#define vshlq_n_s32(__a, __imm) __arm_vshlq_n_s32(__a, __imm)
#define vrshrq_n_s32(__a, __imm) __arm_vrshrq_n_s32(__a, __imm)
#define vqshlq_n_s32(__a, __imm) __arm_vqshlq_n_s32(__a, __imm)
+#define vqmovntq_u16(__a, __b) __arm_vqmovntq_u16(__a, __b)
+#define vqmovnbq_u16(__a, __b) __arm_vqmovnbq_u16(__a, __b)
+#define vmulltq_poly_p8(__a, __b) __arm_vmulltq_poly_p8(__a, __b)
+#define vmullbq_poly_p8(__a, __b) __arm_vmullbq_poly_p8(__a, __b)
+#define vmovntq_u16(__a, __b) __arm_vmovntq_u16(__a, __b)
+#define vmovnbq_u16(__a, __b) __arm_vmovnbq_u16(__a, __b)
+#define vmlaldavq_u16(__a, __b) __arm_vmlaldavq_u16(__a, __b)
+#define vqmovuntq_s16(__a, __b) __arm_vqmovuntq_s16(__a, __b)
+#define vqmovunbq_s16(__a, __b) __arm_vqmovunbq_s16(__a, __b)
+#define vshlltq_n_u8(__a, __imm) __arm_vshlltq_n_u8(__a, __imm)
+#define vshllbq_n_u8(__a, __imm) __arm_vshllbq_n_u8(__a, __imm)
+#define vorrq_n_u16(__a, __imm) __arm_vorrq_n_u16(__a, __imm)
+#define vbicq_n_u16(__a, __imm) __arm_vbicq_n_u16(__a, __imm)
+#define vcmpneq_n_f16(__a, __b) __arm_vcmpneq_n_f16(__a, __b)
+#define vcmpneq_f16(__a, __b) __arm_vcmpneq_f16(__a, __b)
+#define vcmpltq_n_f16(__a, __b) __arm_vcmpltq_n_f16(__a, __b)
+#define vcmpltq_f16(__a, __b) __arm_vcmpltq_f16(__a, __b)
+#define vcmpleq_n_f16(__a, __b) __arm_vcmpleq_n_f16(__a, __b)
+#define vcmpleq_f16(__a, __b) __arm_vcmpleq_f16(__a, __b)
+#define vcmpgtq_n_f16(__a, __b) __arm_vcmpgtq_n_f16(__a, __b)
+#define vcmpgtq_f16(__a, __b) __arm_vcmpgtq_f16(__a, __b)
+#define vcmpgeq_n_f16(__a, __b) __arm_vcmpgeq_n_f16(__a, __b)
+#define vcmpgeq_f16(__a, __b) __arm_vcmpgeq_f16(__a, __b)
+#define vcmpeqq_n_f16(__a, __b) __arm_vcmpeqq_n_f16(__a, __b)
+#define vcmpeqq_f16(__a, __b) __arm_vcmpeqq_f16(__a, __b)
+#define vsubq_f16(__a, __b) __arm_vsubq_f16(__a, __b)
+#define vqmovntq_s16(__a, __b) __arm_vqmovntq_s16(__a, __b)
+#define vqmovnbq_s16(__a, __b) __arm_vqmovnbq_s16(__a, __b)
+#define vqdmulltq_s16(__a, __b) __arm_vqdmulltq_s16(__a, __b)
+#define vqdmulltq_n_s16(__a, __b) __arm_vqdmulltq_n_s16(__a, __b)
+#define vqdmullbq_s16(__a, __b) __arm_vqdmullbq_s16(__a, __b)
+#define vqdmullbq_n_s16(__a, __b) __arm_vqdmullbq_n_s16(__a, __b)
+#define vorrq_f16(__a, __b) __arm_vorrq_f16(__a, __b)
+#define vornq_f16(__a, __b) __arm_vornq_f16(__a, __b)
+#define vmulq_n_f16(__a, __b) __arm_vmulq_n_f16(__a, __b)
+#define vmulq_f16(__a, __b) __arm_vmulq_f16(__a, __b)
+#define vmovntq_s16(__a, __b) __arm_vmovntq_s16(__a, __b)
+#define vmovnbq_s16(__a, __b) __arm_vmovnbq_s16(__a, __b)
+#define vmlsldavxq_s16(__a, __b) __arm_vmlsldavxq_s16(__a, __b)
+#define vmlsldavq_s16(__a, __b) __arm_vmlsldavq_s16(__a, __b)
+#define vmlaldavxq_s16(__a, __b) __arm_vmlaldavxq_s16(__a, __b)
+#define vmlaldavq_s16(__a, __b) __arm_vmlaldavq_s16(__a, __b)
+#define vminnmvq_f16(__a, __b) __arm_vminnmvq_f16(__a, __b)
+#define vminnmq_f16(__a, __b) __arm_vminnmq_f16(__a, __b)
+#define vminnmavq_f16(__a, __b) __arm_vminnmavq_f16(__a, __b)
+#define vminnmaq_f16(__a, __b) __arm_vminnmaq_f16(__a, __b)
+#define vmaxnmvq_f16(__a, __b) __arm_vmaxnmvq_f16(__a, __b)
+#define vmaxnmq_f16(__a, __b) __arm_vmaxnmq_f16(__a, __b)
+#define vmaxnmavq_f16(__a, __b) __arm_vmaxnmavq_f16(__a, __b)
+#define vmaxnmaq_f16(__a, __b) __arm_vmaxnmaq_f16(__a, __b)
+#define veorq_f16(__a, __b) __arm_veorq_f16(__a, __b)
+#define vcmulq_rot90_f16(__a, __b) __arm_vcmulq_rot90_f16(__a, __b)
+#define vcmulq_rot270_f16(__a, __b) __arm_vcmulq_rot270_f16(__a, __b)
+#define vcmulq_rot180_f16(__a, __b) __arm_vcmulq_rot180_f16(__a, __b)
+#define vcmulq_f16(__a, __b) __arm_vcmulq_f16(__a, __b)
+#define vcaddq_rot90_f16(__a, __b) __arm_vcaddq_rot90_f16(__a, __b)
+#define vcaddq_rot270_f16(__a, __b) __arm_vcaddq_rot270_f16(__a, __b)
+#define vbicq_f16(__a, __b) __arm_vbicq_f16(__a, __b)
+#define vandq_f16(__a, __b) __arm_vandq_f16(__a, __b)
+#define vaddq_n_f16(__a, __b) __arm_vaddq_n_f16(__a, __b)
+#define vabdq_f16(__a, __b) __arm_vabdq_f16(__a, __b)
+#define vshlltq_n_s8(__a, __imm) __arm_vshlltq_n_s8(__a, __imm)
+#define vshllbq_n_s8(__a, __imm) __arm_vshllbq_n_s8(__a, __imm)
+#define vorrq_n_s16(__a, __imm) __arm_vorrq_n_s16(__a, __imm)
+#define vbicq_n_s16(__a, __imm) __arm_vbicq_n_s16(__a, __imm)
+#define vqmovntq_u32(__a, __b) __arm_vqmovntq_u32(__a, __b)
+#define vqmovnbq_u32(__a, __b) __arm_vqmovnbq_u32(__a, __b)
+#define vmulltq_poly_p16(__a, __b) __arm_vmulltq_poly_p16(__a, __b)
+#define vmullbq_poly_p16(__a, __b) __arm_vmullbq_poly_p16(__a, __b)
+#define vmovntq_u32(__a, __b) __arm_vmovntq_u32(__a, __b)
+#define vmovnbq_u32(__a, __b) __arm_vmovnbq_u32(__a, __b)
+#define vmlaldavq_u32(__a, __b) __arm_vmlaldavq_u32(__a, __b)
+#define vqmovuntq_s32(__a, __b) __arm_vqmovuntq_s32(__a, __b)
+#define vqmovunbq_s32(__a, __b) __arm_vqmovunbq_s32(__a, __b)
+#define vshlltq_n_u16(__a, __imm) __arm_vshlltq_n_u16(__a, __imm)
+#define vshllbq_n_u16(__a, __imm) __arm_vshllbq_n_u16(__a, __imm)
+#define vorrq_n_u32(__a, __imm) __arm_vorrq_n_u32(__a, __imm)
+#define vbicq_n_u32(__a, __imm) __arm_vbicq_n_u32(__a, __imm)
+#define vcmpneq_n_f32(__a, __b) __arm_vcmpneq_n_f32(__a, __b)
+#define vcmpneq_f32(__a, __b) __arm_vcmpneq_f32(__a, __b)
+#define vcmpltq_n_f32(__a, __b) __arm_vcmpltq_n_f32(__a, __b)
+#define vcmpltq_f32(__a, __b) __arm_vcmpltq_f32(__a, __b)
+#define vcmpleq_n_f32(__a, __b) __arm_vcmpleq_n_f32(__a, __b)
+#define vcmpleq_f32(__a, __b) __arm_vcmpleq_f32(__a, __b)
+#define vcmpgtq_n_f32(__a, __b) __arm_vcmpgtq_n_f32(__a, __b)
+#define vcmpgtq_f32(__a, __b) __arm_vcmpgtq_f32(__a, __b)
+#define vcmpgeq_n_f32(__a, __b) __arm_vcmpgeq_n_f32(__a, __b)
+#define vcmpgeq_f32(__a, __b) __arm_vcmpgeq_f32(__a, __b)
+#define vcmpeqq_n_f32(__a, __b) __arm_vcmpeqq_n_f32(__a, __b)
+#define vcmpeqq_f32(__a, __b) __arm_vcmpeqq_f32(__a, __b)
+#define vsubq_f32(__a, __b) __arm_vsubq_f32(__a, __b)
+#define vqmovntq_s32(__a, __b) __arm_vqmovntq_s32(__a, __b)
+#define vqmovnbq_s32(__a, __b) __arm_vqmovnbq_s32(__a, __b)
+#define vqdmulltq_s32(__a, __b) __arm_vqdmulltq_s32(__a, __b)
+#define vqdmulltq_n_s32(__a, __b) __arm_vqdmulltq_n_s32(__a, __b)
+#define vqdmullbq_s32(__a, __b) __arm_vqdmullbq_s32(__a, __b)
+#define vqdmullbq_n_s32(__a, __b) __arm_vqdmullbq_n_s32(__a, __b)
+#define vorrq_f32(__a, __b) __arm_vorrq_f32(__a, __b)
+#define vornq_f32(__a, __b) __arm_vornq_f32(__a, __b)
+#define vmulq_n_f32(__a, __b) __arm_vmulq_n_f32(__a, __b)
+#define vmulq_f32(__a, __b) __arm_vmulq_f32(__a, __b)
+#define vmovntq_s32(__a, __b) __arm_vmovntq_s32(__a, __b)
+#define vmovnbq_s32(__a, __b) __arm_vmovnbq_s32(__a, __b)
+#define vmlsldavxq_s32(__a, __b) __arm_vmlsldavxq_s32(__a, __b)
+#define vmlsldavq_s32(__a, __b) __arm_vmlsldavq_s32(__a, __b)
+#define vmlaldavxq_s32(__a, __b) __arm_vmlaldavxq_s32(__a, __b)
+#define vmlaldavq_s32(__a, __b) __arm_vmlaldavq_s32(__a, __b)
+#define vminnmvq_f32(__a, __b) __arm_vminnmvq_f32(__a, __b)
+#define vminnmq_f32(__a, __b) __arm_vminnmq_f32(__a, __b)
+#define vminnmavq_f32(__a, __b) __arm_vminnmavq_f32(__a, __b)
+#define vminnmaq_f32(__a, __b) __arm_vminnmaq_f32(__a, __b)
+#define vmaxnmvq_f32(__a, __b) __arm_vmaxnmvq_f32(__a, __b)
+#define vmaxnmq_f32(__a, __b) __arm_vmaxnmq_f32(__a, __b)
+#define vmaxnmavq_f32(__a, __b) __arm_vmaxnmavq_f32(__a, __b)
+#define vmaxnmaq_f32(__a, __b) __arm_vmaxnmaq_f32(__a, __b)
+#define veorq_f32(__a, __b) __arm_veorq_f32(__a, __b)
+#define vcmulq_rot90_f32(__a, __b) __arm_vcmulq_rot90_f32(__a, __b)
+#define vcmulq_rot270_f32(__a, __b) __arm_vcmulq_rot270_f32(__a, __b)
+#define vcmulq_rot180_f32(__a, __b) __arm_vcmulq_rot180_f32(__a, __b)
+#define vcmulq_f32(__a, __b) __arm_vcmulq_f32(__a, __b)
+#define vcaddq_rot90_f32(__a, __b) __arm_vcaddq_rot90_f32(__a, __b)
+#define vcaddq_rot270_f32(__a, __b) __arm_vcaddq_rot270_f32(__a, __b)
+#define vbicq_f32(__a, __b) __arm_vbicq_f32(__a, __b)
+#define vandq_f32(__a, __b) __arm_vandq_f32(__a, __b)
+#define vaddq_n_f32(__a, __b) __arm_vaddq_n_f32(__a, __b)
+#define vabdq_f32(__a, __b) __arm_vabdq_f32(__a, __b)
+#define vshlltq_n_s16(__a, __imm) __arm_vshlltq_n_s16(__a, __imm)
+#define vshllbq_n_s16(__a, __imm) __arm_vshllbq_n_s16(__a, __imm)
+#define vorrq_n_s32(__a, __imm) __arm_vorrq_n_s32(__a, __imm)
+#define vbicq_n_s32(__a, __imm) __arm_vbicq_n_s32(__a, __imm)
+#define vrmlaldavhq_u32(__a, __b) __arm_vrmlaldavhq_u32(__a, __b)
+#define vctp8q_m(__a, __p) __arm_vctp8q_m(__a, __p)
+#define vctp64q_m(__a, __p) __arm_vctp64q_m(__a, __p)
+#define vctp32q_m(__a, __p) __arm_vctp32q_m(__a, __p)
+#define vctp16q_m(__a, __p) __arm_vctp16q_m(__a, __p)
+#define vaddlvaq_u32(__a, __b) __arm_vaddlvaq_u32(__a, __b)
+#define vrmlsldavhxq_s32(__a, __b) __arm_vrmlsldavhxq_s32(__a, __b)
+#define vrmlsldavhq_s32(__a, __b) __arm_vrmlsldavhq_s32(__a, __b)
+#define vrmlaldavhxq_s32(__a, __b) __arm_vrmlaldavhxq_s32(__a, __b)
+#define vrmlaldavhq_s32(__a, __b) __arm_vrmlaldavhq_s32(__a, __b)
+#define vcvttq_f16_f32(__a, __b) __arm_vcvttq_f16_f32(__a, __b)
+#define vcvtbq_f16_f32(__a, __b) __arm_vcvtbq_f16_f32(__a, __b)
+#define vaddlvaq_s32(__a, __b) __arm_vaddlvaq_s32(__a, __b)
#endif
__extension__ extern __inline void
return __builtin_mve_vqshlq_n_sv4si (__a, __imm);
}
-#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
-
-__extension__ extern __inline void
+__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vst4q_f16 (float16_t * __addr, float16x8x4_t __value)
+__arm_vqmovntq_u16 (uint8x16_t __a, uint16x8_t __b)
{
- union { float16x8x4_t __i; __builtin_neon_xi __o; } __rv;
- __rv.__i = __value;
- __builtin_mve_vst4qv8hf (__addr, __rv.__o);
+ return __builtin_mve_vqmovntq_uv8hi (__a, __b);
}
-__extension__ extern __inline void
+__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vst4q_f32 (float32_t * __addr, float32x4x4_t __value)
+__arm_vqmovnbq_u16 (uint8x16_t __a, uint16x8_t __b)
{
- union { float32x4x4_t __i; __builtin_neon_xi __o; } __rv;
- __rv.__i = __value;
- __builtin_mve_vst4qv4sf (__addr, __rv.__o);
+ return __builtin_mve_vqmovnbq_uv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndxq_f16 (float16x8_t __a)
+__arm_vmulltq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
{
- return __builtin_mve_vrndxq_fv8hf (__a);
+ return __builtin_mve_vmulltq_poly_pv16qi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndxq_f32 (float32x4_t __a)
+__arm_vmullbq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
{
- return __builtin_mve_vrndxq_fv4sf (__a);
+ return __builtin_mve_vmullbq_poly_pv16qi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndq_f16 (float16x8_t __a)
+__arm_vmovntq_u16 (uint8x16_t __a, uint16x8_t __b)
{
- return __builtin_mve_vrndq_fv8hf (__a);
+ return __builtin_mve_vmovntq_uv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndq_f32 (float32x4_t __a)
+__arm_vmovnbq_u16 (uint8x16_t __a, uint16x8_t __b)
{
- return __builtin_mve_vrndq_fv4sf (__a);
+ return __builtin_mve_vmovnbq_uv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndpq_f16 (float16x8_t __a)
+__arm_vmlaldavq_u16 (uint16x8_t __a, uint16x8_t __b)
{
- return __builtin_mve_vrndpq_fv8hf (__a);
+ return __builtin_mve_vmlaldavq_uv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndpq_f32 (float32x4_t __a)
+__arm_vqmovuntq_s16 (uint8x16_t __a, int16x8_t __b)
{
- return __builtin_mve_vrndpq_fv4sf (__a);
+ return __builtin_mve_vqmovuntq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndnq_f16 (float16x8_t __a)
+__arm_vqmovunbq_s16 (uint8x16_t __a, int16x8_t __b)
{
- return __builtin_mve_vrndnq_fv8hf (__a);
+ return __builtin_mve_vqmovunbq_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndnq_f32 (float32x4_t __a)
+__arm_vshlltq_n_u8 (uint8x16_t __a, const int __imm)
{
- return __builtin_mve_vrndnq_fv4sf (__a);
+ return __builtin_mve_vshlltq_n_uv16qi (__a, __imm);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndmq_f16 (float16x8_t __a)
+__arm_vshllbq_n_u8 (uint8x16_t __a, const int __imm)
{
- return __builtin_mve_vrndmq_fv8hf (__a);
+ return __builtin_mve_vshllbq_n_uv16qi (__a, __imm);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndmq_f32 (float32x4_t __a)
+__arm_vorrq_n_u16 (uint16x8_t __a, const int __imm)
{
- return __builtin_mve_vrndmq_fv4sf (__a);
+ return __builtin_mve_vorrq_n_uv8hi (__a, __imm);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndaq_f16 (float16x8_t __a)
+__arm_vbicq_n_u16 (uint16x8_t __a, const int __imm)
{
- return __builtin_mve_vrndaq_fv8hf (__a);
+ return __builtin_mve_vbicq_n_uv8hi (__a, __imm);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrndaq_f32 (float32x4_t __a)
+__arm_vqmovntq_s16 (int8x16_t __a, int16x8_t __b)
{
- return __builtin_mve_vrndaq_fv4sf (__a);
+ return __builtin_mve_vqmovntq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrev64q_f16 (float16x8_t __a)
+__arm_vqmovnbq_s16 (int8x16_t __a, int16x8_t __b)
{
- return __builtin_mve_vrev64q_fv8hf (__a);
+ return __builtin_mve_vqmovnbq_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrev64q_f32 (float32x4_t __a)
+__arm_vqdmulltq_s16 (int16x8_t __a, int16x8_t __b)
{
- return __builtin_mve_vrev64q_fv4sf (__a);
+ return __builtin_mve_vqdmulltq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vnegq_f16 (float16x8_t __a)
+__arm_vqdmulltq_n_s16 (int16x8_t __a, int16_t __b)
{
- return __builtin_mve_vnegq_fv8hf (__a);
+ return __builtin_mve_vqdmulltq_n_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vnegq_f32 (float32x4_t __a)
+__arm_vqdmullbq_s16 (int16x8_t __a, int16x8_t __b)
{
- return __builtin_mve_vnegq_fv4sf (__a);
+ return __builtin_mve_vqdmullbq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_f16 (float16_t __a)
+__arm_vqdmullbq_n_s16 (int16x8_t __a, int16_t __b)
{
- return __builtin_mve_vdupq_n_fv8hf (__a);
+ return __builtin_mve_vqdmullbq_n_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_f32 (float32_t __a)
+__arm_vmovntq_s16 (int8x16_t __a, int16x8_t __b)
{
- return __builtin_mve_vdupq_n_fv4sf (__a);
+ return __builtin_mve_vmovntq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vabsq_f16 (float16x8_t __a)
+__arm_vmovnbq_s16 (int8x16_t __a, int16x8_t __b)
{
- return __builtin_mve_vabsq_fv8hf (__a);
+ return __builtin_mve_vmovnbq_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vabsq_f32 (float32x4_t __a)
+__arm_vmlsldavxq_s16 (int16x8_t __a, int16x8_t __b)
{
- return __builtin_mve_vabsq_fv4sf (__a);
+ return __builtin_mve_vmlsldavxq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vrev32q_f16 (float16x8_t __a)
+__arm_vmlsldavq_s16 (int16x8_t __a, int16x8_t __b)
{
- return __builtin_mve_vrev32q_fv8hf (__a);
+ return __builtin_mve_vmlsldavq_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvttq_f32_f16 (float16x8_t __a)
+__arm_vmlaldavxq_s16 (int16x8_t __a, int16x8_t __b)
{
- return __builtin_mve_vcvttq_f32_f16v4sf (__a);
+ return __builtin_mve_vmlaldavxq_sv8hi (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtbq_f32_f16 (float16x8_t __a)
+__arm_vmlaldavq_s16 (int16x8_t __a, int16x8_t __b)
{
- return __builtin_mve_vcvtbq_f32_f16v4sf (__a);
+ return __builtin_mve_vmlaldavq_sv8hi (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_f16_s16 (int16x8_t __a)
+__arm_vshlltq_n_s8 (int8x16_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_to_f_sv8hf (__a);
+ return __builtin_mve_vshlltq_n_sv16qi (__a, __imm);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_f32_s32 (int32x4_t __a)
+__arm_vshllbq_n_s8 (int8x16_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_to_f_sv4sf (__a);
+ return __builtin_mve_vshllbq_n_sv16qi (__a, __imm);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_f16_u16 (uint16x8_t __a)
+__arm_vorrq_n_s16 (int16x8_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_to_f_uv8hf (__a);
+ return __builtin_mve_vorrq_n_sv8hi (__a, __imm);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_f32_u32 (uint32x4_t __a)
+__arm_vbicq_n_s16 (int16x8_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_to_f_uv4sf (__a);
+ return __builtin_mve_vbicq_n_sv8hi (__a, __imm);
}
-__extension__ extern __inline int16x8_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_s16_f16 (float16x8_t __a)
+__arm_vqmovntq_u32 (uint16x8_t __a, uint32x4_t __b)
{
- return __builtin_mve_vcvtq_from_f_sv8hi (__a);
+ return __builtin_mve_vqmovntq_uv4si (__a, __b);
}
-__extension__ extern __inline int32x4_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_s32_f32 (float32x4_t __a)
+__arm_vqmovnbq_u32 (uint16x8_t __a, uint32x4_t __b)
{
- return __builtin_mve_vcvtq_from_f_sv4si (__a);
+ return __builtin_mve_vqmovnbq_uv4si (__a, __b);
}
-__extension__ extern __inline uint16x8_t
+__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_u16_f16 (float16x8_t __a)
+__arm_vmulltq_poly_p16 (uint16x8_t __a, uint16x8_t __b)
{
- return __builtin_mve_vcvtq_from_f_uv8hi (__a);
+ return __builtin_mve_vmulltq_poly_pv8hi (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_u32_f32 (float32x4_t __a)
+__arm_vmullbq_poly_p16 (uint16x8_t __a, uint16x8_t __b)
{
- return __builtin_mve_vcvtq_from_f_uv4si (__a);
+ return __builtin_mve_vmullbq_poly_pv8hi (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtpq_u16_f16 (float16x8_t __a)
+__arm_vmovntq_u32 (uint16x8_t __a, uint32x4_t __b)
{
- return __builtin_mve_vcvtpq_uv8hi (__a);
+ return __builtin_mve_vmovntq_uv4si (__a, __b);
}
-__extension__ extern __inline uint32x4_t
+__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtpq_u32_f32 (float32x4_t __a)
+__arm_vmovnbq_u32 (uint16x8_t __a, uint32x4_t __b)
{
- return __builtin_mve_vcvtpq_uv4si (__a);
+ return __builtin_mve_vmovnbq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_u32 (uint32x4_t __a, uint32x4_t __b)
+{
+ return __builtin_mve_vmlaldavq_uv4si (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtnq_u16_f16 (float16x8_t __a)
+__arm_vqmovuntq_s32 (uint16x8_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtnq_uv8hi (__a);
+ return __builtin_mve_vqmovuntq_sv4si (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtmq_u16_f16 (float16x8_t __a)
+__arm_vqmovunbq_s32 (uint16x8_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtmq_uv8hi (__a);
+ return __builtin_mve_vqmovunbq_sv4si (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtmq_u32_f32 (float32x4_t __a)
+__arm_vshlltq_n_u16 (uint16x8_t __a, const int __imm)
{
- return __builtin_mve_vcvtmq_uv4si (__a);
+ return __builtin_mve_vshlltq_n_uv8hi (__a, __imm);
}
-__extension__ extern __inline uint16x8_t
+__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtaq_u16_f16 (float16x8_t __a)
+__arm_vshllbq_n_u16 (uint16x8_t __a, const int __imm)
{
- return __builtin_mve_vcvtaq_uv8hi (__a);
+ return __builtin_mve_vshllbq_n_uv8hi (__a, __imm);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtaq_u32_f32 (float32x4_t __a)
+__arm_vorrq_n_u32 (uint32x4_t __a, const int __imm)
{
- return __builtin_mve_vcvtaq_uv4si (__a);
+ return __builtin_mve_vorrq_n_uv4si (__a, __imm);
}
- __extension__ extern __inline int16x8_t
- __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtaq_s16_f16 (float16x8_t __a)
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_n_u32 (uint32x4_t __a, const int __imm)
{
- return __builtin_mve_vcvtaq_sv8hi (__a);
+ return __builtin_mve_vbicq_n_uv4si (__a, __imm);
}
-__extension__ extern __inline int32x4_t
+__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtaq_s32_f32 (float32x4_t __a)
+__arm_vqmovntq_s32 (int16x8_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtaq_sv4si (__a);
+ return __builtin_mve_vqmovntq_sv4si (__a, __b);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtnq_s16_f16 (float16x8_t __a)
+__arm_vqmovnbq_s32 (int16x8_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtnq_sv8hi (__a);
+ return __builtin_mve_vqmovnbq_sv4si (__a, __b);
}
-__extension__ extern __inline int32x4_t
+__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtnq_s32_f32 (float32x4_t __a)
+__arm_vqdmulltq_s32 (int32x4_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtnq_sv4si (__a);
+ return __builtin_mve_vqdmulltq_sv4si (__a, __b);
}
-__extension__ extern __inline int16x8_t
+__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtpq_s16_f16 (float16x8_t __a)
+__arm_vqdmulltq_n_s32 (int32x4_t __a, int32_t __b)
{
- return __builtin_mve_vcvtpq_sv8hi (__a);
+ return __builtin_mve_vqdmulltq_n_sv4si (__a, __b);
}
-__extension__ extern __inline int32x4_t
+__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtpq_s32_f32 (float32x4_t __a)
+__arm_vqdmullbq_s32 (int32x4_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtpq_sv4si (__a);
+ return __builtin_mve_vqdmullbq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_n_s32 (int32x4_t __a, int32_t __b)
+{
+ return __builtin_mve_vqdmullbq_n_sv4si (__a, __b);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtmq_s16_f16 (float16x8_t __a)
+__arm_vmovntq_s32 (int16x8_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtmq_sv8hi (__a);
+ return __builtin_mve_vmovntq_sv4si (__a, __b);
}
-__extension__ extern __inline int32x4_t
+__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtmq_s32_f32 (float32x4_t __a)
+__arm_vmovnbq_s32 (int16x8_t __a, int32x4_t __b)
{
- return __builtin_mve_vcvtmq_sv4si (__a);
+ return __builtin_mve_vmovnbq_sv4si (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vsubq_n_f16 (float16x8_t __a, float16_t __b)
+__arm_vmlsldavxq_s32 (int32x4_t __a, int32x4_t __b)
{
- return __builtin_mve_vsubq_n_fv8hf (__a, __b);
+ return __builtin_mve_vmlsldavxq_sv4si (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vsubq_n_f32 (float32x4_t __a, float32_t __b)
+__arm_vmlsldavq_s32 (int32x4_t __a, int32x4_t __b)
{
- return __builtin_mve_vsubq_n_fv4sf (__a, __b);
+ return __builtin_mve_vmlsldavq_sv4si (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbrsrq_n_f16 (float16x8_t __a, int32_t __b)
+__arm_vmlaldavxq_s32 (int32x4_t __a, int32x4_t __b)
{
- return __builtin_mve_vbrsrq_n_fv8hf (__a, __b);
+ return __builtin_mve_vmlaldavxq_sv4si (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vbrsrq_n_f32 (float32x4_t __a, int32_t __b)
+__arm_vmlaldavq_s32 (int32x4_t __a, int32x4_t __b)
{
- return __builtin_mve_vbrsrq_n_fv4sf (__a, __b);
+ return __builtin_mve_vmlaldavq_sv4si (__a, __b);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_f16_s16 (int16x8_t __a, const int __imm6)
+__arm_vshlltq_n_s16 (int16x8_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_n_to_f_sv8hf (__a, __imm6);
+ return __builtin_mve_vshlltq_n_sv8hi (__a, __imm);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_f32_s32 (int32x4_t __a, const int __imm6)
+__arm_vshllbq_n_s16 (int16x8_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_n_to_f_sv4sf (__a, __imm6);
+ return __builtin_mve_vshllbq_n_sv8hi (__a, __imm);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_f16_u16 (uint16x8_t __a, const int __imm6)
+__arm_vorrq_n_s32 (int32x4_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_n_to_f_uv8hf (__a, __imm6);
+ return __builtin_mve_vorrq_n_sv4si (__a, __imm);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_f32_u32 (uint32x4_t __a, const int __imm6)
+__arm_vbicq_n_s32 (int32x4_t __a, const int __imm)
{
- return __builtin_mve_vcvtq_n_to_f_uv4sf (__a, __imm6);
+ return __builtin_mve_vbicq_n_sv4si (__a, __imm);
}
-__extension__ extern __inline float16x8_t
+__extension__ extern __inline uint64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcreateq_f16 (uint64_t __a, uint64_t __b)
+__arm_vrmlaldavhq_u32 (uint32x4_t __a, uint32x4_t __b)
{
- return __builtin_mve_vcreateq_fv8hf (__a, __b);
+ return __builtin_mve_vrmlaldavhq_uv4si (__a, __b);
}
-__extension__ extern __inline float32x4_t
+__extension__ extern __inline mve_pred16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcreateq_f32 (uint64_t __a, uint64_t __b)
+__arm_vctp8q_m (uint32_t __a, mve_pred16_t __p)
{
- return __builtin_mve_vcreateq_fv4sf (__a, __b);
+ return __builtin_mve_vctp8q_mhi (__a, __p);
}
-__extension__ extern __inline int16x8_t
+__extension__ extern __inline mve_pred16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_s16_f16 (float16x8_t __a, const int __imm6)
+__arm_vctp64q_m (uint32_t __a, mve_pred16_t __p)
{
- return __builtin_mve_vcvtq_n_from_f_sv8hi (__a, __imm6);
+ return __builtin_mve_vctp64q_mhi (__a, __p);
}
-__extension__ extern __inline int32x4_t
+__extension__ extern __inline mve_pred16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_s32_f32 (float32x4_t __a, const int __imm6)
+__arm_vctp32q_m (uint32_t __a, mve_pred16_t __p)
{
- return __builtin_mve_vcvtq_n_from_f_sv4si (__a, __imm6);
+ return __builtin_mve_vctp32q_mhi (__a, __p);
}
-__extension__ extern __inline uint16x8_t
+__extension__ extern __inline mve_pred16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_u16_f16 (float16x8_t __a, const int __imm6)
+__arm_vctp16q_m (uint32_t __a, mve_pred16_t __p)
{
- return __builtin_mve_vcvtq_n_from_f_uv8hi (__a, __imm6);
+ return __builtin_mve_vctp16q_mhi (__a, __p);
}
-__extension__ extern __inline uint32x4_t
+__extension__ extern __inline uint64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vcvtq_n_u32_f32 (float32x4_t __a, const int __imm6)
+__arm_vaddlvaq_u32 (uint64_t __a, uint32x4_t __b)
{
- return __builtin_mve_vcvtq_n_from_f_uv4si (__a, __imm6);
+ return __builtin_mve_vaddlvaq_uv4si (__a, __b);
}
-#endif
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhxq_s32 (int32x4_t __a, int32x4_t __b)
+{
+ return __builtin_mve_vrmlsldavhxq_sv4si (__a, __b);
+}
-enum {
- __ARM_mve_type_float16_t = 1,
- __ARM_mve_type_float16_t_ptr,
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhq_s32 (int32x4_t __a, int32x4_t __b)
+{
+ return __builtin_mve_vrmlsldavhq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhxq_s32 (int32x4_t __a, int32x4_t __b)
+{
+ return __builtin_mve_vrmlaldavhxq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq_s32 (int32x4_t __a, int32x4_t __b)
+{
+ return __builtin_mve_vrmlaldavhq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq_s32 (int64_t __a, int32x4_t __b)
+{
+ return __builtin_mve_vaddlvaq_sv4si (__a, __b);
+}
+
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q_f16 (float16_t * __addr, float16x8x4_t __value)
+{
+ union { float16x8x4_t __i; __builtin_neon_xi __o; } __rv;
+ __rv.__i = __value;
+ __builtin_mve_vst4qv8hf (__addr, __rv.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q_f32 (float32_t * __addr, float32x4x4_t __value)
+{
+ union { float32x4x4_t __i; __builtin_neon_xi __o; } __rv;
+ __rv.__i = __value;
+ __builtin_mve_vst4qv4sf (__addr, __rv.__o);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrndxq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrndxq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrndq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrndq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrndpq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrndpq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrndnq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrndnq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrndmq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrndmq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrndaq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrndaq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrev64q_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vrev64q_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vnegq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vnegq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n_f16 (float16_t __a)
+{
+ return __builtin_mve_vdupq_n_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n_f32 (float32_t __a)
+{
+ return __builtin_mve_vdupq_n_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vabsq_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vabsq_fv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vrev32q_fv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvttq_f32_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvttq_f32_f16v4sf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtbq_f32_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtbq_f32_f16v4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_f16_s16 (int16x8_t __a)
+{
+ return __builtin_mve_vcvtq_to_f_sv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_f32_s32 (int32x4_t __a)
+{
+ return __builtin_mve_vcvtq_to_f_sv4sf (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_f16_u16 (uint16x8_t __a)
+{
+ return __builtin_mve_vcvtq_to_f_uv8hf (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_f32_u32 (uint32x4_t __a)
+{
+ return __builtin_mve_vcvtq_to_f_uv4sf (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_s16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtq_from_f_sv8hi (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_s32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtq_from_f_sv4si (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_u16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtq_from_f_uv8hi (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_u32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtq_from_f_uv4si (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_u16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtpq_uv8hi (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_u32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtpq_uv4si (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_u16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtnq_uv8hi (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_u16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtmq_uv8hi (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_u32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtmq_uv4si (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_u16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtaq_uv8hi (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_u32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtaq_uv4si (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_s16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtaq_sv8hi (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_s32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtaq_sv4si (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_s16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtnq_sv8hi (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_s32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtnq_sv4si (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_s16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtpq_sv8hi (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_s32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtpq_sv4si (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_s16_f16 (float16x8_t __a)
+{
+ return __builtin_mve_vcvtmq_sv8hi (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_s32_f32 (float32x4_t __a)
+{
+ return __builtin_mve_vcvtmq_sv4si (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vsubq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vsubq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_n_f16 (float16x8_t __a, int32_t __b)
+{
+ return __builtin_mve_vbrsrq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_n_f32 (float32x4_t __a, int32_t __b)
+{
+ return __builtin_mve_vbrsrq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_f16_s16 (int16x8_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_to_f_sv8hf (__a, __imm6);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_f32_s32 (int32x4_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_to_f_sv4sf (__a, __imm6);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_f16_u16 (uint16x8_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_to_f_uv8hf (__a, __imm6);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_f32_u32 (uint32x4_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_to_f_uv4sf (__a, __imm6);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_f16 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_f32 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_s16_f16 (float16x8_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_sv8hi (__a, __imm6);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_s32_f32 (float32x4_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_sv4si (__a, __imm6);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_u16_f16 (float16x8_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_uv8hi (__a, __imm6);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_u32_f32 (float32x4_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_uv4si (__a, __imm6);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vcmpneq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmpneq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vcmpltq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmpltq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vcmpleq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmpleq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vcmpgtq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmpgtq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vcmpgeq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmpgeq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vcmpeqq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmpeqq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vsubq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vorrq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vornq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vmulq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vmulq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq_f16 (float16_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vminnmvq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vminnmq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq_f16 (float16_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vminnmavq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vminnmaq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq_f16 (float16_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vmaxnmvq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vmaxnmq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq_f16 (float16_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vmaxnmavq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vmaxnmaq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_veorq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmulq_rot90_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmulq_rot270_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmulq_rot180_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcmulq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcaddq_rot90_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vcaddq_rot270_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vbicq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vandq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_n_f16 (float16x8_t __a, float16_t __b)
+{
+ return __builtin_mve_vaddq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_f16 (float16x8_t __a, float16x8_t __b)
+{
+ return __builtin_mve_vabdq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vcmpneq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmpneq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vcmpltq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmpltq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vcmpleq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmpleq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vcmpgtq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmpgtq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vcmpgeq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmpgeq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vcmpeqq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmpeqq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vsubq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vorrq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vornq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vmulq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vmulq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq_f32 (float32_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vminnmvq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vminnmq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq_f32 (float32_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vminnmavq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vminnmaq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq_f32 (float32_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vmaxnmvq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vmaxnmq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq_f32 (float32_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vmaxnmavq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vmaxnmaq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_veorq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmulq_rot90_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmulq_rot270_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmulq_rot180_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcmulq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcaddq_rot90_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcaddq_rot270_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vbicq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vandq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_n_f32 (float32x4_t __a, float32_t __b)
+{
+ return __builtin_mve_vaddq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_f32 (float32x4_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vabdq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvttq_f16_f32 (float16x8_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcvttq_f16_f32v8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtbq_f16_f32 (float16x8_t __a, float32x4_t __b)
+{
+ return __builtin_mve_vcvtbq_f16_f32v8hf (__a, __b);
+}
+
+#endif
+
+enum {
+ __ARM_mve_type_float16_t = 1,
+ __ARM_mve_type_float16_t_ptr,
__ARM_mve_type_float16_t_const_ptr,
__ARM_mve_type_float16x8_t,
__ARM_mve_type_float16x8x2_t,
__ARM_mve_unsupported_type
};
-#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
-#define __ARM_mve_typeid(x) _Generic(x, \
- float16_t: __ARM_mve_type_float16_t, \
- float16_t *: __ARM_mve_type_float16_t_ptr, \
- float16_t const *: __ARM_mve_type_float16_t_const_ptr, \
- float16x8_t: __ARM_mve_type_float16x8_t, \
- float16x8x2_t: __ARM_mve_type_float16x8x2_t, \
- float16x8x4_t: __ARM_mve_type_float16x8x4_t, \
- float32_t: __ARM_mve_type_float32_t, \
- float32_t *: __ARM_mve_type_float32_t_ptr, \
- float32_t const *: __ARM_mve_type_float32_t_const_ptr, \
- float32x4_t: __ARM_mve_type_float32x4_t, \
- float32x4x2_t: __ARM_mve_type_float32x4x2_t, \
- float32x4x4_t: __ARM_mve_type_float32x4x4_t, \
- int16_t: __ARM_mve_type_int16_t, \
- int16_t *: __ARM_mve_type_int16_t_ptr, \
- int16_t const *: __ARM_mve_type_int16_t_const_ptr, \
- int16x8_t: __ARM_mve_type_int16x8_t, \
- int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
- int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
- int32_t: __ARM_mve_type_int32_t, \
- int32_t *: __ARM_mve_type_int32_t_ptr, \
- int32_t const *: __ARM_mve_type_int32_t_const_ptr, \
- int32x4_t: __ARM_mve_type_int32x4_t, \
- int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
- int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
- int64_t: __ARM_mve_type_int64_t, \
- int64_t *: __ARM_mve_type_int64_t_ptr, \
- int64_t const *: __ARM_mve_type_int64_t_const_ptr, \
- int64x2_t: __ARM_mve_type_int64x2_t, \
- int8_t: __ARM_mve_type_int8_t, \
- int8_t *: __ARM_mve_type_int8_t_ptr, \
- int8_t const *: __ARM_mve_type_int8_t_const_ptr, \
- int8x16_t: __ARM_mve_type_int8x16_t, \
- int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
- int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
- uint16_t: __ARM_mve_type_uint16_t, \
- uint16_t *: __ARM_mve_type_uint16_t_ptr, \
- uint16_t const *: __ARM_mve_type_uint16_t_const_ptr, \
- uint16x8_t: __ARM_mve_type_uint16x8_t, \
- uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
- uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
- uint32_t: __ARM_mve_type_uint32_t, \
- uint32_t *: __ARM_mve_type_uint32_t_ptr, \
- uint32_t const *: __ARM_mve_type_uint32_t_const_ptr, \
- uint32x4_t: __ARM_mve_type_uint32x4_t, \
- uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
- uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
- uint64_t: __ARM_mve_type_uint64_t, \
- uint64_t *: __ARM_mve_type_uint64_t_ptr, \
- uint64_t const *: __ARM_mve_type_uint64_t_const_ptr, \
- uint64x2_t: __ARM_mve_type_uint64x2_t, \
- uint8_t: __ARM_mve_type_uint8_t, \
- uint8_t *: __ARM_mve_type_uint8_t_ptr, \
- uint8_t const *: __ARM_mve_type_uint8_t_const_ptr, \
- uint8x16_t: __ARM_mve_type_uint8x16_t, \
- uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
- uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
- default: _Generic(x, \
- signed char: __ARM_mve_type_int8_t, \
- short: __ARM_mve_type_int16_t, \
- int: __ARM_mve_type_int32_t, \
- long: __ARM_mve_type_int32_t, \
- long long: __ARM_mve_type_int64_t, \
- unsigned char: __ARM_mve_type_uint8_t, \
- unsigned short: __ARM_mve_type_uint16_t, \
- unsigned int: __ARM_mve_type_uint32_t, \
- unsigned long: __ARM_mve_type_uint32_t, \
- unsigned long long: __ARM_mve_type_uint64_t, \
- default: __ARM_mve_unsupported_type))
-#else
-#define __ARM_mve_typeid(x) _Generic(x, \
- int16_t: __ARM_mve_type_int16_t, \
- int16_t *: __ARM_mve_type_int16_t_ptr, \
- int16_t const *: __ARM_mve_type_int16_t_const_ptr, \
- int16x8_t: __ARM_mve_type_int16x8_t, \
- int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
- int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
- int32_t: __ARM_mve_type_int32_t, \
- int32_t *: __ARM_mve_type_int32_t_ptr, \
- int32_t const *: __ARM_mve_type_int32_t_const_ptr, \
- int32x4_t: __ARM_mve_type_int32x4_t, \
- int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
- int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
- int64_t: __ARM_mve_type_int64_t, \
- int64_t *: __ARM_mve_type_int64_t_ptr, \
- int64_t const *: __ARM_mve_type_int64_t_const_ptr, \
- int64x2_t: __ARM_mve_type_int64x2_t, \
- int8_t: __ARM_mve_type_int8_t, \
- int8_t *: __ARM_mve_type_int8_t_ptr, \
- int8_t const *: __ARM_mve_type_int8_t_const_ptr, \
- int8x16_t: __ARM_mve_type_int8x16_t, \
- int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
- int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
- uint16_t: __ARM_mve_type_uint16_t, \
- uint16_t *: __ARM_mve_type_uint16_t_ptr, \
- uint16_t const *: __ARM_mve_type_uint16_t_const_ptr, \
- uint16x8_t: __ARM_mve_type_uint16x8_t, \
- uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
- uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
- uint32_t: __ARM_mve_type_uint32_t, \
- uint32_t *: __ARM_mve_type_uint32_t_ptr, \
- uint32_t const *: __ARM_mve_type_uint32_t_const_ptr, \
- uint32x4_t: __ARM_mve_type_uint32x4_t, \
- uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
- uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
- uint64_t: __ARM_mve_type_uint64_t, \
- uint64_t *: __ARM_mve_type_uint64_t_ptr, \
- uint64_t const *: __ARM_mve_type_uint64_t_const_ptr, \
- uint64x2_t: __ARM_mve_type_uint64x2_t, \
- uint8_t: __ARM_mve_type_uint8_t, \
- uint8_t *: __ARM_mve_type_uint8_t_ptr, \
- uint8_t const *: __ARM_mve_type_uint8_t_const_ptr, \
- uint8x16_t: __ARM_mve_type_uint8x16_t, \
- uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
- uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
- default: _Generic(x, \
- signed char: __ARM_mve_type_int8_t, \
- short: __ARM_mve_type_int16_t, \
- int: __ARM_mve_type_int32_t, \
- long: __ARM_mve_type_int32_t, \
- long long: __ARM_mve_type_int64_t, \
- unsigned char: __ARM_mve_type_uint8_t, \
- unsigned short: __ARM_mve_type_uint16_t, \
- unsigned int: __ARM_mve_type_uint32_t, \
- unsigned long: __ARM_mve_type_uint32_t, \
- unsigned long long: __ARM_mve_type_uint64_t, \
- default: __ARM_mve_unsupported_type))
-#endif /* MVE Floating point. */
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+#define __ARM_mve_typeid(x) _Generic(x, \
+ float16_t: __ARM_mve_type_float16_t, \
+ float16_t *: __ARM_mve_type_float16_t_ptr, \
+ float16_t const *: __ARM_mve_type_float16_t_const_ptr, \
+ float16x8_t: __ARM_mve_type_float16x8_t, \
+ float16x8x2_t: __ARM_mve_type_float16x8x2_t, \
+ float16x8x4_t: __ARM_mve_type_float16x8x4_t, \
+ float32_t: __ARM_mve_type_float32_t, \
+ float32_t *: __ARM_mve_type_float32_t_ptr, \
+ float32_t const *: __ARM_mve_type_float32_t_const_ptr, \
+ float32x4_t: __ARM_mve_type_float32x4_t, \
+ float32x4x2_t: __ARM_mve_type_float32x4x2_t, \
+ float32x4x4_t: __ARM_mve_type_float32x4x4_t, \
+ int16_t: __ARM_mve_type_int16_t, \
+ int16_t *: __ARM_mve_type_int16_t_ptr, \
+ int16_t const *: __ARM_mve_type_int16_t_const_ptr, \
+ int16x8_t: __ARM_mve_type_int16x8_t, \
+ int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
+ int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
+ int32_t: __ARM_mve_type_int32_t, \
+ int32_t *: __ARM_mve_type_int32_t_ptr, \
+ int32_t const *: __ARM_mve_type_int32_t_const_ptr, \
+ int32x4_t: __ARM_mve_type_int32x4_t, \
+ int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
+ int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
+ int64_t: __ARM_mve_type_int64_t, \
+ int64_t *: __ARM_mve_type_int64_t_ptr, \
+ int64_t const *: __ARM_mve_type_int64_t_const_ptr, \
+ int64x2_t: __ARM_mve_type_int64x2_t, \
+ int8_t: __ARM_mve_type_int8_t, \
+ int8_t *: __ARM_mve_type_int8_t_ptr, \
+ int8_t const *: __ARM_mve_type_int8_t_const_ptr, \
+ int8x16_t: __ARM_mve_type_int8x16_t, \
+ int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
+ int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
+ uint16_t: __ARM_mve_type_uint16_t, \
+ uint16_t *: __ARM_mve_type_uint16_t_ptr, \
+ uint16_t const *: __ARM_mve_type_uint16_t_const_ptr, \
+ uint16x8_t: __ARM_mve_type_uint16x8_t, \
+ uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
+ uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
+ uint32_t: __ARM_mve_type_uint32_t, \
+ uint32_t *: __ARM_mve_type_uint32_t_ptr, \
+ uint32_t const *: __ARM_mve_type_uint32_t_const_ptr, \
+ uint32x4_t: __ARM_mve_type_uint32x4_t, \
+ uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
+ uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
+ uint64_t: __ARM_mve_type_uint64_t, \
+ uint64_t *: __ARM_mve_type_uint64_t_ptr, \
+ uint64_t const *: __ARM_mve_type_uint64_t_const_ptr, \
+ uint64x2_t: __ARM_mve_type_uint64x2_t, \
+ uint8_t: __ARM_mve_type_uint8_t, \
+ uint8_t *: __ARM_mve_type_uint8_t_ptr, \
+ uint8_t const *: __ARM_mve_type_uint8_t_const_ptr, \
+ uint8x16_t: __ARM_mve_type_uint8x16_t, \
+ uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
+ uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
+ default: _Generic(x, \
+ signed char: __ARM_mve_type_int8_t, \
+ short: __ARM_mve_type_int16_t, \
+ int: __ARM_mve_type_int32_t, \
+ long: __ARM_mve_type_int32_t, \
+ long long: __ARM_mve_type_int64_t, \
+ unsigned char: __ARM_mve_type_uint8_t, \
+ unsigned short: __ARM_mve_type_uint16_t, \
+ unsigned int: __ARM_mve_type_uint32_t, \
+ unsigned long: __ARM_mve_type_uint32_t, \
+ unsigned long long: __ARM_mve_type_uint64_t, \
+ default: __ARM_mve_unsupported_type))
+#else
+#define __ARM_mve_typeid(x) _Generic(x, \
+ int16_t: __ARM_mve_type_int16_t, \
+ int16_t *: __ARM_mve_type_int16_t_ptr, \
+ int16_t const *: __ARM_mve_type_int16_t_const_ptr, \
+ int16x8_t: __ARM_mve_type_int16x8_t, \
+ int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
+ int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
+ int32_t: __ARM_mve_type_int32_t, \
+ int32_t *: __ARM_mve_type_int32_t_ptr, \
+ int32_t const *: __ARM_mve_type_int32_t_const_ptr, \
+ int32x4_t: __ARM_mve_type_int32x4_t, \
+ int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
+ int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
+ int64_t: __ARM_mve_type_int64_t, \
+ int64_t *: __ARM_mve_type_int64_t_ptr, \
+ int64_t const *: __ARM_mve_type_int64_t_const_ptr, \
+ int64x2_t: __ARM_mve_type_int64x2_t, \
+ int8_t: __ARM_mve_type_int8_t, \
+ int8_t *: __ARM_mve_type_int8_t_ptr, \
+ int8_t const *: __ARM_mve_type_int8_t_const_ptr, \
+ int8x16_t: __ARM_mve_type_int8x16_t, \
+ int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
+ int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
+ uint16_t: __ARM_mve_type_uint16_t, \
+ uint16_t *: __ARM_mve_type_uint16_t_ptr, \
+ uint16_t const *: __ARM_mve_type_uint16_t_const_ptr, \
+ uint16x8_t: __ARM_mve_type_uint16x8_t, \
+ uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
+ uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
+ uint32_t: __ARM_mve_type_uint32_t, \
+ uint32_t *: __ARM_mve_type_uint32_t_ptr, \
+ uint32_t const *: __ARM_mve_type_uint32_t_const_ptr, \
+ uint32x4_t: __ARM_mve_type_uint32x4_t, \
+ uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
+ uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
+ uint64_t: __ARM_mve_type_uint64_t, \
+ uint64_t *: __ARM_mve_type_uint64_t_ptr, \
+ uint64_t const *: __ARM_mve_type_uint64_t_const_ptr, \
+ uint64x2_t: __ARM_mve_type_uint64x2_t, \
+ uint8_t: __ARM_mve_type_uint8_t, \
+ uint8_t *: __ARM_mve_type_uint8_t_ptr, \
+ uint8_t const *: __ARM_mve_type_uint8_t_const_ptr, \
+ uint8x16_t: __ARM_mve_type_uint8x16_t, \
+ uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
+ uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
+ default: _Generic(x, \
+ signed char: __ARM_mve_type_int8_t, \
+ short: __ARM_mve_type_int16_t, \
+ int: __ARM_mve_type_int32_t, \
+ long: __ARM_mve_type_int32_t, \
+ long long: __ARM_mve_type_int64_t, \
+ unsigned char: __ARM_mve_type_uint8_t, \
+ unsigned short: __ARM_mve_type_uint16_t, \
+ unsigned int: __ARM_mve_type_uint32_t, \
+ unsigned long: __ARM_mve_type_uint32_t, \
+ unsigned long long: __ARM_mve_type_uint64_t, \
+ default: __ARM_mve_unsupported_type))
+#endif /* MVE Floating point. */
+
+extern void *__ARM_undef;
+#define __ARM_mve_coerce(param, type) \
+ _Generic(param, type: param, default: *(type *)__ARM_undef)
+
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+
+#define vst4q(p0,p1) __arm_vst4q(p0,p1)
+#define __arm_vst4q(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_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
+ int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
+ int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \
+ int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \
+ int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
+
+#define vrndxq(p0) __arm_vrndxq(p0)
+#define __arm_vrndxq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndxq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndxq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrndq(p0) __arm_vrndq(p0)
+#define __arm_vrndq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrndpq(p0) __arm_vrndpq(p0)
+#define __arm_vrndpq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndpq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndpq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrndnq(p0) __arm_vrndnq(p0)
+#define __arm_vrndnq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndnq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndnq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrndmq(p0) __arm_vrndmq(p0)
+#define __arm_vrndmq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndmq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndmq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrndaq(p0) __arm_vrndaq(p0)
+#define __arm_vrndaq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndaq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndaq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrev64q(p0) __arm_vrev64q(p0)
+#define __arm_vrev64q(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev64q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vrev64q_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vrev64q_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev64q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev64q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrev64q_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev64q_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrev64q_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vnegq(p0) __arm_vnegq(p0)
+#define __arm_vnegq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vnegq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vnegq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vdupq_n(p0) __arm_vdupq_n(p0)
+#define __arm_vdupq_n(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vdupq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vdupq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vabsq(p0) __arm_vabsq(p0)
+#define __arm_vabsq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vabsq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vabsq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define vrev32q(p0) __arm_vrev32q(p0)
+#define __arm_vrev32q(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev32q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vrev32q_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev32q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev32q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev32q_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
+
+#define vcvtbq_f32(p0) __arm_vcvtbq_f32(p0)
+#define __arm_vcvtbq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvtbq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
+
+#define vcvttq_f32(p0) __arm_vcvttq_f32(p0)
+#define __arm_vcvttq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvttq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
+
+#define vrev16q(p0) __arm_vrev16q(p0)
+#define __arm_vrev16q(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev16q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev16q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)));})
+
+#define vqabsq(p0) __arm_vqabsq(p0)
+#define __arm_vqabsq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vqabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vqabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vqabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+
+#define vqnegq(p0) __arm_vqnegq(p0)
+#define __arm_vqnegq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vqnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vqnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vqnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+
+#define vmvnq(p0) __arm_vmvnq(p0)
+#define __arm_vmvnq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vmvnq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vmvnq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vmvnq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmvnq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmvnq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vmvnq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+
+#define vmovlbq(p0) __arm_vmovlbq(p0)
+#define __arm_vmovlbq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovlbq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
+
+#define vmovltq(p0) __arm_vmovltq(p0)
+#define __arm_vmovltq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovltq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
+
+#define vclzq(p0) __arm_vclzq(p0)
+#define __arm_vclzq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vclzq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vclzq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vclzq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vclzq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vclzq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vclzq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+
+#define vclsq(p0) __arm_vclsq(p0)
+#define __arm_vclsq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vclsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vclsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vclsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+
+#define vcvtq(p0) __arm_vcvtq(p0)
+#define __arm_vcvtq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_f16_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vcvtq_f32_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+
+#define vsubq(p0,p1) __arm_vsubq(p0,p1)
+#define __arm_vsubq(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_float16x8_t][__ARM_mve_type_float16_t]: __arm_vsubq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vsubq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vsubq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vsubq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vsubq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vsubq_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_vsubq_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_vsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vsubq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsubq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vsubq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vsubq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vshlq(p0,p1) __arm_vshlq(p0,p1)
+#define __arm_vshlq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vshlq_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_vshlq_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_vshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vshrq(p0,p1) __arm_vshrq(p0,p1)
+#define __arm_vshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vcvtq_n(p0,p1) __arm_vcvtq_n(p0,p1)
+#define __arm_vcvtq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_n_f16_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vcvtq_n_f32_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_n_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_n_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vorrq(p0,p1) __arm_vorrq(p0,p1)
+#define __arm_vorrq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vorrq_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_vorrq_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_vorrq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vorrq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vorrq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vorrq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vorrq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vorrq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vabdq(p0,p1) __arm_vabdq(p0,p1)
+#define __arm_vabdq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_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_vabdq_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_vabdq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vaddq(p0,p1) __arm_vaddq(p0,p1)
+#define __arm_vaddq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vaddq_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_vaddq_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_vaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vaddq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vaddq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vaddq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vandq(p0,p1) __arm_vandq(p0,p1)
+#define __arm_vandq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vandq_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_vandq_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_vandq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vandq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vandq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vandq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vandq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vandq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vbicq(p0,p1) __arm_vbicq(p0,p1)
+#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_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)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbicq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbicq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vornq(p0,p1) __arm_vornq(p0,p1)
+#define __arm_vornq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vornq_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_vornq_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_vornq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vornq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vornq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vornq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vornq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vornq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmulq_n(p0,p1) __arm_vmulq_n(p0,p1)
+#define __arm_vmulq_n(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vmulq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vmulq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vmulq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vmulq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vmulq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vmulq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vmulq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vmulq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vmulq(p0,p1) __arm_vmulq(p0,p1)
+#define __arm_vmulq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulq_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_vmulq_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_vmulq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmulq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmulq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcaddq_rot270(p0,p1) __arm_vcaddq_rot270(p0,p1)
+#define __arm_vcaddq_rot270(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcaddq_rot270_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_vcaddq_rot270_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_vcaddq_rot270_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcaddq_rot270_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot270_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcaddq_rot270_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot270_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot270_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpeqq(p0,p1) __arm_vcmpeqq(p0,p1)
+#define __arm_vcmpeqq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpeqq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpeqq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpeqq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpeqq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpeqq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpeqq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpeqq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpeqq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpeqq_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_vcmpeqq_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_vcmpeqq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpeqq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpeqq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpeqq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpeqq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpeqq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcaddq_rot90(p0,p1) __arm_vcaddq_rot90(p0,p1)
+#define __arm_vcaddq_rot90(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcaddq_rot90_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_vcaddq_rot90_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_vcaddq_rot90_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcaddq_rot90_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot90_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcaddq_rot90_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot90_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot90_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpgeq_n(p0,p1) __arm_vcmpgeq_n(p0,p1)
+#define __arm_vcmpgeq_n(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgeq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
+#define __arm_vcmpgeq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgeq_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_vcmpgeq_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_vcmpgeq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpgtq_n(p0,p1) __arm_vcmpgtq_n(p0,p1)
+#define __arm_vcmpgtq_n(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgtq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgtq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgtq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgtq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpgtq(p0,p1) __arm_vcmpgtq(p0,p1)
+#define __arm_vcmpgtq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgtq_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_vcmpgtq_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_vcmpgtq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgtq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgtq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpleq(p0,p1) __arm_vcmpleq(p0,p1)
+#define __arm_vcmpleq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpleq_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_vcmpleq_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_vcmpleq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpleq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpleq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpleq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpleq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpleq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpleq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpleq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpltq(p0,p1) __arm_vcmpltq(p0,p1)
+#define __arm_vcmpltq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpltq_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_vcmpltq_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_vcmpltq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpltq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpltq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpltq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpltq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpltq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpneq(p0,p1) __arm_vcmpneq(p0,p1)
+#define __arm_vcmpneq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpneq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpneq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpneq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpneq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpneq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpneq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpneq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpneq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpneq_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_vcmpneq_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_vcmpneq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpneq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpneq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpneq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpneq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpneq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq(p0,p1) __arm_vcmulq(p0,p1)
+#define __arm_vcmulq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq_rot180(p0,p1) __arm_vcmulq_rot180(p0,p1)
+#define __arm_vcmulq_rot180(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot180_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot180_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq_rot270(p0,p1) __arm_vcmulq_rot270(p0,p1)
+#define __arm_vcmulq_rot270(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot270_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot270_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq_rot90(p0,p1) __arm_vcmulq_rot90(p0,p1)
+#define __arm_vcmulq_rot90(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot90_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define veorq(p0,p1) __arm_veorq(p0,p1)
+#define __arm_veorq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_veorq_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_veorq_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_veorq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_veorq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_veorq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_veorq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_veorq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_veorq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmaq(p0,p1) __arm_vmaxnmaq(p0,p1)
+#define __arm_vmaxnmaq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmavq(p0,p1) __arm_vmaxnmavq(p0,p1)
+#define __arm_vmaxnmavq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmq(p0,p1) __arm_vmaxnmq(p0,p1)
+#define __arm_vmaxnmq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmvq(p0,p1) __arm_vmaxnmvq(p0,p1)
+#define __arm_vmaxnmvq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmvq(p0,p1) __arm_vmaxnmvq(p0,p1)
+#define __arm_vmaxnmvq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vminnmaq(p0,p1) __arm_vminnmaq(p0,p1)
+#define __arm_vminnmaq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vminnmavq(p0,p1) __arm_vminnmavq(p0,p1)
+#define __arm_vminnmavq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vbrsrq(p0,p1) __arm_vbrsrq(p0,p1)
+#define __arm_vbrsrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vbrsrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vbrsrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vbrsrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vbrsrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbrsrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbrsrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1), \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vbrsrq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), p1), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vbrsrq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), p1));})
+
+#define vminnmq(p0,p1) __arm_vminnmq(p0,p1)
+#define __arm_vminnmq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vminnmvq(p0,p1) __arm_vminnmvq(p0,p1)
+#define __arm_vminnmvq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
+#define __arm_vcmpgeq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgeq_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_vcmpgeq_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_vcmpgeq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgeq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
+ int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vshlq_r(p0,p1) __arm_vshlq_r(p0,p1)
+#define __arm_vshlq_r(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlq_r_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vshlq_r_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlq_r_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vshlq_n(p0,p1) __arm_vshlq_n(p0,p1)
+#define __arm_vshlq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vshlltq(p0,p1) __arm_vshlltq(p0,p1)
+#define __arm_vshlltq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlltq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlltq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlltq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
-extern void *__ARM_undef;
-#define __ARM_mve_coerce(param, type) \
- _Generic(param, type: param, default: *(type *)__ARM_undef)
+#define vshllbq(p0,p1) __arm_vshllbq(p0,p1)
+#define __arm_vshllbq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshllbq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshllbq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshllbq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshllbq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
-#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+#define vrshrq(p0,p1) __arm_vrshrq(p0,p1)
+#define __arm_vrshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vrshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vrshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vst4q(p0,p1) __arm_vst4q(p0,p1)
-#define __arm_vst4q(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vrshrq(p0,p1) __arm_vrshrq(p0,p1)
+#define __arm_vrshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vrshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vrshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vrshlq(p0,p1) __arm_vrshlq(p0,p1)
+#define __arm_vrshlq(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_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
- int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
- int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
- int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \
- int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \
- int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_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_vrshlq_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_vrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vrndxq(p0) __arm_vrndxq(p0)
-#define __arm_vrndxq(p0) ({ __typeof(p0) __p0 = (p0); \
+#define vrmulhq(p0,p1) __arm_vrmulhq(p0,p1)
+#define __arm_vrmulhq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrmulhq_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_vrmulhq_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_vrmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vrmulhq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrmulhq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmulhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vrhaddq(p0,p1) __arm_vrhaddq(p0,p1)
+#define __arm_vrhaddq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrhaddq_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_vrhaddq_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_vrhaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vrhaddq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrhaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqsubq(p0,p1) __arm_vqsubq(p0,p1)
+#define __arm_vqsubq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqsubq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqsubq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vqsubq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqsubq_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_vqsubq_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_vqsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vqsubq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqsubq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vqsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqshluq(p0,p1) __arm_vqshluq(p0,p1)
+#define __arm_vqshluq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndxq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndxq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshluq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshluq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshluq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1));})
-#define vrndq(p0) __arm_vrndq(p0)
-#define __arm_vrndq(p0) ({ __typeof(p0) __p0 = (p0); \
+#define vqshlq(p0,p1) __arm_vqshlq(p0,p1)
+#define __arm_vqshlq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqshlq_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_vqshlq_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_vqshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqshlq_r(p0,p1) __arm_vqshlq_r(p0,p1)
+#define __arm_vqshlq_r(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshlq_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshlq_r_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshlq_r_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vqshlq_r_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vqshlq_n(p0,p1) __arm_vqshlq_n(p0,p1)
+#define __arm_vqshlq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vqshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vrndpq(p0) __arm_vrndpq(p0)
-#define __arm_vrndpq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndpq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndpq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vqrshlq(p0,p1) __arm_vqrshlq(p0,p1)
+#define __arm_vqrshlq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrshlq_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_vqrshlq_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_vqrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-#define vrndnq(p0) __arm_vrndnq(p0)
-#define __arm_vrndnq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndnq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndnq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vqrdmulhq(p0,p1) __arm_vqrdmulhq(p0,p1)
+#define __arm_vqrdmulhq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrdmulhq_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_vqrdmulhq_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_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqrdmulhq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-#define vrndmq(p0) __arm_vrndmq(p0)
-#define __arm_vrndmq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndmq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndmq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vmlaldavxq(p0,p1) __arm_vmlaldavxq(p0,p1)
+#define __arm_vmlaldavxq(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_int16x8_t]: __arm_vmlaldavxq_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_vmlaldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vrndaq(p0) __arm_vrndaq(p0)
-#define __arm_vrndaq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndaq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndaq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vqmovuntq(p0,p1) __arm_vqmovuntq(p0,p1)
+#define __arm_vqmovuntq(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_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovuntq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovuntq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vrev64q(p0) __arm_vrev64q(p0)
-#define __arm_vrev64q(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev64q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vrev64q_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vrev64q_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev64q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev64q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrev64q_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev64q_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrev64q_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vqmovntq(p0,p1) __arm_vqmovntq(p0,p1)
+#define __arm_vqmovntq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vnegq(p0) __arm_vnegq(p0)
-#define __arm_vnegq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vnegq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vnegq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vqmovnbq(p0,p1) __arm_vqmovnbq(p0,p1)
+#define __arm_vqmovnbq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vabsq(p0) __arm_vabsq(p0)
-#define __arm_vabsq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vabsq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vabsq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+#define vqdmulltq(p0,p1) __arm_vqdmulltq(p0,p1)
+#define __arm_vqdmulltq(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_int16_t]: __arm_vqdmulltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmulltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmulltq_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_vqdmulltq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vrev32q(p0) __arm_vrev32q(p0)
-#define __arm_vrev32q(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev32q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vrev32q_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev32q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev32q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev32q_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
+#define vqmovunbq(p0,p1) __arm_vqmovunbq(p0,p1)
+#define __arm_vqmovunbq(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_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovunbq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vcvtbq_f32(p0) __arm_vcvtbq_f32(p0)
-#define __arm_vcvtbq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvtbq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
+#define vqdmullbq(p0,p1) __arm_vqdmullbq(p0,p1)
+#define __arm_vqdmullbq(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_int16_t]: __arm_vqdmullbq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmullbq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmullbq_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_vqdmullbq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vcvttq_f32(p0) __arm_vcvttq_f32(p0)
-#define __arm_vcvttq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvttq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
+#define vqdmulhq(p0,p1) __arm_vqdmulhq(p0,p1)
+#define __arm_vqdmulhq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqdmulhq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqdmulhq_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_vqdmulhq_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_vqdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vrev16q(p0) __arm_vrev16q(p0)
-#define __arm_vrev16q(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev16q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev16q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)));})
+#define vqaddq(p0,p1) __arm_vqaddq(p0,p1)
+#define __arm_vqaddq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vqaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqaddq_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_vqaddq_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_vqaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vqaddq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vqaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vqabsq(p0) __arm_vqabsq(p0)
-#define __arm_vqabsq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vqabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vqabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vqabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+#define vmulltq_poly(p0,p1) __arm_vmulltq_poly(p0,p1)
+#define __arm_vmulltq_poly(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
-#define vqnegq(p0) __arm_vqnegq(p0)
-#define __arm_vqnegq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vqnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vqnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vqnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+#define vmullbq_poly(p0,p1) __arm_vmullbq_poly(p0,p1)
+#define __arm_vmullbq_poly(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
-#define vmvnq(p0) __arm_vmvnq(p0)
-#define __arm_vmvnq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vmvnq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vmvnq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vmvnq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmvnq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmvnq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t]: __arm_vmvnq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+#define vmulltq_int(p0,p1) __arm_vmulltq_int(p0,p1)
+#define __arm_vmulltq_int(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulltq_int_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_vmulltq_int_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_vmulltq_int_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_int_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_int_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulltq_int_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vmovlbq(p0) __arm_vmovlbq(p0)
-#define __arm_vmovlbq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovlbq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
+#define vhaddq(p0,p1) __arm_vhaddq(p0,p1)
+#define __arm_vhaddq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vhaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vhaddq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vhaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vhaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhaddq_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_vhaddq_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_vhaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vhaddq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vhaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vmovltq(p0) __arm_vmovltq(p0)
-#define __arm_vmovltq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovltq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
+#define vhcaddq_rot270(p0,p1) __arm_vhcaddq_rot270(p0,p1)
+#define __arm_vhcaddq_rot270(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhcaddq_rot270_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_vhcaddq_rot270_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_vhcaddq_rot270_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vclzq(p0) __arm_vclzq(p0)
-#define __arm_vclzq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vclzq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vclzq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vclzq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vclzq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vclzq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t]: __arm_vclzq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+#define vhcaddq_rot90(p0,p1) __arm_vhcaddq_rot90(p0,p1)
+#define __arm_vhcaddq_rot90(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhcaddq_rot90_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_vhcaddq_rot90_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_vhcaddq_rot90_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vclsq(p0) __arm_vclsq(p0)
-#define __arm_vclsq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vclsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vclsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vclsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+#define vhsubq(p0,p1) __arm_vhsubq(p0,p1)
+#define __arm_vhsubq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vhsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vhsubq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vhsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhsubq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vhsubq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhsubq_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_vhsubq_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_vhsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vhsubq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vhsubq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vhsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vcvtq(p0) __arm_vcvtq(p0)
-#define __arm_vcvtq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_f16_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vcvtq_f32_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+#define vminq(p0,p1) __arm_vminq(p0,p1)
+#define __arm_vminq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vminq_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_vminq_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_vminq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vminq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vminq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vminq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vsubq(p0,p1) __arm_vsubq(p0,p1)
-#define __arm_vsubq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vminaq(p0,p1) __arm_vminaq(p0,p1)
+#define __arm_vminaq(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_float16x8_t][__ARM_mve_type_float16_t]: __arm_vsubq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
- int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vsubq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vsubq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vsubq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vsubq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vminaq_s8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminaq_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminaq_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vbrsrq(p0,p1) __arm_vbrsrq(p0,p1)
-#define __arm_vbrsrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vbrsrq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), p1), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vbrsrq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), p1));})
+#define vmaxq(p0,p1) __arm_vmaxq(p0,p1)
+#define __arm_vmaxq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmaxq_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_vmaxq_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_vmaxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vshlq(p0,p1) __arm_vshlq(p0,p1)
-#define __arm_vshlq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vmaxaq(p0,p1) __arm_vmaxaq(p0,p1)
+#define __arm_vmaxaq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vshlq_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_vshlq_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_vshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmaxaq_s8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxaq_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxaq_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vshrq(p0,p1) __arm_vshrq(p0,p1)
-#define __arm_vshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
- int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
- int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+#define vmovntq(p0,p1) __arm_vmovntq(p0,p1)
+#define __arm_vmovntq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vcvtq_n(p0,p1) __arm_vcvtq_n(p0,p1)
-#define __arm_vcvtq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_n_f16_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vcvtq_n_f32_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
- int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_n_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
- int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_n_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+#define vmovnbq(p0,p1) __arm_vmovnbq(p0,p1)
+#define __arm_vmovnbq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
-#define __arm_vcmpgeq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vmulhq(p0,p1) __arm_vmulhq(p0,p1)
+#define __arm_vmulhq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgeq_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_vcmpgeq_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_vcmpgeq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgeq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
- int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
- int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulhq_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_vmulhq_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_vmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulhq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulhq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmullbq_int(p0,p1) __arm_vmullbq_int(p0,p1)
+#define __arm_vmullbq_int(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmullbq_int_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_vmullbq_int_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_vmullbq_int_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_int_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_int_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmullbq_int_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
#define vcmpgtq(p0,p1) __arm_vcmpgtq(p0,p1)
#define __arm_vcmpgtq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgtq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
-#else /* MVE Interger. */
+#else /* MVE Interger. srinath*/
#define vst4q(p0,p1) __arm_vst4q(p0,p1)
#define __arm_vst4q(p0,p1) ({ __typeof(p0) __p0 = (p0); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vsubq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsubq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vsubq_n(p0,p1) __arm_vsubq_n(p0,p1)
-#define __arm_vsubq_n(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_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vsubq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vrshlq_n(p0,p1) __arm_vrshlq_n(p0,p1)
-#define __arm_vrshlq_n(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_int8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-
#define vrshlq(p0,p1) __arm_vrshlq(p0,p1)
#define __arm_vrshlq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_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_vrshlq_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_vrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vrshlq_n(p0,p1) __arm_vrshlq_n(p0,p1)
-#define __arm_vrshlq_n(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_int8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-
-#define vrshlq(p0,p1) __arm_vrshlq(p0,p1)
-#define __arm_vrshlq(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_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_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_vrshlq_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_vrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrhaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vqsubq_n(p0,p1) __arm_vqsubq_n(p0,p1)
-#define __arm_vqsubq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vqsubq(p0,p1) __arm_vqsubq(p0,p1)
+#define __arm_vqsubq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqsubq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vqsubq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vqsubq(p0,p1) __arm_vqsubq(p0,p1)
-#define __arm_vqsubq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqsubq_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_vqsubq_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_vqsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshluq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshluq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1));})
-#define vrshrq_n(p0,p1) __arm_vrshrq_n(p0,p1)
-#define __arm_vrshrq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vrshrq(p0,p1) __arm_vrshrq(p0,p1)
+#define __arm_vrshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vrshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vqshluq_n(p0,p1) __arm_vqshluq_n(p0,p1)
-#define __arm_vqshluq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshluq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
- int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshluq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
- int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshluq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1));})
-
#define vqshlq_n(p0,p1) __arm_vqshlq_n(p0,p1)
#define __arm_vqshlq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vqrshlq_n(p0,p1) __arm_vqrshlq_n(p0,p1)
-#define __arm_vqrshlq_n(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_int8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-
#define vqrshlq(p0,p1) __arm_vqrshlq(p0,p1)
#define __arm_vqrshlq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vqrdmulhq_n(p0,p1) __arm_vqrdmulhq_n(p0,p1)
-#define __arm_vqrdmulhq_n(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqrdmulhq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
#define vqrdmulhq(p0,p1) __arm_vqrdmulhq(p0,p1)
#define __arm_vqrdmulhq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrdmulhq_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_vqrdmulhq_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_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vqdmulhq_n(p0,p1) __arm_vqdmulhq_n(p0,p1)
-#define __arm_vqdmulhq_n(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqdmulhq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqrdmulhq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
#define vqdmulhq(p0,p1) __arm_vqdmulhq(p0,p1)
#define __arm_vqdmulhq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqdmulhq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqdmulhq_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_vqdmulhq_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_vqdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vqaddq_n(p0,p1) __arm_vqaddq_n(p0,p1)
-#define __arm_vqaddq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vqaddq(p0,p1) __arm_vqaddq(p0,p1)
+#define __arm_vqaddq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vqaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vqaddq(p0,p1) __arm_vqaddq(p0,p1)
-#define __arm_vqaddq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqaddq_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_vqaddq_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_vqaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vqaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vorrq_n(p0,p1) __arm_vorrq_n(p0,p1)
-#define __arm_vorrq_n(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_int32_t]: __arm_vorrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int)), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vorrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int)), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vorrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vorrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int)));})
-
#define vorrq(p0,p1) __arm_vorrq(p0,p1)
#define __arm_vorrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxaq_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxaq_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vhsubq_n(p0,p1) __arm_vhsubq_n(p0,p1)
-#define __arm_vhsubq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vhsubq(p0,p1) __arm_vhsubq(p0,p1)
+#define __arm_vhsubq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vhsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vhsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhsubq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vhsubq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vhsubq(p0,p1) __arm_vhsubq(p0,p1)
-#define __arm_vhsubq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhsubq_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_vhsubq_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_vhsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vhcaddq_rot270_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_vhcaddq_rot270_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vhaddq_n(p0,p1) __arm_vhaddq_n(p0,p1)
-#define __arm_vhaddq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vhaddq(p0,p1) __arm_vhaddq(p0,p1)
+#define __arm_vhaddq(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vhaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vhaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vhaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vhaddq(p0,p1) __arm_vhaddq(p0,p1)
-#define __arm_vhaddq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhaddq_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_vhaddq_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_vhaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vaddq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vaddq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vaddq(p0,p1) __arm_vaddq(p0,p1)
-#define __arm_vaddq(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_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vaddq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vaddq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpneq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpneq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
+
+#define vqmovntq(p0,p1) __arm_vqmovntq(p0,p1)
+#define __arm_vqmovntq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqmovnbq(p0,p1) __arm_vqmovnbq(p0,p1)
+#define __arm_vqmovnbq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmulltq_poly(p0,p1) __arm_vmulltq_poly(p0,p1)
+#define __arm_vmulltq_poly(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
+
+#define vmullbq_poly(p0,p1) __arm_vmullbq_poly(p0,p1)
+#define __arm_vmullbq_poly(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
+
+#define vmovntq(p0,p1) __arm_vmovntq(p0,p1)
+#define __arm_vmovntq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmovnbq(p0,p1) __arm_vmovnbq(p0,p1)
+#define __arm_vmovnbq(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_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmlaldavxq(p0,p1) __arm_vmlaldavxq(p0,p1)
+#define __arm_vmlaldavxq(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_int16x8_t]: __arm_vmlaldavxq_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_vmlaldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqmovuntq(p0,p1) __arm_vqmovuntq(p0,p1)
+#define __arm_vqmovuntq(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_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovuntq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovuntq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vshlltq(p0,p1) __arm_vshlltq(p0,p1)
+#define __arm_vshlltq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlltq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlltq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlltq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
+
+#define vshllbq(p0,p1) __arm_vshllbq(p0,p1)
+#define __arm_vshllbq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshllbq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshllbq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshllbq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshllbq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
+
+#define vmlaldavq(p0,p1) __arm_vmlaldavq(p0,p1)
+#define __arm_vmlaldavq(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_int16x8_t]: __arm_vmlaldavq_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_vmlaldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqmovunbq(p0,p1) __arm_vqmovunbq(p0,p1)
+#define __arm_vqmovunbq(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_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovunbq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqdmulltq(p0,p1) __arm_vqdmulltq(p0,p1)
+#define __arm_vqdmulltq(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_int16_t]: __arm_vqdmulltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmulltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmulltq_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_vqdmulltq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqdmullbq(p0,p1) __arm_vqdmullbq(p0,p1)
+#define __arm_vqdmullbq(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_int16_t]: __arm_vqdmullbq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqdmullbq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmullbq_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_vqdmullbq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vcmpgeq_n(p0,p1) __arm_vcmpgeq_n(p0,p1)
+#define __arm_vcmpgeq_n(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_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgeq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+
#define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
#define __arm_vcmpgeq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+#define vaddlvaq(p0,p1) __arm_vaddlvaq(p0,p1)
+#define __arm_vaddlvaq(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_int64_t][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vrmlaldavhq(p0,p1) __arm_vrmlaldavhq(p0,p1)
+#define __arm_vrmlaldavhq(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_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq(p0,p1)
+#define __arm_vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq_s32(p0,p1)
+
+#define vrmlsldavhq(p0,p1) __arm_vrmlsldavhq(p0,p1)
+#define __arm_vrmlsldavhq(p0,p1) __arm_vrmlsldavhq_s32(p0,p1)
+
+#define vrmlsldavhq(p0,p1) __arm_vrmlsldavhq(p0,p1)
+#define __arm_vrmlsldavhq(p0,p1) __arm_vrmlsldavhq_s32(p0,p1)
+
+#define vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq(p0,p1)
+#define __arm_vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq_s32(p0,p1)
+
+#define vmlsldavxq(p0,p1) __arm_vmlsldavxq(p0,p1)
+#define __arm_vmlsldavxq(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_int16x8_t]: __arm_vmlsldavxq_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_vmlsldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmlsldavq(p0,p1) __arm_vmlsldavq(p0,p1)
+#define __arm_vmlsldavq(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_int16x8_t]: __arm_vmlsldavq_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_vmlsldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
#endif /* MVE Floating point. */
#ifdef __cplusplus
along with GCC; see the file COPYING3. If not see
<http://www.gnu.org/licenses/>. */
-VAR5 (STORE1, vst4q, v16qi, v8hi, v4si, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndxq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndpq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndnq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndmq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndaq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrev64q_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vnegq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vdupq_n_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vabsq_f, v8hf, v4sf)
-VAR1 (UNOP_NONE_NONE, vrev32q_f, v8hf)
-VAR1 (UNOP_NONE_NONE, vcvttq_f32_f16, v4sf)
-VAR1 (UNOP_NONE_NONE, vcvtbq_f32_f16, v4sf)
-VAR2 (UNOP_NONE_SNONE, vcvtq_to_f_s, v8hf, v4sf)
-VAR2 (UNOP_NONE_UNONE, vcvtq_to_f_u, v8hf, v4sf)
-VAR3 (UNOP_SNONE_SNONE, vrev64q_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vqnegq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vqabsq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vnegq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vmvnq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vdupq_n_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vclzq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vclsq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vaddvq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vabsq_s, v16qi, v8hi, v4si)
-VAR2 (UNOP_SNONE_SNONE, vrev32q_s, v16qi, v8hi)
-VAR2 (UNOP_SNONE_SNONE, vmovltq_s, v16qi, v8hi)
-VAR2 (UNOP_SNONE_SNONE, vmovlbq_s, v16qi, v8hi)
-VAR2 (UNOP_SNONE_NONE, vcvtq_from_f_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtpq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtnq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtmq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtaq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_IMM, vmvnq_n_s, v8hi, v4si)
-VAR1 (UNOP_SNONE_SNONE, vrev16q_s, v16qi)
-VAR1 (UNOP_SNONE_SNONE, vaddlvq_s, v4si)
-VAR3 (UNOP_UNONE_UNONE, vrev64q_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vmvnq_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vdupq_n_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vclzq_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vaddvq_u, v16qi, v8hi, v4si)
-VAR2 (UNOP_UNONE_UNONE, vrev32q_u, v16qi, v8hi)
-VAR2 (UNOP_UNONE_UNONE, vmovltq_u, v16qi, v8hi)
-VAR2 (UNOP_UNONE_UNONE, vmovlbq_u, v16qi, v8hi)
-VAR2 (UNOP_UNONE_NONE, vcvtq_from_f_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtpq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtnq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtmq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtaq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_IMM, vmvnq_n_u, v8hi, v4si)
-VAR1 (UNOP_UNONE_UNONE, vrev16q_u, v16qi)
-VAR1 (UNOP_UNONE_UNONE, vaddlvq_u, v4si)
-VAR1 (UNOP_UNONE_UNONE, vctp16q, hi)
-VAR1 (UNOP_UNONE_UNONE, vctp32q, hi)
-VAR1 (UNOP_UNONE_UNONE, vctp64q, hi)
-VAR1 (UNOP_UNONE_UNONE, vctp8q, hi)
-VAR1 (UNOP_UNONE_UNONE, vpnot, hi)
-VAR2 (BINOP_NONE_NONE_NONE, vsubq_n_f, v8hf, v4sf)
-VAR2 (BINOP_NONE_NONE_NONE, vbrsrq_n_f, v8hf, v4sf)
-VAR2 (BINOP_NONE_NONE_IMM, vcvtq_n_to_f_s, v8hf, v4sf)
-VAR2 (BINOP_NONE_UNONE_IMM, vcvtq_n_to_f_u, v8hf, v4sf)
-VAR2 (BINOP_NONE_UNONE_UNONE, vcreateq_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_IMM, vcvtq_n_from_f_u, v8hi, v4si)
-VAR2 (BINOP_NONE_NONE_IMM, vcvtq_n_from_f_s, v8hi, v4si)
-VAR4 (BINOP_UNONE_UNONE_UNONE, vcreateq_u, v16qi, v8hi, v4si, v2di)
-VAR4 (BINOP_NONE_UNONE_UNONE, vcreateq_s, v16qi, v8hi, v4si, v2di)
-VAR3 (BINOP_UNONE_UNONE_IMM, vshrq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vshrq_n_s, v16qi, v8hi, v4si)
-VAR1 (BINOP_NONE_NONE_UNONE, vaddlvq_p_s, v4si)
-VAR1 (BINOP_UNONE_UNONE_UNONE, vaddlvq_p_u, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpneq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpneq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vsubq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vsubq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vrmulhq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vrhaddq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqsubq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqsubq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqaddq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqaddq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vorrq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vornq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulltq_int_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmullbq_int_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulhq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmladavq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vminvq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vminq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmaxvq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmaxq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhsubq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhsubq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhaddq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhaddq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, veorq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpneq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmphiq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmphiq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpeqq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpeqq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpcsq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpcsq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcaddq_rot90_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcaddq_rot270_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vbicq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vandq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vaddvq_p_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vaddvaq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vaddq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vabdq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vshlq_r_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vrshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vrshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqshlq_r_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqrshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqrshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vminavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vminaq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vmaxavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vmaxaq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vbrsrq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_IMM, vshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_IMM, vrshrq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_IMM, vqshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpneq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpltq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpltq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpleq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpleq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgtq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgtq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgeq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgeq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpeqq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpeqq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_IMM, vqshluq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_UNONE, vaddvq_p_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vsubq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vsubq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vshlq_r_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrshlq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrhaddq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqsubq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqsubq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqshlq_r_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrshlq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrdmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrdmulhq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqdmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqdmulhq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqaddq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqaddq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vorrq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vornq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulltq_int_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmullbq_int_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmlsdavxq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmlsdavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmladavxq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmladavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vminvq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vminq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmaxvq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmaxq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhsubq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhsubq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhcaddq_rot90_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhcaddq_rot270_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhaddq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhaddq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, veorq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vcaddq_rot90_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vcaddq_rot270_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vbrsrq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vbicq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vandq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vaddvaq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vaddq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vabdq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vshlq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vrshrq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vqshlq_n_s, v16qi, v8hi, v4si)
+VAR5(STORE1, vst4q, v16qi, v8hi, v4si, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndxq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndpq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndnq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndmq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndaq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrev64q_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vnegq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vdupq_n_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vabsq_f, v8hf, v4sf)
+VAR1(UNOP_NONE_NONE, vrev32q_f, v8hf)
+VAR1(UNOP_NONE_NONE, vcvttq_f32_f16, v4sf)
+VAR1(UNOP_NONE_NONE, vcvtbq_f32_f16, v4sf)
+VAR2(UNOP_NONE_SNONE, vcvtq_to_f_s, v8hf, v4sf)
+VAR2(UNOP_NONE_UNONE, vcvtq_to_f_u, v8hf, v4sf)
+VAR3(UNOP_SNONE_SNONE, vrev64q_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vqnegq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vqabsq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vnegq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vmvnq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vdupq_n_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vclzq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vclsq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vaddvq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vabsq_s, v16qi, v8hi, v4si)
+VAR2(UNOP_SNONE_SNONE, vrev32q_s, v16qi, v8hi)
+VAR2(UNOP_SNONE_SNONE, vmovltq_s, v16qi, v8hi)
+VAR2(UNOP_SNONE_SNONE, vmovlbq_s, v16qi, v8hi)
+VAR2(UNOP_SNONE_NONE, vcvtq_from_f_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtpq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtnq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtmq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtaq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_IMM, vmvnq_n_s, v8hi, v4si)
+VAR1(UNOP_SNONE_SNONE, vrev16q_s, v16qi)
+VAR1(UNOP_SNONE_SNONE, vaddlvq_s, v4si)
+VAR3(UNOP_UNONE_UNONE, vrev64q_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vmvnq_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vdupq_n_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vclzq_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vaddvq_u, v16qi, v8hi, v4si)
+VAR2(UNOP_UNONE_UNONE, vrev32q_u, v16qi, v8hi)
+VAR2(UNOP_UNONE_UNONE, vmovltq_u, v16qi, v8hi)
+VAR2(UNOP_UNONE_UNONE, vmovlbq_u, v16qi, v8hi)
+VAR2(UNOP_UNONE_NONE, vcvtq_from_f_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtpq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtnq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtmq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtaq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_IMM, vmvnq_n_u, v8hi, v4si)
+VAR1(UNOP_UNONE_UNONE, vrev16q_u, v16qi)
+VAR1(UNOP_UNONE_UNONE, vaddlvq_u, v4si)
+VAR1(UNOP_UNONE_UNONE, vctp16q, hi)
+VAR1(UNOP_UNONE_UNONE, vctp32q, hi)
+VAR1(UNOP_UNONE_UNONE, vctp64q, hi)
+VAR1(UNOP_UNONE_UNONE, vctp8q, hi)
+VAR1(UNOP_UNONE_UNONE, vpnot, hi)
+VAR2(BINOP_NONE_NONE_NONE, vsubq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vbrsrq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_IMM, vcvtq_n_to_f_s, v8hf, v4sf)
+VAR2(BINOP_NONE_UNONE_IMM, vcvtq_n_to_f_u, v8hf, v4sf)
+VAR2(BINOP_NONE_UNONE_UNONE, vcreateq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_IMM, vcvtq_n_from_f_u, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_IMM, vcvtq_n_from_f_s, v8hi, v4si)
+VAR4(BINOP_UNONE_UNONE_UNONE, vcreateq_u, v16qi, v8hi, v4si, v2di)
+VAR4(BINOP_NONE_UNONE_UNONE, vcreateq_s, v16qi, v8hi, v4si, v2di)
+VAR3(BINOP_UNONE_UNONE_IMM, vshrq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vshrq_n_s, v16qi, v8hi, v4si)
+VAR1(BINOP_NONE_NONE_UNONE, vaddlvq_p_s, v4si)
+VAR1(BINOP_UNONE_UNONE_UNONE, vaddlvq_p_u, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpneq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpneq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vsubq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vsubq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vrmulhq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vrhaddq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqsubq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqsubq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqaddq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqaddq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vorrq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vornq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulltq_int_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmullbq_int_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulhq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmladavq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vminvq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vminq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmaxvq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmaxq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhsubq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhsubq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhaddq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhaddq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, veorq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpneq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmphiq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmphiq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpeqq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpeqq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpcsq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpcsq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcaddq_rot90_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcaddq_rot270_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vbicq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vandq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vaddvq_p_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vaddvaq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vaddq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vabdq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vshlq_r_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vrshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vrshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqshlq_r_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqrshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqrshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vminavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vminaq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vmaxavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vmaxaq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vbrsrq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_IMM, vshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_IMM, vrshrq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_IMM, vqshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpneq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpltq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpltq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpleq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpleq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgtq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgtq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgeq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgeq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpeqq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpeqq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_IMM, vqshluq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_UNONE, vaddvq_p_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vsubq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vsubq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vshlq_r_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrshlq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrhaddq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqsubq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqsubq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqshlq_r_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrshlq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrdmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrdmulhq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqdmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqdmulhq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqaddq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqaddq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vorrq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vornq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulltq_int_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmullbq_int_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmlsdavxq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmlsdavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmladavxq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmladavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vminvq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vminq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmaxvq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmaxq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhsubq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhsubq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhcaddq_rot90_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhcaddq_rot270_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhaddq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhaddq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, veorq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vcaddq_rot90_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vcaddq_rot270_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vbrsrq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vbicq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vandq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vaddvaq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vaddq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vabdq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vshlq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vrshrq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vqshlq_n_s, v16qi, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vqmovntq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vqmovnbq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmulltq_poly_p, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmullbq_poly_p, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmovntq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmovnbq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmlaldavq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_NONE, vqmovuntq_s, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_NONE, vqmovunbq_s, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_IMM, vshlltq_n_u, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_IMM, vshllbq_n_u, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_IMM, vorrq_n_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_IMM, vbicq_n_u, v8hi, v4si)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpneq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpneq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpltq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpltq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpleq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpleq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgtq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgtq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgeq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgeq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpeqq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpeqq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vsubq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vqmovntq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqmovnbq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmulltq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmulltq_n_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmullbq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmullbq_n_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vorrq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vornq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmulq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmulq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmovntq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmovnbq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlsldavxq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlsldavq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlaldavxq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlaldavq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vminnmvq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vminnmq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vminnmavq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vminnmaq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmvq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmavq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmaq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, veorq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_rot90_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_rot270_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_rot180_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcaddq_rot90_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcaddq_rot270_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vbicq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vandq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vaddq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vabdq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_IMM, vshlltq_n_s, v16qi, v8hi)
+VAR2(BINOP_NONE_NONE_IMM, vshllbq_n_s, v16qi, v8hi)
+VAR2(BINOP_NONE_NONE_IMM, vorrq_n_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_IMM, vbicq_n_s, v8hi, v4si)
+VAR1(BINOP_UNONE_UNONE_UNONE, vrmlaldavhq_u, v4si)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp8q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp64q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp32q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp16q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vaddlvaq_u, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlsldavhxq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlsldavhq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlaldavhxq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlaldavhq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vcvttq_f16_f32, v8hf)
+VAR1(BINOP_NONE_NONE_NONE, vcvtbq_f16_f32, v8hf)
+VAR1(BINOP_NONE_NONE_NONE, vaddlvaq_s, v4si)
projects / gcc.git / commitdiff