[v2,35/36] arm: [MVE intrinsics] rework vsbcq vsbciq

Implement vsbcq vsbciq using the new MVE builtins framework.

We re-use most of the code introduced by the previous patches.

2024-08-28  Christophe Lyon  <christophe.lyon@linaro.org>

	gcc/

	* config/arm/arm-mve-builtins-base.cc (class vadc_vsbc_impl): Add
	support for vsbciq and vsbcq.
	(vadciq, vadcq): Add new parameter.
	(vsbciq): New.
	(vsbcq): New.
	* config/arm/arm-mve-builtins-base.def (vsbciq): New.
	(vsbcq): New.
	* config/arm/arm-mve-builtins-base.h (vsbciq): New.
	(vsbcq): New.
	* config/arm/arm_mve.h (vsbciq): Delete.
	(vsbciq_m): Delete.
	(vsbcq): Delete.
	(vsbcq_m): Delete.
	(vsbciq_s32): Delete.
	(vsbciq_u32): Delete.
	(vsbciq_m_s32): Delete.
	(vsbciq_m_u32): Delete.
	(vsbcq_s32): Delete.
	(vsbcq_u32): Delete.
	(vsbcq_m_s32): Delete.
	(vsbcq_m_u32): Delete.
	(__arm_vsbciq_s32): Delete.
	(__arm_vsbciq_u32): Delete.
	(__arm_vsbciq_m_s32): Delete.
	(__arm_vsbciq_m_u32): Delete.
	(__arm_vsbcq_s32): Delete.
	(__arm_vsbcq_u32): Delete.
	(__arm_vsbcq_m_s32): Delete.
	(__arm_vsbcq_m_u32): Delete.
	(__arm_vsbciq): Delete.
	(__arm_vsbciq_m): Delete.
	(__arm_vsbcq): Delete.
	(__arm_vsbcq_m): Delete.
---
 gcc/config/arm/arm-mve-builtins-base.cc  |  56 +++++---
 gcc/config/arm/arm-mve-builtins-base.def |   2 +
 gcc/config/arm/arm-mve-builtins-base.h   |   2 +
 gcc/config/arm/arm_mve.h                 | 170 -----------------------
 4 files changed, 42 insertions(+), 188 deletions(-)

On 04/09/2024 14:26, Christophe Lyon wrote:
> Implement vsbcq vsbciq using the new MVE builtins framework.
> 
> We re-use most of the code introduced by the previous patches.
> 
> 2024-08-28  Christophe Lyon  <christophe.lyon@linaro.org>
> 
> 	gcc/
> 
> 	* config/arm/arm-mve-builtins-base.cc (class vadc_vsbc_impl): Add
> 	support for vsbciq and vsbcq.
> 	(vadciq, vadcq): Add new parameter.
> 	(vsbciq): New.
> 	(vsbcq): New.
> 	* config/arm/arm-mve-builtins-base.def (vsbciq): New.
> 	(vsbcq): New.
> 	* config/arm/arm-mve-builtins-base.h (vsbciq): New.
> 	(vsbcq): New.
> 	* config/arm/arm_mve.h (vsbciq): Delete.
> 	(vsbciq_m): Delete.
> 	(vsbcq): Delete.
> 	(vsbcq_m): Delete.
> 	(vsbciq_s32): Delete.
> 	(vsbciq_u32): Delete.
> 	(vsbciq_m_s32): Delete.
> 	(vsbciq_m_u32): Delete.
> 	(vsbcq_s32): Delete.
> 	(vsbcq_u32): Delete.
> 	(vsbcq_m_s32): Delete.
> 	(vsbcq_m_u32): Delete.
> 	(__arm_vsbciq_s32): Delete.
> 	(__arm_vsbciq_u32): Delete.
> 	(__arm_vsbciq_m_s32): Delete.
> 	(__arm_vsbciq_m_u32): Delete.
> 	(__arm_vsbcq_s32): Delete.
> 	(__arm_vsbcq_u32): Delete.
> 	(__arm_vsbcq_m_s32): Delete.
> 	(__arm_vsbcq_m_u32): Delete.
> 	(__arm_vsbciq): Delete.
> 	(__arm_vsbciq_m): Delete.
> 	(__arm_vsbcq): Delete.
> 	(__arm_vsbcq_m): Delete.

OK.

R.

> ---
>  gcc/config/arm/arm-mve-builtins-base.cc  |  56 +++++---
>  gcc/config/arm/arm-mve-builtins-base.def |   2 +
>  gcc/config/arm/arm-mve-builtins-base.h   |   2 +
>  gcc/config/arm/arm_mve.h                 | 170 -----------------------
>  4 files changed, 42 insertions(+), 188 deletions(-)
> 
> diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc
> index 9c2e11356ef..02fccdcb71f 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.cc
> +++ b/gcc/config/arm/arm-mve-builtins-base.cc
> @@ -559,12 +559,14 @@ public:
>  class vadc_vsbc_impl : public function_base
>  {
>  public:
> -  CONSTEXPR vadc_vsbc_impl (bool init_carry)
> -    : m_init_carry (init_carry)
> +  CONSTEXPR vadc_vsbc_impl (bool init_carry, bool add)
> +    : m_init_carry (init_carry), m_add (add)
>    {}
>  
>    /* Initialize carry with 0 (vadci).  */
>    bool m_init_carry;
> +  /* Add (true) or Sub (false).  */
> +  bool m_add;
>  
>    unsigned int
>    call_properties (const function_instance &) const override
> @@ -647,26 +649,42 @@ public:
>        {
>        case PRED_none:
>  	/* No predicate.  */
> -	unspec = m_init_carry
> -	  ? (e.type_suffix (0).unsigned_p
> -	     ? VADCIQ_U
> -	     : VADCIQ_S)
> -	  : (e.type_suffix (0).unsigned_p
> -	     ? VADCQ_U
> -	     : VADCQ_S);
> +	unspec = m_add
> +	  ? (m_init_carry
> +	     ? (e.type_suffix (0).unsigned_p
> +		? VADCIQ_U
> +		: VADCIQ_S)
> +	     : (e.type_suffix (0).unsigned_p
> +		? VADCQ_U
> +		: VADCQ_S))
> +	  : (m_init_carry
> +	     ? (e.type_suffix (0).unsigned_p
> +		? VSBCIQ_U
> +		: VSBCIQ_S)
> +	     : (e.type_suffix (0).unsigned_p
> +		? VSBCQ_U
> +		: VSBCQ_S));
>  	code = code_for_mve_q_v4si (unspec, unspec);
>  	insns = e.use_exact_insn (code);
>  	break;
>  
>        case PRED_m:
>  	/* "m" predicate.  */
> -	unspec = m_init_carry
> -	  ? (e.type_suffix (0).unsigned_p
> -	     ? VADCIQ_M_U
> -	     : VADCIQ_M_S)
> -	  : (e.type_suffix (0).unsigned_p
> -	     ? VADCQ_M_U
> -	     : VADCQ_M_S);
> +	unspec = m_add
> +	  ? (m_init_carry
> +	     ? (e.type_suffix (0).unsigned_p
> +		? VADCIQ_M_U
> +		: VADCIQ_M_S)
> +	     : (e.type_suffix (0).unsigned_p
> +		? VADCQ_M_U
> +		: VADCQ_M_S))
> +	  : (m_init_carry
> +	     ? (e.type_suffix (0).unsigned_p
> +		? VSBCIQ_M_U
> +		: VSBCIQ_M_S)
> +	     : (e.type_suffix (0).unsigned_p
> +		? VSBCQ_M_U
> +		: VSBCQ_M_S));
>  	code = code_for_mve_q_m_v4si (unspec, unspec);
>  	insns = e.use_cond_insn (code, 0);
>  	break;
> @@ -862,8 +880,8 @@ namespace arm_mve {
>  FUNCTION_PRED_P_S_U (vabavq, VABAVQ)
>  FUNCTION_WITHOUT_N (vabdq, VABDQ)
>  FUNCTION (vabsq, unspec_based_mve_function_exact_insn, (ABS, ABS, ABS, -1, -1, -1, VABSQ_M_S, -1, VABSQ_M_F, -1, -1, -1))
> -FUNCTION (vadciq, vadc_vsbc_impl, (true))
> -FUNCTION (vadcq, vadc_vsbc_impl, (false))
> +FUNCTION (vadciq, vadc_vsbc_impl, (true, true))
> +FUNCTION (vadcq, vadc_vsbc_impl, (false, true))
>  FUNCTION_WITH_RTX_M_N (vaddq, PLUS, VADDQ)
>  FUNCTION_PRED_P_S_U (vaddlvaq, VADDLVAQ)
>  FUNCTION_PRED_P_S_U (vaddlvq, VADDLVQ)
> @@ -1026,6 +1044,8 @@ FUNCTION_WITH_M_N_NO_F (vrshlq, VRSHLQ)
>  FUNCTION_ONLY_N_NO_F (vrshrnbq, VRSHRNBQ)
>  FUNCTION_ONLY_N_NO_F (vrshrntq, VRSHRNTQ)
>  FUNCTION_ONLY_N_NO_F (vrshrq, VRSHRQ)
> +FUNCTION (vsbciq, vadc_vsbc_impl, (true, false))
> +FUNCTION (vsbcq, vadc_vsbc_impl, (false, false))
>  FUNCTION (vshlcq, vshlc_impl,)
>  FUNCTION_ONLY_N_NO_F (vshllbq, VSHLLBQ)
>  FUNCTION_ONLY_N_NO_F (vshlltq, VSHLLTQ)
> diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def
> index 37efa6bf13e..b8a8cf2c555 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.def
> +++ b/gcc/config/arm/arm-mve-builtins-base.def
> @@ -154,6 +154,8 @@ DEF_MVE_FUNCTION (vrshlq, binary_round_lshift, all_integer, mx_or_none)
>  DEF_MVE_FUNCTION (vrshrnbq, binary_rshift_narrow, integer_16_32, m_or_none)
>  DEF_MVE_FUNCTION (vrshrntq, binary_rshift_narrow, integer_16_32, m_or_none)
>  DEF_MVE_FUNCTION (vrshrq, binary_rshift, all_integer, mx_or_none)
> +DEF_MVE_FUNCTION (vsbciq, vadc_vsbc, integer_32, m_or_none)
> +DEF_MVE_FUNCTION (vsbcq, vadc_vsbc, integer_32, m_or_none)
>  DEF_MVE_FUNCTION (vshlcq, vshlc, all_integer, m_or_none)
>  DEF_MVE_FUNCTION (vshllbq, binary_widen_n, integer_8_16, mx_or_none)
>  DEF_MVE_FUNCTION (vshlltq, binary_widen_n, integer_8_16, mx_or_none)
> diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h
> index eb8423c3fe2..da630d48e11 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.h
> +++ b/gcc/config/arm/arm-mve-builtins-base.h
> @@ -190,6 +190,8 @@ extern const function_base *const vrshlq;
>  extern const function_base *const vrshrnbq;
>  extern const function_base *const vrshrntq;
>  extern const function_base *const vrshrq;
> +extern const function_base *const vsbciq;
> +extern const function_base *const vsbcq;
>  extern const function_base *const vshlcq;
>  extern const function_base *const vshllbq;
>  extern const function_base *const vshlltq;
> diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
> index dd7b6f5cdab..34f024b29f4 100644
> --- a/gcc/config/arm/arm_mve.h
> +++ b/gcc/config/arm/arm_mve.h
> @@ -85,10 +85,6 @@
>  #define vstrdq_scatter_base_wb_p(__addr, __offset, __value, __p) __arm_vstrdq_scatter_base_wb_p(__addr, __offset, __value, __p)
>  #define vstrwq_scatter_base_wb_p(__addr, __offset, __value, __p) __arm_vstrwq_scatter_base_wb_p(__addr, __offset, __value, __p)
>  #define vstrwq_scatter_base_wb(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb(__addr, __offset, __value)
> -#define vsbciq(__a, __b, __carry_out) __arm_vsbciq(__a, __b, __carry_out)
> -#define vsbciq_m(__inactive, __a, __b, __carry_out, __p) __arm_vsbciq_m(__inactive, __a, __b, __carry_out, __p)
> -#define vsbcq(__a, __b, __carry) __arm_vsbcq(__a, __b, __carry)
> -#define vsbcq_m(__inactive, __a, __b, __carry, __p) __arm_vsbcq_m(__inactive, __a, __b, __carry, __p)
>  #define vst1q_p(__addr, __value, __p) __arm_vst1q_p(__addr, __value, __p)
>  #define vst2q(__addr, __value) __arm_vst2q(__addr, __value)
>  #define vld1q_z(__base, __p) __arm_vld1q_z(__base, __p)
> @@ -317,14 +313,6 @@
>  #define vstrwq_scatter_base_wb_s32(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb_s32(__addr, __offset, __value)
>  #define vstrwq_scatter_base_wb_u32(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb_u32(__addr, __offset, __value)
>  #define vstrwq_scatter_base_wb_f32(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb_f32(__addr, __offset, __value)
> -#define vsbciq_s32(__a, __b,  __carry_out) __arm_vsbciq_s32(__a, __b,  __carry_out)
> -#define vsbciq_u32(__a, __b,  __carry_out) __arm_vsbciq_u32(__a, __b,  __carry_out)
> -#define vsbciq_m_s32(__inactive, __a, __b,  __carry_out, __p) __arm_vsbciq_m_s32(__inactive, __a, __b,  __carry_out, __p)
> -#define vsbciq_m_u32(__inactive, __a, __b,  __carry_out, __p) __arm_vsbciq_m_u32(__inactive, __a, __b,  __carry_out, __p)
> -#define vsbcq_s32(__a, __b,  __carry) __arm_vsbcq_s32(__a, __b,  __carry)
> -#define vsbcq_u32(__a, __b,  __carry) __arm_vsbcq_u32(__a, __b,  __carry)
> -#define vsbcq_m_s32(__inactive, __a, __b,  __carry, __p) __arm_vsbcq_m_s32(__inactive, __a, __b,  __carry, __p)
> -#define vsbcq_m_u32(__inactive, __a, __b,  __carry, __p) __arm_vsbcq_m_u32(__inactive, __a, __b,  __carry, __p)
>  #define vst1q_p_u8(__addr, __value, __p) __arm_vst1q_p_u8(__addr, __value, __p)
>  #define vst1q_p_s8(__addr, __value, __p) __arm_vst1q_p_s8(__addr, __value, __p)
>  #define vst2q_s8(__addr, __value) __arm_vst2q_s8(__addr, __value)
> @@ -1678,82 +1666,6 @@ __arm_vstrwq_scatter_base_wb_u32 (uint32x4_t * __addr, const int __offset, uint3
>    *__addr = __builtin_mve_vstrwq_scatter_base_wb_uv4si (*__addr, __offset, __value);
>  }
>  
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq_s32 (int32x4_t __a, int32x4_t __b, unsigned * __carry_out)
> -{
> -  int32x4_t __res = __builtin_mve_vsbciq_sv4si (__a, __b);
> -  *__carry_out = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq_u32 (uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out)
> -{
> -  uint32x4_t __res = __builtin_mve_vsbciq_uv4si (__a, __b);
> -  *__carry_out = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
> -{
> -  int32x4_t __res = __builtin_mve_vsbciq_m_sv4si (__inactive, __a, __b, __p);
> -  *__carry_out = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
> -{
> -  uint32x4_t __res = __builtin_mve_vsbciq_m_uv4si (__inactive, __a, __b, __p);
> -  *__carry_out = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq_s32 (int32x4_t __a, int32x4_t __b, unsigned * __carry)
> -{
> -  __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
> -  int32x4_t __res = __builtin_mve_vsbcq_sv4si (__a, __b);
> -  *__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq_u32 (uint32x4_t __a, uint32x4_t __b, unsigned * __carry)
> -{
> -  __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
> -  uint32x4_t __res =  __builtin_mve_vsbcq_uv4si (__a, __b);
> -  *__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry, mve_pred16_t __p)
> -{
> -  __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
> -  int32x4_t __res = __builtin_mve_vsbcq_m_sv4si (__inactive, __a, __b, __p);
> -  *__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry, mve_pred16_t __p)
> -{
> -  __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
> -  uint32x4_t __res = __builtin_mve_vsbcq_m_uv4si (__inactive, __a, __b, __p);
> -  *__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
> -  return __res;
> -}
> -
>  __extension__ extern __inline void
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vst1q_p_u8 (uint8_t * __addr, uint8x16_t __value, mve_pred16_t __p)
> @@ -3554,62 +3466,6 @@ __arm_vstrwq_scatter_base_wb (uint32x4_t * __addr, const int __offset, uint32x4_
>   __arm_vstrwq_scatter_base_wb_u32 (__addr, __offset, __value);
>  }
>  
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq (int32x4_t __a, int32x4_t __b, unsigned * __carry_out)
> -{
> - return __arm_vsbciq_s32 (__a, __b, __carry_out);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq (uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out)
> -{
> - return __arm_vsbciq_u32 (__a, __b, __carry_out);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
> -{
> - return __arm_vsbciq_m_s32 (__inactive, __a, __b, __carry_out, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbciq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
> -{
> - return __arm_vsbciq_m_u32 (__inactive, __a, __b, __carry_out, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq (int32x4_t __a, int32x4_t __b, unsigned * __carry)
> -{
> - return __arm_vsbcq_s32 (__a, __b, __carry);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq (uint32x4_t __a, uint32x4_t __b, unsigned * __carry)
> -{
> - return __arm_vsbcq_u32 (__a, __b, __carry);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry, mve_pred16_t __p)
> -{
> - return __arm_vsbcq_m_s32 (__inactive, __a, __b, __carry, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vsbcq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry, mve_pred16_t __p)
> -{
> - return __arm_vsbcq_m_u32 (__inactive, __a, __b, __carry, __p);
> -}
> -
>  __extension__ extern __inline void
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vst1q_p (uint8_t * __addr, uint8x16_t __value, mve_pred16_t __p)
> @@ -5171,32 +5027,6 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1, p2), \
>    int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1, p2)))
>  
> -#define __arm_vsbciq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
> -  __typeof(p1) __p1 = (p1); \
> -  __typeof(p2) __p2 = (p2); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbciq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3, p4), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbciq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3, p4));})
> -
> -#define __arm_vsbciq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
> -  __typeof(p1) __p1 = (p1); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbciq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbciq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
> -
> -#define __arm_vsbcq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
> -  __typeof(p1) __p1 = (p1); \
> -  __typeof(p2) __p2 = (p2); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbcq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3, p4), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3, p4));})
> -
> -#define __arm_vsbcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
> -  __typeof(p1) __p1 = (p1); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbcq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
> -
>  #define __arm_vldrbq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
>    _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
>    int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \