3_t tab, uint8x8_t idx)
{
  poly8x8_t result = r;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b - v18.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}


__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx3q_s8 (int8x16_t r, int8x16x3_t tab, uint8x16_t idx)
{
  int8x16_t result = r;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b - v18.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx3q_u8 (uint8x16_t r, uint8x16x3_t tab, uint8x16_t idx)
{
  uint8x16_t result = r;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b - v18.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx3q_p8 (poly8x16_t r, poly8x16x3_t tab, uint8x16_t idx)
{
  poly8x16_t result = r;
  __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b - v18.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18");
  return result;
}


__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vqtbx4_s8 (int8x8_t r, int8x16x4_t tab, uint8x8_t idx)
{
  int8x8_t result = r;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b - v19.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vqtbx4_u8 (uint8x8_t r, uint8x16x4_t tab, uint8x8_t idx)
{
  uint8x8_t result = r;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b - v19.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vqtbx4_p8 (poly8x8_t r, poly8x16x4_t tab, uint8x8_t idx)
{
  poly8x8_t result = r;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbx %0.8b, {v16.16b - v19.16b}, %2.8b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}


__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vqtbx4q_s8 (int8x16_t r, int8x16x4_t tab, uint8x16_t idx)
{
  int8x16_t result = r;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b - v19.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vqtbx4q_u8 (uint8x16_t r, uint8x16x4_t tab, uint8x16_t idx)
{
  uint8x16_t result = r;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b - v19.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vqtbx4q_p8 (poly8x16_t r, poly8x16x4_t tab, uint8x16_t idx)
{
  poly8x16_t result = r;
  __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
    "tbx %0.16b, {v16.16b - v19.16b}, %2.16b\n\t"
    :"+w"(result)
    :"Q"(tab),"w"(idx)
    :"memory", "v16", "v17", "v18", "v19");
  return result;
}



__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 (((uint64_t) 0x0)));
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : );
  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 (((uint64_t) 0x0)));
  __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
           : "=w"(result)
           : "w"(temp), "w"(idx)
           : );
  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)
           : );
  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)
           : );
  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)
           : );
  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 (((uint64_t) 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 (((uint64_t) 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 (((uint64_t) 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)
           : );
  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)
           : );
  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)
           : );
  return result;
}







__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);
}



__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;
}



__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);
}



__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);
}


#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")


__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



__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);
}



__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);
}



__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);
}



__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;
}



__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);
}



__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;
}



__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 == ((int64_t) 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 == ((uint64_t) 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 == ((int64_t) 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 == ((uint64_t) 0));
}



__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;
}



__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);
}



__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;
}



__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 >= ((int64_t) 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 >= ((int64_t) 0));
}



__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;
}



__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);
}



__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;
}



__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 > ((int64_t) 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 > ((int64_t) 0));
}



__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;
}



__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);
}



__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;
}



__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 <= ((int64_t) 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 <= ((int64_t) 0));
}



__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;
}



__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);
}



__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;
}



__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 < ((int64_t) 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 < ((int64_t) 0));
}



__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;
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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 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);
}



__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 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);
}



__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 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);
}



__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 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);
}



__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 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);
}



__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};
}



__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};
}



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vdup_lane_f32 (float32x2_t __a, const int __b)
{
  return vdup_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vdup_lane_f64 (float64x1_t __a, const int __b)
{
  return vdup_n_f64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vdup_lane_p8 (poly8x8_t __a, const int __b)
{
  return vdup_n_p8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vdup_lane_p16 (poly16x4_t __a, const int __b)
{
  return vdup_n_p16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vdup_lane_s8 (int8x8_t __a, const int __b)
{
  return vdup_n_s8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vdup_lane_s16 (int16x4_t __a, const int __b)
{
  return vdup_n_s16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vdup_lane_s32 (int32x2_t __a, const int __b)
{
  return vdup_n_s32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vdup_lane_s64 (int64x1_t __a, const int __b)
{
  return vdup_n_s64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vdup_lane_u8 (uint8x8_t __a, const int __b)
{
  return vdup_n_u8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vdup_lane_u16 (uint16x4_t __a, const int __b)
{
  return vdup_n_u16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vdup_lane_u32 (uint32x2_t __a, const int __b)
{
  return vdup_n_u32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vdup_lane_u64 (uint64x1_t __a, const int __b)
{
  return vdup_n_u64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vdup_laneq_f32 (float32x4_t __a, const int __b)
{
  return vdup_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vdup_laneq_f64 (float64x2_t __a, const int __b)
{
  return vdup_n_f64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vdup_laneq_p8 (poly8x16_t __a, const int __b)
{
  return vdup_n_p8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vdup_laneq_p16 (poly16x8_t __a, const int __b)
{
  return vdup_n_p16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vdup_laneq_s8 (int8x16_t __a, const int __b)
{
  return vdup_n_s8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vdup_laneq_s16 (int16x8_t __a, const int __b)
{
  return vdup_n_s16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vdup_laneq_s32 (int32x4_t __a, const int __b)
{
  return vdup_n_s32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vdup_laneq_s64 (int64x2_t __a, const int __b)
{
  return vdup_n_s64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vdup_laneq_u8 (uint8x16_t __a, const int __b)
{
  return vdup_n_u8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vdup_laneq_u16 (uint16x8_t __a, const int __b)
{
  return vdup_n_u16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vdup_laneq_u32 (uint32x4_t __a, const int __b)
{
  return vdup_n_u32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vdup_laneq_u64 (uint64x2_t __a, const int __b)
{
  return vdup_n_u64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}


__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vdupq_lane_f32 (float32x2_t __a, const int __b)
{
  return vdupq_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vdupq_lane_f64 (float64x1_t __a, const int __b)
{
  return vdupq_n_f64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vdupq_lane_p8 (poly8x8_t __a, const int __b)
{
  return vdupq_n_p8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vdupq_lane_p16 (poly16x4_t __a, const int __b)
{
  return vdupq_n_p16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vdupq_lane_s8 (int8x8_t __a, const int __b)
{
  return vdupq_n_s8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vdupq_lane_s16 (int16x4_t __a, const int __b)
{
  return vdupq_n_s16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vdupq_lane_s32 (int32x2_t __a, const int __b)
{
  return vdupq_n_s32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vdupq_lane_s64 (int64x1_t __a, const int __b)
{
  return vdupq_n_s64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vdupq_lane_u8 (uint8x8_t __a, const int __b)
{
  return vdupq_n_u8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vdupq_lane_u16 (uint16x4_t __a, const int __b)
{
  return vdupq_n_u16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vdupq_lane_u32 (uint32x2_t __a, const int __b)
{
  return vdupq_n_u32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vdupq_lane_u64 (uint64x1_t __a, const int __b)
{
  return vdupq_n_u64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}


__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vdupq_laneq_f32 (float32x4_t __a, const int __b)
{
  return vdupq_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vdupq_laneq_f64 (float64x2_t __a, const int __b)
{
  return vdupq_n_f64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vdupq_laneq_p8 (poly8x16_t __a, const int __b)
{
  return vdupq_n_p8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vdupq_laneq_p16 (poly16x8_t __a, const int __b)
{
  return vdupq_n_p16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vdupq_laneq_s8 (int8x16_t __a, const int __b)
{
  return vdupq_n_s8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vdupq_laneq_s16 (int16x8_t __a, const int __b)
{
  return vdupq_n_s16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vdupq_laneq_s32 (int32x4_t __a, const int __b)
{
  return vdupq_n_s32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vdupq_laneq_s64 (int64x2_t __a, const int __b)
{
  return vdupq_n_s64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vdupq_laneq_u8 (uint8x16_t __a, const int __b)
{
  return vdupq_n_u8 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vdupq_laneq_u16 (uint16x8_t __a, const int __b)
{
  return vdupq_n_u16 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vdupq_laneq_u32 (uint32x4_t __a, const int __b)
{
  return vdupq_n_u32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vdupq_laneq_u64 (uint64x2_t __a, const int __b)
{
  return vdupq_n_u64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; }));
}


__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vdupb_lane_p8 (poly8x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vdupb_lane_s8 (int8x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vdupb_lane_u8 (uint8x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}


__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vduph_lane_p16 (poly16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vduph_lane_s16 (int16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vduph_lane_u16 (uint16x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}


__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vdups_lane_f32 (float32x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vdups_lane_s32 (int32x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vdups_lane_u32 (uint32x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}


__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vdupd_lane_f64 (float64x1_t __a, const int __b)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b);
  return __a[0];
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vdupd_lane_s64 (int64x1_t __a, const int __b)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b);
  return __a[0];
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vdupd_lane_u64 (uint64x1_t __a, const int __b)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b);
  return __a[0];
}


__extension__ static __inline poly8_t __attribute__ ((__always_inline__))
vdupb_laneq_p8 (poly8x16_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int8_t __attribute__ ((__always_inline__))
vdupb_laneq_s8 (int8x16_t __a, const int __attribute__ ((unused)) __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint8_t __attribute__ ((__always_inline__))
vdupb_laneq_u8 (uint8x16_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}


__extension__ static __inline poly16_t __attribute__ ((__always_inline__))
vduph_laneq_p16 (poly16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int16_t __attribute__ ((__always_inline__))
vduph_laneq_s16 (int16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint16_t __attribute__ ((__always_inline__))
vduph_laneq_u16 (uint16x8_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}


__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vdups_laneq_f32 (float32x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int32_t __attribute__ ((__always_inline__))
vdups_laneq_s32 (int32x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint32_t __attribute__ ((__always_inline__))
vdups_laneq_u32 (uint32x4_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}


__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vdupd_laneq_f64 (float64x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline int64_t __attribute__ ((__always_inline__))
vdupd_laneq_s64 (int64x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}

__extension__ static __inline uint64_t __attribute__ ((__always_inline__))
vdupd_laneq_u64 (uint64x2_t __a, const int __b)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __b); __a[__b]; });
}



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vext_f32 (float32x2_t __a, float32x2_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);



  return __builtin_shuffle (__a, __b, (uint32x2_t) {__c, __c+1});

}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vext_f64 (float64x1_t __a, float64x1_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);

  return __a;
}
__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vext_p8 (poly8x8_t __a, poly8x8_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b,
      (uint8x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vext_p16 (poly16x4_t __a, poly16x4_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b, (uint16x4_t) {__c, __c+1, __c+2, __c+3});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vext_s8 (int8x8_t __a, int8x8_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b,
      (uint8x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vext_s16 (int16x4_t __a, int16x4_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b, (uint16x4_t) {__c, __c+1, __c+2, __c+3});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vext_s32 (int32x2_t __a, int32x2_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);



  return __builtin_shuffle (__a, __b, (uint32x2_t) {__c, __c+1});

}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vext_s64 (int64x1_t __a, int64x1_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);

  return __a;
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vext_u8 (uint8x8_t __a, uint8x8_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b,
      (uint8x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vext_u16 (uint16x4_t __a, uint16x4_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b, (uint16x4_t) {__c, __c+1, __c+2, __c+3});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vext_u32 (uint32x2_t __a, uint32x2_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);



  return __builtin_shuffle (__a, __b, (uint32x2_t) {__c, __c+1});

}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vext_u64 (uint64x1_t __a, uint64x1_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);

  return __a;
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vextq_f32 (float32x4_t __a, float32x4_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b, (uint32x4_t) {__c, __c+1, __c+2, __c+3});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vextq_f64 (float64x2_t __a, float64x2_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);



  return __builtin_shuffle (__a, __b, (uint64x2_t) {__c, __c+1});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vextq_p8 (poly8x16_t __a, poly8x16_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);





  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});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vextq_p16 (poly16x8_t __a, poly16x8_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b,
      (uint16x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vextq_s8 (int8x16_t __a, int8x16_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);





  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});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vextq_s16 (int16x8_t __a, int16x8_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b,
      (uint16x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vextq_s32 (int32x4_t __a, int32x4_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b, (uint32x4_t) {__c, __c+1, __c+2, __c+3});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vextq_s64 (int64x2_t __a, int64x2_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);



  return __builtin_shuffle (__a, __b, (uint64x2_t) {__c, __c+1});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vextq_u8 (uint8x16_t __a, uint8x16_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);





  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});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vextq_u16 (uint16x8_t __a, uint16x8_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b,
      (uint16x8_t) {__c, __c+1, __c+2, __c+3, __c+4, __c+5, __c+6, __c+7});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vextq_u32 (uint32x4_t __a, uint32x4_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);




  return __builtin_shuffle (__a, __b, (uint32x4_t) {__c, __c+1, __c+2, __c+3});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vextq_u64 (uint64x2_t __a, uint64x2_t __b, __const int __c)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __c);



  return __builtin_shuffle (__a, __b, (uint64x2_t) {__c, __c+1});

}



__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);
}



__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,
        vdup_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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, __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; }), __a);
}



__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,
        vdup_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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, __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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, __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; }), __a);
}



__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,
        vdupq_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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);
}



__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,
        vdupq_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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,
        vdupq_n_f64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })),
        __a);
}



__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);
}




__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,
        vdup_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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, __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; }), __a);
}



__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,
        vdup_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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, __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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, __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; }), __a);
}



__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,
        vdupq_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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);
}



__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,
        vdupq_n_f32 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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,
        vdupq_n_f64 (__extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })),
        __a);
}



__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};
}



__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);
}



__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);
}



__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);
}



__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
vld1_lane_f16 (const float16_t *__src, float16x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vld1_lane_f32 (const float32_t *__src, float32x2_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vld1_lane_f64 (const float64_t *__src, float64x1_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vld1_lane_p8 (const poly8_t *__src, poly8x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vld1_lane_p16 (const poly16_t *__src, poly16x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vld1_lane_s8 (const int8_t *__src, int8x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vld1_lane_s16 (const int16_t *__src, int16x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vld1_lane_s32 (const int32_t *__src, int32x2_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vld1_lane_s64 (const int64_t *__src, int64x1_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vld1_lane_u8 (const uint8_t *__src, uint8x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vld1_lane_u16 (const uint16_t *__src, uint16x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vld1_lane_u32 (const uint32_t *__src, uint32x2_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vld1_lane_u64 (const uint64_t *__src, uint64x1_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}



__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
vld1q_lane_f16 (const float16_t *__src, float16x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vld1q_lane_f32 (const float32_t *__src, float32x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vld1q_lane_f64 (const float64_t *__src, float64x2_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vld1q_lane_p8 (const poly8_t *__src, poly8x16_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vld1q_lane_p16 (const poly16_t *__src, poly16x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vld1q_lane_s8 (const int8_t *__src, int8x16_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vld1q_lane_s16 (const int16_t *__src, int16x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vld1q_lane_s32 (const int32_t *__src, int32x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vld1q_lane_s64 (const int64_t *__src, int64x2_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vld1q_lane_u8 (const uint8_t *__src, uint8x16_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vld1q_lane_u16 (const uint16_t *__src, uint16x8_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vld1q_lane_u32 (const uint32_t *__src, uint32x4_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vld1q_lane_u64 (const uint64_t *__src, uint64x2_t __vec, const int __lane)
{
  return __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __lane); __vec[__lane] = *__src; __vec; });
}



__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;
}



__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;
}
# 17572 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x4x2_t __attribute__ ((__always_inline__)) vld2_lane_f16 (const float16_t * __ptr, float16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float16x8x2_t __temp; __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (0)); __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (0)); __o = __builtin_aarch64_set_qregoiv8hf (__o, (float16x8_t) __temp.val[0], 0); __o = __builtin_aarch64_set_qregoiv8hf (__o, (float16x8_t) __temp.val[1], 1); __o = __builtin_aarch64_ld2_lanev4hf ( (__builtin_aarch64_simd_hf *) __ptr, __o, __c); __b.val[0] = (float16x4_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (float16x4_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vld2_lane_f32 (const float32_t * __ptr, float32x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float32x4x2_t __temp; __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (0)); __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (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); __o = __builtin_aarch64_ld2_lanev2sf ( (__builtin_aarch64_simd_sf *) __ptr, __o, __c); __b.val[0] = (float32x2_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (float32x2_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline float64x1x2_t __attribute__ ((__always_inline__)) vld2_lane_f64 (const float64_t * __ptr, float64x1x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float64x2x2_t __temp; __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (0)); __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (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); __o = __builtin_aarch64_ld2_lanedf ( (__builtin_aarch64_simd_df *) __ptr, __o, __c); __b.val[0] = (float64x1_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (float64x1_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) vld2_lane_p8 (const poly8_t * __ptr, poly8x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; poly8x16x2_t __temp; __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (0)); __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (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); __o = __builtin_aarch64_ld2_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (poly8x8_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (poly8x8_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) vld2_lane_p16 (const poly16_t * __ptr, poly16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; poly16x8x2_t __temp; __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (0)); __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (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); __o = __builtin_aarch64_ld2_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (poly16x4_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (poly16x4_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) vld2_lane_s8 (const int8_t * __ptr, int8x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int8x16x2_t __temp; __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (0)); __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (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); __o = __builtin_aarch64_ld2_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (int8x8_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (int8x8_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) vld2_lane_s16 (const int16_t * __ptr, int16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int16x8x2_t __temp; __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (0)); __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (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); __o = __builtin_aarch64_ld2_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (int16x4_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (int16x4_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) vld2_lane_s32 (const int32_t * __ptr, int32x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int32x4x2_t __temp; __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (0)); __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (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); __o = __builtin_aarch64_ld2_lanev2si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); __b.val[0] = (int32x2_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (int32x2_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__)) vld2_lane_s64 (const int64_t * __ptr, int64x1x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int64x2x2_t __temp; __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (0)); __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (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); __o = __builtin_aarch64_ld2_lanedi ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); __b.val[0] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) vld2_lane_u8 (const uint8_t * __ptr, uint8x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint8x16x2_t __temp; __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (0)); __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (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); __o = __builtin_aarch64_ld2_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (uint8x8_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (uint8x8_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) vld2_lane_u16 (const uint16_t * __ptr, uint16x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint16x8x2_t __temp; __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (0)); __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (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); __o = __builtin_aarch64_ld2_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (uint16x4_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (uint16x4_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) vld2_lane_u32 (const uint32_t * __ptr, uint32x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint32x4x2_t __temp; __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (0)); __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (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); __o = __builtin_aarch64_ld2_lanev2si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); __b.val[0] = (uint32x2_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (uint32x2_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }

__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__)) vld2_lane_u64 (const uint64_t * __ptr, uint64x1x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint64x2x2_t __temp; __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (0)); __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (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); __o = __builtin_aarch64_ld2_lanedi ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); __b.val[0] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 0); __b.val[1] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 1); return __b; }
# 17618 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x8x2_t __attribute__ ((__always_inline__)) vld2q_lane_f16 (const float16_t * __ptr, float16x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float16x8x2_t 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_lanev8hf ( (__builtin_aarch64_simd_hf *) __ptr, __o, __c); ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vld2q_lane_f32 (const float32_t * __ptr, float32x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float32x4x2_t 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_lanev4sf ( (__builtin_aarch64_simd_sf *) __ptr, __o, __c); ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline float64x2x2_t __attribute__ ((__always_inline__)) vld2q_lane_f64 (const float64_t * __ptr, float64x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; float64x2x2_t 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_lanev2df ( (__builtin_aarch64_simd_df *) __ptr, __o, __c); ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) vld2q_lane_p8 (const poly8_t * __ptr, poly8x16x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; poly8x16x2_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) vld2q_lane_p16 (const poly16_t * __ptr, poly16x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; poly16x8x2_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) vld2q_lane_s8 (const int8_t * __ptr, int8x16x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int8x16x2_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) vld2q_lane_s16 (const int16_t * __ptr, int16x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int16x8x2_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) vld2q_lane_s32 (const int32_t * __ptr, int32x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int32x4x2_t 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_lanev4si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); 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_lane_s64 (const int64_t * __ptr, int64x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; int64x2x2_t 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_lanev2di ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) vld2q_lane_u8 (const uint8_t * __ptr, uint8x16x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint8x16x2_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) vld2q_lane_u16 (const uint16_t * __ptr, uint16x8x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint16x8x2_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) vld2q_lane_u32 (const uint32_t * __ptr, uint32x4x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint32x4x2_t 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_lanev4si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); 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_lane_u64 (const uint64_t * __ptr, uint64x2x2_t __b, const int __c) { __builtin_aarch64_simd_oi __o; uint64x2x2_t 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_lanev2di ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregoiv4si (__o, 0); ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregoiv4si (__o, 1); return ret; }
# 17666 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x4x3_t __attribute__ ((__always_inline__)) vld3_lane_f16 (const float16_t * __ptr, float16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float16x8x3_t __temp; __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (0)); __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (0)); __temp.val[2] = vcombine_f16 (__b.val[2], vcreate_f16 (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); __o = __builtin_aarch64_ld3_lanev4hf ( (__builtin_aarch64_simd_hf *) __ptr, __o, __c); __b.val[0] = (float16x4_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (float16x4_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (float16x4_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__)) vld3_lane_f32 (const float32_t * __ptr, float32x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float32x4x3_t __temp; __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (0)); __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (0)); __temp.val[2] = vcombine_f32 (__b.val[2], vcreate_f32 (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); __o = __builtin_aarch64_ld3_lanev2sf ( (__builtin_aarch64_simd_sf *) __ptr, __o, __c); __b.val[0] = (float32x2_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (float32x2_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (float32x2_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline float64x1x3_t __attribute__ ((__always_inline__)) vld3_lane_f64 (const float64_t * __ptr, float64x1x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float64x2x3_t __temp; __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (0)); __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (0)); __temp.val[2] = vcombine_f64 (__b.val[2], vcreate_f64 (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); __o = __builtin_aarch64_ld3_lanedf ( (__builtin_aarch64_simd_df *) __ptr, __o, __c); __b.val[0] = (float64x1_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (float64x1_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (float64x1_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__)) vld3_lane_p8 (const poly8_t * __ptr, poly8x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; poly8x16x3_t __temp; __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (0)); __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (0)); __temp.val[2] = vcombine_p8 (__b.val[2], vcreate_p8 (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); __o = __builtin_aarch64_ld3_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (poly8x8_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (poly8x8_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (poly8x8_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__)) vld3_lane_p16 (const poly16_t * __ptr, poly16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; poly16x8x3_t __temp; __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (0)); __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (0)); __temp.val[2] = vcombine_p16 (__b.val[2], vcreate_p16 (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); __o = __builtin_aarch64_ld3_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (poly16x4_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (poly16x4_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (poly16x4_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__)) vld3_lane_s8 (const int8_t * __ptr, int8x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int8x16x3_t __temp; __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (0)); __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (0)); __temp.val[2] = vcombine_s8 (__b.val[2], vcreate_s8 (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); __o = __builtin_aarch64_ld3_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (int8x8_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (int8x8_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (int8x8_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__)) vld3_lane_s16 (const int16_t * __ptr, int16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int16x8x3_t __temp; __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (0)); __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (0)); __temp.val[2] = vcombine_s16 (__b.val[2], vcreate_s16 (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); __o = __builtin_aarch64_ld3_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (int16x4_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (int16x4_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (int16x4_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__)) vld3_lane_s32 (const int32_t * __ptr, int32x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int32x4x3_t __temp; __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (0)); __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (0)); __temp.val[2] = vcombine_s32 (__b.val[2], vcreate_s32 (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); __o = __builtin_aarch64_ld3_lanev2si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); __b.val[0] = (int32x2_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (int32x2_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (int32x2_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__)) vld3_lane_s64 (const int64_t * __ptr, int64x1x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int64x2x3_t __temp; __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (0)); __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (0)); __temp.val[2] = vcombine_s64 (__b.val[2], vcreate_s64 (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); __o = __builtin_aarch64_ld3_lanedi ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); __b.val[0] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__)) vld3_lane_u8 (const uint8_t * __ptr, uint8x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint8x16x3_t __temp; __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (0)); __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (0)); __temp.val[2] = vcombine_u8 (__b.val[2], vcreate_u8 (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); __o = __builtin_aarch64_ld3_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (uint8x8_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (uint8x8_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (uint8x8_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__)) vld3_lane_u16 (const uint16_t * __ptr, uint16x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint16x8x3_t __temp; __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (0)); __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (0)); __temp.val[2] = vcombine_u16 (__b.val[2], vcreate_u16 (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); __o = __builtin_aarch64_ld3_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (uint16x4_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (uint16x4_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (uint16x4_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__)) vld3_lane_u32 (const uint32_t * __ptr, uint32x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint32x4x3_t __temp; __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (0)); __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (0)); __temp.val[2] = vcombine_u32 (__b.val[2], vcreate_u32 (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); __o = __builtin_aarch64_ld3_lanev2si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); __b.val[0] = (uint32x2_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (uint32x2_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (uint32x2_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }

__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__)) vld3_lane_u64 (const uint64_t * __ptr, uint64x1x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint64x2x3_t __temp; __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (0)); __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (0)); __temp.val[2] = vcombine_u64 (__b.val[2], vcreate_u64 (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); __o = __builtin_aarch64_ld3_lanedi ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); __b.val[0] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 0); __b.val[1] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 1); __b.val[2] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 2); return __b; }
# 17714 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x8x3_t __attribute__ ((__always_inline__)) vld3q_lane_f16 (const float16_t * __ptr, float16x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float16x8x3_t 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_lanev8hf ( (__builtin_aarch64_simd_hf *) __ptr, __o, __c); ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (float16x8_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__)) vld3q_lane_f32 (const float32_t * __ptr, float32x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float32x4x3_t 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_lanev4sf ( (__builtin_aarch64_simd_sf *) __ptr, __o, __c); ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline float64x2x3_t __attribute__ ((__always_inline__)) vld3q_lane_f64 (const float64_t * __ptr, float64x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; float64x2x3_t 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_lanev2df ( (__builtin_aarch64_simd_df *) __ptr, __o, __c); ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline poly8x16x3_t __attribute__ ((__always_inline__)) vld3q_lane_p8 (const poly8_t * __ptr, poly8x16x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; poly8x16x3_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__)) vld3q_lane_p16 (const poly16_t * __ptr, poly16x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; poly16x8x3_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline int8x16x3_t __attribute__ ((__always_inline__)) vld3q_lane_s8 (const int8_t * __ptr, int8x16x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int8x16x3_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__)) vld3q_lane_s16 (const int16_t * __ptr, int16x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int16x8x3_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__)) vld3q_lane_s32 (const int32_t * __ptr, int32x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int32x4x3_t 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_lanev4si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); 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_lane_s64 (const int64_t * __ptr, int64x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; int64x2x3_t 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_lanev2di ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline uint8x16x3_t __attribute__ ((__always_inline__)) vld3q_lane_u8 (const uint8_t * __ptr, uint8x16x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint8x16x3_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__)) vld3q_lane_u16 (const uint16_t * __ptr, uint16x8x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint16x8x3_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__)) vld3q_lane_u32 (const uint32_t * __ptr, uint32x4x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint32x4x3_t 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_lanev4si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); 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_lane_u64 (const uint64_t * __ptr, uint64x2x3_t __b, const int __c) { __builtin_aarch64_simd_ci __o; uint64x2x3_t 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_lanev2di ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregciv4si (__o, 0); ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregciv4si (__o, 1); ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregciv4si (__o, 2); return ret; }
# 17770 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x4x4_t __attribute__ ((__always_inline__)) vld4_lane_f16 (const float16_t * __ptr, float16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float16x8x4_t __temp; __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (0)); __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (0)); __temp.val[2] = vcombine_f16 (__b.val[2], vcreate_f16 (0)); __temp.val[3] = vcombine_f16 (__b.val[3], vcreate_f16 (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); __o = __builtin_aarch64_ld4_lanev4hf ( (__builtin_aarch64_simd_hf *) __ptr, __o, __c); __b.val[0] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__)) vld4_lane_f32 (const float32_t * __ptr, float32x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float32x4x4_t __temp; __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (0)); __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (0)); __temp.val[2] = vcombine_f32 (__b.val[2], vcreate_f32 (0)); __temp.val[3] = vcombine_f32 (__b.val[3], vcreate_f32 (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); __o = __builtin_aarch64_ld4_lanev2sf ( (__builtin_aarch64_simd_sf *) __ptr, __o, __c); __b.val[0] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline float64x1x4_t __attribute__ ((__always_inline__)) vld4_lane_f64 (const float64_t * __ptr, float64x1x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float64x2x4_t __temp; __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (0)); __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (0)); __temp.val[2] = vcombine_f64 (__b.val[2], vcreate_f64 (0)); __temp.val[3] = vcombine_f64 (__b.val[3], vcreate_f64 (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); __o = __builtin_aarch64_ld4_lanedf ( (__builtin_aarch64_simd_df *) __ptr, __o, __c); __b.val[0] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__)) vld4_lane_p8 (const poly8_t * __ptr, poly8x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; poly8x16x4_t __temp; __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (0)); __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (0)); __temp.val[2] = vcombine_p8 (__b.val[2], vcreate_p8 (0)); __temp.val[3] = vcombine_p8 (__b.val[3], vcreate_p8 (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); __o = __builtin_aarch64_ld4_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__)) vld4_lane_p16 (const poly16_t * __ptr, poly16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; poly16x8x4_t __temp; __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (0)); __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (0)); __temp.val[2] = vcombine_p16 (__b.val[2], vcreate_p16 (0)); __temp.val[3] = vcombine_p16 (__b.val[3], vcreate_p16 (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); __o = __builtin_aarch64_ld4_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__)) vld4_lane_s8 (const int8_t * __ptr, int8x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int8x16x4_t __temp; __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (0)); __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (0)); __temp.val[2] = vcombine_s8 (__b.val[2], vcreate_s8 (0)); __temp.val[3] = vcombine_s8 (__b.val[3], vcreate_s8 (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); __o = __builtin_aarch64_ld4_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__)) vld4_lane_s16 (const int16_t * __ptr, int16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int16x8x4_t __temp; __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (0)); __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (0)); __temp.val[2] = vcombine_s16 (__b.val[2], vcreate_s16 (0)); __temp.val[3] = vcombine_s16 (__b.val[3], vcreate_s16 (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); __o = __builtin_aarch64_ld4_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__)) vld4_lane_s32 (const int32_t * __ptr, int32x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int32x4x4_t __temp; __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (0)); __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (0)); __temp.val[2] = vcombine_s32 (__b.val[2], vcreate_s32 (0)); __temp.val[3] = vcombine_s32 (__b.val[3], vcreate_s32 (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); __o = __builtin_aarch64_ld4_lanev2si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); __b.val[0] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__)) vld4_lane_s64 (const int64_t * __ptr, int64x1x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int64x2x4_t __temp; __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (0)); __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (0)); __temp.val[2] = vcombine_s64 (__b.val[2], vcreate_s64 (0)); __temp.val[3] = vcombine_s64 (__b.val[3], vcreate_s64 (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); __o = __builtin_aarch64_ld4_lanedi ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); __b.val[0] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__)) vld4_lane_u8 (const uint8_t * __ptr, uint8x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint8x16x4_t __temp; __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (0)); __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (0)); __temp.val[2] = vcombine_u8 (__b.val[2], vcreate_u8 (0)); __temp.val[3] = vcombine_u8 (__b.val[3], vcreate_u8 (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); __o = __builtin_aarch64_ld4_lanev8qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); __b.val[0] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__)) vld4_lane_u16 (const uint16_t * __ptr, uint16x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint16x8x4_t __temp; __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (0)); __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (0)); __temp.val[2] = vcombine_u16 (__b.val[2], vcreate_u16 (0)); __temp.val[3] = vcombine_u16 (__b.val[3], vcreate_u16 (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); __o = __builtin_aarch64_ld4_lanev4hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); __b.val[0] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__)) vld4_lane_u32 (const uint32_t * __ptr, uint32x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint32x4x4_t __temp; __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (0)); __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (0)); __temp.val[2] = vcombine_u32 (__b.val[2], vcreate_u32 (0)); __temp.val[3] = vcombine_u32 (__b.val[3], vcreate_u32 (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); __o = __builtin_aarch64_ld4_lanev2si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); __b.val[0] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }

__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__)) vld4_lane_u64 (const uint64_t * __ptr, uint64x1x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint64x2x4_t __temp; __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (0)); __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (0)); __temp.val[2] = vcombine_u64 (__b.val[2], vcreate_u64 (0)); __temp.val[3] = vcombine_u64 (__b.val[3], vcreate_u64 (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); __o = __builtin_aarch64_ld4_lanedi ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); __b.val[0] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 0); __b.val[1] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 1); __b.val[2] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 2); __b.val[3] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 3); return __b; }
# 17820 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float16x8x4_t __attribute__ ((__always_inline__)) vld4q_lane_f16 (const float16_t * __ptr, float16x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float16x8x4_t 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_lanev8hf ( (__builtin_aarch64_simd_hf *) __ptr, __o, __c); ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__)) vld4q_lane_f32 (const float32_t * __ptr, float32x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float32x4x4_t 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_lanev4sf ( (__builtin_aarch64_simd_sf *) __ptr, __o, __c); ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline float64x2x4_t __attribute__ ((__always_inline__)) vld4q_lane_f64 (const float64_t * __ptr, float64x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; float64x2x4_t 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_lanev2df ( (__builtin_aarch64_simd_df *) __ptr, __o, __c); ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline poly8x16x4_t __attribute__ ((__always_inline__)) vld4q_lane_p8 (const poly8_t * __ptr, poly8x16x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; poly8x16x4_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__)) vld4q_lane_p16 (const poly16_t * __ptr, poly16x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; poly16x8x4_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline int8x16x4_t __attribute__ ((__always_inline__)) vld4q_lane_s8 (const int8_t * __ptr, int8x16x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int8x16x4_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__)) vld4q_lane_s16 (const int16_t * __ptr, int16x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int16x8x4_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__)) vld4q_lane_s32 (const int32_t * __ptr, int32x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int32x4x4_t 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_lanev4si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); 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_lane_s64 (const int64_t * __ptr, int64x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; int64x2x4_t 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_lanev2di ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline uint8x16x4_t __attribute__ ((__always_inline__)) vld4q_lane_u8 (const uint8_t * __ptr, uint8x16x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint8x16x4_t 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_lanev16qi ( (__builtin_aarch64_simd_qi *) __ptr, __o, __c); ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__)) vld4q_lane_u16 (const uint16_t * __ptr, uint16x8x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint16x8x4_t 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_lanev8hi ( (__builtin_aarch64_simd_hi *) __ptr, __o, __c); ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }
__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__)) vld4q_lane_u32 (const uint32_t * __ptr, uint32x4x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint32x4x4_t 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_lanev4si ( (__builtin_aarch64_simd_si *) __ptr, __o, __c); 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_lane_u64 (const uint64_t * __ptr, uint64x2x4_t __b, const int __c) { __builtin_aarch64_simd_xi __o; uint64x2x4_t 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_lanev2di ( (__builtin_aarch64_simd_di *) __ptr, __o, __c); ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0); ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1); ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2); ret.val[3] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3); return ret; }





__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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;
}



__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })));
}



__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })));
}



__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })));
}



__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;
}



__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })));
}



__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })));
}



__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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__c), sizeof(__c[0]), __lane); __c[__lane]; })));
}



__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);
}



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_lane_f32 (float32x2_t __a, float32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmul_lane_s32 (int32x2_t __a, int32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmul_lane_u16 (uint16x4_t __a, uint16x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmul_lane_u32 (uint32x2_t __a, uint32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmuld_lane_f64 (float64_t __a, float64x1_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline float64_t __attribute__ ((__always_inline__))
vmuld_laneq_f64 (float64_t __a, float64x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmuls_lane_f32 (float32_t __a, float32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline float32_t __attribute__ ((__always_inline__))
vmuls_laneq_f32 (float32_t __a, float32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vmul_laneq_f32 (float32x2_t __a, float32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vmul_laneq_f64 (float64x1_t __a, float64x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vmul_laneq_s16 (int16x4_t __a, int16x8_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vmul_laneq_s32 (int32x2_t __a, int32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vmul_laneq_u16 (uint16x4_t __a, uint16x8_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vmul_laneq_u32 (uint32x2_t __a, uint32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__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 };
}



__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_lane_f32 (float32x4_t __a, float32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulq_lane_f64 (float64x2_t __a, float64x1_t __b, const int __lane)
{
  __builtin_aarch64_im_lane_boundsi (sizeof(__a), sizeof(__a[0]), __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 * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmulq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmulq_lane_u16 (uint16x8_t __a, uint16x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmulq_lane_u32 (uint32x4_t __a, uint32x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vmulq_laneq_f32 (float32x4_t __a, float32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vmulq_laneq_f64 (float64x2_t __a, float64x2_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vmulq_laneq_s16 (int16x8_t __a, int16x8_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vmulq_laneq_s32 (int32x4_t __a, int32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vmulq_laneq_u16 (uint16x8_t __a, uint16x8_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vmulq_laneq_u32 (uint32x4_t __a, uint32x4_t __b, const int __lane)
{
  return __a * __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__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;
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}




__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 });
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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);
}



__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")



__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



__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);
}



__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);
}



__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);
}



__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);
}


__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);
}



__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);
}



__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);
}



__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];
}



__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);
}



__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_f16 (float16_t *__a, float16x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_f32 (float32_t *__a, float32x2_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_f64 (float64_t *__a, float64x1_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_p8 (poly8_t *__a, poly8x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_p16 (poly16_t *__a, poly16x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s8 (int8_t *__a, int8x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s16 (int16_t *__a, int16x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s32 (int32_t *__a, int32x2_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_s64 (int64_t *__a, int64x1_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u8 (uint8_t *__a, uint8x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u16 (uint16_t *__a, uint16x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u32 (uint32_t *__a, uint32x2_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1_lane_u64 (uint64_t *__a, uint64x1_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_f16 (float16_t *__a, float16x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_f32 (float32_t *__a, float32x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_f64 (float64_t *__a, float64x2_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_p8 (poly8_t *__a, poly8x16_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_p16 (poly16_t *__a, poly16x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s8 (int8_t *__a, int8x16_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s16 (int16_t *__a, int16x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s32 (int32_t *__a, int32x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_s64 (int64_t *__a, int64x2_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u8 (uint8_t *__a, uint8x16_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u16 (uint16_t *__a, uint16x8_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u32 (uint32_t *__a, uint32x4_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}

__extension__ static __inline void __attribute__ ((__always_inline__))
vst1q_lane_u64 (uint64_t *__a, uint64x2_t __b, const int __lane)
{
  *__a = __extension__ ({ __builtin_aarch64_im_lane_boundsi (sizeof(__b), sizeof(__b[0]), __lane); __b[__lane]; });
}



__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 (((int64_t) 0)));
  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f16 (val.val[1], vcreate_f16 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (((int64_t) 0)));
  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (((uint64_t) 0)));
  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (((uint64_t) 0)));
  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (((int64_t) 0)));
  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (((uint64_t) 0)));
  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (((int64_t) 0)));
  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (((uint64_t) 0)));
  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (((int64_t) 0)));
  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (((uint64_t) 0)));
  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (((uint64_t) 0)));
  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (((uint64_t) 0)));
  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f16 (val.val[1], vcreate_f16 (((uint64_t) 0)));
  temp.val[2] = vcombine_f16 (val.val[2], vcreate_f16 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (((uint64_t) 0)));
  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (((int64_t) 0)));
  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (((int64_t) 0)));
  temp.val[3] = vcombine_s64 (val.val[3], vcreate_s64 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (((uint64_t) 0)));
  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (((uint64_t) 0)));
  temp.val[3] = vcombine_u64 (val.val[3], vcreate_u64 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (((uint64_t) 0)));
  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (((uint64_t) 0)));
  temp.val[3] = vcombine_f64 (val.val[3], vcreate_f64 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (((int64_t) 0)));
  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (((int64_t) 0)));
  temp.val[3] = vcombine_s8 (val.val[3], vcreate_s8 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (((uint64_t) 0)));
  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (((uint64_t) 0)));
  temp.val[3] = vcombine_p8 (val.val[3], vcreate_p8 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (((int64_t) 0)));
  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (((int64_t) 0)));
  temp.val[3] = vcombine_s16 (val.val[3], vcreate_s16 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (((uint64_t) 0)));
  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (((uint64_t) 0)));
  temp.val[3] = vcombine_p16 (val.val[3], vcreate_p16 (((uint64_t) 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 (((int64_t) 0)));
  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (((int64_t) 0)));
  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (((int64_t) 0)));
  temp.val[3] = vcombine_s32 (val.val[3], vcreate_s32 (((int64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (((uint64_t) 0)));
  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (((uint64_t) 0)));
  temp.val[3] = vcombine_u8 (val.val[3], vcreate_u8 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (((uint64_t) 0)));
  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (((uint64_t) 0)));
  temp.val[3] = vcombine_u16 (val.val[3], vcreate_u16 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (((uint64_t) 0)));
  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (((uint64_t) 0)));
  temp.val[3] = vcombine_u32 (val.val[3], vcreate_u32 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f16 (val.val[1], vcreate_f16 (((uint64_t) 0)));
  temp.val[2] = vcombine_f16 (val.val[2], vcreate_f16 (((uint64_t) 0)));
  temp.val[3] = vcombine_f16 (val.val[3], vcreate_f16 (((uint64_t) 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 (((uint64_t) 0)));
  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (((uint64_t) 0)));
  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (((uint64_t) 0)));
  temp.val[3] = vcombine_f32 (val.val[3], vcreate_f32 (((uint64_t) 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);
}



__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;
}



__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);
}



__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);
}



__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;
}



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vtrn1_f32 (float32x2_t __a, float32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtrn1_p8 (poly8x8_t __a, poly8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 2, 10, 4, 12, 6, 14});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vtrn1_p16 (poly16x4_t __a, poly16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtrn1_s8 (int8x8_t __a, int8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 2, 10, 4, 12, 6, 14});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vtrn1_s16 (int16x4_t __a, int16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vtrn1_s32 (int32x2_t __a, int32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtrn1_u8 (uint8x8_t __a, uint8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 2, 10, 4, 12, 6, 14});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtrn1_u16 (uint16x4_t __a, uint16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vtrn1_u32 (uint32x2_t __a, uint32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vtrn1q_f32 (float32x4_t __a, float32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 2, 6});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vtrn1q_f64 (float64x2_t __a, float64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vtrn1q_p8 (poly8x16_t __a, poly8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vtrn1q_p16 (poly16x8_t __a, poly16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vtrn1q_s8 (int8x16_t __a, int8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vtrn1q_s16 (int16x8_t __a, int16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vtrn1q_s32 (int32x4_t __a, int32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 2, 6});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vtrn1q_s64 (int64x2_t __a, int64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtrn1q_u8 (uint8x16_t __a, uint8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtrn1q_u16 (uint16x8_t __a, uint16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vtrn1q_u32 (uint32x4_t __a, uint32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 2, 6});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vtrn1q_u64 (uint64x2_t __a, uint64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vtrn2_f32 (float32x2_t __a, float32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vtrn2_p8 (poly8x8_t __a, poly8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 9, 3, 11, 5, 13, 7, 15});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vtrn2_p16 (poly16x4_t __a, poly16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vtrn2_s8 (int8x8_t __a, int8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 9, 3, 11, 5, 13, 7, 15});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vtrn2_s16 (int16x4_t __a, int16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vtrn2_s32 (int32x2_t __a, int32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vtrn2_u8 (uint8x8_t __a, uint8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 9, 3, 11, 5, 13, 7, 15});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vtrn2_u16 (uint16x4_t __a, uint16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vtrn2_u32 (uint32x2_t __a, uint32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vtrn2q_f32 (float32x4_t __a, float32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 5, 3, 7});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vtrn2q_f64 (float64x2_t __a, float64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vtrn2q_p8 (poly8x16_t __a, poly8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vtrn2q_p16 (poly16x8_t __a, poly16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vtrn2q_s8 (int8x16_t __a, int8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vtrn2q_s16 (int16x8_t __a, int16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vtrn2q_s32 (int32x4_t __a, int32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 5, 3, 7});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vtrn2q_s64 (int64x2_t __a, int64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vtrn2q_u8 (uint8x16_t __a, uint8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vtrn2q_u16 (uint16x8_t __a, uint16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vtrn2q_u32 (uint32x4_t __a, uint32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 5, 3, 7});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vtrn2q_u64 (uint64x2_t __a, uint64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__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)};
}



__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) != ((int64_t) 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) != ((uint64_t) 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) != ((int64_t) 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) != ((uint64_t) 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;
}



__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);
}
# 24868 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vuzp1_f32 (float32x2_t __a, float32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vuzp1_p8 (poly8x8_t __a, poly8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 2, 4, 6, 8, 10, 12, 14});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vuzp1_p16 (poly16x4_t __a, poly16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vuzp1_s8 (int8x8_t __a, int8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 2, 4, 6, 8, 10, 12, 14});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vuzp1_s16 (int16x4_t __a, int16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vuzp1_s32 (int32x2_t __a, int32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vuzp1_u8 (uint8x8_t __a, uint8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 2, 4, 6, 8, 10, 12, 14});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vuzp1_u16 (uint16x4_t __a, uint16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vuzp1_u32 (uint32x2_t __a, uint32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vuzp1q_f32 (float32x4_t __a, float32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 2, 4, 6});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vuzp1q_f64 (float64x2_t __a, float64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vuzp1q_p8 (poly8x16_t __a, poly8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vuzp1q_p16 (poly16x8_t __a, poly16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vuzp1q_s8 (int8x16_t __a, int8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vuzp1q_s16 (int16x8_t __a, int16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vuzp1q_s32 (int32x4_t __a, int32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 2, 4, 6});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vuzp1q_s64 (int64x2_t __a, int64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vuzp1q_u8 (uint8x16_t __a, uint8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vuzp1q_u16 (uint16x8_t __a, uint16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vuzp1q_u32 (uint32x4_t __a, uint32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 2, 4, 6});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vuzp1q_u64 (uint64x2_t __a, uint64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vuzp2_f32 (float32x2_t __a, float32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vuzp2_p8 (poly8x8_t __a, poly8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 3, 5, 7, 9, 11, 13, 15});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vuzp2_p16 (poly16x4_t __a, poly16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vuzp2_s8 (int8x8_t __a, int8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 3, 5, 7, 9, 11, 13, 15});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vuzp2_s16 (int16x4_t __a, int16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vuzp2_s32 (int32x2_t __a, int32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vuzp2_u8 (uint8x8_t __a, uint8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {1, 3, 5, 7, 9, 11, 13, 15});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vuzp2_u16 (uint16x4_t __a, uint16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vuzp2_u32 (uint32x2_t __a, uint32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vuzp2q_f32 (float32x4_t __a, float32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 3, 5, 7});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vuzp2q_f64 (float64x2_t __a, float64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vuzp2q_p8 (poly8x16_t __a, poly8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vuzp2q_p16 (poly16x8_t __a, poly16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vuzp2q_s8 (int8x16_t __a, int8x16_t __b)
{




  return __builtin_shuffle (__a, __b,
      (uint8x16_t) {1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vuzp2q_s16 (int16x8_t __a, int16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vuzp2q_s32 (int32x4_t __a, int32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 3, 5, 7});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vuzp2q_s64 (int64x2_t __a, int64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vuzp2q_u8 (uint8x16_t __a, uint8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vuzp2q_u16 (uint16x8_t __a, uint16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vuzp2q_u32 (uint32x4_t __a, uint32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {1, 3, 5, 7});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vuzp2q_u64 (uint64x2_t __a, uint64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vuzp_f32 (float32x2_t a, float32x2_t b) { return (float32x2x2_t) {vuzp1_f32 (a, b), vuzp2_f32 (a, b)}; } __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) vuzp_p8 (poly8x8_t a, poly8x8_t b) { return (poly8x8x2_t) {vuzp1_p8 (a, b), vuzp2_p8 (a, b)}; } __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) vuzp_p16 (poly16x4_t a, poly16x4_t b) { return (poly16x4x2_t) {vuzp1_p16 (a, b), vuzp2_p16 (a, b)}; } __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) vuzp_s8 (int8x8_t a, int8x8_t b) { return (int8x8x2_t) {vuzp1_s8 (a, b), vuzp2_s8 (a, b)}; } __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) vuzp_s16 (int16x4_t a, int16x4_t b) { return (int16x4x2_t) {vuzp1_s16 (a, b), vuzp2_s16 (a, b)}; } __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) vuzp_s32 (int32x2_t a, int32x2_t b) { return (int32x2x2_t) {vuzp1_s32 (a, b), vuzp2_s32 (a, b)}; } __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) vuzp_u8 (uint8x8_t a, uint8x8_t b) { return (uint8x8x2_t) {vuzp1_u8 (a, b), vuzp2_u8 (a, b)}; } __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) vuzp_u16 (uint16x4_t a, uint16x4_t b) { return (uint16x4x2_t) {vuzp1_u16 (a, b), vuzp2_u16 (a, b)}; } __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) vuzp_u32 (uint32x2_t a, uint32x2_t b) { return (uint32x2x2_t) {vuzp1_u32 (a, b), vuzp2_u32 (a, b)}; } __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vuzpq_f32 (float32x4_t a, float32x4_t b) { return (float32x4x2_t) {vuzp1q_f32 (a, b), vuzp2q_f32 (a, b)}; } __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) vuzpq_p8 (poly8x16_t a, poly8x16_t b) { return (poly8x16x2_t) {vuzp1q_p8 (a, b), vuzp2q_p8 (a, b)}; } __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) vuzpq_p16 (poly16x8_t a, poly16x8_t b) { return (poly16x8x2_t) {vuzp1q_p16 (a, b), vuzp2q_p16 (a, b)}; } __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) vuzpq_s8 (int8x16_t a, int8x16_t b) { return (int8x16x2_t) {vuzp1q_s8 (a, b), vuzp2q_s8 (a, b)}; } __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) vuzpq_s16 (int16x8_t a, int16x8_t b) { return (int16x8x2_t) {vuzp1q_s16 (a, b), vuzp2q_s16 (a, b)}; } __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) vuzpq_s32 (int32x4_t a, int32x4_t b) { return (int32x4x2_t) {vuzp1q_s32 (a, b), vuzp2q_s32 (a, b)}; } __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) vuzpq_u8 (uint8x16_t a, uint8x16_t b) { return (uint8x16x2_t) {vuzp1q_u8 (a, b), vuzp2q_u8 (a, b)}; } __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) vuzpq_u16 (uint16x8_t a, uint16x8_t b) { return (uint16x8x2_t) {vuzp1q_u16 (a, b), vuzp2q_u16 (a, b)}; } __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) vuzpq_u32 (uint32x4_t a, uint32x4_t b) { return (uint32x4x2_t) {vuzp1q_u32 (a, b), vuzp2q_u32 (a, b)}; }



__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vzip1_f32 (float32x2_t __a, float32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vzip1_p8 (poly8x8_t __a, poly8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 1, 9, 2, 10, 3, 11});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vzip1_p16 (poly16x4_t __a, poly16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vzip1_s8 (int8x8_t __a, int8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 1, 9, 2, 10, 3, 11});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vzip1_s16 (int16x4_t __a, int16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vzip1_s32 (int32x2_t __a, int32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vzip1_u8 (uint8x8_t __a, uint8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {0, 8, 1, 9, 2, 10, 3, 11});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vzip1_u16 (uint16x4_t __a, uint16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vzip1_u32 (uint32x2_t __a, uint32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {0, 2});

}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vzip1q_f32 (float32x4_t __a, float32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 1, 5});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vzip1q_f64 (float64x2_t __a, float64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vzip1q_p8 (poly8x16_t __a, poly8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vzip1q_p16 (poly16x8_t __a, poly16x8_t __b)
{




  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vzip1q_s8 (int8x16_t __a, int8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vzip1q_s16 (int16x8_t __a, int16x8_t __b)
{




  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vzip1q_s32 (int32x4_t __a, int32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 1, 5});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vzip1q_s64 (int64x2_t __a, int64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vzip1q_u8 (uint8x16_t __a, uint8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vzip1q_u16 (uint16x8_t __a, uint16x8_t __b)
{




  return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vzip1q_u32 (uint32x4_t __a, uint32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {0, 4, 1, 5});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vzip1q_u64 (uint64x2_t __a, uint64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {0, 2});

}

__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vzip2_f32 (float32x2_t __a, float32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vzip2_p8 (poly8x8_t __a, poly8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {4, 12, 5, 13, 6, 14, 7, 15});

}

__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vzip2_p16 (poly16x4_t __a, poly16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7});

}

__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vzip2_s8 (int8x8_t __a, int8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {4, 12, 5, 13, 6, 14, 7, 15});

}

__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vzip2_s16 (int16x4_t __a, int16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7});

}

__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vzip2_s32 (int32x2_t __a, int32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vzip2_u8 (uint8x8_t __a, uint8x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint8x8_t) {4, 12, 5, 13, 6, 14, 7, 15});

}

__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vzip2_u16 (uint16x4_t __a, uint16x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7});

}

__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vzip2_u32 (uint32x2_t __a, uint32x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x2_t) {1, 3});

}

__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vzip2q_f32 (float32x4_t __a, float32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {2, 6, 3, 7});

}

__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vzip2q_f64 (float64x2_t __a, float64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vzip2q_p8 (poly8x16_t __a, poly8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31});

}

__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vzip2q_p16 (poly16x8_t __a, poly16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {4, 12, 5, 13, 6, 14, 7, 15});

}

__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vzip2q_s8 (int8x16_t __a, int8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31});

}

__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vzip2q_s16 (int16x8_t __a, int16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {4, 12, 5, 13, 6, 14, 7, 15});

}

__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vzip2q_s32 (int32x4_t __a, int32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {2, 6, 3, 7});

}

__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vzip2q_s64 (int64x2_t __a, int64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vzip2q_u8 (uint8x16_t __a, uint8x16_t __b)
{




  return __builtin_shuffle (__a, __b, (uint8x16_t)
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31});

}

__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vzip2q_u16 (uint16x8_t __a, uint16x8_t __b)
{



  return __builtin_shuffle (__a, __b, (uint16x8_t)
      {4, 12, 5, 13, 6, 14, 7, 15});

}

__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vzip2q_u32 (uint32x4_t __a, uint32x4_t __b)
{



  return __builtin_shuffle (__a, __b, (uint32x4_t) {2, 6, 3, 7});

}

__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vzip2q_u64 (uint64x2_t __a, uint64x2_t __b)
{



  return __builtin_shuffle (__a, __b, (uint64x2_t) {1, 3});

}

__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vzip_f32 (float32x2_t a, float32x2_t b) { return (float32x2x2_t) {vzip1_f32 (a, b), vzip2_f32 (a, b)}; } __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) vzip_p8 (poly8x8_t a, poly8x8_t b) { return (poly8x8x2_t) {vzip1_p8 (a, b), vzip2_p8 (a, b)}; } __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) vzip_p16 (poly16x4_t a, poly16x4_t b) { return (poly16x4x2_t) {vzip1_p16 (a, b), vzip2_p16 (a, b)}; } __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) vzip_s8 (int8x8_t a, int8x8_t b) { return (int8x8x2_t) {vzip1_s8 (a, b), vzip2_s8 (a, b)}; } __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) vzip_s16 (int16x4_t a, int16x4_t b) { return (int16x4x2_t) {vzip1_s16 (a, b), vzip2_s16 (a, b)}; } __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) vzip_s32 (int32x2_t a, int32x2_t b) { return (int32x2x2_t) {vzip1_s32 (a, b), vzip2_s32 (a, b)}; } __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) vzip_u8 (uint8x8_t a, uint8x8_t b) { return (uint8x8x2_t) {vzip1_u8 (a, b), vzip2_u8 (a, b)}; } __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) vzip_u16 (uint16x4_t a, uint16x4_t b) { return (uint16x4x2_t) {vzip1_u16 (a, b), vzip2_u16 (a, b)}; } __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) vzip_u32 (uint32x2_t a, uint32x2_t b) { return (uint32x2x2_t) {vzip1_u32 (a, b), vzip2_u32 (a, b)}; } __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vzipq_f32 (float32x4_t a, float32x4_t b) { return (float32x4x2_t) {vzip1q_f32 (a, b), vzip2q_f32 (a, b)}; } __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) vzipq_p8 (poly8x16_t a, poly8x16_t b) { return (poly8x16x2_t) {vzip1q_p8 (a, b), vzip2q_p8 (a, b)}; } __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) vzipq_p16 (poly16x8_t a, poly16x8_t b) { return (poly16x8x2_t) {vzip1q_p16 (a, b), vzip2q_p16 (a, b)}; } __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) vzipq_s8 (int8x16_t a, int8x16_t b) { return (int8x16x2_t) {vzip1q_s8 (a, b), vzip2q_s8 (a, b)}; } __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) vzipq_s16 (int16x8_t a, int16x8_t b) { return (int16x8x2_t) {vzip1q_s16 (a, b), vzip2q_s16 (a, b)}; } __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) vzipq_s32 (int32x4_t a, int32x4_t b) { return (int32x4x2_t) {vzip1q_s32 (a, b), vzip2q_s32 (a, b)}; } __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) vzipq_u8 (uint8x16_t a, uint8x16_t b) { return (uint8x16x2_t) {vzip1q_u8 (a, b), vzip2q_u8 (a, b)}; } __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) vzipq_u16 (uint16x8_t a, uint16x8_t b) { return (uint16x8x2_t) {vzip1q_u16 (a, b), vzip2q_u16 (a, b)}; } __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) vzipq_u32 (uint32x4_t a, uint32x4_t b) { return (uint32x4x2_t) {vzip1q_u32 (a, b), vzip2q_u32 (a, b)}; }
# 25801 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/arm_neon.h" 3 4
#pragma GCC pop_options
# 12 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c" 2

# 1 "../../third_party/libvpx/source/config/linux/arm64/./vpx_config.h" 1
# 14 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c" 2
# 1 "../../third_party/libvpx/source/config/linux/arm64/./vpx_dsp_rtcd.h" 1
# 14 "../../third_party/libvpx/source/config/linux/arm64/./vpx_dsp_rtcd.h"
# 1 "../../third_party/libvpx/source/libvpx/vpx/vpx_integer.h" 1
# 15 "../../third_party/libvpx/source/libvpx/vpx/vpx_integer.h"
# 1 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stddef.h" 1 3 4
# 149 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stddef.h" 3 4
typedef long int ptrdiff_t;
# 216 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stddef.h" 3 4
typedef long unsigned int size_t;
# 328 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stddef.h" 3 4
typedef unsigned int wchar_t;
# 426 "/usr/lib/gcc-cross/aarch64-linux-gnu/5/include/stddef.h" 3 4
typedef struct {
  long long __max_align_ll __attribute__((__aligned__(__alignof__(long long))));
  long double __max_align_ld __attribute__((__aligned__(__alignof__(long double))));
} max_align_t;
# 16 "../../third_party/libvpx/source/libvpx/vpx/vpx_integer.h" 2
# 60 "../../third_party/libvpx/source/libvpx/vpx/vpx_integer.h"
# 1 "/usr/aarch64-linux-gnu/include/inttypes.h" 1 3
# 34 "/usr/aarch64-linux-gnu/include/inttypes.h" 3
typedef unsigned int __gwchar_t;
# 266 "/usr/aarch64-linux-gnu/include/inttypes.h" 3





typedef struct
  {
    long int quot;
    long int rem;
  } imaxdiv_t;
# 290 "/usr/aarch64-linux-gnu/include/inttypes.h" 3
extern intmax_t imaxabs (intmax_t __n) __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__const__));


extern imaxdiv_t imaxdiv (intmax_t __numer, intmax_t __denom)
      __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__const__));


extern intmax_t strtoimax (const char *__restrict __nptr,
      char **__restrict __endptr, int __base) __attribute__ ((__nothrow__ , __leaf__));


extern uintmax_t strtoumax (const char *__restrict __nptr,
       char ** __restrict __endptr, int __base) __attribute__ ((__nothrow__ , __leaf__));


extern intmax_t wcstoimax (const __gwchar_t *__restrict __nptr,
      __gwchar_t **__restrict __endptr, int __base)
     __attribute__ ((__nothrow__ , __leaf__));


extern uintmax_t wcstoumax (const __gwchar_t *__restrict __nptr,
       __gwchar_t ** __restrict __endptr, int __base)
     __attribute__ ((__nothrow__ , __leaf__));





extern long int __strtol_internal (const char *__restrict __nptr,
       char **__restrict __endptr,
       int __base, int __group)
  __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__nonnull__ (1))) __attribute__ ((__warn_unused_result__));

extern __inline __attribute__ ((__gnu_inline__)) intmax_t
__attribute__ ((__nothrow__ , __leaf__)) strtoimax (const char *__restrict nptr, char **__restrict endptr, int base)

{
  return __strtol_internal (nptr, endptr, base, 0);
}

extern unsigned long int __strtoul_internal (const char *__restrict __nptr,
          char ** __restrict __endptr,
          int __base, int __group)
  __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__nonnull__ (1))) __attribute__ ((__warn_unused_result__));

extern __inline __attribute__ ((__gnu_inline__)) uintmax_t
__attribute__ ((__nothrow__ , __leaf__)) strtoumax (const char *__restrict nptr, char **__restrict endptr, int base)

{
  return __strtoul_internal (nptr, endptr, base, 0);
}

extern long int __wcstol_internal (const __gwchar_t * __restrict __nptr,
       __gwchar_t **__restrict __endptr,
       int __base, int __group)
  __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__nonnull__ (1))) __attribute__ ((__warn_unused_result__));

extern __inline __attribute__ ((__gnu_inline__)) intmax_t
__attribute__ ((__nothrow__ , __leaf__)) wcstoimax (const __gwchar_t *__restrict nptr, __gwchar_t **__restrict endptr, int base)

{
  return __wcstol_internal (nptr, endptr, base, 0);
}

extern unsigned long int __wcstoul_internal (const __gwchar_t *
          __restrict __nptr,
          __gwchar_t **
          __restrict __endptr,
          int __base, int __group)
  __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__nonnull__ (1))) __attribute__ ((__warn_unused_result__));

extern __inline __attribute__ ((__gnu_inline__)) uintmax_t
__attribute__ ((__nothrow__ , __leaf__)) wcstoumax (const __gwchar_t *__restrict nptr, __gwchar_t **__restrict endptr, int base)

{
  return __wcstoul_internal (nptr, endptr, base, 0);
}
# 432 "/usr/aarch64-linux-gnu/include/inttypes.h" 3

# 61 "../../third_party/libvpx/source/libvpx/vpx/vpx_integer.h" 2
# 15 "../../third_party/libvpx/source/config/linux/arm64/./vpx_dsp_rtcd.h" 2
# 1 "../../third_party/libvpx/source/libvpx/vpx_dsp/vpx_dsp_common.h" 1
# 16 "../../third_party/libvpx/source/libvpx/vpx_dsp/vpx_dsp_common.h"
# 1 "../../third_party/libvpx/source/libvpx/vpx_ports/mem.h" 1
# 14 "../../third_party/libvpx/source/libvpx/vpx_ports/mem.h"
# 1 "../../third_party/libvpx/source/config/linux/arm64/vpx_config.h" 1
# 15 "../../third_party/libvpx/source/libvpx/vpx_ports/mem.h" 2
# 17 "../../third_party/libvpx/source/libvpx/vpx_dsp/vpx_dsp_common.h" 2
# 42 "../../third_party/libvpx/source/libvpx/vpx_dsp/vpx_dsp_common.h"

# 42 "../../third_party/libvpx/source/libvpx/vpx_dsp/vpx_dsp_common.h"
typedef int32_t tran_high_t;
typedef int16_t tran_low_t;


static inline uint8_t clip_pixel(int val) {
  return (val > 255) ? 255 : (val < 0) ? 0 : val;
}

static inline int clamp(int value, int low, int high) {
  return value < low ? low : (value > high ? high : value);
}

static inline double fclamp(double value, double low, double high) {
  return value < low ? low : (value > high ? high : value);
}
# 16 "../../third_party/libvpx/source/config/linux/arm64/./vpx_dsp_rtcd.h" 2






unsigned int vpx_avg_4x4_c(const uint8_t *, int p);
unsigned int vpx_avg_4x4_neon(const uint8_t *, int p);


unsigned int vpx_avg_8x8_c(const uint8_t *, int p);
unsigned int vpx_avg_8x8_neon(const uint8_t *, int p);


void vpx_comp_avg_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, int height, const uint8_t *ref, int ref_stride);


void vpx_convolve8_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve8_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve8_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve8_avg_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve8_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve8_avg_horiz_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve8_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve8_avg_vert_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve8_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve8_horiz_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve8_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve8_vert_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve_avg_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_convolve_copy_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);
void vpx_convolve_copy_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_d117_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d117_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d117_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d117_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d135_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d135_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d135_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d135_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d135_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d135_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d135_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d135_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d153_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d153_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d153_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d153_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d207e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d45_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d45_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d45_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_d45_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d45e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_d63f_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_128_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_128_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_128_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_128_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_128_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_128_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_128_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_128_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_left_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_left_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_left_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_left_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_left_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_left_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_left_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_left_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_top_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_top_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_top_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_top_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_top_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_top_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_dc_top_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_dc_top_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_fdct16x16_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct16x16_1_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct32x32_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct32x32_1_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct32x32_rd_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct4x4_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct4x4_1_c(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct8x8_c(const int16_t *input, tran_low_t *output, int stride);
void vpx_fdct8x8_neon(const int16_t *input, tran_low_t *output, int stride);


void vpx_fdct8x8_1_c(const int16_t *input, tran_low_t *output, int stride);
void vpx_fdct8x8_1_neon(const int16_t *input, tran_low_t *output, int stride);


void vpx_get16x16var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum);
void vpx_get16x16var_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum);


unsigned int vpx_get4x4sse_cs_c(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride);
unsigned int vpx_get4x4sse_cs_neon(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride);


void vpx_get8x8var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum);
void vpx_get8x8var_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum);


unsigned int vpx_get_mb_ss_c(const int16_t *);


void vpx_h_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_h_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_h_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_h_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_h_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_h_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_h_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_h_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_hadamard_16x16_c(const int16_t *src_diff, int src_stride, int16_t *coeff);
void vpx_hadamard_16x16_neon(const int16_t *src_diff, int src_stride, int16_t *coeff);


void vpx_hadamard_8x8_c(const int16_t *src_diff, int src_stride, int16_t *coeff);
void vpx_hadamard_8x8_neon(const int16_t *src_diff, int src_stride, int16_t *coeff);


void vpx_he_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_idct16x16_10_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct16x16_10_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct16x16_1_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct16x16_1_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct16x16_256_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct16x16_256_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct32x32_1024_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct32x32_1024_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct32x32_135_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct32x32_135_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct32x32_1_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct32x32_1_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct32x32_34_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct32x32_34_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct4x4_16_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct4x4_1_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct8x8_12_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct8x8_12_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct8x8_1_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct8x8_1_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_idct8x8_64_add_c(const tran_low_t *input, uint8_t *dest, int stride);
void vpx_idct8x8_64_add_neon(const tran_low_t *input, uint8_t *dest, int stride);


int16_t vpx_int_pro_col_c(const uint8_t *ref, const int width);
int16_t vpx_int_pro_col_neon(const uint8_t *ref, const int width);


void vpx_int_pro_row_c(int16_t *hbuf, const uint8_t *ref, const int ref_stride, const int height);
void vpx_int_pro_row_neon(int16_t *hbuf, const uint8_t *ref, const int ref_stride, const int height);


void vpx_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_iwht4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int stride);


void vpx_lpf_horizontal_16_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_horizontal_16_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_horizontal_16_dual_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_horizontal_16_dual_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_horizontal_4_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_horizontal_4_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_horizontal_4_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);
void vpx_lpf_horizontal_4_dual_neon(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);


void vpx_lpf_horizontal_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_horizontal_8_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_horizontal_8_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);
void vpx_lpf_horizontal_8_dual_neon(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);


void vpx_lpf_vertical_16_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_vertical_16_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_vertical_16_dual_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_vertical_16_dual_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_vertical_4_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_vertical_4_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_vertical_4_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);
void vpx_lpf_vertical_4_dual_neon(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);


void vpx_lpf_vertical_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
void vpx_lpf_vertical_8_neon(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);


void vpx_lpf_vertical_8_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);
void vpx_lpf_vertical_8_dual_neon(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1);


void vpx_mbpost_proc_across_ip_c(unsigned char *dst, int pitch, int rows, int cols,int flimit);


void vpx_mbpost_proc_down_c(unsigned char *dst, int pitch, int rows, int cols,int flimit);


void vpx_minmax_8x8_c(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max);
void vpx_minmax_8x8_neon(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max);


unsigned int vpx_mse16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse);
unsigned int vpx_mse16x16_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse);


unsigned int vpx_mse16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse);


unsigned int vpx_mse8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse);


unsigned int vpx_mse8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse);


void vpx_plane_add_noise_c(uint8_t *start, const int8_t *noise, int blackclamp, int whiteclamp, int width, int height, int pitch);


void vpx_post_proc_down_and_across_mb_row_c(unsigned char *src, unsigned char *dst, int src_pitch, int dst_pitch, int cols, unsigned char *flimits, int size);
void vpx_post_proc_down_and_across_mb_row_neon(unsigned char *src, unsigned char *dst, int src_pitch, int dst_pitch, int cols, unsigned char *flimits, int size);


void vpx_quantize_b_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan);


void vpx_quantize_b_32x32_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan);


unsigned int vpx_sad16x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad16x16_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad16x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad16x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad16x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);
void vpx_sad16x16x4d_neon(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad16x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad16x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad16x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad16x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad16x8_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad16x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad16x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad16x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad16x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad32x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad32x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad32x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad32x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad32x32_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad32x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad32x32x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad32x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);
void vpx_sad32x32x4d_neon(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad32x32x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad32x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad32x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad32x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad4x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad4x4_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad4x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad4x4x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad4x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad4x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad4x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad4x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad4x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad64x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad64x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad64x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad64x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad64x64_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad64x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad64x64x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad64x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);
void vpx_sad64x64x4d_neon(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad64x64x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad8x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad8x16_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad8x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad8x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad8x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad8x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad8x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad8x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad8x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad8x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


unsigned int vpx_sad8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);
unsigned int vpx_sad8x8_neon(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride);


unsigned int vpx_sad8x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred);


void vpx_sad8x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


void vpx_sad8x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array);


void vpx_sad8x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array);


int vpx_satd_c(const int16_t *coeff, int length);
int vpx_satd_neon(const int16_t *coeff, int length);


void vpx_scaled_2d_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_scaled_avg_2d_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_scaled_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_scaled_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_scaled_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


void vpx_scaled_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h);


uint32_t vpx_sub_pixel_avg_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_avg_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred);


uint32_t vpx_sub_pixel_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);
uint32_t vpx_sub_pixel_variance16x16_neon(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);
uint32_t vpx_sub_pixel_variance32x32_neon(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);
uint32_t vpx_sub_pixel_variance64x64_neon(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


uint32_t vpx_sub_pixel_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);
uint32_t vpx_sub_pixel_variance8x8_neon(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse);


void vpx_subtract_block_c(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride);
void vpx_subtract_block_neon(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride);


uint64_t vpx_sum_squares_2d_i16_c(const int16_t *src, int stride, int size);


void vpx_tm_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_tm_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_tm_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_tm_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_tm_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_tm_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_tm_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_tm_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_v_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_v_predictor_16x16_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_v_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_v_predictor_32x32_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_v_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_v_predictor_4x4_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


void vpx_v_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);
void vpx_v_predictor_8x8_neon(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


unsigned int vpx_variance16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance16x16_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance16x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance16x8_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance32x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance32x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance32x32_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance32x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance32x64_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance4x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance4x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance64x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance64x32_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance64x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance64x64_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance8x16_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance8x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


unsigned int vpx_variance8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);
unsigned int vpx_variance8x8_neon(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse);


void vpx_ve_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left);


int vpx_vector_var_c(const int16_t *ref, const int16_t *src, const int bwl);
int vpx_vector_var_neon(const int16_t *ref, const int16_t *src, const int bwl);


void vpx_dsp_rtcd(void);

# 1 "../../third_party/libvpx/source/config/linux/arm64/./vpx_config.h" 1
# 840 "../../third_party/libvpx/source/config/linux/arm64/./vpx_dsp_rtcd.h" 2
# 15 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c" 2
# 1 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 1
# 17 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
# 1 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h" 1
# 24 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
static inline int16x8x2_t vpx_vtrnq_s64(int32x4_t a0, int32x4_t a1) {
  int16x8x2_t b0;
  b0.val[0] = vcombine_s16(vreinterpret_s16_s32(vget_low_s32(a0)),
                           vreinterpret_s16_s32(vget_low_s32(a1)));
  b0.val[1] = vcombine_s16(vreinterpret_s16_s32(vget_high_s32(a0)),
                           vreinterpret_s16_s32(vget_high_s32(a1)));
  return b0;
}

static inline uint8x16x2_t vpx_vtrnq_u64(uint32x4_t a0, uint32x4_t a1) {
  uint8x16x2_t b0;
  b0.val[0] = vcombine_u8(vreinterpret_u8_u32(vget_low_u32(a0)),
                          vreinterpret_u8_u32(vget_low_u32(a1)));
  b0.val[1] = vcombine_u8(vreinterpret_u8_u32(vget_high_u32(a0)),
                          vreinterpret_u8_u32(vget_high_u32(a1)));
  return b0;
}

static inline uint16x8x2_t vpx_vtrnq_u64_to_u16(uint32x4_t a0, uint32x4_t a1) {
  uint16x8x2_t b0;
  b0.val[0] = vcombine_u16(vreinterpret_u16_u32(vget_low_u32(a0)),
                           vreinterpret_u16_u32(vget_low_u32(a1)));
  b0.val[1] = vcombine_u16(vreinterpret_u16_u32(vget_high_u32(a0)),
                           vreinterpret_u16_u32(vget_high_u32(a1)));
  return b0;
}

static inline void transpose_u8_4x4(uint8x8_t *a0, uint8x8_t *a1) {







  const uint16x4x2_t b0 =
      vtrn_u16(vreinterpret_u16_u8(*a0), vreinterpret_u16_u8(*a1));





  const uint32x2x2_t c0 = vtrn_u32(vreinterpret_u32_u16(b0.val[0]),
                                   vreinterpret_u32_u16(b0.val[1]));





  const uint8x8x2_t d0 =
      vtrn_u8(vreinterpret_u8_u32(c0.val[0]), vreinterpret_u8_u32(c0.val[1]));

  *a0 = d0.val[0];
  *a1 = d0.val[1];
}

static inline void transpose_s16_4x4d(int16x4_t *a0, int16x4_t *a1,
                                      int16x4_t *a2, int16x4_t *a3) {
# 93 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const int16x4x2_t b0 = vtrn_s16(*a0, *a1);
  const int16x4x2_t b1 = vtrn_s16(*a2, *a3);







  const int32x2x2_t c0 = vtrn_s32(vreinterpret_s32_s16(b0.val[0]),
                                  vreinterpret_s32_s16(b1.val[0]));
  const int32x2x2_t c1 = vtrn_s32(vreinterpret_s32_s16(b0.val[1]),
                                  vreinterpret_s32_s16(b1.val[1]));

  *a0 = vreinterpret_s16_s32(c0.val[0]);
  *a1 = vreinterpret_s16_s32(c1.val[0]);
  *a2 = vreinterpret_s16_s32(c0.val[1]);
  *a3 = vreinterpret_s16_s32(c1.val[1]);
}

static inline void transpose_u16_4x4q(uint16x8_t *a0, uint16x8_t *a1) {







  const uint32x4x2_t b0 =
      vtrnq_u32(vreinterpretq_u32_u16(*a0), vreinterpretq_u32_u16(*a1));





  const uint32x4_t c0 =
      vcombine_u32(vget_low_u32(b0.val[0]), vget_low_u32(b0.val[1]));
  const uint32x4_t c1 =
      vcombine_u32(vget_high_u32(b0.val[0]), vget_high_u32(b0.val[1]));





  const uint16x8x2_t d0 =
      vtrnq_u16(vreinterpretq_u16_u32(c0), vreinterpretq_u16_u32(c1));

  *a0 = d0.val[0];
  *a1 = d0.val[1];
}

static inline void transpose_s16_4x8(const int16x4_t a0, const int16x4_t a1,
                                     const int16x4_t a2, const int16x4_t a3,
                                     const int16x4_t a4, const int16x4_t a5,
                                     const int16x4_t a6, const int16x4_t a7,
                                     int16x8_t *o0, int16x8_t *o1,
                                     int16x8_t *o2, int16x8_t *o3) {
# 169 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const int16x4x2_t b0 = vtrn_s16(a0, a1);
  const int16x4x2_t b1 = vtrn_s16(a2, a3);
  const int16x4x2_t b2 = vtrn_s16(a4, a5);
  const int16x4x2_t b3 = vtrn_s16(a6, a7);
# 184 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const int32x2x2_t c0 = vtrn_s32(vreinterpret_s32_s16(b0.val[0]),
                                  vreinterpret_s32_s16(b1.val[0]));
  const int32x2x2_t c1 = vtrn_s32(vreinterpret_s32_s16(b0.val[1]),
                                  vreinterpret_s32_s16(b1.val[1]));
  const int32x2x2_t c2 = vtrn_s32(vreinterpret_s32_s16(b2.val[0]),
                                  vreinterpret_s32_s16(b3.val[0]));
  const int32x2x2_t c3 = vtrn_s32(vreinterpret_s32_s16(b2.val[1]),
                                  vreinterpret_s32_s16(b3.val[1]));







  *o0 = vcombine_s16(vreinterpret_s16_s32(c0.val[0]),
                     vreinterpret_s16_s32(c2.val[0]));
  *o1 = vcombine_s16(vreinterpret_s16_s32(c1.val[0]),
                     vreinterpret_s16_s32(c3.val[0]));
  *o2 = vcombine_s16(vreinterpret_s16_s32(c0.val[1]),
                     vreinterpret_s16_s32(c2.val[1]));
  *o3 = vcombine_s16(vreinterpret_s16_s32(c1.val[1]),
                     vreinterpret_s16_s32(c3.val[1]));
}

static inline void transpose_u8_8x4(uint8x8_t *a0, uint8x8_t *a1, uint8x8_t *a2,
                                    uint8x8_t *a3) {
# 222 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x8x2_t b0 = vtrn_u8(*a0, *a1);
  const uint8x8x2_t b1 = vtrn_u8(*a2, *a3);







  const uint16x4x2_t c0 =
      vtrn_u16(vreinterpret_u16_u8(b0.val[0]), vreinterpret_u16_u8(b1.val[0]));
  const uint16x4x2_t c1 =
      vtrn_u16(vreinterpret_u16_u8(b0.val[1]), vreinterpret_u16_u8(b1.val[1]));

  *a0 = vreinterpret_u8_u16(c0.val[0]);
  *a1 = vreinterpret_u8_u16(c1.val[0]);
  *a2 = vreinterpret_u8_u16(c0.val[1]);
  *a3 = vreinterpret_u8_u16(c1.val[1]);
}

static inline void transpose_u16_8x4(uint16x8_t *a0, uint16x8_t *a1,
                                     uint16x8_t *a2, uint16x8_t *a3) {
# 255 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint16x8x2_t b0 = vtrnq_u16(*a0, *a1);
  const uint16x8x2_t b1 = vtrnq_u16(*a2, *a3);







  const uint32x4x2_t c0 = vtrnq_u32(vreinterpretq_u32_u16(b0.val[0]),
                                    vreinterpretq_u32_u16(b1.val[0]));
  const uint32x4x2_t c1 = vtrnq_u32(vreinterpretq_u32_u16(b0.val[1]),
                                    vreinterpretq_u32_u16(b1.val[1]));

  *a0 = vreinterpretq_u16_u32(c0.val[0]);
  *a1 = vreinterpretq_u16_u32(c1.val[0]);
  *a2 = vreinterpretq_u16_u32(c0.val[1]);
  *a3 = vreinterpretq_u16_u32(c1.val[1]);
}



static inline void transpose_u8_8x8(uint8x8_t *a0, uint8x8_t *a1, uint8x8_t *a2,
                                    uint8x8_t *a3, uint8x8_t *a4, uint8x8_t *a5,
                                    uint8x8_t *a6, uint8x8_t *a7) {
# 295 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x16x2_t b0 =
      vtrnq_u8(vcombine_u8(*a0, *a4), vcombine_u8(*a1, *a5));
  const uint8x16x2_t b1 =
      vtrnq_u8(vcombine_u8(*a2, *a6), vcombine_u8(*a3, *a7));







  const uint16x8x2_t c0 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[0]),
                                    vreinterpretq_u16_u8(b1.val[0]));
  const uint16x8x2_t c1 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[1]),
                                    vreinterpretq_u16_u8(b1.val[1]));






  const uint32x4x2_t d0 = vuzpq_u32(vreinterpretq_u32_u16(c0.val[0]),
                                    vreinterpretq_u32_u16(c1.val[0]));
  const uint32x4x2_t d1 = vuzpq_u32(vreinterpretq_u32_u16(c0.val[1]),
                                    vreinterpretq_u32_u16(c1.val[1]));

  *a0 = vreinterpret_u8_u32(vget_low_u32(d0.val[0]));
  *a1 = vreinterpret_u8_u32(vget_high_u32(d0.val[0]));
  *a2 = vreinterpret_u8_u32(vget_low_u32(d1.val[0]));
  *a3 = vreinterpret_u8_u32(vget_high_u32(d1.val[0]));
  *a4 = vreinterpret_u8_u32(vget_low_u32(d0.val[1]));
  *a5 = vreinterpret_u8_u32(vget_high_u32(d0.val[1]));
  *a6 = vreinterpret_u8_u32(vget_low_u32(d1.val[1]));
  *a7 = vreinterpret_u8_u32(vget_high_u32(d1.val[1]));
}

static inline void transpose_s16_8x8(int16x8_t *a0, int16x8_t *a1,
                                     int16x8_t *a2, int16x8_t *a3,
                                     int16x8_t *a4, int16x8_t *a5,
                                     int16x8_t *a6, int16x8_t *a7) {
# 354 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const int16x8x2_t b0 = vtrnq_s16(*a0, *a1);
  const int16x8x2_t b1 = vtrnq_s16(*a2, *a3);
  const int16x8x2_t b2 = vtrnq_s16(*a4, *a5);
  const int16x8x2_t b3 = vtrnq_s16(*a6, *a7);
# 369 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const int32x4x2_t c0 = vtrnq_s32(vreinterpretq_s32_s16(b0.val[0]),
                                   vreinterpretq_s32_s16(b1.val[0]));
  const int32x4x2_t c1 = vtrnq_s32(vreinterpretq_s32_s16(b0.val[1]),
                                   vreinterpretq_s32_s16(b1.val[1]));
  const int32x4x2_t c2 = vtrnq_s32(vreinterpretq_s32_s16(b2.val[0]),
                                   vreinterpretq_s32_s16(b3.val[0]));
  const int32x4x2_t c3 = vtrnq_s32(vreinterpretq_s32_s16(b2.val[1]),
                                   vreinterpretq_s32_s16(b3.val[1]));
# 387 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const int16x8x2_t d0 = vpx_vtrnq_s64(c0.val[0], c2.val[0]);
  const int16x8x2_t d1 = vpx_vtrnq_s64(c1.val[0], c3.val[0]);
  const int16x8x2_t d2 = vpx_vtrnq_s64(c0.val[1], c2.val[1]);
  const int16x8x2_t d3 = vpx_vtrnq_s64(c1.val[1], c3.val[1]);

  *a0 = d0.val[0];
  *a1 = d1.val[0];
  *a2 = d2.val[0];
  *a3 = d3.val[0];
  *a4 = d0.val[1];
  *a5 = d1.val[1];
  *a6 = d2.val[1];
  *a7 = d3.val[1];
}

static inline void transpose_u16_8x8(uint16x8_t *a0, uint16x8_t *a1,
                                     uint16x8_t *a2, uint16x8_t *a3,
                                     uint16x8_t *a4, uint16x8_t *a5,
                                     uint16x8_t *a6, uint16x8_t *a7) {
# 425 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint16x8x2_t b0 = vtrnq_u16(*a0, *a1);
  const uint16x8x2_t b1 = vtrnq_u16(*a2, *a3);
  const uint16x8x2_t b2 = vtrnq_u16(*a4, *a5);
  const uint16x8x2_t b3 = vtrnq_u16(*a6, *a7);
# 440 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint32x4x2_t c0 = vtrnq_u32(vreinterpretq_u32_u16(b0.val[0]),
                                    vreinterpretq_u32_u16(b1.val[0]));
  const uint32x4x2_t c1 = vtrnq_u32(vreinterpretq_u32_u16(b0.val[1]),
                                    vreinterpretq_u32_u16(b1.val[1]));
  const uint32x4x2_t c2 = vtrnq_u32(vreinterpretq_u32_u16(b2.val[0]),
                                    vreinterpretq_u32_u16(b3.val[0]));
  const uint32x4x2_t c3 = vtrnq_u32(vreinterpretq_u32_u16(b2.val[1]),
                                    vreinterpretq_u32_u16(b3.val[1]));
# 458 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint16x8x2_t d0 = vpx_vtrnq_u64_to_u16(c0.val[0], c2.val[0]);
  const uint16x8x2_t d1 = vpx_vtrnq_u64_to_u16(c1.val[0], c3.val[0]);
  const uint16x8x2_t d2 = vpx_vtrnq_u64_to_u16(c0.val[1], c2.val[1]);
  const uint16x8x2_t d3 = vpx_vtrnq_u64_to_u16(c1.val[1], c3.val[1]);

  *a0 = d0.val[0];
  *a1 = d1.val[0];
  *a2 = d2.val[0];
  *a3 = d3.val[0];
  *a4 = d0.val[1];
  *a5 = d1.val[1];
  *a6 = d2.val[1];
  *a7 = d3.val[1];
}

static inline void transpose_u8_16x8(
    const uint8x16_t i0, const uint8x16_t i1, const uint8x16_t i2,
    const uint8x16_t i3, const uint8x16_t i4, const uint8x16_t i5,
    const uint8x16_t i6, const uint8x16_t i7, uint8x8_t *o0, uint8x8_t *o1,
    uint8x8_t *o2, uint8x8_t *o3, uint8x8_t *o4, uint8x8_t *o5, uint8x8_t *o6,
    uint8x8_t *o7, uint8x8_t *o8, uint8x8_t *o9, uint8x8_t *o10, uint8x8_t *o11,
    uint8x8_t *o12, uint8x8_t *o13, uint8x8_t *o14, uint8x8_t *o15) {
# 498 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x16x2_t b0 = vtrnq_u8(i0, i1);
  const uint8x16x2_t b1 = vtrnq_u8(i2, i3);
  const uint8x16x2_t b2 = vtrnq_u8(i4, i5);
  const uint8x16x2_t b3 = vtrnq_u8(i6, i7);
# 512 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint16x8x2_t c0 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[0]),
                                    vreinterpretq_u16_u8(b1.val[0]));
  const uint16x8x2_t c1 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[1]),
                                    vreinterpretq_u16_u8(b1.val[1]));
  const uint16x8x2_t c2 = vtrnq_u16(vreinterpretq_u16_u8(b2.val[0]),
                                    vreinterpretq_u16_u8(b3.val[0]));
  const uint16x8x2_t c3 = vtrnq_u16(vreinterpretq_u16_u8(b2.val[1]),
                                    vreinterpretq_u16_u8(b3.val[1]));
# 530 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint32x4x2_t d0 = vtrnq_u32(vreinterpretq_u32_u16(c0.val[0]),
                                    vreinterpretq_u32_u16(c2.val[0]));
  const uint32x4x2_t d1 = vtrnq_u32(vreinterpretq_u32_u16(c0.val[1]),
                                    vreinterpretq_u32_u16(c2.val[1]));
  const uint32x4x2_t d2 = vtrnq_u32(vreinterpretq_u32_u16(c1.val[0]),
                                    vreinterpretq_u32_u16(c3.val[0]));
  const uint32x4x2_t d3 = vtrnq_u32(vreinterpretq_u32_u16(c1.val[1]),
                                    vreinterpretq_u32_u16(c3.val[1]));
# 556 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  *o0 = vget_low_u8(vreinterpretq_u8_u32(d0.val[0]));
  *o1 = vget_low_u8(vreinterpretq_u8_u32(d2.val[0]));
  *o2 = vget_low_u8(vreinterpretq_u8_u32(d1.val[0]));
  *o3 = vget_low_u8(vreinterpretq_u8_u32(d3.val[0]));
  *o4 = vget_low_u8(vreinterpretq_u8_u32(d0.val[1]));
  *o5 = vget_low_u8(vreinterpretq_u8_u32(d2.val[1]));
  *o6 = vget_low_u8(vreinterpretq_u8_u32(d1.val[1]));
  *o7 = vget_low_u8(vreinterpretq_u8_u32(d3.val[1]));
  *o8 = vget_high_u8(vreinterpretq_u8_u32(d0.val[0]));
  *o9 = vget_high_u8(vreinterpretq_u8_u32(d2.val[0]));
  *o10 = vget_high_u8(vreinterpretq_u8_u32(d1.val[0]));
  *o11 = vget_high_u8(vreinterpretq_u8_u32(d3.val[0]));
  *o12 = vget_high_u8(vreinterpretq_u8_u32(d0.val[1]));
  *o13 = vget_high_u8(vreinterpretq_u8_u32(d2.val[1]));
  *o14 = vget_high_u8(vreinterpretq_u8_u32(d1.val[1]));
  *o15 = vget_high_u8(vreinterpretq_u8_u32(d3.val[1]));
}

static inline void transpose_u8_8x16(
    const uint8x8_t i0, const uint8x8_t i1, const uint8x8_t i2,
    const uint8x8_t i3, const uint8x8_t i4, const uint8x8_t i5,
    const uint8x8_t i6, const uint8x8_t i7, const uint8x8_t i8,
    const uint8x8_t i9, const uint8x8_t i10, const uint8x8_t i11,
    const uint8x8_t i12, const uint8x8_t i13, const uint8x8_t i14,
    const uint8x8_t i15, uint8x16_t *o0, uint8x16_t *o1, uint8x16_t *o2,
    uint8x16_t *o3, uint8x16_t *o4, uint8x16_t *o5, uint8x16_t *o6,
    uint8x16_t *o7) {
# 609 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x16_t a0 = vcombine_u8(i0, i8);
  const uint8x16_t a1 = vcombine_u8(i1, i9);
  const uint8x16_t a2 = vcombine_u8(i2, i10);
  const uint8x16_t a3 = vcombine_u8(i3, i11);
  const uint8x16_t a4 = vcombine_u8(i4, i12);
  const uint8x16_t a5 = vcombine_u8(i5, i13);
  const uint8x16_t a6 = vcombine_u8(i6, i14);
  const uint8x16_t a7 = vcombine_u8(i7, i15);
# 627 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x16x2_t b0 = vtrnq_u8(a0, a1);
  const uint8x16x2_t b1 = vtrnq_u8(a2, a3);
  const uint8x16x2_t b2 = vtrnq_u8(a4, a5);
  const uint8x16x2_t b3 = vtrnq_u8(a6, a7);
# 641 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint16x8x2_t c0 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[0]),
                                    vreinterpretq_u16_u8(b1.val[0]));
  const uint16x8x2_t c1 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[1]),
                                    vreinterpretq_u16_u8(b1.val[1]));
  const uint16x8x2_t c2 = vtrnq_u16(vreinterpretq_u16_u8(b2.val[0]),
                                    vreinterpretq_u16_u8(b3.val[0]));
  const uint16x8x2_t c3 = vtrnq_u16(vreinterpretq_u16_u8(b2.val[1]),
                                    vreinterpretq_u16_u8(b3.val[1]));
# 659 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint32x4x2_t d0 = vtrnq_u32(vreinterpretq_u32_u16(c0.val[0]),
                                    vreinterpretq_u32_u16(c2.val[0]));
  const uint32x4x2_t d1 = vtrnq_u32(vreinterpretq_u32_u16(c0.val[1]),
                                    vreinterpretq_u32_u16(c2.val[1]));
  const uint32x4x2_t d2 = vtrnq_u32(vreinterpretq_u32_u16(c1.val[0]),
                                    vreinterpretq_u32_u16(c3.val[0]));
  const uint32x4x2_t d3 = vtrnq_u32(vreinterpretq_u32_u16(c1.val[1]),
                                    vreinterpretq_u32_u16(c3.val[1]));
# 677 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  *o0 = vreinterpretq_u8_u32(d0.val[0]);
  *o1 = vreinterpretq_u8_u32(d2.val[0]);
  *o2 = vreinterpretq_u8_u32(d1.val[0]);
  *o3 = vreinterpretq_u8_u32(d3.val[0]);
  *o4 = vreinterpretq_u8_u32(d0.val[1]);
  *o5 = vreinterpretq_u8_u32(d2.val[1]);
  *o6 = vreinterpretq_u8_u32(d1.val[1]);
  *o7 = vreinterpretq_u8_u32(d3.val[1]);
}

static inline void transpose_u8_16x16(
    const uint8x16_t i0, const uint8x16_t i1, const uint8x16_t i2,
    const uint8x16_t i3, const uint8x16_t i4, const uint8x16_t i5,
    const uint8x16_t i6, const uint8x16_t i7, const uint8x16_t i8,
    const uint8x16_t i9, const uint8x16_t i10, const uint8x16_t i11,
    const uint8x16_t i12, const uint8x16_t i13, const uint8x16_t i14,
    const uint8x16_t i15, uint8x16_t *o0, uint8x16_t *o1, uint8x16_t *o2,
    uint8x16_t *o3, uint8x16_t *o4, uint8x16_t *o5, uint8x16_t *o6,
    uint8x16_t *o7, uint8x16_t *o8, uint8x16_t *o9, uint8x16_t *o10,
    uint8x16_t *o11, uint8x16_t *o12, uint8x16_t *o13, uint8x16_t *o14,
    uint8x16_t *o15) {
# 732 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x16x2_t b0 = vtrnq_u8(i0, i1);
  const uint8x16x2_t b1 = vtrnq_u8(i2, i3);
  const uint8x16x2_t b2 = vtrnq_u8(i4, i5);
  const uint8x16x2_t b3 = vtrnq_u8(i6, i7);
  const uint8x16x2_t b4 = vtrnq_u8(i8, i9);
  const uint8x16x2_t b5 = vtrnq_u8(i10, i11);
  const uint8x16x2_t b6 = vtrnq_u8(i12, i13);
  const uint8x16x2_t b7 = vtrnq_u8(i14, i15);
# 758 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint16x8x2_t c0 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[0]),
                                    vreinterpretq_u16_u8(b1.val[0]));
  const uint16x8x2_t c1 = vtrnq_u16(vreinterpretq_u16_u8(b0.val[1]),
                                    vreinterpretq_u16_u8(b1.val[1]));
  const uint16x8x2_t c2 = vtrnq_u16(vreinterpretq_u16_u8(b2.val[0]),
                                    vreinterpretq_u16_u8(b3.val[0]));
  const uint16x8x2_t c3 = vtrnq_u16(vreinterpretq_u16_u8(b2.val[1]),
                                    vreinterpretq_u16_u8(b3.val[1]));
  const uint16x8x2_t c4 = vtrnq_u16(vreinterpretq_u16_u8(b4.val[0]),
                                    vreinterpretq_u16_u8(b5.val[0]));
  const uint16x8x2_t c5 = vtrnq_u16(vreinterpretq_u16_u8(b4.val[1]),
                                    vreinterpretq_u16_u8(b5.val[1]));
  const uint16x8x2_t c6 = vtrnq_u16(vreinterpretq_u16_u8(b6.val[0]),
                                    vreinterpretq_u16_u8(b7.val[0]));
  const uint16x8x2_t c7 = vtrnq_u16(vreinterpretq_u16_u8(b6.val[1]),
                                    vreinterpretq_u16_u8(b7.val[1]));
# 792 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint32x4x2_t d0 = vtrnq_u32(vreinterpretq_u32_u16(c0.val[0]),
                                    vreinterpretq_u32_u16(c2.val[0]));
  const uint32x4x2_t d1 = vtrnq_u32(vreinterpretq_u32_u16(c0.val[1]),
                                    vreinterpretq_u32_u16(c2.val[1]));
  const uint32x4x2_t d2 = vtrnq_u32(vreinterpretq_u32_u16(c1.val[0]),
                                    vreinterpretq_u32_u16(c3.val[0]));
  const uint32x4x2_t d3 = vtrnq_u32(vreinterpretq_u32_u16(c1.val[1]),
                                    vreinterpretq_u32_u16(c3.val[1]));
  const uint32x4x2_t d4 = vtrnq_u32(vreinterpretq_u32_u16(c4.val[0]),
                                    vreinterpretq_u32_u16(c6.val[0]));
  const uint32x4x2_t d5 = vtrnq_u32(vreinterpretq_u32_u16(c4.val[1]),
                                    vreinterpretq_u32_u16(c6.val[1]));
  const uint32x4x2_t d6 = vtrnq_u32(vreinterpretq_u32_u16(c5.val[0]),
                                    vreinterpretq_u32_u16(c7.val[0]));
  const uint32x4x2_t d7 = vtrnq_u32(vreinterpretq_u32_u16(c5.val[1]),
                                    vreinterpretq_u32_u16(c7.val[1]));
# 826 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  const uint8x16x2_t e0 = vpx_vtrnq_u64(d0.val[0], d4.val[0]);
  const uint8x16x2_t e1 = vpx_vtrnq_u64(d2.val[0], d6.val[0]);
  const uint8x16x2_t e2 = vpx_vtrnq_u64(d1.val[0], d5.val[0]);
  const uint8x16x2_t e3 = vpx_vtrnq_u64(d3.val[0], d7.val[0]);
  const uint8x16x2_t e4 = vpx_vtrnq_u64(d0.val[1], d4.val[1]);
  const uint8x16x2_t e5 = vpx_vtrnq_u64(d2.val[1], d6.val[1]);
  const uint8x16x2_t e6 = vpx_vtrnq_u64(d1.val[1], d5.val[1]);
  const uint8x16x2_t e7 = vpx_vtrnq_u64(d3.val[1], d7.val[1]);
# 852 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/transpose_neon.h"
  *o0 = e0.val[0];
  *o1 = e1.val[0];
  *o2 = e2.val[0];
  *o3 = e3.val[0];
  *o4 = e4.val[0];
  *o5 = e5.val[0];
  *o6 = e6.val[0];
  *o7 = e7.val[0];
  *o8 = e0.val[1];
  *o9 = e1.val[1];
  *o10 = e2.val[1];
  *o11 = e3.val[1];
  *o12 = e4.val[1];
  *o13 = e5.val[1];
  *o14 = e6.val[1];
  *o15 = e7.val[1];
}
# 18 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 2





static inline int16x8_t load_tran_low_to_s16(const tran_low_t *buf) {







  return vld1q_s16(buf);

}


static inline int16x8_t multiply_shift_and_narrow_s16(const int16x8_t a,
                                                      const int16_t a_const) {
# 46 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
  return vqrdmulhq_n_s16(a, a_const * 2);
}


static inline int16x8_t add_multiply_shift_and_narrow_s16(
    const int16x8_t a, const int16x8_t b, const int16_t ab_const) {







  int32x4_t temp_low = vaddl_s16(vget_low_s16(a), vget_low_s16(b));
  int32x4_t temp_high = vaddl_s16(vget_high_s16(a), vget_high_s16(b));
  temp_low = vmulq_n_s32(temp_low, ab_const);
  temp_high = vmulq_n_s32(temp_high, ab_const);
  return vcombine_s16(
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     __extension__ ({ int32x4_t a_ = (
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                     temp_low
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     ); int16x4_t result; __asm__ ("rshrn %0.4h,%1.4s,%2" : "=w"(result) : "w"(a_), "i"(
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                     14
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     ) : ); result; })
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                               , 
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 __extension__ ({ int32x4_t a_ = (
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                 temp_high
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 ); int16x4_t result; __asm__ ("rshrn %0.4h,%1.4s,%2" : "=w"(result) : "w"(a_), "i"(
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                 14
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 ) : ); result; })
# 63 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                                            );
}


static inline int16x8_t sub_multiply_shift_and_narrow_s16(
    const int16x8_t a, const int16x8_t b, const int16_t ab_const) {
  int32x4_t temp_low = vsubl_s16(vget_low_s16(a), vget_low_s16(b));
  int32x4_t temp_high = vsubl_s16(vget_high_s16(a), vget_high_s16(b));
  temp_low = vmulq_n_s32(temp_low, ab_const);
  temp_high = vmulq_n_s32(temp_high, ab_const);
  return vcombine_s16(
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     __extension__ ({ int32x4_t a_ = (
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                     temp_low
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     ); int16x4_t result; __asm__ ("rshrn %0.4h,%1.4s,%2" : "=w"(result) : "w"(a_), "i"(
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                     14
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     ) : ); result; })
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                               , 
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 __extension__ ({ int32x4_t a_ = (
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                 temp_high
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 ); int16x4_t result; __asm__ ("rshrn %0.4h,%1.4s,%2" : "=w"(result) : "w"(a_), "i"(
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                 14
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 ) : ); result; })
# 73 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                                            );
}



static inline int16x8_t multiply_accumulate_shift_and_narrow_s16(
    const int16x8_t a, const int16_t a_const, const int16x8_t b,
    const int16_t b_const) {
  int32x4_t temp_low = vmull_n_s16(vget_low_s16(a), a_const);
  int32x4_t temp_high = vmull_n_s16(vget_high_s16(a), a_const);
  temp_low = vmlal_n_s16(temp_low, vget_low_s16(b), b_const);
  temp_high = vmlal_n_s16(temp_high, vget_high_s16(b), b_const);
  return vcombine_s16(
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     __extension__ ({ int32x4_t a_ = (
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                     temp_low
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     ); int16x4_t result; __asm__ ("rshrn %0.4h,%1.4s,%2" : "=w"(result) : "w"(a_), "i"(
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                     14
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                     ) : ); result; })
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                               , 
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 __extension__ ({ int32x4_t a_ = (
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                 temp_high
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 ); int16x4_t result; __asm__ ("rshrn %0.4h,%1.4s,%2" : "=w"(result) : "w"(a_), "i"(
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                 14
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h" 3 4
                                                 ) : ); result; })
# 85 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct_neon.h"
                                                                            );
}

static inline void load_and_transpose_s16_8x8(const int16_t *a, int a_stride,
                                              int16x8_t *a0, int16x8_t *a1,
                                              int16x8_t *a2, int16x8_t *a3,
                                              int16x8_t *a4, int16x8_t *a5,
                                              int16x8_t *a6, int16x8_t *a7) {
  *a0 = vld1q_s16(a);
  a += a_stride;
  *a1 = vld1q_s16(a);
  a += a_stride;
  *a2 = vld1q_s16(a);
  a += a_stride;
  *a3 = vld1q_s16(a);
  a += a_stride;
  *a4 = vld1q_s16(a);
  a += a_stride;
  *a5 = vld1q_s16(a);
  a += a_stride;
  *a6 = vld1q_s16(a);
  a += a_stride;
  *a7 = vld1q_s16(a);

  transpose_s16_8x8(a0, a1, a2, a3, a4, a5, a6, a7);
}


static inline void add_and_store_u8_s16(const int16x8_t a0, const int16x8_t a1,
                                        const int16x8_t a2, const int16x8_t a3,
                                        const int16x8_t a4, const int16x8_t a5,
                                        const int16x8_t a6, const int16x8_t a7,
                                        uint8_t *b, const int b_stride) {
  uint8x8_t b0, b1, b2, b3, b4, b5, b6, b7;
  int16x8_t c0, c1, c2, c3, c4, c5, c6, c7;
  b0 = vld1_u8(b);
  b += b_stride;
  b1 = vld1_u8(b);
  b += b_stride;
  b2 = vld1_u8(b);
  b += b_stride;
  b3 = vld1_u8(b);
  b += b_stride;
  b4 = vld1_u8(b);
  b += b_stride;
  b5 = vld1_u8(b);
  b += b_stride;
  b6 = vld1_u8(b);
  b += b_stride;
  b7 = vld1_u8(b);
  b -= (7 * b_stride);


  c0 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b0)), a0, 6);
  c1 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b1)), a1, 6);
  c2 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b2)), a2, 6);
  c3 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b3)), a3, 6);
  c4 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b4)), a4, 6);
  c5 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b5)), a5, 6);
  c6 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b6)), a6, 6);
  c7 = vrsraq_n_s16(vreinterpretq_s16_u16(vmovl_u8(b7)), a7, 6);

  b0 = vqmovun_s16(c0);
  b1 = vqmovun_s16(c1);
  b2 = vqmovun_s16(c2);
  b3 = vqmovun_s16(c3);
  b4 = vqmovun_s16(c4);
  b5 = vqmovun_s16(c5);
  b6 = vqmovun_s16(c6);
  b7 = vqmovun_s16(c7);

  vst1_u8(b, b0);
  b += b_stride;
  vst1_u8(b, b1);
  b += b_stride;
  vst1_u8(b, b2);
  b += b_stride;
  vst1_u8(b, b3);
  b += b_stride;
  vst1_u8(b, b4);
  b += b_stride;
  vst1_u8(b, b5);
  b += b_stride;
  vst1_u8(b, b6);
  b += b_stride;
  vst1_u8(b, b7);
}
# 16 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c" 2
# 1 "../../third_party/libvpx/source/libvpx/vpx_dsp/txfm_common.h" 1
# 28 "../../third_party/libvpx/source/libvpx/vpx_dsp/txfm_common.h"
static const tran_high_t cospi_1_64 = 16364;
static const tran_high_t cospi_2_64 = 16305;
static const tran_high_t cospi_3_64 = 16207;
static const tran_high_t cospi_4_64 = 16069;
static const tran_high_t cospi_5_64 = 15893;
static const tran_high_t cospi_6_64 = 15679;
static const tran_high_t cospi_7_64 = 15426;
static const tran_high_t cospi_8_64 = 15137;
static const tran_high_t cospi_9_64 = 14811;
static const tran_high_t cospi_10_64 = 14449;
static const tran_high_t cospi_11_64 = 14053;
static const tran_high_t cospi_12_64 = 13623;
static const tran_high_t cospi_13_64 = 13160;
static const tran_high_t cospi_14_64 = 12665;
static const tran_high_t cospi_15_64 = 12140;
static const tran_high_t cospi_16_64 = 11585;
static const tran_high_t cospi_17_64 = 11003;
static const tran_high_t cospi_18_64 = 10394;
static const tran_high_t cospi_19_64 = 9760;
static const tran_high_t cospi_20_64 = 9102;
static const tran_high_t cospi_21_64 = 8423;
static const tran_high_t cospi_22_64 = 7723;
static const tran_high_t cospi_23_64 = 7005;
static const tran_high_t cospi_24_64 = 6270;
static const tran_high_t cospi_25_64 = 5520;
static const tran_high_t cospi_26_64 = 4756;
static const tran_high_t cospi_27_64 = 3981;
static const tran_high_t cospi_28_64 = 3196;
static const tran_high_t cospi_29_64 = 2404;
static const tran_high_t cospi_30_64 = 1606;
static const tran_high_t cospi_31_64 = 804;


static const tran_high_t sinpi_1_9 = 5283;
static const tran_high_t sinpi_2_9 = 9929;
static const tran_high_t sinpi_3_9 = 13377;
static const tran_high_t sinpi_4_9 = 15212;
# 17 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c" 2
# 37 "../../third_party/libvpx/source/libvpx/vpx_dsp/arm/idct32x32_34_add_neon.c"
static void idct32_6_neon(const int16_t *input, int16_t *output) {
  int16x8_t in0, in1, in2, in3, in4, in5, in6, in7;
  int16x8_t s1_0, s1_1, s1_2, s1_3, s1_4, s1_5, s1_6, s1_7, s1_8, s1_9, s1_10,
      s1_11, s1_12, s1_13, s1_14, s1_15, s1_16, s1_17, s1_18, s1_19, s1_20,
      s1_21, s1_22, s1_23, s1_24, s1_25, s1_26, s1_27, s1_28, s1_29, s1_30,
      s1_31;
  int16x8_t s2_0, s2_1, s2_2, s2_3, s2_4, s2_5, s2_6, s2_7, s2_8, s2_9, s2_10,
      s2_11, s2_12, s2_13, s2_14, s2_15, s2_16, s2_17, s2_18, s2_19, s2_20,
      s2_21, s2_22, s2_23, s2_24, s2_25, s2_26, s2_27, s2_28, s2_29, s2_30,
      s2_31;
  int16x8_t s3_24, s3_25, s3_26, s3_27;

  load_and_transpose_s16_8x8(input, 32, &in0, &in1, &in2, &in3, &in4, &in5,
                             &in6, &in7);



  s1_16 = multiply_shift_and_narrow_s16(in1, cospi_31_64);

  s1_31 = multiply_shift_and_narrow_s16(in1, cospi_1_64);

  s1_20 = multiply_shift_and_narrow_s16(in5, cospi_27_64);
  s1_27 = multiply_shift_and_narrow_s16(in5, cospi_5_64);

  s1_23 = multiply_shift_and_narrow_s16(in3, -cospi_29_64);
  s1_24 = multiply_shift_and_narrow_s16(in3, cospi_3_64);


  s2_8 = multiply_shift_and_narrow_s16(in2, cospi_30_64);
  s2_15 = multiply_shift_and_narrow_s16(in2, cospi_2_64);


  s1_4 = multiply_shift_and_narrow_s16(in4, cospi_28_64);
  s1_7 = multiply_shift_and_narrow_s16(in4, cospi_4_64);

  s1_17 = multiply_accumulate_shift_and_narrow_s16(s1_16, -cospi_4_64, s1_31,
                                                   cospi_28_64);
  s1_30 = multiply_accumulate_shift_and_narrow_s16(s1_16, cospi_28_64, s1_31,
                                                   cospi_4_64);

  s1_21 = multiply_accumulate_shift_and_narrow_s16(s1_20, -cospi_20_64, s1_27,
                                                   cospi_12_64);
  s1_26 = multiply_accumulate_shift_and_narrow_s16(s1_20, cospi_12_64, s1_27,
                                                   cospi_20_64);

  s1_22 = multiply_accumulate_shift_and_narrow_s16(s1_23, -cospi_12_64, s1_24,
                                                   -cospi_20_64);
  s1_25 = multiply_accumulate_shift_and_narrow_s16(s1_23, -cospi_20_64, s1_24,
                                                   cospi_12_64);


  s1_0 = multiply_shift_and_narrow_s16(in0, cospi_16_64);

  s2_9 = multiply_accumulate_shift_and_narrow_s16(s2_8, -cospi_8_64, s2_15,
                                                  cospi_24_64);
  s2_14 = multiply_accumulate_shift_and_narrow_s16(s2_8, cospi_24_64, s2_15,
                                                   cospi_8_64);

  s2_20 = vsubq_s16(s1_23, s1_20);
  s2_21 = vsubq_s16(s1_22, s1_21);
  s2_22 = vaddq_s16(s1_21, s1_22);
  s2_23 = vaddq_s16(s1_20, s1_23);
  s2_24 = vaddq_s16(s1_24, s1_27);
  s2_25 = vaddq_s16(s1_25, s1_26);
  s2_26 = vsubq_s16(s1_25, s1_26);
  s2_27 = vsubq_s16(s1_24, s1_27);


  s1_5 = sub_multiply_shift_and_narrow_s16(s1_7, s1_4, cospi_16_64);
  s1_6 = add_multiply_shift_and_narrow_s16(s1_4, s1_7, cospi_16_64);

  s1_18 = multiply_accumulate_shift_and_narrow_s16(s1_17, -cospi_8_64, s1_30,
                                                   cospi_24_64);
  s1_29 = multiply_accumulate_shift_and_narrow_s16(s1_17, cospi_24_64, s1_30,
                                                   cospi_8_64);

  s1_19 = multiply_accumulate_shift_and_narrow_s16(s1_16, -cospi_8_64, s1_31,
                                                   cospi_24_64);
  s1_28 = multiply_accumulate_shift_and_narrow_s16(s1_16, cospi_24_64, s1_31,
                                                   cospi_8_64);

  s1_20 = multiply_accumulate_shift_and_narrow_s16(s2_20, -cospi_24_64, s2_27,
                                                   -cospi_8_64);
  s1_27 = multiply_accumulate_shift_and_narrow_s16(s2_20, -cospi_8_64, s2_27,
                                                   cospi_24_64);

  s1_21 = multiply_accumulate_shift_and_narrow_s16(s2_21, -cospi_24_64, s2_26,
                                                   -cospi_8_64);
  s1_26 = multiply_accumulate_shift_and_narrow_s16(s2_21, -cospi_8_64, s2_26,
                                                   cospi_24_64);


  s2_0 = vaddq_s16(s1_0, s1_7);
  s2_1 = vaddq_s16(s1_0, s1_6);
  s2_2 = vaddq_s16(s1_0, s1_5);
  s2_3 = vaddq_s16(s1_0, s1_4);
  s2_4 = vsubq_s16(s1_0, s1_4);
  s2_5 = vsubq_s16(s1_0, s1_5);
  s2_6 = vsubq_s16(s1_0, s1_6);
  s2_7 = vsubq_s16(s1_0, s1_7);

  s2_10 = sub_multiply_shift_and_narrow_s16(s2_14, s2_9, cospi_16_64);
  s2_13 = add_multiply_shift_and_narrow_s16(s2_9, s2_14, cospi_16_64);

  s2_11 = sub_multiply_shift_and_narrow_s16(s2_15, s2_8, cospi_16_64);
  s2_12 = add_multiply_shift_and_narrow_s16(s2_8, s2_15, cospi_16_64);

  s2_16 = vaddq_s16(s1_16, s2_23);
  s2_17 = vaddq_s16(s1_17, s2_22);
  s2_18 = vaddq_s16(s1_18, s1_21);
  s2_19 = vaddq_s16(s1_19, s1_20);
  s2_20 = vsubq_s16(s1_19, s1_20);
  s2_21 = vsubq_s16(s1_18, s1_21);
  s2_22 = vsubq_s16(s1_17, s2_22);
  s2_23 = vsubq_s16(s1_16, s2_23);

  s3_24 = vsubq_s16(s1_31, s2_24);
  s3_25 = vsubq_s16(s1_30, s2_25);
  s3_26 = vsubq_s16(s1_29, s1_26);
  s3_27 = vsubq_s16(s1_28, s1_27);
  s2_28 = vaddq_s16(s1_27, s1_28);
  s2_29 = vaddq_s16(s1_26, s1_29);
  s2_30 = vaddq_s16(s2_25, s1_30);
  s2_31 = vaddq_s16(s2_24, s1_31);


  s1_0 = vaddq_s16(s2_0, s2_15);
  s1_1 = vaddq_s16(s2_1, s2_14);
  s1_2 = vaddq_s16(s2_2, s2_13);
  s1_3 = vaddq_s16(s2_3, s2_12);
  s1_4 = vaddq_s16(s2_4, s2_11);
  s1_5 = vaddq_s16(s2_5, s2_10);
  s1_6 = vaddq_s16(s2_6, s2_9);
  s1_7 = vaddq_s16(s2_7, s2_8);
  s1_8 = vsubq_s16(s2_7, s2_8);
  s1_9 = vsubq_s16(s2_6, s2_9);
  s1_10 = vsubq_s16(s2_5, s2_10);
  s1_11 = vsubq_s16(s2_4, s2_11);
  s1_12 = vsubq_s16(s2_3, s2_12);
  s1_13 = vsubq_s16(s2_2, s2_13);
  s1_14 = vsubq_s16(s2_1, s2_14);
  s1_15 = vsubq_s16(s2_0, s2_15);

  s1_20 = sub_multiply_shift_and_narrow_s16(s3_27, s2_20, cospi_16_64);
  s1_27 = add_multiply_shift_and_narrow_s16(s2_20, s3_27, cospi_16_64);

  s1_21 = sub_multiply_shift_and_narrow_s16(s3_26, s2_21, cospi_16_64);
  s1_26 = add_multiply_shift_and_narrow_s16(s2_21, s3_26, cospi_16_64);

  s1_22 = sub_multiply_shift_and_narrow_s16(s3_25, s2_22, cospi_16_64);
  s1_25 = add_multiply_shift_and_narrow_s16(s2_22, s3_25, cospi_16_64);

  s1_23 = sub_multiply_shift_and_narrow_s16(s3_24, s2_23, cospi_16_64);
  s1_24 = add_multiply_shift_and_narrow_s16(s2_23, s3_24, cospi_16_64);


  vst1q_s16(output, vaddq_s16(s1_0, s2_31));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_1, s2_30));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_2, s2_29));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_3, s2_28));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_4, s1_27));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_5, s1_26));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_6, s1_25));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_7, s1_24));
  output += 8;

  vst1q_s16(output, vaddq_s16(s1_8, s1_23));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_9, s1_22));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_10, s1_21));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_11, s1_20));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_12, s2_19));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_13, s2_18));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_14, s2_17));
  output += 8;
  vst1q_s16(output, vaddq_s16(s1_15, s2_16));
  output += 8;

  vst1q_s16(output, vsubq_s16(s1_15, s2_16));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_14, s2_17));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_13, s2_18));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_12, s2_19));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_11, s1_20));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_10, s1_21));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_9, s1_22));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_8, s1_23));
  output += 8;

  vst1q_s16(output, vsubq_s16(s1_7, s1_24));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_6, s1_25));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_5, s1_26));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_4, s1_27));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_3, s2_28));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_2, s2_29));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_1, s2_30));
  output += 8;
  vst1q_s16(output, vsubq_s16(s1_0, s2_31));
}

static void idct32_8_neon(const int16_t *input, uint8_t *output, int stride) {
  int16x8_t in0, in1, in2, in3, in4, in5, in6, in7;
  int16x8_t out0, out1, out2, out3, out4, out5, out6, out7;
  int16x8_t s1_0, s1_1, s1_2, s1_3, s1_4, s1_5, s1_6, s1_7, s1_8, s1_9, s1_10,
      s1_11, s1_12, s1_13, s1_14, s1_15, s1_16, s1_17, s1_18, s1_19, s1_20,
      s1_21, s1_22, s1_23, s1_24, s1_25, s1_26, s1_27, s1_28, s1_29, s1_30,
      s1_31;
  int16x8_t s2_0, s2_1, s2_2, s2_3, s2_4, s2_5, s2_6, s2_7, s2_8, s2_9, s2_10,
      s2_11, s2_12, s2_13, s2_14, s2_15, s2_16, s2_17, s2_18, s2_19, s2_20,
      s2_21, s2_22, s2_23, s2_24, s2_25, s2_26, s2_27, s2_28, s2_29, s2_30,
      s2_31;
  int16x8_t s3_24, s3_25, s3_26, s3_27;

  load_and_transpose_s16_8x8(input, 8, &in0, &in1, &in2, &in3, &in4, &in5, &in6,
                             &in7);


  s1_16 = multiply_shift_and_narrow_s16(in1, cospi_31_64);
  s1_31 = multiply_shift_and_narrow_s16(in1, cospi_1_64);


  s1_19 = multiply_shift_and_narrow_s16(in7, -cospi_25_64);
  s1_28 = multiply_shift_and_narrow_s16(in7, cospi_7_64);

  s1_20 = multiply_shift_and_narrow_s16(in5, cospi_27_64);
  s1_27 = multiply_shift_and_narrow_s16(in5, cospi_5_64);

  s1_23 = multiply_shift_and_narrow_s16(in3, -cospi_29_64);
  s1_24 = multiply_shift_and_narrow_s16(in3, cospi_3_64);


  s2_8 = multiply_shift_and_narrow_s16(in2, cospi_30_64);
  s2_15 = multiply_shift_and_narrow_s16(in2, cospi_2_64);

  s2_11 = multiply_shift_and_narrow_s16(in6, -cospi_26_64);
  s2_12 = multiply_shift_and_narrow_s16(in6, cospi_6_64);


  s1_4 = multiply_shift_and_narrow_s16(in4, cospi_28_64);
  s1_7 = multiply_shift_and_narrow_s16(in4, cospi_4_64);

  s1_17 = multiply_accumulate_shift_and_narrow_s16(s1_16, -cospi_4_64, s1_31,
                                                   cospi_28_64);
  s1_30 = multiply_accumulate_shift_and_narrow_s16(s1_16, cospi_28_64, s1_31,
                                                   cospi_4_64);


  s1_18 = multiply_accumulate_shift_and_narrow_s16(s1_19, -cospi_28_64, s1_28,
                                                   -cospi_4_64);
  s1_29 = multiply_accumulate_shift_and_narrow_s16(s1_19, -cospi_4_64, s1_28,
                                                   cospi_28_64);

  s1_21 = multiply_accumulate_shift_and_narrow_s16(s1_20, -cospi_20_64, s1_27,
                                                   cospi_12_64);
  s1_26 = multiply_accumulate_shift_and_narrow_s16(s1_20, cospi_12_64, s1_27,
                                                   cospi_20_64);

  s1_22 = multiply_accumulate_shift_and_narrow_s16(s1_23, -cospi_12_64, s1_24,
                                                   -cospi_20_64);
  s1_25 = multiply_accumulate_shift_and_narrow_s16(s1_23, -cospi_20_64, s1_24,
                                                   cospi_12_64);


  s1_0 = multiply_shift_and_narrow_s16(in0, cospi_16_64);

  s2_9 = multiply_accumulate_shift_and_narrow_s16(s2_8, -cospi_8_64, s2_15,
                                                  cospi_24_64);
  s2_14 = multiply_accumulate_shift_and_narrow_s16(s2_8, cospi_24_64, s2_15,
                                                   cospi_8_64);

  s2_10 = multiply_accumulate_shift_and_narrow_s16(s2_11, -cospi_24_64, s2_12,
                                                   -cospi_8_64);
  s2_13 = multiply_accumulate_shift_and_narrow_s16(s2_11, -cospi_8_64, s2_12,
                                                   cospi_24_64);

  s2_16 = vaddq_s16(s1_16, s1_19);

  s2_17 = vaddq_s16(s1_17, s1_18);
  s2_18 = vsubq_s16(s1_17, s1_18);

  s2_19 = vsubq_s16(s1_16, s1_19);

  s2_20 = vsubq_s16(s1_23, s1_20);
  s2_21 = vsubq_s16(s1_22, s1_21);

  s2_22 = vaddq_s16(s1_21, s1_22);
  s2_23 = vaddq_s16(s1_20, s1_23);

  s2_24 = vaddq_s16(s1_24, s1_27);
  s2_25 = vaddq_s16(s1_25, s1_26);
  s2_26 = vsubq_s16(s1_25, s1_26);
  s2_27 = vsubq_s16(s1_24, s1_27);

  s2_28 = vsubq_s16(s1_31, s1_28);
  s2_29 = vsubq_s16(s1_30, s1_29);
  s2_30 = vaddq_s16(s1_29, s1_30);
  s2_31 = vaddq_s16(s1_28, s1_31);


  s1_5 = sub_multiply_shift_and_narrow_s16(s1_7, s1_4, cospi_16_64);
  s1_6 = add_multiply_shift_and_narrow_s16(s1_4, s1_7, cospi_16_64);

  s1_8 = vaddq_s16(s2_8, s2_11);
  s1_9 = vaddq_s16(s2_9, s2_10);
  s1_10 = vsubq_s16(s2_9, s2_10);
  s1_11 = vsubq_s16(s2_8, s2_11);
  s1_12 = vsubq_s16(s2_15, s2_12);
  s1_13 = vsubq_s16(s2_14, s2_13);
  s1_14 = vaddq_s16(s2_13, s2_14);
  s1_15 = vaddq_s16(s2_12, s2_15);

  s1_18 = multiply_accumulate_shift_and_narrow_s16(s2_18, -cospi_8_64, s2_29,
                                                   cospi_24_64);
  s1_29 = multiply_accumulate_shift_and_narrow_s16(s2_18, cospi_24_64, s2_29,
                                                   cospi_8_64);

  s1_19 = multiply_accumulate_shift_and_narrow_s16(s2_19, -cospi_8_64, s2_28,
                                                   cospi_24_64);
  s1_28 = multiply_accumulate_shift_and_narrow_s16(s2_19, cospi_24_64, s2_28,
                                                   cospi_8_64);

  s1_20 = multiply_accumulate_shift_and_narrow_s16(s2_20, -cospi_24_64, s2_27,
                                                   -cospi_8_64);
  s1_27 = multiply_accumulate_shift_and_narrow_s16(s2_20, -cospi_8_64, s2_27,
                                                   cospi_24_64);

  s1_21 = multiply_accumulate_shift_and_narrow_s16(s2_21, -cospi_24_64, s2_26,
                                                   -cospi_8_64);
  s1_26 = multiply_accumulate_shift_and_narrow_s16(s2_21, -cospi_8_64, s2_26,
                                                   cospi_24_64);


  s2_0 = vaddq_s16(s1_0, s1_7);
  s2_1 = vaddq_s16(s1_0, s1_6);
  s2_2 = vaddq_s16(s1_0, s1_5);
  s2_3 = vaddq_s16(s1_0, s1_4);
  s2_4 = vsubq_s16(s1_0, s1_4);
  s2_5 = vsubq_s16(s1_0, s1_5);
  s2_6 = vsubq_s16(s1_0, s1_6);
  s2_7 = vsubq_s16(s1_0, s1_7);

  s2_10 = sub_multiply_shift_and_narrow_s16(s1_13, s1_10, cospi_16_64);
  s2_13 = add_multiply_shift_and_narrow_s16(s1_10, s1_13, cospi_16_64);

  s2_11 = sub_multiply_shift_and_narrow_s16(s1_12, s1_11, cospi_16_64);
  s2_12 = add_multiply_shift_and_narrow_s16(s1_11, s1_12, cospi_16_64);

  s1_16 = vaddq_s16(s2_16, s2_23);
  s1_17 = vaddq_s16(s2_17, s2_22);
  s2_18 = vaddq_s16(s1_18, s1_21);
  s2_19 = vaddq_s16(s1_19, s1_20);
  s2_20 = vsubq_s16(s1_19, s1_20);
  s2_21 = vsubq_s16(s1_18, s1_21);
  s1_22 = vsubq_s16(s2_17, s2_22);
  s1_23 = vsubq_s16(s2_16, s2_23);

  s3_24 = vsubq_s16(s2_31, s2_24);
  s3_25 = vsubq_s16(s2_30, s2_25);
  s3_26 = vsubq_s16(s1_29, s1_26);
  s3_27 = vsubq_s16(s1_28, s1_27);
  s2_28 = vaddq_s16(s1_27, s1_28);
  s2_29 = vaddq_s16(s1_26, s1_29);
  s2_30 = vaddq_s16(s2_25, s2_30);
  s2_31 = vaddq_s16(s2_24, s2_31);


  s1_0 = vaddq_s16(s2_0, s1_15);
  s1_1 = vaddq_s16(s2_1, s1_14);
  s1_2 = vaddq_s16(s2_2, s2_13);
  s1_3 = vaddq_s16(s2_3, s2_12);
  s1_4 = vaddq_s16(s2_4, s2_11);
  s1_5 = vaddq_s16(s2_5, s2_10);
  s1_6 = vaddq_s16(s2_6, s1_9);
  s1_7 = vaddq_s16(s2_7, s1_8);
  s1_8 = vsubq_s16(s2_7, s1_8);
  s1_9 = vsubq_s16(s2_6, s1_9);
  s1_10 = vsubq_s16(s2_5, s2_10);
  s1_11 = vsubq_s16(s2_4, s2_11);
  s1_12 = vsubq_s16(s2_3, s2_12);
  s1_13 = vsubq_s16(s2_2, s2_13);
  s1_14 = vsubq_s16(s2_1, s1_14);
  s1_15 = vsubq_s16(s2_0, s1_15);

  s1_20 = sub_multiply_shift_and_narrow_s16(s3_27, s2_20, cospi_16_64);
  s1_27 = add_multiply_shift_and_narrow_s16(s2_20, s3_27, cospi_16_64);

  s1_21 = sub_multiply_shift_and_narrow_s16(s3_26, s2_21, cospi_16_64);
  s1_26 = add_multiply_shift_and_narrow_s16(s2_21, s3_26, cospi_16_64);

  s2_22 = sub_multiply_shift_and_narrow_s16(s3_25, s1_22, cospi_16_64);
  s1_25 = add_multiply_shift_and_narrow_s16(s1_22, s3_25, cospi_16_64);

  s2_23 = sub_multiply_shift_and_narrow_s16(s3_24, s1_23, cospi_16_64);
  s1_24 = add_multiply_shift_and_narrow_s16(s1_23, s3_24, cospi_16_64);


  out0 = vaddq_s16(s1_0, s2_31);
  out1 = vaddq_s16(s1_1, s2_30);
  out2 = vaddq_s16(s1_2, s2_29);
  out3 = vaddq_s16(s1_3, s2_28);
  out4 = vaddq_s16(s1_4, s1_27);
  out5 = vaddq_s16(s1_5, s1_26);
  out6 = vaddq_s16(s1_6, s1_25);
  out7 = vaddq_s16(s1_7, s1_24);

  add_and_store_u8_s16(out0, out1, out2, out3, out4, out5, out6, out7, output,
                       stride);

  out0 = vaddq_s16(s1_8, s2_23);
  out1 = vaddq_s16(s1_9, s2_22);
  out2 = vaddq_s16(s1_10, s1_21);
  out3 = vaddq_s16(s1_11, s1_20);
  out4 = vaddq_s16(s1_12, s2_19);
  out5 = vaddq_s16(s1_13, s2_18);
  out6 = vaddq_s16(s1_14, s1_17);
  out7 = vaddq_s16(s1_15, s1_16);

  add_and_store_u8_s16(out0, out1, out2, out3, out4, out5, out6, out7,
                       output + (8 * stride), stride);

  out0 = vsubq_s16(s1_15, s1_16);
  out1 = vsubq_s16(s1_14, s1_17);
  out2 = vsubq_s16(s1_13, s2_18);
  out3 = vsubq_s16(s1_12, s2_19);
  out4 = vsubq_s16(s1_11, s1_20);
  out5 = vsubq_s16(s1_10, s1_21);
  out6 = vsubq_s16(s1_9, s2_22);
  out7 = vsubq_s16(s1_8, s2_23);

  add_and_store_u8_s16(out0, out1, out2, out3, out4, out5, out6, out7,
                       output + (16 * stride), stride);

  out0 = vsubq_s16(s1_7, s1_24);
  out1 = vsubq_s16(s1_6, s1_25);
  out2 = vsubq_s16(s1_5, s1_26);
  out3 = vsubq_s16(s1_4, s1_27);
  out4 = vsubq_s16(s1_3, s2_28);
  out5 = vsubq_s16(s1_2, s2_29);
  out6 = vsubq_s16(s1_1, s2_30);
  out7 = vsubq_s16(s1_0, s2_31);

  add_and_store_u8_s16(out0, out1, out2, out3, out4, out5, out6, out7,
                       output + (24 * stride), stride);
}

void vpx_idct32x32_34_add_neon(const int16_t *input, uint8_t *dest,
                               int stride) {
  int i;
  int16_t temp[32 * 8];
  int16_t *t = temp;

  idct32_6_neon(input, t);

  for (i = 0; i < 32; i += 8) {
    idct32_8_neon(t, dest, stride);
    t += (8 * 8);
    dest += 8;
  }
}