__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq_n_u16 (uint16x8_t __a, const int __imm)
+__arm_vbicq_n_u16 (uint16x8_t __a, const uint16_t __imm)
{
return __builtin_mve_vbicq_n_uv8hi (__a, __imm);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq_n_s16 (int16x8_t __a, const int __imm)
+__arm_vbicq_n_s16 (int16x8_t __a, const int16_t __imm)
{
return __builtin_mve_vbicq_n_sv8hi (__a, __imm);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq_n_u32 (uint32x4_t __a, const int __imm)
+__arm_vbicq_n_u32 (uint32x4_t __a, const uint32_t __imm)
{
return __builtin_mve_vbicq_n_uv4si (__a, __imm);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq_n_s32 (int32x4_t __a, const int __imm)
+__arm_vbicq_n_s32 (int32x4_t __a, const int32_t __imm)
{
return __builtin_mve_vbicq_n_sv4si (__a, __imm);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq (uint16x8_t __a, const int __imm)
+__arm_vbicq (uint16x8_t __a, const uint16_t __imm)
{
return __arm_vbicq_n_u16 (__a, __imm);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq (int16x8_t __a, const int __imm)
+__arm_vbicq (int16x8_t __a, const int16_t __imm)
{
return __arm_vbicq_n_s16 (__a, __imm);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq (uint32x4_t __a, const int __imm)
+__arm_vbicq (uint32x4_t __a, const uint32_t __imm)
{
return __arm_vbicq_n_u32 (__a, __imm);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbicq (int32x4_t __a, const int __imm)
+__arm_vbicq (int32x4_t __a, const int32_t __imm)
{
return __arm_vbicq_n_s32 (__a, __imm);
}
#define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce1(__p1, int)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce1(__p1, int)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce1(__p1, int)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce1(__p1, int)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), (const int16_t) __p1), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), (const int32_t) __p1), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (const uint16_t) __p1), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (const uint32_t) __p1), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
#define __arm_vdupq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2), \
- int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
- int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), (int8_t) __p1, p2), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), (int16_t) __p1, p2), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), (int32_t) __p1, p2), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint8_t) __p1, p2), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint16_t) __p1, p2), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), (float16_t) __p1, p2), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), (float32_t) __p1, p2));})
#define __arm_vfmaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
#define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
- int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));})
#define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
- int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
#define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
- int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));})
#define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
- int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
#define __arm_vldrwq_gather_offset(p0,p1) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce(p0, int32_t const *), p1), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1), \
- int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce(p0, float32_t const *), p1)))
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \
+ int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce1(p0, float32_t *), p1)))
#define __arm_vldrwq_gather_offset_z(p0,p1,p2) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce(p0, int32_t const *), p1, p2), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1, p2), \
- int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce(p0, float32_t const *), p1, p2)))
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1, p2), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1, p2), \
+ int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1, p2)))
#define __arm_vldrwq_gather_shifted_offset(p0,p1) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t const *), p1), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1), \
- int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t const *), p1)))
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \
+ int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce1(p0, float32_t *), p1)))
#define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(p0, int32_t const *), p1, p2), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1, p2), \
- int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce(p0, float32_t const *), p1, p2)))
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1, p2), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1, p2), \
+ int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1, p2)))
#define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
#define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce1(__p1, int)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce1(__p1, int)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce1(__p1, int)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce1(__p1, int)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), (const int16_t) __p1), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), (const int32_t) __p1), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (const uint16_t) __p1), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (const uint32_t) __p1), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
#define __arm_vdupq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2));})
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), (int8_t) __p1, p2), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), (int16_t) __p1, p2), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), (int32_t) __p1, p2), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint8_t) __p1, p2), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint16_t) __p1, p2), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2));})
#define __arm_vmaxaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
#define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
#define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
#define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
#define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
#define __arm_vldrwq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1));})
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1));})
#define __arm_vldrwq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1, p2), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1, p2));})
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1, p2), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1, p2));})
#define __arm_vldrwq_gather_shifted_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1));})
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1));})
#define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1, p2), \
- int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1, p2));})
+ int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1, p2), \
+ int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1, p2));})
#define __arm_vst1q(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
#define __arm_vdwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u8 ((uint32_t) __p1, p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
#define __arm_vdwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u16 ((uint32_t) __p1, p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
#define __arm_vdwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u32 ((uint32_t) __p1, p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
#define __arm_viwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
+ int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u8 ((uint32_t) __p1, p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
#define __arm_viwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
+ int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u16 ((uint32_t) __p1, p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
#define __arm_viwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
+ int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u32 ((uint32_t) __p1, p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
#define __arm_vidupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u8 ((uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vddupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u8 ((uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vidupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u16 ((uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vddupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u16 ((uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vidupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u32 ((uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vddupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u32 ((uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vshrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_wb_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
#define __arm_vldrdq_gather_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce(p0, int64_t const *), p1), \
- int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1)))
+ int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce1(p0, int64_t *), p1), \
+ int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1)))
#define __arm_vldrdq_gather_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce(p0, int64_t const *), p1, p2), \
- int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1, p2)))
+ int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce1(p0, int64_t *), p1, p2), \
+ int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1, p2)))
#define __arm_vldrdq_gather_shifted_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce(p0, int64_t const *), p1), \
- int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1)))
+ int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce1(p0, int64_t *), p1), \
+ int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1)))
#define __arm_vldrdq_gather_shifted_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
- int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce(p0, int64_t const *), p1, p2), \
- int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1, p2)))
+ int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce1(p0, int64_t *), p1, p2), \
+ int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1, p2)))
#define __arm_vadciq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
#define __arm_vidupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t), p2, p3), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t), p2, p3), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint32_t) __p1, p2, p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint32_t) __p1, p2, p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vddupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t), p2, p3), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t), p2, p3), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2, p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint32_t) __p1, p2, p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint32_t) __p1, p2, p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2, p3), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
#define __arm_vidupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u16 (__ARM_mve_coerce(__p0, uint32_t), p1), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u16 ((uint32_t) __p0, p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
#define __arm_vidupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u32 (__ARM_mve_coerce(__p0, uint32_t), p1), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u32 ((uint32_t) __p0, p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
#define __arm_vidupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u8 (__ARM_mve_coerce(__p0, uint32_t), p1), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u8 ((uint32_t) __p0, p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
#define __arm_vddupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u16 (__ARM_mve_coerce(__p0, uint32_t), p1), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u16 ((uint32_t) __p0, p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
#define __arm_vddupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u32 (__ARM_mve_coerce(__p0, uint32_t), p1), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u32 ((uint32_t) __p0, p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
#define __arm_vddupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u8 (__ARM_mve_coerce(__p0, uint32_t), p1), \
+ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u8 ((uint32_t) __p0, p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
#define __arm_viwdupq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \