#include <arm_neon.h>

Load & store

Loads and stores of one to four vectors, with de-interleaving (ld2–ld4 / st2–st4), single-lane and replicate forms, and load-acquire/store-release lanes.

intrinsic family of arm_neon.h

850 macros

macrovld1q_bf16

#define vld1q_bf16(__p0) __extension__ ({
  bfloat16x8_t __ret;
  __ret = __builtin_bit_cast(bfloat16x8_t, __builtin_neon_vld1q_bf16(__p0, 43));
  __ret;
})

macrovld1_bf16

#define vld1_bf16(__p0) __extension__ ({
  bfloat16x4_t __ret;
  __ret = __builtin_bit_cast(bfloat16x4_t, __builtin_neon_vld1_bf16(__p0, 11));
  __ret;
})

macrovld1q_dup_bf16

#define vld1q_dup_bf16(__p0) __extension__ ({
  bfloat16x8_t __ret;
  __ret = __builtin_bit_cast(bfloat16x8_t, __builtin_neon_vld1q_dup_bf16(__p0, 43));
  __ret;
})

macrovld1_dup_bf16

#define vld1_dup_bf16(__p0) __extension__ ({
  bfloat16x4_t __ret;
  __ret = __builtin_bit_cast(bfloat16x4_t, __builtin_neon_vld1_dup_bf16(__p0, 11));
  __ret;
})

macrovld1q_lane_bf16

#define vld1q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8_t __ret;
  bfloat16x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(bfloat16x8_t, __builtin_neon_vld1q_lane_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 43));
  __ret;
})

macrovld1_lane_bf16

#define vld1_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4_t __ret;
  bfloat16x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(bfloat16x4_t, __builtin_neon_vld1_lane_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 11));
  __ret;
})

macrovld1q_bf16_x2

#define vld1q_bf16_x2(__p0) __extension__ ({
  bfloat16x8x2_t __ret;
  __builtin_neon_vld1q_bf16_x2(&__ret, __p0, 43);
  __ret;
})

macrovld1_bf16_x2

#define vld1_bf16_x2(__p0) __extension__ ({
  bfloat16x4x2_t __ret;
  __builtin_neon_vld1_bf16_x2(&__ret, __p0, 11);
  __ret;
})

macrovld1q_bf16_x3

#define vld1q_bf16_x3(__p0) __extension__ ({
  bfloat16x8x3_t __ret;
  __builtin_neon_vld1q_bf16_x3(&__ret, __p0, 43);
  __ret;
})

macrovld1_bf16_x3

#define vld1_bf16_x3(__p0) __extension__ ({
  bfloat16x4x3_t __ret;
  __builtin_neon_vld1_bf16_x3(&__ret, __p0, 11);
  __ret;
})

macrovld1q_bf16_x4

#define vld1q_bf16_x4(__p0) __extension__ ({
  bfloat16x8x4_t __ret;
  __builtin_neon_vld1q_bf16_x4(&__ret, __p0, 43);
  __ret;
})

macrovld1_bf16_x4

#define vld1_bf16_x4(__p0) __extension__ ({
  bfloat16x4x4_t __ret;
  __builtin_neon_vld1_bf16_x4(&__ret, __p0, 11);
  __ret;
})

macrovld2q_bf16

#define vld2q_bf16(__p0) __extension__ ({
  bfloat16x8x2_t __ret;
  __builtin_neon_vld2q_bf16(&__ret, __p0, 43);
  __ret;
})

macrovld2_bf16

#define vld2_bf16(__p0) __extension__ ({
  bfloat16x4x2_t __ret;
  __builtin_neon_vld2_bf16(&__ret, __p0, 11);
  __ret;
})

macrovld2q_dup_bf16

#define vld2q_dup_bf16(__p0) __extension__ ({
  bfloat16x8x2_t __ret;
  __builtin_neon_vld2q_dup_bf16(&__ret, __p0, 43);
  __ret;
})

macrovld2_dup_bf16

#define vld2_dup_bf16(__p0) __extension__ ({
  bfloat16x4x2_t __ret;
  __builtin_neon_vld2_dup_bf16(&__ret, __p0, 11);
  __ret;
})

macrovld2q_lane_bf16

#define vld2q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8x2_t __ret;
  bfloat16x8x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_bf16(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 43);
  __ret;
})

macrovld2_lane_bf16

#define vld2_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4x2_t __ret;
  bfloat16x4x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_bf16(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 11);
  __ret;
})

macrovld3q_bf16

#define vld3q_bf16(__p0) __extension__ ({
  bfloat16x8x3_t __ret;
  __builtin_neon_vld3q_bf16(&__ret, __p0, 43);
  __ret;
})

macrovld3_bf16

#define vld3_bf16(__p0) __extension__ ({
  bfloat16x4x3_t __ret;
  __builtin_neon_vld3_bf16(&__ret, __p0, 11);
  __ret;
})

macrovld3q_dup_bf16

#define vld3q_dup_bf16(__p0) __extension__ ({
  bfloat16x8x3_t __ret;
  __builtin_neon_vld3q_dup_bf16(&__ret, __p0, 43);
  __ret;
})

macrovld3_dup_bf16

#define vld3_dup_bf16(__p0) __extension__ ({
  bfloat16x4x3_t __ret;
  __builtin_neon_vld3_dup_bf16(&__ret, __p0, 11);
  __ret;
})

macrovld3q_lane_bf16

#define vld3q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8x3_t __ret;
  bfloat16x8x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_bf16(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 43);
  __ret;
})

macrovld3_lane_bf16

#define vld3_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4x3_t __ret;
  bfloat16x4x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_bf16(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 11);
  __ret;
})

macrovld4q_bf16

#define vld4q_bf16(__p0) __extension__ ({
  bfloat16x8x4_t __ret;
  __builtin_neon_vld4q_bf16(&__ret, __p0, 43);
  __ret;
})

macrovld4_bf16

#define vld4_bf16(__p0) __extension__ ({
  bfloat16x4x4_t __ret;
  __builtin_neon_vld4_bf16(&__ret, __p0, 11);
  __ret;
})

macrovld4q_dup_bf16

#define vld4q_dup_bf16(__p0) __extension__ ({
  bfloat16x8x4_t __ret;
  __builtin_neon_vld4q_dup_bf16(&__ret, __p0, 43);
  __ret;
})

macrovld4_dup_bf16

#define vld4_dup_bf16(__p0) __extension__ ({
  bfloat16x4x4_t __ret;
  __builtin_neon_vld4_dup_bf16(&__ret, __p0, 11);
  __ret;
})

macrovld4q_lane_bf16

#define vld4q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8x4_t __ret;
  bfloat16x8x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_bf16(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 43);
  __ret;
})

macrovld4_lane_bf16

#define vld4_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4x4_t __ret;
  bfloat16x4x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_bf16(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 11);
  __ret;
})

macrovst1q_bf16

#define vst1q_bf16(__p0, __p1) __extension__ ({
  bfloat16x8_t __s1 = __p1;
  __builtin_neon_vst1q_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1), 43);
})

macrovst1_bf16

#define vst1_bf16(__p0, __p1) __extension__ ({
  bfloat16x4_t __s1 = __p1;
  __builtin_neon_vst1_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1), 11);
})

macrovst1q_lane_bf16

#define vst1q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8_t __s1 = __p1;
  __builtin_neon_vst1q_lane_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 43);
})

macrovst1_lane_bf16

#define vst1_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4_t __s1 = __p1;
  __builtin_neon_vst1_lane_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 11);
})

macrovst1q_bf16_x2

#define vst1q_bf16_x2(__p0, __p1) __extension__ ({
  bfloat16x8x2_t __s1 = __p1;
  __builtin_neon_vst1q_bf16_x2(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 43);
})

macrovst1_bf16_x2

#define vst1_bf16_x2(__p0, __p1) __extension__ ({
  bfloat16x4x2_t __s1 = __p1;
  __builtin_neon_vst1_bf16_x2(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 11);
})

macrovst1q_bf16_x3

#define vst1q_bf16_x3(__p0, __p1) __extension__ ({
  bfloat16x8x3_t __s1 = __p1;
  __builtin_neon_vst1q_bf16_x3(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 43);
})

macrovst1_bf16_x3

#define vst1_bf16_x3(__p0, __p1) __extension__ ({
  bfloat16x4x3_t __s1 = __p1;
  __builtin_neon_vst1_bf16_x3(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 11);
})

macrovst1q_bf16_x4

#define vst1q_bf16_x4(__p0, __p1) __extension__ ({
  bfloat16x8x4_t __s1 = __p1;
  __builtin_neon_vst1q_bf16_x4(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 43);
})

macrovst1_bf16_x4

#define vst1_bf16_x4(__p0, __p1) __extension__ ({
  bfloat16x4x4_t __s1 = __p1;
  __builtin_neon_vst1_bf16_x4(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 11);
})

macrovst2q_bf16

#define vst2q_bf16(__p0, __p1) __extension__ ({
  bfloat16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 43);
})

macrovst2_bf16

#define vst2_bf16(__p0, __p1) __extension__ ({
  bfloat16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 11);
})

macrovst2q_lane_bf16

#define vst2q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 43);
})

macrovst2_lane_bf16

#define vst2_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 11);
})

macrovst3q_bf16

#define vst3q_bf16(__p0, __p1) __extension__ ({
  bfloat16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 43);
})

macrovst3_bf16

#define vst3_bf16(__p0, __p1) __extension__ ({
  bfloat16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 11);
})

macrovst3q_lane_bf16

#define vst3q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 43);
})

macrovst3_lane_bf16

#define vst3_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 11);
})

macrovst4q_bf16

#define vst4q_bf16(__p0, __p1) __extension__ ({
  bfloat16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 43);
})

macrovst4_bf16

#define vst4_bf16(__p0, __p1) __extension__ ({
  bfloat16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 11);
})

macrovst4q_lane_bf16

#define vst4q_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_bf16(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 43);
})

macrovst4_lane_bf16

#define vst4_lane_bf16(__p0, __p1, __p2) __extension__ ({
  bfloat16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_bf16(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 11);
})

macrovld1_p8

#define vld1_p8(__p0) __extension__ ({
  poly8x8_t __ret;
  __ret = __builtin_bit_cast(poly8x8_t, __builtin_neon_vld1_v(__p0, 4));
  __ret;
})

macrovld1_p16

#define vld1_p16(__p0) __extension__ ({
  poly16x4_t __ret;
  __ret = __builtin_bit_cast(poly16x4_t, __builtin_neon_vld1_v(__p0, 5));
  __ret;
})

macrovld1q_p8

#define vld1q_p8(__p0) __extension__ ({
  poly8x16_t __ret;
  __ret = __builtin_bit_cast(poly8x16_t, __builtin_neon_vld1q_v(__p0, 36));
  __ret;
})

macrovld1q_p16

#define vld1q_p16(__p0) __extension__ ({
  poly16x8_t __ret;
  __ret = __builtin_bit_cast(poly16x8_t, __builtin_neon_vld1q_v(__p0, 37));
  __ret;
})

macrovld1q_u8

#define vld1q_u8(__p0) __extension__ ({
  uint8x16_t __ret;
  __ret = __builtin_bit_cast(uint8x16_t, __builtin_neon_vld1q_v(__p0, 48));
  __ret;
})

macrovld1q_u32

#define vld1q_u32(__p0) __extension__ ({
  uint32x4_t __ret;
  __ret = __builtin_bit_cast(uint32x4_t, __builtin_neon_vld1q_v(__p0, 50));
  __ret;
})

macrovld1q_u64

#define vld1q_u64(__p0) __extension__ ({
  uint64x2_t __ret;
  __ret = __builtin_bit_cast(uint64x2_t, __builtin_neon_vld1q_v(__p0, 51));
  __ret;
})

macrovld1q_u16

#define vld1q_u16(__p0) __extension__ ({
  uint16x8_t __ret;
  __ret = __builtin_bit_cast(uint16x8_t, __builtin_neon_vld1q_v(__p0, 49));
  __ret;
})

macrovld1q_s8

#define vld1q_s8(__p0) __extension__ ({
  int8x16_t __ret;
  __ret = __builtin_bit_cast(int8x16_t, __builtin_neon_vld1q_v(__p0, 32));
  __ret;
})

macrovld1q_f32

#define vld1q_f32(__p0) __extension__ ({
  float32x4_t __ret;
  __ret = __builtin_bit_cast(float32x4_t, __builtin_neon_vld1q_v(__p0, 41));
  __ret;
})

macrovld1q_s32

#define vld1q_s32(__p0) __extension__ ({
  int32x4_t __ret;
  __ret = __builtin_bit_cast(int32x4_t, __builtin_neon_vld1q_v(__p0, 34));
  __ret;
})

macrovld1q_s64

#define vld1q_s64(__p0) __extension__ ({
  int64x2_t __ret;
  __ret = __builtin_bit_cast(int64x2_t, __builtin_neon_vld1q_v(__p0, 35));
  __ret;
})

macrovld1q_s16

#define vld1q_s16(__p0) __extension__ ({
  int16x8_t __ret;
  __ret = __builtin_bit_cast(int16x8_t, __builtin_neon_vld1q_v(__p0, 33));
  __ret;
})

macrovld1_u8

#define vld1_u8(__p0) __extension__ ({
  uint8x8_t __ret;
  __ret = __builtin_bit_cast(uint8x8_t, __builtin_neon_vld1_v(__p0, 16));
  __ret;
})

macrovld1_u32

#define vld1_u32(__p0) __extension__ ({
  uint32x2_t __ret;
  __ret = __builtin_bit_cast(uint32x2_t, __builtin_neon_vld1_v(__p0, 18));
  __ret;
})

macrovld1_u64

#define vld1_u64(__p0) __extension__ ({
  uint64x1_t __ret;
  __ret = __builtin_bit_cast(uint64x1_t, __builtin_neon_vld1_v(__p0, 19));
  __ret;
})

macrovld1_u16

#define vld1_u16(__p0) __extension__ ({
  uint16x4_t __ret;
  __ret = __builtin_bit_cast(uint16x4_t, __builtin_neon_vld1_v(__p0, 17));
  __ret;
})

macrovld1_s8

#define vld1_s8(__p0) __extension__ ({
  int8x8_t __ret;
  __ret = __builtin_bit_cast(int8x8_t, __builtin_neon_vld1_v(__p0, 0));
  __ret;
})

macrovld1_f32

#define vld1_f32(__p0) __extension__ ({
  float32x2_t __ret;
  __ret = __builtin_bit_cast(float32x2_t, __builtin_neon_vld1_v(__p0, 9));
  __ret;
})

macrovld1_s32

#define vld1_s32(__p0) __extension__ ({
  int32x2_t __ret;
  __ret = __builtin_bit_cast(int32x2_t, __builtin_neon_vld1_v(__p0, 2));
  __ret;
})

macrovld1_s64

#define vld1_s64(__p0) __extension__ ({
  int64x1_t __ret;
  __ret = __builtin_bit_cast(int64x1_t, __builtin_neon_vld1_v(__p0, 3));
  __ret;
})

macrovld1_s16

#define vld1_s16(__p0) __extension__ ({
  int16x4_t __ret;
  __ret = __builtin_bit_cast(int16x4_t, __builtin_neon_vld1_v(__p0, 1));
  __ret;
})

macrovld1_dup_p8

#define vld1_dup_p8(__p0) __extension__ ({
  poly8x8_t __ret;
  __ret = __builtin_bit_cast(poly8x8_t, __builtin_neon_vld1_dup_v(__p0, 4));
  __ret;
})

macrovld1_dup_p16

#define vld1_dup_p16(__p0) __extension__ ({
  poly16x4_t __ret;
  __ret = __builtin_bit_cast(poly16x4_t, __builtin_neon_vld1_dup_v(__p0, 5));
  __ret;
})

macrovld1q_dup_p8

#define vld1q_dup_p8(__p0) __extension__ ({
  poly8x16_t __ret;
  __ret = __builtin_bit_cast(poly8x16_t, __builtin_neon_vld1q_dup_v(__p0, 36));
  __ret;
})

macrovld1q_dup_p16

#define vld1q_dup_p16(__p0) __extension__ ({
  poly16x8_t __ret;
  __ret = __builtin_bit_cast(poly16x8_t, __builtin_neon_vld1q_dup_v(__p0, 37));
  __ret;
})

macrovld1q_dup_u8

#define vld1q_dup_u8(__p0) __extension__ ({
  uint8x16_t __ret;
  __ret = __builtin_bit_cast(uint8x16_t, __builtin_neon_vld1q_dup_v(__p0, 48));
  __ret;
})

macrovld1q_dup_u32

#define vld1q_dup_u32(__p0) __extension__ ({
  uint32x4_t __ret;
  __ret = __builtin_bit_cast(uint32x4_t, __builtin_neon_vld1q_dup_v(__p0, 50));
  __ret;
})

macrovld1q_dup_u64

#define vld1q_dup_u64(__p0) __extension__ ({
  uint64x2_t __ret;
  __ret = __builtin_bit_cast(uint64x2_t, __builtin_neon_vld1q_dup_v(__p0, 51));
  __ret;
})

macrovld1q_dup_u16

#define vld1q_dup_u16(__p0) __extension__ ({
  uint16x8_t __ret;
  __ret = __builtin_bit_cast(uint16x8_t, __builtin_neon_vld1q_dup_v(__p0, 49));
  __ret;
})

macrovld1q_dup_s8

#define vld1q_dup_s8(__p0) __extension__ ({
  int8x16_t __ret;
  __ret = __builtin_bit_cast(int8x16_t, __builtin_neon_vld1q_dup_v(__p0, 32));
  __ret;
})

macrovld1q_dup_f32

#define vld1q_dup_f32(__p0) __extension__ ({
  float32x4_t __ret;
  __ret = __builtin_bit_cast(float32x4_t, __builtin_neon_vld1q_dup_v(__p0, 41));
  __ret;
})

macrovld1q_dup_s32

#define vld1q_dup_s32(__p0) __extension__ ({
  int32x4_t __ret;
  __ret = __builtin_bit_cast(int32x4_t, __builtin_neon_vld1q_dup_v(__p0, 34));
  __ret;
})

macrovld1q_dup_s64

#define vld1q_dup_s64(__p0) __extension__ ({
  int64x2_t __ret;
  __ret = __builtin_bit_cast(int64x2_t, __builtin_neon_vld1q_dup_v(__p0, 35));
  __ret;
})

macrovld1q_dup_s16

#define vld1q_dup_s16(__p0) __extension__ ({
  int16x8_t __ret;
  __ret = __builtin_bit_cast(int16x8_t, __builtin_neon_vld1q_dup_v(__p0, 33));
  __ret;
})

macrovld1_dup_u8

#define vld1_dup_u8(__p0) __extension__ ({
  uint8x8_t __ret;
  __ret = __builtin_bit_cast(uint8x8_t, __builtin_neon_vld1_dup_v(__p0, 16));
  __ret;
})

macrovld1_dup_u32

#define vld1_dup_u32(__p0) __extension__ ({
  uint32x2_t __ret;
  __ret = __builtin_bit_cast(uint32x2_t, __builtin_neon_vld1_dup_v(__p0, 18));
  __ret;
})

macrovld1_dup_u64

#define vld1_dup_u64(__p0) __extension__ ({
  uint64x1_t __ret;
  __ret = __builtin_bit_cast(uint64x1_t, __builtin_neon_vld1_dup_v(__p0, 19));
  __ret;
})

macrovld1_dup_u16

#define vld1_dup_u16(__p0) __extension__ ({
  uint16x4_t __ret;
  __ret = __builtin_bit_cast(uint16x4_t, __builtin_neon_vld1_dup_v(__p0, 17));
  __ret;
})

macrovld1_dup_s8

#define vld1_dup_s8(__p0) __extension__ ({
  int8x8_t __ret;
  __ret = __builtin_bit_cast(int8x8_t, __builtin_neon_vld1_dup_v(__p0, 0));
  __ret;
})

macrovld1_dup_f32

#define vld1_dup_f32(__p0) __extension__ ({
  float32x2_t __ret;
  __ret = __builtin_bit_cast(float32x2_t, __builtin_neon_vld1_dup_v(__p0, 9));
  __ret;
})

macrovld1_dup_s32

#define vld1_dup_s32(__p0) __extension__ ({
  int32x2_t __ret;
  __ret = __builtin_bit_cast(int32x2_t, __builtin_neon_vld1_dup_v(__p0, 2));
  __ret;
})

macrovld1_dup_s64

#define vld1_dup_s64(__p0) __extension__ ({
  int64x1_t __ret;
  __ret = __builtin_bit_cast(int64x1_t, __builtin_neon_vld1_dup_v(__p0, 3));
  __ret;
})

macrovld1_dup_s16

#define vld1_dup_s16(__p0) __extension__ ({
  int16x4_t __ret;
  __ret = __builtin_bit_cast(int16x4_t, __builtin_neon_vld1_dup_v(__p0, 1));
  __ret;
})

macrovld1_lane_p8

#define vld1_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8_t __ret;
  poly8x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly8x8_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 4));
  __ret;
})

macrovld1_lane_p16

#define vld1_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4_t __ret;
  poly16x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly16x4_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 5));
  __ret;
})

macrovld1q_lane_p8

#define vld1q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16_t __ret;
  poly8x16_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly8x16_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 36));
  __ret;
})

macrovld1q_lane_p16

#define vld1q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8_t __ret;
  poly16x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly16x8_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 37));
  __ret;
})

macrovld1q_lane_u8

#define vld1q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16_t __ret;
  uint8x16_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint8x16_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 48));
  __ret;
})

macrovld1q_lane_u32

#define vld1q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4_t __ret;
  uint32x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint32x4_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 50));
  __ret;
})

macrovld1q_lane_u64

#define vld1q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2_t __ret;
  uint64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint64x2_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 51));
  __ret;
})

macrovld1q_lane_u16

#define vld1q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8_t __ret;
  uint16x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint16x8_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 49));
  __ret;
})

macrovld1q_lane_s8

#define vld1q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16_t __ret;
  int8x16_t __s1 = __p1;
  __ret = __builtin_bit_cast(int8x16_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 32));
  __ret;
})

macrovld1q_lane_f32

#define vld1q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4_t __ret;
  float32x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(float32x4_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 41));
  __ret;
})

macrovld1q_lane_s32

#define vld1q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4_t __ret;
  int32x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(int32x4_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 34));
  __ret;
})

macrovld1q_lane_s64

#define vld1q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2_t __ret;
  int64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(int64x2_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 35));
  __ret;
})

macrovld1q_lane_s16

#define vld1q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8_t __ret;
  int16x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(int16x8_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 33));
  __ret;
})

macrovld1_lane_u8

#define vld1_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8_t __ret;
  uint8x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint8x8_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 16));
  __ret;
})

macrovld1_lane_u32

#define vld1_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2_t __ret;
  uint32x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint32x2_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 18));
  __ret;
})

macrovld1_lane_u64

#define vld1_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1_t __ret;
  uint64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint64x1_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 19));
  __ret;
})

macrovld1_lane_u16

#define vld1_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4_t __ret;
  uint16x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint16x4_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 17));
  __ret;
})

macrovld1_lane_s8

#define vld1_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8_t __ret;
  int8x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(int8x8_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 0));
  __ret;
})

macrovld1_lane_f32

#define vld1_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2_t __ret;
  float32x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(float32x2_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 9));
  __ret;
})

macrovld1_lane_s32

#define vld1_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2_t __ret;
  int32x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(int32x2_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 2));
  __ret;
})

macrovld1_lane_s64

#define vld1_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1_t __ret;
  int64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(int64x1_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 3));
  __ret;
})

macrovld1_lane_s16

#define vld1_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4_t __ret;
  int16x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(int16x4_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 1));
  __ret;
})

macrovld1_p8_x2

#define vld1_p8_x2(__p0) __extension__ ({
  poly8x8x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 4);
  __ret;
})

macrovld1_p16_x2

#define vld1_p16_x2(__p0) __extension__ ({
  poly16x4x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 5);
  __ret;
})

macrovld1q_p8_x2

#define vld1q_p8_x2(__p0) __extension__ ({
  poly8x16x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 36);
  __ret;
})

macrovld1q_p16_x2

#define vld1q_p16_x2(__p0) __extension__ ({
  poly16x8x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 37);
  __ret;
})

macrovld1q_u8_x2

#define vld1q_u8_x2(__p0) __extension__ ({
  uint8x16x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 48);
  __ret;
})

macrovld1q_u32_x2

#define vld1q_u32_x2(__p0) __extension__ ({
  uint32x4x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 50);
  __ret;
})

macrovld1q_u64_x2

#define vld1q_u64_x2(__p0) __extension__ ({
  uint64x2x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 51);
  __ret;
})

macrovld1q_u16_x2

#define vld1q_u16_x2(__p0) __extension__ ({
  uint16x8x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 49);
  __ret;
})

macrovld1q_s8_x2

#define vld1q_s8_x2(__p0) __extension__ ({
  int8x16x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 32);
  __ret;
})

macrovld1q_f32_x2

#define vld1q_f32_x2(__p0) __extension__ ({
  float32x4x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 41);
  __ret;
})

macrovld1q_s32_x2

#define vld1q_s32_x2(__p0) __extension__ ({
  int32x4x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 34);
  __ret;
})

macrovld1q_s64_x2

#define vld1q_s64_x2(__p0) __extension__ ({
  int64x2x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 35);
  __ret;
})

macrovld1q_s16_x2

#define vld1q_s16_x2(__p0) __extension__ ({
  int16x8x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 33);
  __ret;
})

macrovld1_u8_x2

#define vld1_u8_x2(__p0) __extension__ ({
  uint8x8x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 16);
  __ret;
})

macrovld1_u32_x2

#define vld1_u32_x2(__p0) __extension__ ({
  uint32x2x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 18);
  __ret;
})

macrovld1_u64_x2

#define vld1_u64_x2(__p0) __extension__ ({
  uint64x1x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 19);
  __ret;
})

macrovld1_u16_x2

#define vld1_u16_x2(__p0) __extension__ ({
  uint16x4x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 17);
  __ret;
})

macrovld1_s8_x2

#define vld1_s8_x2(__p0) __extension__ ({
  int8x8x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 0);
  __ret;
})

macrovld1_f32_x2

#define vld1_f32_x2(__p0) __extension__ ({
  float32x2x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 9);
  __ret;
})

macrovld1_s32_x2

#define vld1_s32_x2(__p0) __extension__ ({
  int32x2x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 2);
  __ret;
})

macrovld1_s64_x2

#define vld1_s64_x2(__p0) __extension__ ({
  int64x1x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 3);
  __ret;
})

macrovld1_s16_x2

#define vld1_s16_x2(__p0) __extension__ ({
  int16x4x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 1);
  __ret;
})

macrovld1_p8_x3

#define vld1_p8_x3(__p0) __extension__ ({
  poly8x8x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 4);
  __ret;
})

macrovld1_p16_x3

#define vld1_p16_x3(__p0) __extension__ ({
  poly16x4x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 5);
  __ret;
})

macrovld1q_p8_x3

#define vld1q_p8_x3(__p0) __extension__ ({
  poly8x16x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 36);
  __ret;
})

macrovld1q_p16_x3

#define vld1q_p16_x3(__p0) __extension__ ({
  poly16x8x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 37);
  __ret;
})

macrovld1q_u8_x3

#define vld1q_u8_x3(__p0) __extension__ ({
  uint8x16x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 48);
  __ret;
})

macrovld1q_u32_x3

#define vld1q_u32_x3(__p0) __extension__ ({
  uint32x4x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 50);
  __ret;
})

macrovld1q_u64_x3

#define vld1q_u64_x3(__p0) __extension__ ({
  uint64x2x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 51);
  __ret;
})

macrovld1q_u16_x3

#define vld1q_u16_x3(__p0) __extension__ ({
  uint16x8x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 49);
  __ret;
})

macrovld1q_s8_x3

#define vld1q_s8_x3(__p0) __extension__ ({
  int8x16x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 32);
  __ret;
})

macrovld1q_f32_x3

#define vld1q_f32_x3(__p0) __extension__ ({
  float32x4x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 41);
  __ret;
})

macrovld1q_s32_x3

#define vld1q_s32_x3(__p0) __extension__ ({
  int32x4x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 34);
  __ret;
})

macrovld1q_s64_x3

#define vld1q_s64_x3(__p0) __extension__ ({
  int64x2x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 35);
  __ret;
})

macrovld1q_s16_x3

#define vld1q_s16_x3(__p0) __extension__ ({
  int16x8x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 33);
  __ret;
})

macrovld1_u8_x3

#define vld1_u8_x3(__p0) __extension__ ({
  uint8x8x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 16);
  __ret;
})

macrovld1_u32_x3

#define vld1_u32_x3(__p0) __extension__ ({
  uint32x2x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 18);
  __ret;
})

macrovld1_u64_x3

#define vld1_u64_x3(__p0) __extension__ ({
  uint64x1x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 19);
  __ret;
})

macrovld1_u16_x3

#define vld1_u16_x3(__p0) __extension__ ({
  uint16x4x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 17);
  __ret;
})

macrovld1_s8_x3

#define vld1_s8_x3(__p0) __extension__ ({
  int8x8x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 0);
  __ret;
})

macrovld1_f32_x3

#define vld1_f32_x3(__p0) __extension__ ({
  float32x2x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 9);
  __ret;
})

macrovld1_s32_x3

#define vld1_s32_x3(__p0) __extension__ ({
  int32x2x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 2);
  __ret;
})

macrovld1_s64_x3

#define vld1_s64_x3(__p0) __extension__ ({
  int64x1x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 3);
  __ret;
})

macrovld1_s16_x3

#define vld1_s16_x3(__p0) __extension__ ({
  int16x4x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 1);
  __ret;
})

macrovld1_p8_x4

#define vld1_p8_x4(__p0) __extension__ ({
  poly8x8x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 4);
  __ret;
})

macrovld1_p16_x4

#define vld1_p16_x4(__p0) __extension__ ({
  poly16x4x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 5);
  __ret;
})

macrovld1q_p8_x4

#define vld1q_p8_x4(__p0) __extension__ ({
  poly8x16x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 36);
  __ret;
})

macrovld1q_p16_x4

#define vld1q_p16_x4(__p0) __extension__ ({
  poly16x8x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 37);
  __ret;
})

macrovld1q_u8_x4

#define vld1q_u8_x4(__p0) __extension__ ({
  uint8x16x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 48);
  __ret;
})

macrovld1q_u32_x4

#define vld1q_u32_x4(__p0) __extension__ ({
  uint32x4x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 50);
  __ret;
})

macrovld1q_u64_x4

#define vld1q_u64_x4(__p0) __extension__ ({
  uint64x2x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 51);
  __ret;
})

macrovld1q_u16_x4

#define vld1q_u16_x4(__p0) __extension__ ({
  uint16x8x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 49);
  __ret;
})

macrovld1q_s8_x4

#define vld1q_s8_x4(__p0) __extension__ ({
  int8x16x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 32);
  __ret;
})

macrovld1q_f32_x4

#define vld1q_f32_x4(__p0) __extension__ ({
  float32x4x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 41);
  __ret;
})

macrovld1q_s32_x4

#define vld1q_s32_x4(__p0) __extension__ ({
  int32x4x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 34);
  __ret;
})

macrovld1q_s64_x4

#define vld1q_s64_x4(__p0) __extension__ ({
  int64x2x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 35);
  __ret;
})

macrovld1q_s16_x4

#define vld1q_s16_x4(__p0) __extension__ ({
  int16x8x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 33);
  __ret;
})

macrovld1_u8_x4

#define vld1_u8_x4(__p0) __extension__ ({
  uint8x8x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 16);
  __ret;
})

macrovld1_u32_x4

#define vld1_u32_x4(__p0) __extension__ ({
  uint32x2x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 18);
  __ret;
})

macrovld1_u64_x4

#define vld1_u64_x4(__p0) __extension__ ({
  uint64x1x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 19);
  __ret;
})

macrovld1_u16_x4

#define vld1_u16_x4(__p0) __extension__ ({
  uint16x4x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 17);
  __ret;
})

macrovld1_s8_x4

#define vld1_s8_x4(__p0) __extension__ ({
  int8x8x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 0);
  __ret;
})

macrovld1_f32_x4

#define vld1_f32_x4(__p0) __extension__ ({
  float32x2x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 9);
  __ret;
})

macrovld1_s32_x4

#define vld1_s32_x4(__p0) __extension__ ({
  int32x2x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 2);
  __ret;
})

macrovld1_s64_x4

#define vld1_s64_x4(__p0) __extension__ ({
  int64x1x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 3);
  __ret;
})

macrovld1_s16_x4

#define vld1_s16_x4(__p0) __extension__ ({
  int16x4x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 1);
  __ret;
})

macrovld2_p8

#define vld2_p8(__p0) __extension__ ({
  poly8x8x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 4);
  __ret;
})

macrovld2_p16

#define vld2_p16(__p0) __extension__ ({
  poly16x4x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 5);
  __ret;
})

macrovld2q_p8

#define vld2q_p8(__p0) __extension__ ({
  poly8x16x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 36);
  __ret;
})

macrovld2q_p16

#define vld2q_p16(__p0) __extension__ ({
  poly16x8x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 37);
  __ret;
})

macrovld2q_u8

#define vld2q_u8(__p0) __extension__ ({
  uint8x16x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 48);
  __ret;
})

macrovld2q_u32

#define vld2q_u32(__p0) __extension__ ({
  uint32x4x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 50);
  __ret;
})

macrovld2q_u16

#define vld2q_u16(__p0) __extension__ ({
  uint16x8x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 49);
  __ret;
})

macrovld2q_s8

#define vld2q_s8(__p0) __extension__ ({
  int8x16x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 32);
  __ret;
})

macrovld2q_f32

#define vld2q_f32(__p0) __extension__ ({
  float32x4x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 41);
  __ret;
})

macrovld2q_s32

#define vld2q_s32(__p0) __extension__ ({
  int32x4x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 34);
  __ret;
})

macrovld2q_s16

#define vld2q_s16(__p0) __extension__ ({
  int16x8x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 33);
  __ret;
})

macrovld2_u8

#define vld2_u8(__p0) __extension__ ({
  uint8x8x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 16);
  __ret;
})

macrovld2_u32

#define vld2_u32(__p0) __extension__ ({
  uint32x2x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 18);
  __ret;
})

macrovld2_u64

#define vld2_u64(__p0) __extension__ ({
  uint64x1x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 19);
  __ret;
})

macrovld2_u16

#define vld2_u16(__p0) __extension__ ({
  uint16x4x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 17);
  __ret;
})

macrovld2_s8

#define vld2_s8(__p0) __extension__ ({
  int8x8x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 0);
  __ret;
})

macrovld2_f32

#define vld2_f32(__p0) __extension__ ({
  float32x2x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 9);
  __ret;
})

macrovld2_s32

#define vld2_s32(__p0) __extension__ ({
  int32x2x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 2);
  __ret;
})

macrovld2_s64

#define vld2_s64(__p0) __extension__ ({
  int64x1x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 3);
  __ret;
})

macrovld2_s16

#define vld2_s16(__p0) __extension__ ({
  int16x4x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 1);
  __ret;
})

macrovld2_dup_p8

#define vld2_dup_p8(__p0) __extension__ ({
  poly8x8x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 4);
  __ret;
})

macrovld2_dup_p16

#define vld2_dup_p16(__p0) __extension__ ({
  poly16x4x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 5);
  __ret;
})

macrovld2q_dup_p8

#define vld2q_dup_p8(__p0) __extension__ ({
  poly8x16x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 36);
  __ret;
})

macrovld2q_dup_p16

#define vld2q_dup_p16(__p0) __extension__ ({
  poly16x8x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 37);
  __ret;
})

macrovld2q_dup_u8

#define vld2q_dup_u8(__p0) __extension__ ({
  uint8x16x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 48);
  __ret;
})

macrovld2q_dup_u32

#define vld2q_dup_u32(__p0) __extension__ ({
  uint32x4x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 50);
  __ret;
})

macrovld2q_dup_u64

#define vld2q_dup_u64(__p0) __extension__ ({
  uint64x2x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 51);
  __ret;
})

macrovld2q_dup_u16

#define vld2q_dup_u16(__p0) __extension__ ({
  uint16x8x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 49);
  __ret;
})

macrovld2q_dup_s8

#define vld2q_dup_s8(__p0) __extension__ ({
  int8x16x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 32);
  __ret;
})

macrovld2q_dup_f32

#define vld2q_dup_f32(__p0) __extension__ ({
  float32x4x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 41);
  __ret;
})

macrovld2q_dup_s32

#define vld2q_dup_s32(__p0) __extension__ ({
  int32x4x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 34);
  __ret;
})

macrovld2q_dup_s64

#define vld2q_dup_s64(__p0) __extension__ ({
  int64x2x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 35);
  __ret;
})

macrovld2q_dup_s16

#define vld2q_dup_s16(__p0) __extension__ ({
  int16x8x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 33);
  __ret;
})

macrovld2_dup_u8

#define vld2_dup_u8(__p0) __extension__ ({
  uint8x8x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 16);
  __ret;
})

macrovld2_dup_u32

#define vld2_dup_u32(__p0) __extension__ ({
  uint32x2x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 18);
  __ret;
})

macrovld2_dup_u64

#define vld2_dup_u64(__p0) __extension__ ({
  uint64x1x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 19);
  __ret;
})

macrovld2_dup_u16

#define vld2_dup_u16(__p0) __extension__ ({
  uint16x4x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 17);
  __ret;
})

macrovld2_dup_s8

#define vld2_dup_s8(__p0) __extension__ ({
  int8x8x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 0);
  __ret;
})

macrovld2_dup_f32

#define vld2_dup_f32(__p0) __extension__ ({
  float32x2x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 9);
  __ret;
})

macrovld2_dup_s32

#define vld2_dup_s32(__p0) __extension__ ({
  int32x2x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 2);
  __ret;
})

macrovld2_dup_s64

#define vld2_dup_s64(__p0) __extension__ ({
  int64x1x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 3);
  __ret;
})

macrovld2_dup_s16

#define vld2_dup_s16(__p0) __extension__ ({
  int16x4x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 1);
  __ret;
})

macrovld2_lane_p8

#define vld2_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8x2_t __ret;
  poly8x8x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 4);
  __ret;
})

macrovld2_lane_p16

#define vld2_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4x2_t __ret;
  poly16x4x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 5);
  __ret;
})

macrovld2q_lane_p16

#define vld2q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8x2_t __ret;
  poly16x8x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 37);
  __ret;
})

macrovld2q_lane_u32

#define vld2q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4x2_t __ret;
  uint32x4x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 50);
  __ret;
})

macrovld2q_lane_u16

#define vld2q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8x2_t __ret;
  uint16x8x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 49);
  __ret;
})

macrovld2q_lane_f32

#define vld2q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4x2_t __ret;
  float32x4x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 41);
  __ret;
})

macrovld2q_lane_s32

#define vld2q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4x2_t __ret;
  int32x4x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 34);
  __ret;
})

macrovld2q_lane_s16

#define vld2q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8x2_t __ret;
  int16x8x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 33);
  __ret;
})

macrovld2_lane_u8

#define vld2_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8x2_t __ret;
  uint8x8x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 16);
  __ret;
})

macrovld2_lane_u32

#define vld2_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2x2_t __ret;
  uint32x2x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 18);
  __ret;
})

macrovld2_lane_u16

#define vld2_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4x2_t __ret;
  uint16x4x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 17);
  __ret;
})

macrovld2_lane_s8

#define vld2_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8x2_t __ret;
  int8x8x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 0);
  __ret;
})

macrovld2_lane_f32

#define vld2_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2x2_t __ret;
  float32x2x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 9);
  __ret;
})

macrovld2_lane_s32

#define vld2_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2x2_t __ret;
  int32x2x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 2);
  __ret;
})

macrovld2_lane_s16

#define vld2_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4x2_t __ret;
  int16x4x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 1);
  __ret;
})

macrovld3_p8

#define vld3_p8(__p0) __extension__ ({
  poly8x8x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 4);
  __ret;
})

macrovld3_p16

#define vld3_p16(__p0) __extension__ ({
  poly16x4x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 5);
  __ret;
})

macrovld3q_p8

#define vld3q_p8(__p0) __extension__ ({
  poly8x16x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 36);
  __ret;
})

macrovld3q_p16

#define vld3q_p16(__p0) __extension__ ({
  poly16x8x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 37);
  __ret;
})

macrovld3q_u8

#define vld3q_u8(__p0) __extension__ ({
  uint8x16x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 48);
  __ret;
})

macrovld3q_u32

#define vld3q_u32(__p0) __extension__ ({
  uint32x4x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 50);
  __ret;
})

macrovld3q_u16

#define vld3q_u16(__p0) __extension__ ({
  uint16x8x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 49);
  __ret;
})

macrovld3q_s8

#define vld3q_s8(__p0) __extension__ ({
  int8x16x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 32);
  __ret;
})

macrovld3q_f32

#define vld3q_f32(__p0) __extension__ ({
  float32x4x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 41);
  __ret;
})

macrovld3q_s32

#define vld3q_s32(__p0) __extension__ ({
  int32x4x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 34);
  __ret;
})

macrovld3q_s16

#define vld3q_s16(__p0) __extension__ ({
  int16x8x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 33);
  __ret;
})

macrovld3_u8

#define vld3_u8(__p0) __extension__ ({
  uint8x8x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 16);
  __ret;
})

macrovld3_u32

#define vld3_u32(__p0) __extension__ ({
  uint32x2x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 18);
  __ret;
})

macrovld3_u64

#define vld3_u64(__p0) __extension__ ({
  uint64x1x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 19);
  __ret;
})

macrovld3_u16

#define vld3_u16(__p0) __extension__ ({
  uint16x4x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 17);
  __ret;
})

macrovld3_s8

#define vld3_s8(__p0) __extension__ ({
  int8x8x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 0);
  __ret;
})

macrovld3_f32

#define vld3_f32(__p0) __extension__ ({
  float32x2x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 9);
  __ret;
})

macrovld3_s32

#define vld3_s32(__p0) __extension__ ({
  int32x2x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 2);
  __ret;
})

macrovld3_s64

#define vld3_s64(__p0) __extension__ ({
  int64x1x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 3);
  __ret;
})

macrovld3_s16

#define vld3_s16(__p0) __extension__ ({
  int16x4x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 1);
  __ret;
})

macrovld3_dup_p8

#define vld3_dup_p8(__p0) __extension__ ({
  poly8x8x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 4);
  __ret;
})

macrovld3_dup_p16

#define vld3_dup_p16(__p0) __extension__ ({
  poly16x4x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 5);
  __ret;
})

macrovld3q_dup_p8

#define vld3q_dup_p8(__p0) __extension__ ({
  poly8x16x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 36);
  __ret;
})

macrovld3q_dup_p16

#define vld3q_dup_p16(__p0) __extension__ ({
  poly16x8x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 37);
  __ret;
})

macrovld3q_dup_u8

#define vld3q_dup_u8(__p0) __extension__ ({
  uint8x16x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 48);
  __ret;
})

macrovld3q_dup_u32

#define vld3q_dup_u32(__p0) __extension__ ({
  uint32x4x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 50);
  __ret;
})

macrovld3q_dup_u64

#define vld3q_dup_u64(__p0) __extension__ ({
  uint64x2x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 51);
  __ret;
})

macrovld3q_dup_u16

#define vld3q_dup_u16(__p0) __extension__ ({
  uint16x8x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 49);
  __ret;
})

macrovld3q_dup_s8

#define vld3q_dup_s8(__p0) __extension__ ({
  int8x16x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 32);
  __ret;
})

macrovld3q_dup_f32

#define vld3q_dup_f32(__p0) __extension__ ({
  float32x4x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 41);
  __ret;
})

macrovld3q_dup_s32

#define vld3q_dup_s32(__p0) __extension__ ({
  int32x4x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 34);
  __ret;
})

macrovld3q_dup_s64

#define vld3q_dup_s64(__p0) __extension__ ({
  int64x2x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 35);
  __ret;
})

macrovld3q_dup_s16

#define vld3q_dup_s16(__p0) __extension__ ({
  int16x8x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 33);
  __ret;
})

macrovld3_dup_u8

#define vld3_dup_u8(__p0) __extension__ ({
  uint8x8x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 16);
  __ret;
})

macrovld3_dup_u32

#define vld3_dup_u32(__p0) __extension__ ({
  uint32x2x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 18);
  __ret;
})

macrovld3_dup_u64

#define vld3_dup_u64(__p0) __extension__ ({
  uint64x1x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 19);
  __ret;
})

macrovld3_dup_u16

#define vld3_dup_u16(__p0) __extension__ ({
  uint16x4x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 17);
  __ret;
})

macrovld3_dup_s8

#define vld3_dup_s8(__p0) __extension__ ({
  int8x8x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 0);
  __ret;
})

macrovld3_dup_f32

#define vld3_dup_f32(__p0) __extension__ ({
  float32x2x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 9);
  __ret;
})

macrovld3_dup_s32

#define vld3_dup_s32(__p0) __extension__ ({
  int32x2x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 2);
  __ret;
})

macrovld3_dup_s64

#define vld3_dup_s64(__p0) __extension__ ({
  int64x1x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 3);
  __ret;
})

macrovld3_dup_s16

#define vld3_dup_s16(__p0) __extension__ ({
  int16x4x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 1);
  __ret;
})

macrovld3_lane_p8

#define vld3_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8x3_t __ret;
  poly8x8x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 4);
  __ret;
})

macrovld3_lane_p16

#define vld3_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4x3_t __ret;
  poly16x4x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 5);
  __ret;
})

macrovld3q_lane_p16

#define vld3q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8x3_t __ret;
  poly16x8x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 37);
  __ret;
})

macrovld3q_lane_u32

#define vld3q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4x3_t __ret;
  uint32x4x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 50);
  __ret;
})

macrovld3q_lane_u16

#define vld3q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8x3_t __ret;
  uint16x8x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 49);
  __ret;
})

macrovld3q_lane_f32

#define vld3q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4x3_t __ret;
  float32x4x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 41);
  __ret;
})

macrovld3q_lane_s32

#define vld3q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4x3_t __ret;
  int32x4x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 34);
  __ret;
})

macrovld3q_lane_s16

#define vld3q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8x3_t __ret;
  int16x8x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 33);
  __ret;
})

macrovld3_lane_u8

#define vld3_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8x3_t __ret;
  uint8x8x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 16);
  __ret;
})

macrovld3_lane_u32

#define vld3_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2x3_t __ret;
  uint32x2x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 18);
  __ret;
})

macrovld3_lane_u16

#define vld3_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4x3_t __ret;
  uint16x4x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 17);
  __ret;
})

macrovld3_lane_s8

#define vld3_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8x3_t __ret;
  int8x8x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 0);
  __ret;
})

macrovld3_lane_f32

#define vld3_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2x3_t __ret;
  float32x2x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 9);
  __ret;
})

macrovld3_lane_s32

#define vld3_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2x3_t __ret;
  int32x2x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 2);
  __ret;
})

macrovld3_lane_s16

#define vld3_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4x3_t __ret;
  int16x4x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 1);
  __ret;
})

macrovld4_p8

#define vld4_p8(__p0) __extension__ ({
  poly8x8x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 4);
  __ret;
})

macrovld4_p16

#define vld4_p16(__p0) __extension__ ({
  poly16x4x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 5);
  __ret;
})

macrovld4q_p8

#define vld4q_p8(__p0) __extension__ ({
  poly8x16x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 36);
  __ret;
})

macrovld4q_p16

#define vld4q_p16(__p0) __extension__ ({
  poly16x8x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 37);
  __ret;
})

macrovld4q_u8

#define vld4q_u8(__p0) __extension__ ({
  uint8x16x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 48);
  __ret;
})

macrovld4q_u32

#define vld4q_u32(__p0) __extension__ ({
  uint32x4x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 50);
  __ret;
})

macrovld4q_u16

#define vld4q_u16(__p0) __extension__ ({
  uint16x8x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 49);
  __ret;
})

macrovld4q_s8

#define vld4q_s8(__p0) __extension__ ({
  int8x16x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 32);
  __ret;
})

macrovld4q_f32

#define vld4q_f32(__p0) __extension__ ({
  float32x4x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 41);
  __ret;
})

macrovld4q_s32

#define vld4q_s32(__p0) __extension__ ({
  int32x4x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 34);
  __ret;
})

macrovld4q_s16

#define vld4q_s16(__p0) __extension__ ({
  int16x8x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 33);
  __ret;
})

macrovld4_u8

#define vld4_u8(__p0) __extension__ ({
  uint8x8x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 16);
  __ret;
})

macrovld4_u32

#define vld4_u32(__p0) __extension__ ({
  uint32x2x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 18);
  __ret;
})

macrovld4_u64

#define vld4_u64(__p0) __extension__ ({
  uint64x1x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 19);
  __ret;
})

macrovld4_u16

#define vld4_u16(__p0) __extension__ ({
  uint16x4x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 17);
  __ret;
})

macrovld4_s8

#define vld4_s8(__p0) __extension__ ({
  int8x8x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 0);
  __ret;
})

macrovld4_f32

#define vld4_f32(__p0) __extension__ ({
  float32x2x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 9);
  __ret;
})

macrovld4_s32

#define vld4_s32(__p0) __extension__ ({
  int32x2x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 2);
  __ret;
})

macrovld4_s64

#define vld4_s64(__p0) __extension__ ({
  int64x1x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 3);
  __ret;
})

macrovld4_s16

#define vld4_s16(__p0) __extension__ ({
  int16x4x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 1);
  __ret;
})

macrovld4_dup_p8

#define vld4_dup_p8(__p0) __extension__ ({
  poly8x8x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 4);
  __ret;
})

macrovld4_dup_p16

#define vld4_dup_p16(__p0) __extension__ ({
  poly16x4x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 5);
  __ret;
})

macrovld4q_dup_p8

#define vld4q_dup_p8(__p0) __extension__ ({
  poly8x16x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 36);
  __ret;
})

macrovld4q_dup_p16

#define vld4q_dup_p16(__p0) __extension__ ({
  poly16x8x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 37);
  __ret;
})

macrovld4q_dup_u8

#define vld4q_dup_u8(__p0) __extension__ ({
  uint8x16x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 48);
  __ret;
})

macrovld4q_dup_u32

#define vld4q_dup_u32(__p0) __extension__ ({
  uint32x4x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 50);
  __ret;
})

macrovld4q_dup_u64

#define vld4q_dup_u64(__p0) __extension__ ({
  uint64x2x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 51);
  __ret;
})

macrovld4q_dup_u16

#define vld4q_dup_u16(__p0) __extension__ ({
  uint16x8x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 49);
  __ret;
})

macrovld4q_dup_s8

#define vld4q_dup_s8(__p0) __extension__ ({
  int8x16x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 32);
  __ret;
})

macrovld4q_dup_f32

#define vld4q_dup_f32(__p0) __extension__ ({
  float32x4x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 41);
  __ret;
})

macrovld4q_dup_s32

#define vld4q_dup_s32(__p0) __extension__ ({
  int32x4x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 34);
  __ret;
})

macrovld4q_dup_s64

#define vld4q_dup_s64(__p0) __extension__ ({
  int64x2x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 35);
  __ret;
})

macrovld4q_dup_s16

#define vld4q_dup_s16(__p0) __extension__ ({
  int16x8x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 33);
  __ret;
})

macrovld4_dup_u8

#define vld4_dup_u8(__p0) __extension__ ({
  uint8x8x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 16);
  __ret;
})

macrovld4_dup_u32

#define vld4_dup_u32(__p0) __extension__ ({
  uint32x2x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 18);
  __ret;
})

macrovld4_dup_u64

#define vld4_dup_u64(__p0) __extension__ ({
  uint64x1x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 19);
  __ret;
})

macrovld4_dup_u16

#define vld4_dup_u16(__p0) __extension__ ({
  uint16x4x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 17);
  __ret;
})

macrovld4_dup_s8

#define vld4_dup_s8(__p0) __extension__ ({
  int8x8x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 0);
  __ret;
})

macrovld4_dup_f32

#define vld4_dup_f32(__p0) __extension__ ({
  float32x2x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 9);
  __ret;
})

macrovld4_dup_s32

#define vld4_dup_s32(__p0) __extension__ ({
  int32x2x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 2);
  __ret;
})

macrovld4_dup_s64

#define vld4_dup_s64(__p0) __extension__ ({
  int64x1x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 3);
  __ret;
})

macrovld4_dup_s16

#define vld4_dup_s16(__p0) __extension__ ({
  int16x4x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 1);
  __ret;
})

macrovld4_lane_p8

#define vld4_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8x4_t __ret;
  poly8x8x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 4);
  __ret;
})

macrovld4_lane_p16

#define vld4_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4x4_t __ret;
  poly16x4x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 5);
  __ret;
})

macrovld4q_lane_p16

#define vld4q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8x4_t __ret;
  poly16x8x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 37);
  __ret;
})

macrovld4q_lane_u32

#define vld4q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4x4_t __ret;
  uint32x4x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 50);
  __ret;
})

macrovld4q_lane_u16

#define vld4q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8x4_t __ret;
  uint16x8x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 49);
  __ret;
})

macrovld4q_lane_f32

#define vld4q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4x4_t __ret;
  float32x4x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 41);
  __ret;
})

macrovld4q_lane_s32

#define vld4q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4x4_t __ret;
  int32x4x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 34);
  __ret;
})

macrovld4q_lane_s16

#define vld4q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8x4_t __ret;
  int16x8x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 33);
  __ret;
})

macrovld4_lane_u8

#define vld4_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8x4_t __ret;
  uint8x8x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 16);
  __ret;
})

macrovld4_lane_u32

#define vld4_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2x4_t __ret;
  uint32x2x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 18);
  __ret;
})

macrovld4_lane_u16

#define vld4_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4x4_t __ret;
  uint16x4x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 17);
  __ret;
})

macrovld4_lane_s8

#define vld4_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8x4_t __ret;
  int8x8x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 0);
  __ret;
})

macrovld4_lane_f32

#define vld4_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2x4_t __ret;
  float32x2x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 9);
  __ret;
})

macrovld4_lane_s32

#define vld4_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2x4_t __ret;
  int32x2x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 2);
  __ret;
})

macrovld4_lane_s16

#define vld4_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4x4_t __ret;
  int16x4x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 1);
  __ret;
})

macrovst1_p8

#define vst1_p8(__p0, __p1) __extension__ ({
  poly8x8_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 4);
})

macrovst1_p16

#define vst1_p16(__p0, __p1) __extension__ ({
  poly16x4_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 5);
})

macrovst1q_p8

#define vst1q_p8(__p0, __p1) __extension__ ({
  poly8x16_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 36);
})

macrovst1q_p16

#define vst1q_p16(__p0, __p1) __extension__ ({
  poly16x8_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 37);
})

macrovst1q_u8

#define vst1q_u8(__p0, __p1) __extension__ ({
  uint8x16_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 48);
})

macrovst1q_u32

#define vst1q_u32(__p0, __p1) __extension__ ({
  uint32x4_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 50);
})

macrovst1q_u64

#define vst1q_u64(__p0, __p1) __extension__ ({
  uint64x2_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 51);
})

macrovst1q_u16

#define vst1q_u16(__p0, __p1) __extension__ ({
  uint16x8_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 49);
})

macrovst1q_s8

#define vst1q_s8(__p0, __p1) __extension__ ({
  int8x16_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 32);
})

macrovst1q_f32

#define vst1q_f32(__p0, __p1) __extension__ ({
  float32x4_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 41);
})

macrovst1q_s32

#define vst1q_s32(__p0, __p1) __extension__ ({
  int32x4_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 34);
})

macrovst1q_s64

#define vst1q_s64(__p0, __p1) __extension__ ({
  int64x2_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 35);
})

macrovst1q_s16

#define vst1q_s16(__p0, __p1) __extension__ ({
  int16x8_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 33);
})

macrovst1_u8

#define vst1_u8(__p0, __p1) __extension__ ({
  uint8x8_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 16);
})

macrovst1_u32

#define vst1_u32(__p0, __p1) __extension__ ({
  uint32x2_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 18);
})

macrovst1_u64

#define vst1_u64(__p0, __p1) __extension__ ({
  uint64x1_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 19);
})

macrovst1_u16

#define vst1_u16(__p0, __p1) __extension__ ({
  uint16x4_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 17);
})

macrovst1_s8

#define vst1_s8(__p0, __p1) __extension__ ({
  int8x8_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 0);
})

macrovst1_f32

#define vst1_f32(__p0, __p1) __extension__ ({
  float32x2_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 9);
})

macrovst1_s32

#define vst1_s32(__p0, __p1) __extension__ ({
  int32x2_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 2);
})

macrovst1_s64

#define vst1_s64(__p0, __p1) __extension__ ({
  int64x1_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 3);
})

macrovst1_s16

#define vst1_s16(__p0, __p1) __extension__ ({
  int16x4_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 1);
})

macrovst1_lane_p8

#define vst1_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 4);
})

macrovst1_lane_p16

#define vst1_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 5);
})

macrovst1q_lane_p8

#define vst1q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 36);
})

macrovst1q_lane_p16

#define vst1q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 37);
})

macrovst1q_lane_u8

#define vst1q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 48);
})

macrovst1q_lane_u32

#define vst1q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 50);
})

macrovst1q_lane_u64

#define vst1q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 51);
})

macrovst1q_lane_u16

#define vst1q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 49);
})

macrovst1q_lane_s8

#define vst1q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 32);
})

macrovst1q_lane_f32

#define vst1q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 41);
})

macrovst1q_lane_s32

#define vst1q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 34);
})

macrovst1q_lane_s64

#define vst1q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 35);
})

macrovst1q_lane_s16

#define vst1q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 33);
})

macrovst1_lane_u8

#define vst1_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 16);
})

macrovst1_lane_u32

#define vst1_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 18);
})

macrovst1_lane_u64

#define vst1_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 19);
})

macrovst1_lane_u16

#define vst1_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 17);
})

macrovst1_lane_s8

#define vst1_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 0);
})

macrovst1_lane_f32

#define vst1_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 9);
})

macrovst1_lane_s32

#define vst1_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 2);
})

macrovst1_lane_s64

#define vst1_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 3);
})

macrovst1_lane_s16

#define vst1_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 1);
})

macrovst1_p8_x2

#define vst1_p8_x2(__p0, __p1) __extension__ ({
  poly8x8x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 4);
})

macrovst1_p16_x2

#define vst1_p16_x2(__p0, __p1) __extension__ ({
  poly16x4x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 5);
})

macrovst1q_p8_x2

#define vst1q_p8_x2(__p0, __p1) __extension__ ({
  poly8x16x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 36);
})

macrovst1q_p16_x2

#define vst1q_p16_x2(__p0, __p1) __extension__ ({
  poly16x8x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 37);
})

macrovst1q_u8_x2

#define vst1q_u8_x2(__p0, __p1) __extension__ ({
  uint8x16x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 48);
})

macrovst1q_u32_x2

#define vst1q_u32_x2(__p0, __p1) __extension__ ({
  uint32x4x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 50);
})

macrovst1q_u64_x2

#define vst1q_u64_x2(__p0, __p1) __extension__ ({
  uint64x2x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 51);
})

macrovst1q_u16_x2

#define vst1q_u16_x2(__p0, __p1) __extension__ ({
  uint16x8x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 49);
})

macrovst1q_s8_x2

#define vst1q_s8_x2(__p0, __p1) __extension__ ({
  int8x16x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 32);
})

macrovst1q_f32_x2

#define vst1q_f32_x2(__p0, __p1) __extension__ ({
  float32x4x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 41);
})

macrovst1q_s32_x2

#define vst1q_s32_x2(__p0, __p1) __extension__ ({
  int32x4x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 34);
})

macrovst1q_s64_x2

#define vst1q_s64_x2(__p0, __p1) __extension__ ({
  int64x2x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 35);
})

macrovst1q_s16_x2

#define vst1q_s16_x2(__p0, __p1) __extension__ ({
  int16x8x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 33);
})

macrovst1_u8_x2

#define vst1_u8_x2(__p0, __p1) __extension__ ({
  uint8x8x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 16);
})

macrovst1_u32_x2

#define vst1_u32_x2(__p0, __p1) __extension__ ({
  uint32x2x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 18);
})

macrovst1_u64_x2

#define vst1_u64_x2(__p0, __p1) __extension__ ({
  uint64x1x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 19);
})

macrovst1_u16_x2

#define vst1_u16_x2(__p0, __p1) __extension__ ({
  uint16x4x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 17);
})

macrovst1_s8_x2

#define vst1_s8_x2(__p0, __p1) __extension__ ({
  int8x8x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 0);
})

macrovst1_f32_x2

#define vst1_f32_x2(__p0, __p1) __extension__ ({
  float32x2x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 9);
})

macrovst1_s32_x2

#define vst1_s32_x2(__p0, __p1) __extension__ ({
  int32x2x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 2);
})

macrovst1_s64_x2

#define vst1_s64_x2(__p0, __p1) __extension__ ({
  int64x1x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 3);
})

macrovst1_s16_x2

#define vst1_s16_x2(__p0, __p1) __extension__ ({
  int16x4x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 1);
})

macrovst1_p8_x3

#define vst1_p8_x3(__p0, __p1) __extension__ ({
  poly8x8x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 4);
})

macrovst1_p16_x3

#define vst1_p16_x3(__p0, __p1) __extension__ ({
  poly16x4x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 5);
})

macrovst1q_p8_x3

#define vst1q_p8_x3(__p0, __p1) __extension__ ({
  poly8x16x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 36);
})

macrovst1q_p16_x3

#define vst1q_p16_x3(__p0, __p1) __extension__ ({
  poly16x8x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 37);
})

macrovst1q_u8_x3

#define vst1q_u8_x3(__p0, __p1) __extension__ ({
  uint8x16x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 48);
})

macrovst1q_u32_x3

#define vst1q_u32_x3(__p0, __p1) __extension__ ({
  uint32x4x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 50);
})

macrovst1q_u64_x3

#define vst1q_u64_x3(__p0, __p1) __extension__ ({
  uint64x2x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 51);
})

macrovst1q_u16_x3

#define vst1q_u16_x3(__p0, __p1) __extension__ ({
  uint16x8x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 49);
})

macrovst1q_s8_x3

#define vst1q_s8_x3(__p0, __p1) __extension__ ({
  int8x16x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 32);
})

macrovst1q_f32_x3

#define vst1q_f32_x3(__p0, __p1) __extension__ ({
  float32x4x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 41);
})

macrovst1q_s32_x3

#define vst1q_s32_x3(__p0, __p1) __extension__ ({
  int32x4x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 34);
})

macrovst1q_s64_x3

#define vst1q_s64_x3(__p0, __p1) __extension__ ({
  int64x2x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 35);
})

macrovst1q_s16_x3

#define vst1q_s16_x3(__p0, __p1) __extension__ ({
  int16x8x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 33);
})

macrovst1_u8_x3

#define vst1_u8_x3(__p0, __p1) __extension__ ({
  uint8x8x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 16);
})

macrovst1_u32_x3

#define vst1_u32_x3(__p0, __p1) __extension__ ({
  uint32x2x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 18);
})

macrovst1_u64_x3

#define vst1_u64_x3(__p0, __p1) __extension__ ({
  uint64x1x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 19);
})

macrovst1_u16_x3

#define vst1_u16_x3(__p0, __p1) __extension__ ({
  uint16x4x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 17);
})

macrovst1_s8_x3

#define vst1_s8_x3(__p0, __p1) __extension__ ({
  int8x8x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 0);
})

macrovst1_f32_x3

#define vst1_f32_x3(__p0, __p1) __extension__ ({
  float32x2x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 9);
})

macrovst1_s32_x3

#define vst1_s32_x3(__p0, __p1) __extension__ ({
  int32x2x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 2);
})

macrovst1_s64_x3

#define vst1_s64_x3(__p0, __p1) __extension__ ({
  int64x1x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 3);
})

macrovst1_s16_x3

#define vst1_s16_x3(__p0, __p1) __extension__ ({
  int16x4x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 1);
})

macrovst1_p8_x4

#define vst1_p8_x4(__p0, __p1) __extension__ ({
  poly8x8x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 4);
})

macrovst1_p16_x4

#define vst1_p16_x4(__p0, __p1) __extension__ ({
  poly16x4x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 5);
})

macrovst1q_p8_x4

#define vst1q_p8_x4(__p0, __p1) __extension__ ({
  poly8x16x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 36);
})

macrovst1q_p16_x4

#define vst1q_p16_x4(__p0, __p1) __extension__ ({
  poly16x8x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 37);
})

macrovst1q_u8_x4

#define vst1q_u8_x4(__p0, __p1) __extension__ ({
  uint8x16x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 48);
})

macrovst1q_u32_x4

#define vst1q_u32_x4(__p0, __p1) __extension__ ({
  uint32x4x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 50);
})

macrovst1q_u64_x4

#define vst1q_u64_x4(__p0, __p1) __extension__ ({
  uint64x2x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 51);
})

macrovst1q_u16_x4

#define vst1q_u16_x4(__p0, __p1) __extension__ ({
  uint16x8x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 49);
})

macrovst1q_s8_x4

#define vst1q_s8_x4(__p0, __p1) __extension__ ({
  int8x16x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 32);
})

macrovst1q_f32_x4

#define vst1q_f32_x4(__p0, __p1) __extension__ ({
  float32x4x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 41);
})

macrovst1q_s32_x4

#define vst1q_s32_x4(__p0, __p1) __extension__ ({
  int32x4x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 34);
})

macrovst1q_s64_x4

#define vst1q_s64_x4(__p0, __p1) __extension__ ({
  int64x2x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 35);
})

macrovst1q_s16_x4

#define vst1q_s16_x4(__p0, __p1) __extension__ ({
  int16x8x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 33);
})

macrovst1_u8_x4

#define vst1_u8_x4(__p0, __p1) __extension__ ({
  uint8x8x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 16);
})

macrovst1_u32_x4

#define vst1_u32_x4(__p0, __p1) __extension__ ({
  uint32x2x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 18);
})

macrovst1_u64_x4

#define vst1_u64_x4(__p0, __p1) __extension__ ({
  uint64x1x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 19);
})

macrovst1_u16_x4

#define vst1_u16_x4(__p0, __p1) __extension__ ({
  uint16x4x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 17);
})

macrovst1_s8_x4

#define vst1_s8_x4(__p0, __p1) __extension__ ({
  int8x8x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 0);
})

macrovst1_f32_x4

#define vst1_f32_x4(__p0, __p1) __extension__ ({
  float32x2x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 9);
})

macrovst1_s32_x4

#define vst1_s32_x4(__p0, __p1) __extension__ ({
  int32x2x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 2);
})

macrovst1_s64_x4

#define vst1_s64_x4(__p0, __p1) __extension__ ({
  int64x1x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 3);
})

macrovst1_s16_x4

#define vst1_s16_x4(__p0, __p1) __extension__ ({
  int16x4x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 1);
})

macrovst2_p8

#define vst2_p8(__p0, __p1) __extension__ ({
  poly8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 4);
})

macrovst2_p16

#define vst2_p16(__p0, __p1) __extension__ ({
  poly16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 5);
})

macrovst2q_p8

#define vst2q_p8(__p0, __p1) __extension__ ({
  poly8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 36);
})

macrovst2q_p16

#define vst2q_p16(__p0, __p1) __extension__ ({
  poly16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 37);
})

macrovst2q_u8

#define vst2q_u8(__p0, __p1) __extension__ ({
  uint8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 48);
})

macrovst2q_u32

#define vst2q_u32(__p0, __p1) __extension__ ({
  uint32x4x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 50);
})

macrovst2q_u16

#define vst2q_u16(__p0, __p1) __extension__ ({
  uint16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 49);
})

macrovst2q_s8

#define vst2q_s8(__p0, __p1) __extension__ ({
  int8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 32);
})

macrovst2q_f32

#define vst2q_f32(__p0, __p1) __extension__ ({
  float32x4x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 41);
})

macrovst2q_s32

#define vst2q_s32(__p0, __p1) __extension__ ({
  int32x4x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 34);
})

macrovst2q_s16

#define vst2q_s16(__p0, __p1) __extension__ ({
  int16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 33);
})

macrovst2_u8

#define vst2_u8(__p0, __p1) __extension__ ({
  uint8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 16);
})

macrovst2_u32

#define vst2_u32(__p0, __p1) __extension__ ({
  uint32x2x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 18);
})

macrovst2_u64

#define vst2_u64(__p0, __p1) __extension__ ({
  uint64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 19);
})

macrovst2_u16

#define vst2_u16(__p0, __p1) __extension__ ({
  uint16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 17);
})

macrovst2_s8

#define vst2_s8(__p0, __p1) __extension__ ({
  int8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 0);
})

macrovst2_f32

#define vst2_f32(__p0, __p1) __extension__ ({
  float32x2x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 9);
})

macrovst2_s32

#define vst2_s32(__p0, __p1) __extension__ ({
  int32x2x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 2);
})

macrovst2_s64

#define vst2_s64(__p0, __p1) __extension__ ({
  int64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 3);
})

macrovst2_s16

#define vst2_s16(__p0, __p1) __extension__ ({
  int16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 1);
})

macrovst2_lane_p8

#define vst2_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 4);
})

macrovst2_lane_p16

#define vst2_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 5);
})

macrovst2q_lane_p16

#define vst2q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 37);
})

macrovst2q_lane_u32

#define vst2q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 50);
})

macrovst2q_lane_u16

#define vst2q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 49);
})

macrovst2q_lane_f32

#define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 41);
})

macrovst2q_lane_s32

#define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 34);
})

macrovst2q_lane_s16

#define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 33);
})

macrovst2_lane_u8

#define vst2_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 16);
})

macrovst2_lane_u32

#define vst2_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 18);
})

macrovst2_lane_u16

#define vst2_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 17);
})

macrovst2_lane_s8

#define vst2_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 0);
})

macrovst2_lane_f32

#define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 9);
})

macrovst2_lane_s32

#define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 2);
})

macrovst2_lane_s16

#define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 1);
})

macrovst3_p8

#define vst3_p8(__p0, __p1) __extension__ ({
  poly8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 4);
})

macrovst3_p16

#define vst3_p16(__p0, __p1) __extension__ ({
  poly16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 5);
})

macrovst3q_p8

#define vst3q_p8(__p0, __p1) __extension__ ({
  poly8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 36);
})

macrovst3q_p16

#define vst3q_p16(__p0, __p1) __extension__ ({
  poly16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 37);
})

macrovst3q_u8

#define vst3q_u8(__p0, __p1) __extension__ ({
  uint8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 48);
})

macrovst3q_u32

#define vst3q_u32(__p0, __p1) __extension__ ({
  uint32x4x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 50);
})

macrovst3q_u16

#define vst3q_u16(__p0, __p1) __extension__ ({
  uint16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 49);
})

macrovst3q_s8

#define vst3q_s8(__p0, __p1) __extension__ ({
  int8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 32);
})

macrovst3q_f32

#define vst3q_f32(__p0, __p1) __extension__ ({
  float32x4x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 41);
})

macrovst3q_s32

#define vst3q_s32(__p0, __p1) __extension__ ({
  int32x4x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 34);
})

macrovst3q_s16

#define vst3q_s16(__p0, __p1) __extension__ ({
  int16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 33);
})

macrovst3_u8

#define vst3_u8(__p0, __p1) __extension__ ({
  uint8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 16);
})

macrovst3_u32

#define vst3_u32(__p0, __p1) __extension__ ({
  uint32x2x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 18);
})

macrovst3_u64

#define vst3_u64(__p0, __p1) __extension__ ({
  uint64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 19);
})

macrovst3_u16

#define vst3_u16(__p0, __p1) __extension__ ({
  uint16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 17);
})

macrovst3_s8

#define vst3_s8(__p0, __p1) __extension__ ({
  int8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 0);
})

macrovst3_f32

#define vst3_f32(__p0, __p1) __extension__ ({
  float32x2x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 9);
})

macrovst3_s32

#define vst3_s32(__p0, __p1) __extension__ ({
  int32x2x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 2);
})

macrovst3_s64

#define vst3_s64(__p0, __p1) __extension__ ({
  int64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 3);
})

macrovst3_s16

#define vst3_s16(__p0, __p1) __extension__ ({
  int16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 1);
})

macrovst3_lane_p8

#define vst3_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 4);
})

macrovst3_lane_p16

#define vst3_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 5);
})

macrovst3q_lane_p16

#define vst3q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 37);
})

macrovst3q_lane_u32

#define vst3q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 50);
})

macrovst3q_lane_u16

#define vst3q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 49);
})

macrovst3q_lane_f32

#define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 41);
})

macrovst3q_lane_s32

#define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 34);
})

macrovst3q_lane_s16

#define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 33);
})

macrovst3_lane_u8

#define vst3_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 16);
})

macrovst3_lane_u32

#define vst3_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 18);
})

macrovst3_lane_u16

#define vst3_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 17);
})

macrovst3_lane_s8

#define vst3_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 0);
})

macrovst3_lane_f32

#define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 9);
})

macrovst3_lane_s32

#define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 2);
})

macrovst3_lane_s16

#define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 1);
})

macrovst4_p8

#define vst4_p8(__p0, __p1) __extension__ ({
  poly8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 4);
})

macrovst4_p16

#define vst4_p16(__p0, __p1) __extension__ ({
  poly16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 5);
})

macrovst4q_p8

#define vst4q_p8(__p0, __p1) __extension__ ({
  poly8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 36);
})

macrovst4q_p16

#define vst4q_p16(__p0, __p1) __extension__ ({
  poly16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 37);
})

macrovst4q_u8

#define vst4q_u8(__p0, __p1) __extension__ ({
  uint8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 48);
})

macrovst4q_u32

#define vst4q_u32(__p0, __p1) __extension__ ({
  uint32x4x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 50);
})

macrovst4q_u16

#define vst4q_u16(__p0, __p1) __extension__ ({
  uint16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 49);
})

macrovst4q_s8

#define vst4q_s8(__p0, __p1) __extension__ ({
  int8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 32);
})

macrovst4q_f32

#define vst4q_f32(__p0, __p1) __extension__ ({
  float32x4x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 41);
})

macrovst4q_s32

#define vst4q_s32(__p0, __p1) __extension__ ({
  int32x4x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 34);
})

macrovst4q_s16

#define vst4q_s16(__p0, __p1) __extension__ ({
  int16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 33);
})

macrovst4_u8

#define vst4_u8(__p0, __p1) __extension__ ({
  uint8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 16);
})

macrovst4_u32

#define vst4_u32(__p0, __p1) __extension__ ({
  uint32x2x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 18);
})

macrovst4_u64

#define vst4_u64(__p0, __p1) __extension__ ({
  uint64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 19);
})

macrovst4_u16

#define vst4_u16(__p0, __p1) __extension__ ({
  uint16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 17);
})

macrovst4_s8

#define vst4_s8(__p0, __p1) __extension__ ({
  int8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 0);
})

macrovst4_f32

#define vst4_f32(__p0, __p1) __extension__ ({
  float32x2x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 9);
})

macrovst4_s32

#define vst4_s32(__p0, __p1) __extension__ ({
  int32x2x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 2);
})

macrovst4_s64

#define vst4_s64(__p0, __p1) __extension__ ({
  int64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 3);
})

macrovst4_s16

#define vst4_s16(__p0, __p1) __extension__ ({
  int16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 1);
})

macrovst4_lane_p8

#define vst4_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 4);
})

macrovst4_lane_p16

#define vst4_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 5);
})

macrovst4q_lane_p16

#define vst4q_lane_p16(__p0, __p1, __p2) __extension__ ({
  poly16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 37);
})

macrovst4q_lane_u32

#define vst4q_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x4x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 50);
})

macrovst4q_lane_u16

#define vst4q_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 49);
})

macrovst4q_lane_f32

#define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x4x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 41);
})

macrovst4q_lane_s32

#define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x4x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 34);
})

macrovst4q_lane_s16

#define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 33);
})

macrovst4_lane_u8

#define vst4_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 16);
})

macrovst4_lane_u32

#define vst4_lane_u32(__p0, __p1, __p2) __extension__ ({
  uint32x2x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 18);
})

macrovst4_lane_u16

#define vst4_lane_u16(__p0, __p1, __p2) __extension__ ({
  uint16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 17);
})

macrovst4_lane_s8

#define vst4_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 0);
})

macrovst4_lane_f32

#define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({
  float32x2x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 9);
})

macrovst4_lane_s32

#define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({
  int32x2x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 2);
})

macrovst4_lane_s16

#define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({
  int16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 1);
})

macrovld1q_f16

#define vld1q_f16(__p0) __extension__ ({
  float16x8_t __ret;
  __ret = __builtin_bit_cast(float16x8_t, __builtin_neon_vld1q_v(__p0, 40));
  __ret;
})

macrovld1_f16

#define vld1_f16(__p0) __extension__ ({
  float16x4_t __ret;
  __ret = __builtin_bit_cast(float16x4_t, __builtin_neon_vld1_v(__p0, 8));
  __ret;
})

macrovld1q_dup_f16

#define vld1q_dup_f16(__p0) __extension__ ({
  float16x8_t __ret;
  __ret = __builtin_bit_cast(float16x8_t, __builtin_neon_vld1q_dup_v(__p0, 40));
  __ret;
})

macrovld1_dup_f16

#define vld1_dup_f16(__p0) __extension__ ({
  float16x4_t __ret;
  __ret = __builtin_bit_cast(float16x4_t, __builtin_neon_vld1_dup_v(__p0, 8));
  __ret;
})

macrovld1q_lane_f16

#define vld1q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8_t __ret;
  float16x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(float16x8_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 40));
  __ret;
})

macrovld1_lane_f16

#define vld1_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4_t __ret;
  float16x4_t __s1 = __p1;
  __ret = __builtin_bit_cast(float16x4_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 8));
  __ret;
})

macrovld1q_f16_x2

#define vld1q_f16_x2(__p0) __extension__ ({
  float16x8x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 40);
  __ret;
})

macrovld1_f16_x2

#define vld1_f16_x2(__p0) __extension__ ({
  float16x4x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 8);
  __ret;
})

macrovld1q_f16_x3

#define vld1q_f16_x3(__p0) __extension__ ({
  float16x8x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 40);
  __ret;
})

macrovld1_f16_x3

#define vld1_f16_x3(__p0) __extension__ ({
  float16x4x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 8);
  __ret;
})

macrovld1q_f16_x4

#define vld1q_f16_x4(__p0) __extension__ ({
  float16x8x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 40);
  __ret;
})

macrovld1_f16_x4

#define vld1_f16_x4(__p0) __extension__ ({
  float16x4x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 8);
  __ret;
})

macrovld2q_f16

#define vld2q_f16(__p0) __extension__ ({
  float16x8x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 40);
  __ret;
})

macrovld2_f16

#define vld2_f16(__p0) __extension__ ({
  float16x4x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 8);
  __ret;
})

macrovld2q_dup_f16

#define vld2q_dup_f16(__p0) __extension__ ({
  float16x8x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 40);
  __ret;
})

macrovld2_dup_f16

#define vld2_dup_f16(__p0) __extension__ ({
  float16x4x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 8);
  __ret;
})

macrovld2q_lane_f16

#define vld2q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8x2_t __ret;
  float16x8x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 40);
  __ret;
})

macrovld2_lane_f16

#define vld2_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4x2_t __ret;
  float16x4x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 8);
  __ret;
})

macrovld3q_f16

#define vld3q_f16(__p0) __extension__ ({
  float16x8x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 40);
  __ret;
})

macrovld3_f16

#define vld3_f16(__p0) __extension__ ({
  float16x4x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 8);
  __ret;
})

macrovld3q_dup_f16

#define vld3q_dup_f16(__p0) __extension__ ({
  float16x8x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 40);
  __ret;
})

macrovld3_dup_f16

#define vld3_dup_f16(__p0) __extension__ ({
  float16x4x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 8);
  __ret;
})

macrovld3q_lane_f16

#define vld3q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8x3_t __ret;
  float16x8x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 40);
  __ret;
})

macrovld3_lane_f16

#define vld3_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4x3_t __ret;
  float16x4x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 8);
  __ret;
})

macrovld4q_f16

#define vld4q_f16(__p0) __extension__ ({
  float16x8x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 40);
  __ret;
})

macrovld4_f16

#define vld4_f16(__p0) __extension__ ({
  float16x4x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 8);
  __ret;
})

macrovld4q_dup_f16

#define vld4q_dup_f16(__p0) __extension__ ({
  float16x8x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 40);
  __ret;
})

macrovld4_dup_f16

#define vld4_dup_f16(__p0) __extension__ ({
  float16x4x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 8);
  __ret;
})

macrovld4q_lane_f16

#define vld4q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8x4_t __ret;
  float16x8x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 40);
  __ret;
})

macrovld4_lane_f16

#define vld4_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4x4_t __ret;
  float16x4x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 8);
  __ret;
})

macrovst1q_f16

#define vst1q_f16(__p0, __p1) __extension__ ({
  float16x8_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 40);
})

macrovst1_f16

#define vst1_f16(__p0, __p1) __extension__ ({
  float16x4_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 8);
})

macrovst1q_lane_f16

#define vst1q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 40);
})

macrovst1_lane_f16

#define vst1_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 8);
})

macrovst1q_f16_x2

#define vst1q_f16_x2(__p0, __p1) __extension__ ({
  float16x8x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 40);
})

macrovst1_f16_x2

#define vst1_f16_x2(__p0, __p1) __extension__ ({
  float16x4x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 8);
})

macrovst1q_f16_x3

#define vst1q_f16_x3(__p0, __p1) __extension__ ({
  float16x8x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 40);
})

macrovst1_f16_x3

#define vst1_f16_x3(__p0, __p1) __extension__ ({
  float16x4x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 8);
})

macrovst1q_f16_x4

#define vst1q_f16_x4(__p0, __p1) __extension__ ({
  float16x8x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 40);
})

macrovst1_f16_x4

#define vst1_f16_x4(__p0, __p1) __extension__ ({
  float16x4x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 8);
})

macrovst2q_f16

#define vst2q_f16(__p0, __p1) __extension__ ({
  float16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 40);
})

macrovst2_f16

#define vst2_f16(__p0, __p1) __extension__ ({
  float16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 8);
})

macrovst2q_lane_f16

#define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 40);
})

macrovst2_lane_f16

#define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 8);
})

macrovst3q_f16

#define vst3q_f16(__p0, __p1) __extension__ ({
  float16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 40);
})

macrovst3_f16

#define vst3_f16(__p0, __p1) __extension__ ({
  float16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 8);
})

macrovst3q_lane_f16

#define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 40);
})

macrovst3_lane_f16

#define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 8);
})

macrovst4q_f16

#define vst4q_f16(__p0, __p1) __extension__ ({
  float16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 40);
})

macrovst4_f16

#define vst4_f16(__p0, __p1) __extension__ ({
  float16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 8);
})

macrovst4q_lane_f16

#define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x8x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 40);
})

macrovst4_lane_f16

#define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({
  float16x4x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 8);
})

macrovld1_p64

#define vld1_p64(__p0) __extension__ ({
  poly64x1_t __ret;
  __ret = __builtin_bit_cast(poly64x1_t, __builtin_neon_vld1_v(__p0, 6));
  __ret;
})

macrovld1q_p64

#define vld1q_p64(__p0) __extension__ ({
  poly64x2_t __ret;
  __ret = __builtin_bit_cast(poly64x2_t, __builtin_neon_vld1q_v(__p0, 38));
  __ret;
})

macrovld1q_f64

#define vld1q_f64(__p0) __extension__ ({
  float64x2_t __ret;
  __ret = __builtin_bit_cast(float64x2_t, __builtin_neon_vld1q_v(__p0, 42));
  __ret;
})

macrovld1q_mf8

#define vld1q_mf8(__p0) __extension__ ({
  mfloat8x16_t __ret;
  __ret = __builtin_bit_cast(mfloat8x16_t, __builtin_neon_vld1q_v(__p0, 44));
  __ret;
})

macrovld1_f64

#define vld1_f64(__p0) __extension__ ({
  float64x1_t __ret;
  __ret = __builtin_bit_cast(float64x1_t, __builtin_neon_vld1_v(__p0, 10));
  __ret;
})

macrovld1_mf8

#define vld1_mf8(__p0) __extension__ ({
  mfloat8x8_t __ret;
  __ret = __builtin_bit_cast(mfloat8x8_t, __builtin_neon_vld1_v(__p0, 12));
  __ret;
})

macrovld1_dup_p64

#define vld1_dup_p64(__p0) __extension__ ({
  poly64x1_t __ret;
  __ret = __builtin_bit_cast(poly64x1_t, __builtin_neon_vld1_dup_v(__p0, 6));
  __ret;
})

macrovld1q_dup_p64

#define vld1q_dup_p64(__p0) __extension__ ({
  poly64x2_t __ret;
  __ret = __builtin_bit_cast(poly64x2_t, __builtin_neon_vld1q_dup_v(__p0, 38));
  __ret;
})

macrovld1q_dup_f64

#define vld1q_dup_f64(__p0) __extension__ ({
  float64x2_t __ret;
  __ret = __builtin_bit_cast(float64x2_t, __builtin_neon_vld1q_dup_v(__p0, 42));
  __ret;
})

macrovld1q_dup_mf8

#define vld1q_dup_mf8(__p0) __extension__ ({
  mfloat8x16_t __ret;
  __ret = __builtin_bit_cast(mfloat8x16_t, __builtin_neon_vld1q_dup_v(__p0, 44));
  __ret;
})

macrovld1_dup_f64

#define vld1_dup_f64(__p0) __extension__ ({
  float64x1_t __ret;
  __ret = __builtin_bit_cast(float64x1_t, __builtin_neon_vld1_dup_v(__p0, 10));
  __ret;
})

macrovld1_dup_mf8

#define vld1_dup_mf8(__p0) __extension__ ({
  mfloat8x8_t __ret;
  __ret = __builtin_bit_cast(mfloat8x8_t, __builtin_neon_vld1_dup_v(__p0, 12));
  __ret;
})

macrovld1_lane_p64

#define vld1_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1_t __ret;
  poly64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly64x1_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 6));
  __ret;
})

macrovld1q_lane_p64

#define vld1q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2_t __ret;
  poly64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly64x2_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 38));
  __ret;
})

macrovld1q_lane_f64

#define vld1q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2_t __ret;
  float64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(float64x2_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 42));
  __ret;
})

macrovld1q_lane_mf8

#define vld1q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16_t __ret;
  mfloat8x16_t __s1 = __p1;
  __ret = __builtin_bit_cast(mfloat8x16_t, __builtin_neon_vld1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 44));
  __ret;
})

macrovld1_lane_f64

#define vld1_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1_t __ret;
  float64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(float64x1_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 10));
  __ret;
})

macrovld1_lane_mf8

#define vld1_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8_t __ret;
  mfloat8x8_t __s1 = __p1;
  __ret = __builtin_bit_cast(mfloat8x8_t, __builtin_neon_vld1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 12));
  __ret;
})

macrovld1_p64_x2

#define vld1_p64_x2(__p0) __extension__ ({
  poly64x1x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 6);
  __ret;
})

macrovld1q_p64_x2

#define vld1q_p64_x2(__p0) __extension__ ({
  poly64x2x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 38);
  __ret;
})

macrovld1q_f64_x2

#define vld1q_f64_x2(__p0) __extension__ ({
  float64x2x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 42);
  __ret;
})

macrovld1q_mf8_x2

#define vld1q_mf8_x2(__p0) __extension__ ({
  mfloat8x16x2_t __ret;
  __builtin_neon_vld1q_x2_v(&__ret, __p0, 44);
  __ret;
})

macrovld1_f64_x2

#define vld1_f64_x2(__p0) __extension__ ({
  float64x1x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 10);
  __ret;
})

macrovld1_mf8_x2

#define vld1_mf8_x2(__p0) __extension__ ({
  mfloat8x8x2_t __ret;
  __builtin_neon_vld1_x2_v(&__ret, __p0, 12);
  __ret;
})

macrovld1_p64_x3

#define vld1_p64_x3(__p0) __extension__ ({
  poly64x1x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 6);
  __ret;
})

macrovld1q_p64_x3

#define vld1q_p64_x3(__p0) __extension__ ({
  poly64x2x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 38);
  __ret;
})

macrovld1q_f64_x3

#define vld1q_f64_x3(__p0) __extension__ ({
  float64x2x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 42);
  __ret;
})

macrovld1q_mf8_x3

#define vld1q_mf8_x3(__p0) __extension__ ({
  mfloat8x16x3_t __ret;
  __builtin_neon_vld1q_x3_v(&__ret, __p0, 44);
  __ret;
})

macrovld1_f64_x3

#define vld1_f64_x3(__p0) __extension__ ({
  float64x1x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 10);
  __ret;
})

macrovld1_mf8_x3

#define vld1_mf8_x3(__p0) __extension__ ({
  mfloat8x8x3_t __ret;
  __builtin_neon_vld1_x3_v(&__ret, __p0, 12);
  __ret;
})

macrovld1_p64_x4

#define vld1_p64_x4(__p0) __extension__ ({
  poly64x1x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 6);
  __ret;
})

macrovld1q_p64_x4

#define vld1q_p64_x4(__p0) __extension__ ({
  poly64x2x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 38);
  __ret;
})

macrovld1q_f64_x4

#define vld1q_f64_x4(__p0) __extension__ ({
  float64x2x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 42);
  __ret;
})

macrovld1q_mf8_x4

#define vld1q_mf8_x4(__p0) __extension__ ({
  mfloat8x16x4_t __ret;
  __builtin_neon_vld1q_x4_v(&__ret, __p0, 44);
  __ret;
})

macrovld1_f64_x4

#define vld1_f64_x4(__p0) __extension__ ({
  float64x1x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 10);
  __ret;
})

macrovld1_mf8_x4

#define vld1_mf8_x4(__p0) __extension__ ({
  mfloat8x8x4_t __ret;
  __builtin_neon_vld1_x4_v(&__ret, __p0, 12);
  __ret;
})

macrovld2_p64

#define vld2_p64(__p0) __extension__ ({
  poly64x1x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 6);
  __ret;
})

macrovld2q_p64

#define vld2q_p64(__p0) __extension__ ({
  poly64x2x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 38);
  __ret;
})

macrovld2q_u64

#define vld2q_u64(__p0) __extension__ ({
  uint64x2x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 51);
  __ret;
})

macrovld2q_f64

#define vld2q_f64(__p0) __extension__ ({
  float64x2x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 42);
  __ret;
})

macrovld2q_s64

#define vld2q_s64(__p0) __extension__ ({
  int64x2x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 35);
  __ret;
})

macrovld2q_mf8

#define vld2q_mf8(__p0) __extension__ ({
  mfloat8x16x2_t __ret;
  __builtin_neon_vld2q_v(&__ret, __p0, 44);
  __ret;
})

macrovld2_f64

#define vld2_f64(__p0) __extension__ ({
  float64x1x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 10);
  __ret;
})

macrovld2_mf8

#define vld2_mf8(__p0) __extension__ ({
  mfloat8x8x2_t __ret;
  __builtin_neon_vld2_v(&__ret, __p0, 12);
  __ret;
})

macrovld2_dup_p64

#define vld2_dup_p64(__p0) __extension__ ({
  poly64x1x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 6);
  __ret;
})

macrovld2q_dup_p64

#define vld2q_dup_p64(__p0) __extension__ ({
  poly64x2x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 38);
  __ret;
})

macrovld2q_dup_f64

#define vld2q_dup_f64(__p0) __extension__ ({
  float64x2x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 42);
  __ret;
})

macrovld2q_dup_mf8

#define vld2q_dup_mf8(__p0) __extension__ ({
  mfloat8x16x2_t __ret;
  __builtin_neon_vld2q_dup_v(&__ret, __p0, 44);
  __ret;
})

macrovld2_dup_f64

#define vld2_dup_f64(__p0) __extension__ ({
  float64x1x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 10);
  __ret;
})

macrovld2_dup_mf8

#define vld2_dup_mf8(__p0) __extension__ ({
  mfloat8x8x2_t __ret;
  __builtin_neon_vld2_dup_v(&__ret, __p0, 12);
  __ret;
})

macrovld2_lane_p64

#define vld2_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1x2_t __ret;
  poly64x1x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 6);
  __ret;
})

macrovld2q_lane_p8

#define vld2q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16x2_t __ret;
  poly8x16x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 36);
  __ret;
})

macrovld2q_lane_p64

#define vld2q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2x2_t __ret;
  poly64x2x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 38);
  __ret;
})

macrovld2q_lane_u8

#define vld2q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16x2_t __ret;
  uint8x16x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 48);
  __ret;
})

macrovld2q_lane_u64

#define vld2q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2x2_t __ret;
  uint64x2x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 51);
  __ret;
})

macrovld2q_lane_s8

#define vld2q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16x2_t __ret;
  int8x16x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 32);
  __ret;
})

macrovld2q_lane_f64

#define vld2q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2x2_t __ret;
  float64x2x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 42);
  __ret;
})

macrovld2q_lane_s64

#define vld2q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2x2_t __ret;
  int64x2x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 35);
  __ret;
})

macrovld2q_lane_mf8

#define vld2q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16x2_t __ret;
  mfloat8x16x2_t __s1 = __p1;
  __builtin_neon_vld2q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 44);
  __ret;
})

macrovld2_lane_u64

#define vld2_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1x2_t __ret;
  uint64x1x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 19);
  __ret;
})

macrovld2_lane_f64

#define vld2_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1x2_t __ret;
  float64x1x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 10);
  __ret;
})

macrovld2_lane_s64

#define vld2_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1x2_t __ret;
  int64x1x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 3);
  __ret;
})

macrovld2_lane_mf8

#define vld2_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8x2_t __ret;
  mfloat8x8x2_t __s1 = __p1;
  __builtin_neon_vld2_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 12);
  __ret;
})

macrovld3_p64

#define vld3_p64(__p0) __extension__ ({
  poly64x1x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 6);
  __ret;
})

macrovld3q_p64

#define vld3q_p64(__p0) __extension__ ({
  poly64x2x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 38);
  __ret;
})

macrovld3q_u64

#define vld3q_u64(__p0) __extension__ ({
  uint64x2x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 51);
  __ret;
})

macrovld3q_f64

#define vld3q_f64(__p0) __extension__ ({
  float64x2x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 42);
  __ret;
})

macrovld3q_s64

#define vld3q_s64(__p0) __extension__ ({
  int64x2x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 35);
  __ret;
})

macrovld3q_mf8

#define vld3q_mf8(__p0) __extension__ ({
  mfloat8x16x3_t __ret;
  __builtin_neon_vld3q_v(&__ret, __p0, 44);
  __ret;
})

macrovld3_f64

#define vld3_f64(__p0) __extension__ ({
  float64x1x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 10);
  __ret;
})

macrovld3_mf8

#define vld3_mf8(__p0) __extension__ ({
  mfloat8x8x3_t __ret;
  __builtin_neon_vld3_v(&__ret, __p0, 12);
  __ret;
})

macrovld3_dup_p64

#define vld3_dup_p64(__p0) __extension__ ({
  poly64x1x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 6);
  __ret;
})

macrovld3q_dup_p64

#define vld3q_dup_p64(__p0) __extension__ ({
  poly64x2x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 38);
  __ret;
})

macrovld3q_dup_f64

#define vld3q_dup_f64(__p0) __extension__ ({
  float64x2x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 42);
  __ret;
})

macrovld3q_dup_mf8

#define vld3q_dup_mf8(__p0) __extension__ ({
  mfloat8x16x3_t __ret;
  __builtin_neon_vld3q_dup_v(&__ret, __p0, 44);
  __ret;
})

macrovld3_dup_f64

#define vld3_dup_f64(__p0) __extension__ ({
  float64x1x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 10);
  __ret;
})

macrovld3_dup_mf8

#define vld3_dup_mf8(__p0) __extension__ ({
  mfloat8x8x3_t __ret;
  __builtin_neon_vld3_dup_v(&__ret, __p0, 12);
  __ret;
})

macrovld3_lane_p64

#define vld3_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1x3_t __ret;
  poly64x1x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 6);
  __ret;
})

macrovld3q_lane_p8

#define vld3q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16x3_t __ret;
  poly8x16x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 36);
  __ret;
})

macrovld3q_lane_p64

#define vld3q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2x3_t __ret;
  poly64x2x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 38);
  __ret;
})

macrovld3q_lane_u8

#define vld3q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16x3_t __ret;
  uint8x16x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 48);
  __ret;
})

macrovld3q_lane_u64

#define vld3q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2x3_t __ret;
  uint64x2x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 51);
  __ret;
})

macrovld3q_lane_s8

#define vld3q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16x3_t __ret;
  int8x16x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 32);
  __ret;
})

macrovld3q_lane_f64

#define vld3q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2x3_t __ret;
  float64x2x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 42);
  __ret;
})

macrovld3q_lane_s64

#define vld3q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2x3_t __ret;
  int64x2x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 35);
  __ret;
})

macrovld3q_lane_mf8

#define vld3q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16x3_t __ret;
  mfloat8x16x3_t __s1 = __p1;
  __builtin_neon_vld3q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 44);
  __ret;
})

macrovld3_lane_u64

#define vld3_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1x3_t __ret;
  uint64x1x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 19);
  __ret;
})

macrovld3_lane_f64

#define vld3_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1x3_t __ret;
  float64x1x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 10);
  __ret;
})

macrovld3_lane_s64

#define vld3_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1x3_t __ret;
  int64x1x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 3);
  __ret;
})

macrovld3_lane_mf8

#define vld3_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8x3_t __ret;
  mfloat8x8x3_t __s1 = __p1;
  __builtin_neon_vld3_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 12);
  __ret;
})

macrovld4_p64

#define vld4_p64(__p0) __extension__ ({
  poly64x1x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 6);
  __ret;
})

macrovld4q_p64

#define vld4q_p64(__p0) __extension__ ({
  poly64x2x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 38);
  __ret;
})

macrovld4q_u64

#define vld4q_u64(__p0) __extension__ ({
  uint64x2x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 51);
  __ret;
})

macrovld4q_f64

#define vld4q_f64(__p0) __extension__ ({
  float64x2x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 42);
  __ret;
})

macrovld4q_s64

#define vld4q_s64(__p0) __extension__ ({
  int64x2x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 35);
  __ret;
})

macrovld4q_mf8

#define vld4q_mf8(__p0) __extension__ ({
  mfloat8x16x4_t __ret;
  __builtin_neon_vld4q_v(&__ret, __p0, 44);
  __ret;
})

macrovld4_f64

#define vld4_f64(__p0) __extension__ ({
  float64x1x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 10);
  __ret;
})

macrovld4_mf8

#define vld4_mf8(__p0) __extension__ ({
  mfloat8x8x4_t __ret;
  __builtin_neon_vld4_v(&__ret, __p0, 12);
  __ret;
})

macrovld4_dup_p64

#define vld4_dup_p64(__p0) __extension__ ({
  poly64x1x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 6);
  __ret;
})

macrovld4q_dup_p64

#define vld4q_dup_p64(__p0) __extension__ ({
  poly64x2x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 38);
  __ret;
})

macrovld4q_dup_f64

#define vld4q_dup_f64(__p0) __extension__ ({
  float64x2x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 42);
  __ret;
})

macrovld4q_dup_mf8

#define vld4q_dup_mf8(__p0) __extension__ ({
  mfloat8x16x4_t __ret;
  __builtin_neon_vld4q_dup_v(&__ret, __p0, 44);
  __ret;
})

macrovld4_dup_f64

#define vld4_dup_f64(__p0) __extension__ ({
  float64x1x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 10);
  __ret;
})

macrovld4_dup_mf8

#define vld4_dup_mf8(__p0) __extension__ ({
  mfloat8x8x4_t __ret;
  __builtin_neon_vld4_dup_v(&__ret, __p0, 12);
  __ret;
})

macrovld4_lane_p64

#define vld4_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1x4_t __ret;
  poly64x1x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 6);
  __ret;
})

macrovld4q_lane_p8

#define vld4q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16x4_t __ret;
  poly8x16x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 36);
  __ret;
})

macrovld4q_lane_p64

#define vld4q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2x4_t __ret;
  poly64x2x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 38);
  __ret;
})

macrovld4q_lane_u8

#define vld4q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16x4_t __ret;
  uint8x16x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 48);
  __ret;
})

macrovld4q_lane_u64

#define vld4q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2x4_t __ret;
  uint64x2x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 51);
  __ret;
})

macrovld4q_lane_s8

#define vld4q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16x4_t __ret;
  int8x16x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 32);
  __ret;
})

macrovld4q_lane_f64

#define vld4q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2x4_t __ret;
  float64x2x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 42);
  __ret;
})

macrovld4q_lane_s64

#define vld4q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2x4_t __ret;
  int64x2x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 35);
  __ret;
})

macrovld4q_lane_mf8

#define vld4q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16x4_t __ret;
  mfloat8x16x4_t __s1 = __p1;
  __builtin_neon_vld4q_lane_v(&__ret, __p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 44);
  __ret;
})

macrovld4_lane_u64

#define vld4_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1x4_t __ret;
  uint64x1x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 19);
  __ret;
})

macrovld4_lane_f64

#define vld4_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1x4_t __ret;
  float64x1x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 10);
  __ret;
})

macrovld4_lane_s64

#define vld4_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1x4_t __ret;
  int64x1x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 3);
  __ret;
})

macrovld4_lane_mf8

#define vld4_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8x4_t __ret;
  mfloat8x8x4_t __s1 = __p1;
  __builtin_neon_vld4_lane_v(&__ret, __p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 12);
  __ret;
})

macrovldrq_p128

#define vldrq_p128(__p0) __extension__ ({
  poly128_t __ret;
  __ret = __builtin_bit_cast(poly128_t, __builtin_neon_vldrq_p128(__p0));
  __ret;
})

macrovst1_p64

#define vst1_p64(__p0, __p1) __extension__ ({
  poly64x1_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 6);
})

macrovst1q_p64

#define vst1q_p64(__p0, __p1) __extension__ ({
  poly64x2_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 38);
})

macrovst1q_f64

#define vst1q_f64(__p0, __p1) __extension__ ({
  float64x2_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 42);
})

macrovst1q_mf8

#define vst1q_mf8(__p0, __p1) __extension__ ({
  mfloat8x16_t __s1 = __p1;
  __builtin_neon_vst1q_v(__p0, __builtin_bit_cast(int8x16_t, __s1), 44);
})

macrovst1_f64

#define vst1_f64(__p0, __p1) __extension__ ({
  float64x1_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 10);
})

macrovst1_mf8

#define vst1_mf8(__p0, __p1) __extension__ ({
  mfloat8x8_t __s1 = __p1;
  __builtin_neon_vst1_v(__p0, __builtin_bit_cast(int8x8_t, __s1), 12);
})

macrovst1_lane_p64

#define vst1_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 6);
})

macrovst1q_lane_p64

#define vst1q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 38);
})

macrovst1q_lane_f64

#define vst1q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 42);
})

macrovst1q_lane_mf8

#define vst1q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16_t __s1 = __p1;
  __builtin_neon_vst1q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 44);
})

macrovst1_lane_f64

#define vst1_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 10);
})

macrovst1_lane_mf8

#define vst1_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8_t __s1 = __p1;
  __builtin_neon_vst1_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 12);
})

macrovst1_p64_x2

#define vst1_p64_x2(__p0, __p1) __extension__ ({
  poly64x1x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 6);
})

macrovst1q_p64_x2

#define vst1q_p64_x2(__p0, __p1) __extension__ ({
  poly64x2x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 38);
})

macrovst1q_f64_x2

#define vst1q_f64_x2(__p0, __p1) __extension__ ({
  float64x2x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 42);
})

macrovst1q_mf8_x2

#define vst1q_mf8_x2(__p0, __p1) __extension__ ({
  mfloat8x16x2_t __s1 = __p1;
  __builtin_neon_vst1q_x2_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 44);
})

macrovst1_f64_x2

#define vst1_f64_x2(__p0, __p1) __extension__ ({
  float64x1x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 10);
})

macrovst1_mf8_x2

#define vst1_mf8_x2(__p0, __p1) __extension__ ({
  mfloat8x8x2_t __s1 = __p1;
  __builtin_neon_vst1_x2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 12);
})

macrovst1_p64_x3

#define vst1_p64_x3(__p0, __p1) __extension__ ({
  poly64x1x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 6);
})

macrovst1q_p64_x3

#define vst1q_p64_x3(__p0, __p1) __extension__ ({
  poly64x2x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 38);
})

macrovst1q_f64_x3

#define vst1q_f64_x3(__p0, __p1) __extension__ ({
  float64x2x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 42);
})

macrovst1q_mf8_x3

#define vst1q_mf8_x3(__p0, __p1) __extension__ ({
  mfloat8x16x3_t __s1 = __p1;
  __builtin_neon_vst1q_x3_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 44);
})

macrovst1_f64_x3

#define vst1_f64_x3(__p0, __p1) __extension__ ({
  float64x1x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 10);
})

macrovst1_mf8_x3

#define vst1_mf8_x3(__p0, __p1) __extension__ ({
  mfloat8x8x3_t __s1 = __p1;
  __builtin_neon_vst1_x3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 12);
})

macrovst1_p64_x4

#define vst1_p64_x4(__p0, __p1) __extension__ ({
  poly64x1x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 6);
})

macrovst1q_p64_x4

#define vst1q_p64_x4(__p0, __p1) __extension__ ({
  poly64x2x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 38);
})

macrovst1q_f64_x4

#define vst1q_f64_x4(__p0, __p1) __extension__ ({
  float64x2x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 42);
})

macrovst1q_mf8_x4

#define vst1q_mf8_x4(__p0, __p1) __extension__ ({
  mfloat8x16x4_t __s1 = __p1;
  __builtin_neon_vst1q_x4_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 44);
})

macrovst1_f64_x4

#define vst1_f64_x4(__p0, __p1) __extension__ ({
  float64x1x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 10);
})

macrovst1_mf8_x4

#define vst1_mf8_x4(__p0, __p1) __extension__ ({
  mfloat8x8x4_t __s1 = __p1;
  __builtin_neon_vst1_x4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 12);
})

macrovst2_p64

#define vst2_p64(__p0, __p1) __extension__ ({
  poly64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 6);
})

macrovst2q_p64

#define vst2q_p64(__p0, __p1) __extension__ ({
  poly64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 38);
})

macrovst2q_u64

#define vst2q_u64(__p0, __p1) __extension__ ({
  uint64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 51);
})

macrovst2q_f64

#define vst2q_f64(__p0, __p1) __extension__ ({
  float64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 42);
})

macrovst2q_s64

#define vst2q_s64(__p0, __p1) __extension__ ({
  int64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 35);
})

macrovst2q_mf8

#define vst2q_mf8(__p0, __p1) __extension__ ({
  mfloat8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), 44);
})

macrovst2_f64

#define vst2_f64(__p0, __p1) __extension__ ({
  float64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 10);
})

macrovst2_mf8

#define vst2_mf8(__p0, __p1) __extension__ ({
  mfloat8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), 12);
})

macrovst2_lane_p64

#define vst2_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 6);
})

macrovst2q_lane_p8

#define vst2q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 36);
})

macrovst2q_lane_p64

#define vst2q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 38);
})

macrovst2q_lane_u8

#define vst2q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 48);
})

macrovst2q_lane_u64

#define vst2q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 51);
})

macrovst2q_lane_s8

#define vst2q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 32);
})

macrovst2q_lane_f64

#define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 42);
})

macrovst2q_lane_s64

#define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 35);
})

macrovst2q_lane_mf8

#define vst2q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16x2_t __s1 = __p1;
  __builtin_neon_vst2q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __p2, 44);
})

macrovst2_lane_u64

#define vst2_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 19);
})

macrovst2_lane_f64

#define vst2_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 10);
})

macrovst2_lane_s64

#define vst2_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 3);
})

macrovst2_lane_mf8

#define vst2_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8x2_t __s1 = __p1;
  __builtin_neon_vst2_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __p2, 12);
})

macrovst3_p64

#define vst3_p64(__p0, __p1) __extension__ ({
  poly64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 6);
})

macrovst3q_p64

#define vst3q_p64(__p0, __p1) __extension__ ({
  poly64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 38);
})

macrovst3q_u64

#define vst3q_u64(__p0, __p1) __extension__ ({
  uint64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 51);
})

macrovst3q_f64

#define vst3q_f64(__p0, __p1) __extension__ ({
  float64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 42);
})

macrovst3q_s64

#define vst3q_s64(__p0, __p1) __extension__ ({
  int64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 35);
})

macrovst3q_mf8

#define vst3q_mf8(__p0, __p1) __extension__ ({
  mfloat8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), 44);
})

macrovst3_f64

#define vst3_f64(__p0, __p1) __extension__ ({
  float64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 10);
})

macrovst3_mf8

#define vst3_mf8(__p0, __p1) __extension__ ({
  mfloat8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), 12);
})

macrovst3_lane_p64

#define vst3_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 6);
})

macrovst3q_lane_p8

#define vst3q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 36);
})

macrovst3q_lane_p64

#define vst3q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 38);
})

macrovst3q_lane_u8

#define vst3q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 48);
})

macrovst3q_lane_u64

#define vst3q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 51);
})

macrovst3q_lane_s8

#define vst3q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 32);
})

macrovst3q_lane_f64

#define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 42);
})

macrovst3q_lane_s64

#define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 35);
})

macrovst3q_lane_mf8

#define vst3q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16x3_t __s1 = __p1;
  __builtin_neon_vst3q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __p2, 44);
})

macrovst3_lane_u64

#define vst3_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 19);
})

macrovst3_lane_f64

#define vst3_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 10);
})

macrovst3_lane_s64

#define vst3_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 3);
})

macrovst3_lane_mf8

#define vst3_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8x3_t __s1 = __p1;
  __builtin_neon_vst3_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __p2, 12);
})

macrovst4_p64

#define vst4_p64(__p0, __p1) __extension__ ({
  poly64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 6);
})

macrovst4q_p64

#define vst4q_p64(__p0, __p1) __extension__ ({
  poly64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 38);
})

macrovst4q_u64

#define vst4q_u64(__p0, __p1) __extension__ ({
  uint64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 51);
})

macrovst4q_f64

#define vst4q_f64(__p0, __p1) __extension__ ({
  float64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 42);
})

macrovst4q_s64

#define vst4q_s64(__p0, __p1) __extension__ ({
  int64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 35);
})

macrovst4q_mf8

#define vst4q_mf8(__p0, __p1) __extension__ ({
  mfloat8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), 44);
})

macrovst4_f64

#define vst4_f64(__p0, __p1) __extension__ ({
  float64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 10);
})

macrovst4_mf8

#define vst4_mf8(__p0, __p1) __extension__ ({
  mfloat8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), 12);
})

macrovst4_lane_p64

#define vst4_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 6);
})

macrovst4q_lane_p8

#define vst4q_lane_p8(__p0, __p1, __p2) __extension__ ({
  poly8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 36);
})

macrovst4q_lane_p64

#define vst4q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 38);
})

macrovst4q_lane_u8

#define vst4q_lane_u8(__p0, __p1, __p2) __extension__ ({
  uint8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 48);
})

macrovst4q_lane_u64

#define vst4q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 51);
})

macrovst4q_lane_s8

#define vst4q_lane_s8(__p0, __p1, __p2) __extension__ ({
  int8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 32);
})

macrovst4q_lane_f64

#define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 42);
})

macrovst4q_lane_s64

#define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 35);
})

macrovst4q_lane_mf8

#define vst4q_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x16x4_t __s1 = __p1;
  __builtin_neon_vst4q_lane_v(__p0, __builtin_bit_cast(int8x16_t, __s1.val[0]), __builtin_bit_cast(int8x16_t, __s1.val[1]), __builtin_bit_cast(int8x16_t, __s1.val[2]), __builtin_bit_cast(int8x16_t, __s1.val[3]), __p2, 44);
})

macrovst4_lane_u64

#define vst4_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 19);
})

macrovst4_lane_f64

#define vst4_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 10);
})

macrovst4_lane_s64

#define vst4_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 3);
})

macrovst4_lane_mf8

#define vst4_lane_mf8(__p0, __p1, __p2) __extension__ ({
  mfloat8x8x4_t __s1 = __p1;
  __builtin_neon_vst4_lane_v(__p0, __builtin_bit_cast(int8x8_t, __s1.val[0]), __builtin_bit_cast(int8x8_t, __s1.val[1]), __builtin_bit_cast(int8x8_t, __s1.val[2]), __builtin_bit_cast(int8x8_t, __s1.val[3]), __p2, 12);
})

macrovstrq_p128

#define vstrq_p128(__p0, __p1) __extension__ ({
  poly128_t __s1 = __p1;
  __builtin_neon_vstrq_p128(__p0, __s1);
})

macrovldap1_lane_p64

#define vldap1_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1_t __ret;
  poly64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly64x1_t, __builtin_neon_vldap1_lane_p64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 6));
  __ret;
})

macrovldap1q_lane_p64

#define vldap1q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2_t __ret;
  poly64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(poly64x2_t, __builtin_neon_vldap1q_lane_p64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 38));
  __ret;
})

macrovldap1q_lane_u64

#define vldap1q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2_t __ret;
  uint64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint64x2_t, __builtin_neon_vldap1q_lane_u64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 51));
  __ret;
})

macrovldap1q_lane_f64

#define vldap1q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2_t __ret;
  float64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(float64x2_t, __builtin_neon_vldap1q_lane_f64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 42));
  __ret;
})

macrovldap1q_lane_s64

#define vldap1q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2_t __ret;
  int64x2_t __s1 = __p1;
  __ret = __builtin_bit_cast(int64x2_t, __builtin_neon_vldap1q_lane_s64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 35));
  __ret;
})

macrovldap1_lane_u64

#define vldap1_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1_t __ret;
  uint64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(uint64x1_t, __builtin_neon_vldap1_lane_u64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 19));
  __ret;
})

macrovldap1_lane_f64

#define vldap1_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1_t __ret;
  float64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(float64x1_t, __builtin_neon_vldap1_lane_f64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 10));
  __ret;
})

macrovldap1_lane_s64

#define vldap1_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1_t __ret;
  int64x1_t __s1 = __p1;
  __ret = __builtin_bit_cast(int64x1_t, __builtin_neon_vldap1_lane_s64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 3));
  __ret;
})

macrovstl1_lane_p64

#define vstl1_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x1_t __s1 = __p1;
  __builtin_neon_vstl1_lane_p64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 6);
})

macrovstl1q_lane_p64

#define vstl1q_lane_p64(__p0, __p1, __p2) __extension__ ({
  poly64x2_t __s1 = __p1;
  __builtin_neon_vstl1q_lane_p64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 38);
})

macrovstl1q_lane_u64

#define vstl1q_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x2_t __s1 = __p1;
  __builtin_neon_vstl1q_lane_u64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 51);
})

macrovstl1q_lane_f64

#define vstl1q_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x2_t __s1 = __p1;
  __builtin_neon_vstl1q_lane_f64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 42);
})

macrovstl1q_lane_s64

#define vstl1q_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x2_t __s1 = __p1;
  __builtin_neon_vstl1q_lane_s64(__p0, __builtin_bit_cast(int8x16_t, __s1), __p2, 35);
})

macrovstl1_lane_u64

#define vstl1_lane_u64(__p0, __p1, __p2) __extension__ ({
  uint64x1_t __s1 = __p1;
  __builtin_neon_vstl1_lane_u64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 19);
})

macrovstl1_lane_f64

#define vstl1_lane_f64(__p0, __p1, __p2) __extension__ ({
  float64x1_t __s1 = __p1;
  __builtin_neon_vstl1_lane_f64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 10);
})

macrovstl1_lane_s64

#define vstl1_lane_s64(__p0, __p1, __p2) __extension__ ({
  int64x1_t __s1 = __p1;
  __builtin_neon_vstl1_lane_s64(__p0, __builtin_bit_cast(int8x8_t, __s1), __p2, 3);
})