#define vpselq_u8(__a, __b, __p) __arm_vpselq_u8(__a, __b, __p)
#define vpselq_s8(__a, __b, __p) __arm_vpselq_s8(__a, __b, __p)
#define vrev64q_m_u8(__inactive, __a, __p) __arm_vrev64q_m_u8(__inactive, __a, __p)
-#define vqrdmlashq_n_u8(__a, __b, __c) __arm_vqrdmlashq_n_u8(__a, __b, __c)
-#define vqrdmlahq_n_u8(__a, __b, __c) __arm_vqrdmlahq_n_u8(__a, __b, __c)
-#define vqdmlahq_n_u8(__a, __b, __c) __arm_vqdmlahq_n_u8(__a, __b, __c)
#define vmvnq_m_u8(__inactive, __a, __p) __arm_vmvnq_m_u8(__inactive, __a, __p)
#define vmlasq_n_u8(__a, __b, __c) __arm_vmlasq_n_u8(__a, __b, __c)
#define vmlaq_n_u8(__a, __b, __c) __arm_vmlaq_n_u8(__a, __b, __c)
#define vpselq_u16(__a, __b, __p) __arm_vpselq_u16(__a, __b, __p)
#define vpselq_s16(__a, __b, __p) __arm_vpselq_s16(__a, __b, __p)
#define vrev64q_m_u16(__inactive, __a, __p) __arm_vrev64q_m_u16(__inactive, __a, __p)
-#define vqrdmlashq_n_u16(__a, __b, __c) __arm_vqrdmlashq_n_u16(__a, __b, __c)
-#define vqrdmlahq_n_u16(__a, __b, __c) __arm_vqrdmlahq_n_u16(__a, __b, __c)
-#define vqdmlahq_n_u16(__a, __b, __c) __arm_vqdmlahq_n_u16(__a, __b, __c)
#define vmvnq_m_u16(__inactive, __a, __p) __arm_vmvnq_m_u16(__inactive, __a, __p)
#define vmlasq_n_u16(__a, __b, __c) __arm_vmlasq_n_u16(__a, __b, __c)
#define vmlaq_n_u16(__a, __b, __c) __arm_vmlaq_n_u16(__a, __b, __c)
#define vpselq_u32(__a, __b, __p) __arm_vpselq_u32(__a, __b, __p)
#define vpselq_s32(__a, __b, __p) __arm_vpselq_s32(__a, __b, __p)
#define vrev64q_m_u32(__inactive, __a, __p) __arm_vrev64q_m_u32(__inactive, __a, __p)
-#define vqrdmlashq_n_u32(__a, __b, __c) __arm_vqrdmlashq_n_u32(__a, __b, __c)
-#define vqrdmlahq_n_u32(__a, __b, __c) __arm_vqrdmlahq_n_u32(__a, __b, __c)
-#define vqdmlahq_n_u32(__a, __b, __c) __arm_vqdmlahq_n_u32(__a, __b, __c)
#define vmvnq_m_u32(__inactive, __a, __p) __arm_vmvnq_m_u32(__inactive, __a, __p)
#define vmlasq_n_u32(__a, __b, __c) __arm_vmlasq_n_u32(__a, __b, __c)
#define vmlaq_n_u32(__a, __b, __c) __arm_vmlaq_n_u32(__a, __b, __c)
#define vmlaldavaq_p_u16(__a, __b, __c, __p) __arm_vmlaldavaq_p_u16(__a, __b, __c, __p)
#define vmlaldavaxq_p_s32(__a, __b, __c, __p) __arm_vmlaldavaxq_p_s32(__a, __b, __c, __p)
#define vmlaldavaxq_p_s16(__a, __b, __c, __p) __arm_vmlaldavaxq_p_s16(__a, __b, __c, __p)
-#define vmlaldavaxq_p_u32(__a, __b, __c, __p) __arm_vmlaldavaxq_p_u32(__a, __b, __c, __p)
-#define vmlaldavaxq_p_u16(__a, __b, __c, __p) __arm_vmlaldavaxq_p_u16(__a, __b, __c, __p)
#define vmlsldavaq_p_s32(__a, __b, __c, __p) __arm_vmlsldavaq_p_s32(__a, __b, __c, __p)
#define vmlsldavaq_p_s16(__a, __b, __c, __p) __arm_vmlsldavaq_p_s16(__a, __b, __c, __p)
#define vmlsldavaxq_p_s32(__a, __b, __c, __p) __arm_vmlsldavaxq_p_s32(__a, __b, __c, __p)
return __builtin_mve_vrev64q_m_uv16qi (__inactive, __a, __p);
}
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlashq_n_u8 (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
-{
- return __builtin_mve_vqrdmlashq_n_uv16qi (__a, __b, __c);
-}
-
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlahq_n_u8 (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
-{
- return __builtin_mve_vqrdmlahq_n_uv16qi (__a, __b, __c);
-}
-
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqdmlahq_n_u8 (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
-{
- return __builtin_mve_vqdmlahq_n_uv16qi (__a, __b, __c);
-}
-
__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmvnq_m_u8 (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
return __builtin_mve_vrev64q_m_uv8hi (__inactive, __a, __p);
}
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlashq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
-{
- return __builtin_mve_vqrdmlashq_n_uv8hi (__a, __b, __c);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlahq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
-{
- return __builtin_mve_vqrdmlahq_n_uv8hi (__a, __b, __c);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqdmlahq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
-{
- return __builtin_mve_vqdmlahq_n_uv8hi (__a, __b, __c);
-}
-
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmvnq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
return __builtin_mve_vrev64q_m_uv4si (__inactive, __a, __p);
}
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlashq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
-{
- return __builtin_mve_vqrdmlashq_n_uv4si (__a, __b, __c);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlahq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
-{
- return __builtin_mve_vqrdmlahq_n_uv4si (__a, __b, __c);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqdmlahq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
-{
- return __builtin_mve_vqdmlahq_n_uv4si (__a, __b, __c);
-}
-
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmvnq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, mve_pred16_t __p)
return __builtin_mve_vmlaldavaxq_p_sv8hi (__a, __b, __c, __p);
}
-__extension__ extern __inline uint64_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmlaldavaxq_p_u32 (uint64_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
-{
- return __builtin_mve_vmlaldavaxq_p_uv4si (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline uint64_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmlaldavaxq_p_u16 (uint64_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p)
-{
- return __builtin_mve_vmlaldavaxq_p_uv8hi (__a, __b, __c, __p);
-}
-
__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmlsldavaq_p_s32 (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
return __arm_vrev64q_m_u8 (__inactive, __a, __p);
}
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlashq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
-{
- return __arm_vqrdmlashq_n_u8 (__a, __b, __c);
-}
-
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlahq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
-{
- return __arm_vqrdmlahq_n_u8 (__a, __b, __c);
-}
-
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqdmlahq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
-{
- return __arm_vqdmlahq_n_u8 (__a, __b, __c);
-}
-
__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmvnq_m (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
return __arm_vrev64q_m_u16 (__inactive, __a, __p);
}
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlashq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
-{
- return __arm_vqrdmlashq_n_u16 (__a, __b, __c);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlahq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
-{
- return __arm_vqrdmlahq_n_u16 (__a, __b, __c);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqdmlahq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
-{
- return __arm_vqdmlahq_n_u16 (__a, __b, __c);
-}
-
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmvnq_m (uint16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
return __arm_vrev64q_m_u32 (__inactive, __a, __p);
}
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlashq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
-{
- return __arm_vqrdmlashq_n_u32 (__a, __b, __c);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqrdmlahq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
-{
- return __arm_vqrdmlahq_n_u32 (__a, __b, __c);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vqdmlahq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
-{
- return __arm_vqdmlahq_n_u32 (__a, __b, __c);
-}
-
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmvnq_m (uint32x4_t __inactive, uint32x4_t __a, mve_pred16_t __p)
return __arm_vmlaldavaxq_p_s16 (__a, __b, __c, __p);
}
-__extension__ extern __inline uint64_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmlaldavaxq_p (uint64_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
-{
- return __arm_vmlaldavaxq_p_u32 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline uint64_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmlaldavaxq_p (uint64_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p)
-{
- return __arm_vmlaldavaxq_p_u16 (__a, __b, __c, __p);
-}
-
__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmlsldavaq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)));})
#define __arm_vqdmlashq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)));})
#define __arm_vmlasq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)));})
#define __arm_vqrdmladhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)));})
#define __arm_vqdmlashq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)));})
#define __arm_vqrdmladhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t)));})
#define __arm_vqdmlsdhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavaxq_p_s16 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
- int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaxq_p_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
- int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavaxq_p_u16 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
- int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavaxq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaxq_p_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
#define __arm_vmlsldavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \