[v2,13/36] arm: [MVE intrinsics] rework vbicq

Implement vbicq using the new MVE builtins framework.

2024-07-11  Christophe Lyon  <christophe.lyon@linaro.org>

	gcc/
	* config/arm/arm-mve-builtins-base.cc (vbicq): New.
	* config/arm/arm-mve-builtins-base.def (vbicq): New.
	* config/arm/arm-mve-builtins-base.h (vbicq): New.
	* config/arm/arm-mve-builtins-functions.h (class
	unspec_based_mve_function_exact_insn_vbic): New.
	* config/arm/arm-mve-builtins.cc
	(function_instance::has_inactive_argument): Add support for vbicq.
	* config/arm/arm_mve.h (vbicq): Delete.
	(vbicq_m_n): Delete.
	(vbicq_m): Delete.
	(vbicq_x): Delete.
	(vbicq_u8): Delete.
	(vbicq_s8): Delete.
	(vbicq_u16): Delete.
	(vbicq_s16): Delete.
	(vbicq_u32): Delete.
	(vbicq_s32): Delete.
	(vbicq_n_u16): Delete.
	(vbicq_f16): Delete.
	(vbicq_n_s16): Delete.
	(vbicq_n_u32): Delete.
	(vbicq_f32): Delete.
	(vbicq_n_s32): Delete.
	(vbicq_m_n_s16): Delete.
	(vbicq_m_n_s32): Delete.
	(vbicq_m_n_u16): Delete.
	(vbicq_m_n_u32): Delete.
	(vbicq_m_s8): Delete.
	(vbicq_m_s32): Delete.
	(vbicq_m_s16): Delete.
	(vbicq_m_u8): Delete.
	(vbicq_m_u32): Delete.
	(vbicq_m_u16): Delete.
	(vbicq_m_f32): Delete.
	(vbicq_m_f16): Delete.
	(vbicq_x_s8): Delete.
	(vbicq_x_s16): Delete.
	(vbicq_x_s32): Delete.
	(vbicq_x_u8): Delete.
	(vbicq_x_u16): Delete.
	(vbicq_x_u32): Delete.
	(vbicq_x_f16): Delete.
	(vbicq_x_f32): Delete.
	(__arm_vbicq_u8): Delete.
	(__arm_vbicq_s8): Delete.
	(__arm_vbicq_u16): Delete.
	(__arm_vbicq_s16): Delete.
	(__arm_vbicq_u32): Delete.
	(__arm_vbicq_s32): Delete.
	(__arm_vbicq_n_u16): Delete.
	(__arm_vbicq_n_s16): Delete.
	(__arm_vbicq_n_u32): Delete.
	(__arm_vbicq_n_s32): Delete.
	(__arm_vbicq_m_n_s16): Delete.
	(__arm_vbicq_m_n_s32): Delete.
	(__arm_vbicq_m_n_u16): Delete.
	(__arm_vbicq_m_n_u32): Delete.
	(__arm_vbicq_m_s8): Delete.
	(__arm_vbicq_m_s32): Delete.
	(__arm_vbicq_m_s16): Delete.
	(__arm_vbicq_m_u8): Delete.
	(__arm_vbicq_m_u32): Delete.
	(__arm_vbicq_m_u16): Delete.
	(__arm_vbicq_x_s8): Delete.
	(__arm_vbicq_x_s16): Delete.
	(__arm_vbicq_x_s32): Delete.
	(__arm_vbicq_x_u8): Delete.
	(__arm_vbicq_x_u16): Delete.
	(__arm_vbicq_x_u32): Delete.
	(__arm_vbicq_f16): Delete.
	(__arm_vbicq_f32): Delete.
	(__arm_vbicq_m_f32): Delete.
	(__arm_vbicq_m_f16): Delete.
	(__arm_vbicq_x_f16): Delete.
	(__arm_vbicq_x_f32): Delete.
	(__arm_vbicq): Delete.
	(__arm_vbicq_m_n): Delete.
	(__arm_vbicq_m): Delete.
	(__arm_vbicq_x): Delete.
	* config/arm/mve.md (mve_vbicq_u<mode>): Rename into ...
	(@mve_vbicq_u<mode>): ... this.
	(mve_vbicq_s<mode>): Rename into ...
	(@mve_vbicq_s<mode>): ... this.
	(mve_vbicq_f<mode>): Rename into ...
	(@mve_vbicq_f<mode>): ... this.
---
 gcc/config/arm/arm-mve-builtins-base.cc     |   1 +
 gcc/config/arm/arm-mve-builtins-base.def    |   2 +
 gcc/config/arm/arm-mve-builtins-base.h      |   1 +
 gcc/config/arm/arm-mve-builtins-functions.h |  54 ++
 gcc/config/arm/arm-mve-builtins.cc          |   1 +
 gcc/config/arm/arm_mve.h                    | 574 --------------------
 gcc/config/arm/mve.md                       |   6 +-
 7 files changed, 62 insertions(+), 577 deletions(-)

On 04/09/2024 14:26, Christophe Lyon wrote:
> Implement vbicq using the new MVE builtins framework.
> 
> 2024-07-11  Christophe Lyon  <christophe.lyon@linaro.org>
> 
> 	gcc/
> 	* config/arm/arm-mve-builtins-base.cc (vbicq): New.
> 	* config/arm/arm-mve-builtins-base.def (vbicq): New.
> 	* config/arm/arm-mve-builtins-base.h (vbicq): New.
> 	* config/arm/arm-mve-builtins-functions.h (class
> 	unspec_based_mve_function_exact_insn_vbic): New.
> 	* config/arm/arm-mve-builtins.cc
> 	(function_instance::has_inactive_argument): Add support for vbicq.
> 	* config/arm/arm_mve.h (vbicq): Delete.
> 	(vbicq_m_n): Delete.
> 	(vbicq_m): Delete.
> 	(vbicq_x): Delete.
> 	(vbicq_u8): Delete.
> 	(vbicq_s8): Delete.
> 	(vbicq_u16): Delete.
> 	(vbicq_s16): Delete.
> 	(vbicq_u32): Delete.
> 	(vbicq_s32): Delete.
> 	(vbicq_n_u16): Delete.
> 	(vbicq_f16): Delete.
> 	(vbicq_n_s16): Delete.
> 	(vbicq_n_u32): Delete.
> 	(vbicq_f32): Delete.
> 	(vbicq_n_s32): Delete.
> 	(vbicq_m_n_s16): Delete.
> 	(vbicq_m_n_s32): Delete.
> 	(vbicq_m_n_u16): Delete.
> 	(vbicq_m_n_u32): Delete.
> 	(vbicq_m_s8): Delete.
> 	(vbicq_m_s32): Delete.
> 	(vbicq_m_s16): Delete.
> 	(vbicq_m_u8): Delete.
> 	(vbicq_m_u32): Delete.
> 	(vbicq_m_u16): Delete.
> 	(vbicq_m_f32): Delete.
> 	(vbicq_m_f16): Delete.
> 	(vbicq_x_s8): Delete.
> 	(vbicq_x_s16): Delete.
> 	(vbicq_x_s32): Delete.
> 	(vbicq_x_u8): Delete.
> 	(vbicq_x_u16): Delete.
> 	(vbicq_x_u32): Delete.
> 	(vbicq_x_f16): Delete.
> 	(vbicq_x_f32): Delete.
> 	(__arm_vbicq_u8): Delete.
> 	(__arm_vbicq_s8): Delete.
> 	(__arm_vbicq_u16): Delete.
> 	(__arm_vbicq_s16): Delete.
> 	(__arm_vbicq_u32): Delete.
> 	(__arm_vbicq_s32): Delete.
> 	(__arm_vbicq_n_u16): Delete.
> 	(__arm_vbicq_n_s16): Delete.
> 	(__arm_vbicq_n_u32): Delete.
> 	(__arm_vbicq_n_s32): Delete.
> 	(__arm_vbicq_m_n_s16): Delete.
> 	(__arm_vbicq_m_n_s32): Delete.
> 	(__arm_vbicq_m_n_u16): Delete.
> 	(__arm_vbicq_m_n_u32): Delete.
> 	(__arm_vbicq_m_s8): Delete.
> 	(__arm_vbicq_m_s32): Delete.
> 	(__arm_vbicq_m_s16): Delete.
> 	(__arm_vbicq_m_u8): Delete.
> 	(__arm_vbicq_m_u32): Delete.
> 	(__arm_vbicq_m_u16): Delete.
> 	(__arm_vbicq_x_s8): Delete.
> 	(__arm_vbicq_x_s16): Delete.
> 	(__arm_vbicq_x_s32): Delete.
> 	(__arm_vbicq_x_u8): Delete.
> 	(__arm_vbicq_x_u16): Delete.
> 	(__arm_vbicq_x_u32): Delete.
> 	(__arm_vbicq_f16): Delete.
> 	(__arm_vbicq_f32): Delete.
> 	(__arm_vbicq_m_f32): Delete.
> 	(__arm_vbicq_m_f16): Delete.
> 	(__arm_vbicq_x_f16): Delete.
> 	(__arm_vbicq_x_f32): Delete.
> 	(__arm_vbicq): Delete.
> 	(__arm_vbicq_m_n): Delete.
> 	(__arm_vbicq_m): Delete.
> 	(__arm_vbicq_x): Delete.
> 	* config/arm/mve.md (mve_vbicq_u<mode>): Rename into ...
> 	(@mve_vbicq_u<mode>): ... this.
> 	(mve_vbicq_s<mode>): Rename into ...
> 	(@mve_vbicq_s<mode>): ... this.
> 	(mve_vbicq_f<mode>): Rename into ...
> 	(@mve_vbicq_f<mode>): ... this.

OK.

R.

> ---
>  gcc/config/arm/arm-mve-builtins-base.cc     |   1 +
>  gcc/config/arm/arm-mve-builtins-base.def    |   2 +
>  gcc/config/arm/arm-mve-builtins-base.h      |   1 +
>  gcc/config/arm/arm-mve-builtins-functions.h |  54 ++
>  gcc/config/arm/arm-mve-builtins.cc          |   1 +
>  gcc/config/arm/arm_mve.h                    | 574 --------------------
>  gcc/config/arm/mve.md                       |   6 +-
>  7 files changed, 62 insertions(+), 577 deletions(-)
> 
> diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc
> index 281f3749bce..e33603ec1f3 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.cc
> +++ b/gcc/config/arm/arm-mve-builtins-base.cc
> @@ -481,6 +481,7 @@ FUNCTION_PRED_P_S_U (vaddlvq, VADDLVQ)
>  FUNCTION_PRED_P_S_U (vaddvq, VADDVQ)
>  FUNCTION_PRED_P_S_U (vaddvaq, VADDVAQ)
>  FUNCTION_WITH_RTX_M (vandq, AND, VANDQ)
> +FUNCTION (vbicq, unspec_based_mve_function_exact_insn_vbic, (VBICQ_N_S, VBICQ_N_U, VBICQ_M_S, VBICQ_M_U, VBICQ_M_F, VBICQ_M_N_S, VBICQ_M_N_U))
>  FUNCTION_ONLY_N (vbrsrq, VBRSRQ)
>  FUNCTION (vcaddq_rot90, unspec_mve_function_exact_insn_rot, (UNSPEC_VCADD90, UNSPEC_VCADD90, UNSPEC_VCADD90, VCADDQ_ROT90_M, VCADDQ_ROT90_M, VCADDQ_ROT90_M_F))
>  FUNCTION (vcaddq_rot270, unspec_mve_function_exact_insn_rot, (UNSPEC_VCADD270, UNSPEC_VCADD270, UNSPEC_VCADD270, VCADDQ_ROT270_M, VCADDQ_ROT270_M, VCADDQ_ROT270_M_F))
> diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def
> index cf733f7627a..aa7b71387f9 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.def
> +++ b/gcc/config/arm/arm-mve-builtins-base.def
> @@ -27,6 +27,7 @@ DEF_MVE_FUNCTION (vaddq, binary_opt_n, all_integer, mx_or_none)
>  DEF_MVE_FUNCTION (vaddvaq, unary_int32_acc, all_integer, p_or_none)
>  DEF_MVE_FUNCTION (vaddvq, unary_int32, all_integer, p_or_none)
>  DEF_MVE_FUNCTION (vandq, binary, all_integer, mx_or_none)
> +DEF_MVE_FUNCTION (vbicq, binary_orrq, all_integer, mx_or_none)
>  DEF_MVE_FUNCTION (vbrsrq, binary_imm32, all_integer, mx_or_none)
>  DEF_MVE_FUNCTION (vcaddq_rot270, binary, all_integer, mx_or_none)
>  DEF_MVE_FUNCTION (vcaddq_rot90, binary, all_integer, mx_or_none)
> @@ -161,6 +162,7 @@ DEF_MVE_FUNCTION (vabdq, binary, all_float, mx_or_none)
>  DEF_MVE_FUNCTION (vabsq, unary, all_float, mx_or_none)
>  DEF_MVE_FUNCTION (vaddq, binary_opt_n, all_float, mx_or_none)
>  DEF_MVE_FUNCTION (vandq, binary, all_float, mx_or_none)
> +DEF_MVE_FUNCTION (vbicq, binary_orrq, all_float, mx_or_none)
>  DEF_MVE_FUNCTION (vbrsrq, binary_imm32, all_float, mx_or_none)
>  DEF_MVE_FUNCTION (vcaddq_rot270, binary, all_float, mx_or_none)
>  DEF_MVE_FUNCTION (vcaddq_rot90, binary, all_float, mx_or_none)
> diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h
> index eb79bae8bf5..e6b828a4e1e 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.h
> +++ b/gcc/config/arm/arm-mve-builtins-base.h
> @@ -32,6 +32,7 @@ extern const function_base *const vaddq;
>  extern const function_base *const vaddvaq;
>  extern const function_base *const vaddvq;
>  extern const function_base *const vandq;
> +extern const function_base *const vbicq;
>  extern const function_base *const vbrsrq;
>  extern const function_base *const vcaddq_rot270;
>  extern const function_base *const vcaddq_rot90;
> diff --git a/gcc/config/arm/arm-mve-builtins-functions.h b/gcc/config/arm/arm-mve-builtins-functions.h
> index 35cb5242b77..0bb91f5ec1f 100644
> --- a/gcc/config/arm/arm-mve-builtins-functions.h
> +++ b/gcc/config/arm/arm-mve-builtins-functions.h
> @@ -468,6 +468,60 @@ public:
>    }
>  };
>  
> +/* Map the function directly to CODE (M) for vbic-like builtins. The difference
> +   with unspec_based_mve_function_exact_insn is that this function has vbic
> +   hardcoded for the PRED_none, MODE_none version, rather than using an
> +   RTX.  */
> +class unspec_based_mve_function_exact_insn_vbic : public unspec_based_mve_function_base
> +{
> +public:
> +  CONSTEXPR unspec_based_mve_function_exact_insn_vbic (int unspec_for_n_sint,
> +						       int unspec_for_n_uint,
> +						       int unspec_for_m_sint,
> +						       int unspec_for_m_uint,
> +						       int unspec_for_m_fp,
> +						       int unspec_for_m_n_sint,
> +						       int unspec_for_m_n_uint)
> +    : unspec_based_mve_function_base (UNKNOWN,
> +				      UNKNOWN,
> +				      UNKNOWN,
> +				      -1, -1, -1, /* No non-predicated, no mode intrinsics.  */
> +				      unspec_for_n_sint,
> +				      unspec_for_n_uint,
> +				      -1,
> +				      unspec_for_m_sint,
> +				      unspec_for_m_uint,
> +				      unspec_for_m_fp,
> +				      unspec_for_m_n_sint,
> +				      unspec_for_m_n_uint,
> +				      -1)
> +  {}
> +
> +  rtx
> +  expand (function_expander &e) const override
> +  {
> +    machine_mode mode = e.vector_mode (0);
> +    insn_code code;
> +
> +    /* No suffix, no predicate, use the right RTX code.  */
> +    if (e.pred == PRED_none
> +	&& e.mode_suffix_id == MODE_none)
> +	  {
> +	    if (e.type_suffix (0).integer_p)
> +	      if (e.type_suffix (0).unsigned_p)
> +		code = code_for_mve_vbicq_u (mode);
> +	      else
> +		code = code_for_mve_vbicq_s (mode);
> +	    else
> +	      code = code_for_mve_vbicq_f (mode);
> +
> +	    return e.use_exact_insn (code);
> +	  }
> +
> +    return expand_unspec (e);
> +  }
> +};
> +
>  /* Map the comparison functions.  */
>  class unspec_based_mve_function_exact_insn_vcmp : public unspec_based_mve_function_base
>  {
> diff --git a/gcc/config/arm/arm-mve-builtins.cc b/gcc/config/arm/arm-mve-builtins.cc
> index 07e63df35e4..13c666b8f6a 100644
> --- a/gcc/config/arm/arm-mve-builtins.cc
> +++ b/gcc/config/arm/arm-mve-builtins.cc
> @@ -737,6 +737,7 @@ function_instance::has_inactive_argument () const
>      return false;
>  
>    if (mode_suffix_id == MODE_r
> +      || (base == functions::vbicq && mode_suffix_id == MODE_n)
>        || base == functions::vcmlaq
>        || base == functions::vcmlaq_rot90
>        || base == functions::vcmlaq_rot180
> diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
> index 448407627e9..3fd6980a58d 100644
> --- a/gcc/config/arm/arm_mve.h
> +++ b/gcc/config/arm/arm_mve.h
> @@ -43,10 +43,7 @@
>  #ifndef __ARM_MVE_PRESERVE_USER_NAMESPACE
>  #define vst4q(__addr, __value) __arm_vst4q(__addr, __value)
>  #define vornq(__a, __b) __arm_vornq(__a, __b)
> -#define vbicq(__a, __b) __arm_vbicq(__a, __b)
> -#define vbicq_m_n(__a, __imm, __p) __arm_vbicq_m_n(__a, __imm, __p)
>  #define vshlcq(__a, __b, __imm) __arm_vshlcq(__a, __b, __imm)
> -#define vbicq_m(__inactive, __a, __b, __p) __arm_vbicq_m(__inactive, __a, __b, __p)
>  #define vornq_m(__inactive, __a, __b, __p) __arm_vornq_m(__inactive, __a, __b, __p)
>  #define vstrbq_scatter_offset(__base, __offset, __value) __arm_vstrbq_scatter_offset(__base, __offset, __value)
>  #define vstrbq(__addr, __value) __arm_vstrbq(__addr, __value)
> @@ -119,7 +116,6 @@
>  #define viwdupq_x_u8(__a, __b, __imm, __p) __arm_viwdupq_x_u8(__a, __b, __imm, __p)
>  #define viwdupq_x_u16(__a, __b, __imm, __p) __arm_viwdupq_x_u16(__a, __b, __imm, __p)
>  #define viwdupq_x_u32(__a, __b, __imm, __p) __arm_viwdupq_x_u32(__a, __b, __imm, __p)
> -#define vbicq_x(__a, __b, __p) __arm_vbicq_x(__a, __b, __p)
>  #define vornq_x(__a, __b, __p) __arm_vornq_x(__a, __b, __p)
>  #define vadciq(__a, __b, __carry_out) __arm_vadciq(__a, __b, __carry_out)
>  #define vadciq_m(__inactive, __a, __b, __carry_out, __p) __arm_vadciq_m(__inactive, __a, __b, __carry_out, __p)
> @@ -153,53 +149,29 @@
>  #define vctp8q(__a) __arm_vctp8q(__a)
>  #define vpnot(__a) __arm_vpnot(__a)
>  #define vornq_u8(__a, __b) __arm_vornq_u8(__a, __b)
> -#define vbicq_u8(__a, __b) __arm_vbicq_u8(__a, __b)
>  #define vornq_s8(__a, __b) __arm_vornq_s8(__a, __b)
> -#define vbicq_s8(__a, __b) __arm_vbicq_s8(__a, __b)
>  #define vornq_u16(__a, __b) __arm_vornq_u16(__a, __b)
> -#define vbicq_u16(__a, __b) __arm_vbicq_u16(__a, __b)
>  #define vornq_s16(__a, __b) __arm_vornq_s16(__a, __b)
> -#define vbicq_s16(__a, __b) __arm_vbicq_s16(__a, __b)
>  #define vornq_u32(__a, __b) __arm_vornq_u32(__a, __b)
> -#define vbicq_u32(__a, __b) __arm_vbicq_u32(__a, __b)
>  #define vornq_s32(__a, __b) __arm_vornq_s32(__a, __b)
> -#define vbicq_s32(__a, __b) __arm_vbicq_s32(__a, __b)
> -#define vbicq_n_u16(__a,  __imm) __arm_vbicq_n_u16(__a,  __imm)
>  #define vornq_f16(__a, __b) __arm_vornq_f16(__a, __b)
> -#define vbicq_f16(__a, __b) __arm_vbicq_f16(__a, __b)
> -#define vbicq_n_s16(__a,  __imm) __arm_vbicq_n_s16(__a,  __imm)
> -#define vbicq_n_u32(__a,  __imm) __arm_vbicq_n_u32(__a,  __imm)
>  #define vornq_f32(__a, __b) __arm_vornq_f32(__a, __b)
> -#define vbicq_f32(__a, __b) __arm_vbicq_f32(__a, __b)
> -#define vbicq_n_s32(__a,  __imm) __arm_vbicq_n_s32(__a,  __imm)
>  #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 vbicq_m_n_s16(__a,  __imm, __p) __arm_vbicq_m_n_s16(__a,  __imm, __p)
> -#define vbicq_m_n_s32(__a,  __imm, __p) __arm_vbicq_m_n_s32(__a,  __imm, __p)
> -#define vbicq_m_n_u16(__a,  __imm, __p) __arm_vbicq_m_n_u16(__a,  __imm, __p)
> -#define vbicq_m_n_u32(__a,  __imm, __p) __arm_vbicq_m_n_u32(__a,  __imm, __p)
>  #define vshlcq_s8(__a,  __b,  __imm) __arm_vshlcq_s8(__a,  __b,  __imm)
>  #define vshlcq_u8(__a,  __b,  __imm) __arm_vshlcq_u8(__a,  __b,  __imm)
>  #define vshlcq_s16(__a,  __b,  __imm) __arm_vshlcq_s16(__a,  __b,  __imm)
>  #define vshlcq_u16(__a,  __b,  __imm) __arm_vshlcq_u16(__a,  __b,  __imm)
>  #define vshlcq_s32(__a,  __b,  __imm) __arm_vshlcq_s32(__a,  __b,  __imm)
>  #define vshlcq_u32(__a,  __b,  __imm) __arm_vshlcq_u32(__a,  __b,  __imm)
> -#define vbicq_m_s8(__inactive, __a, __b, __p) __arm_vbicq_m_s8(__inactive, __a, __b, __p)
> -#define vbicq_m_s32(__inactive, __a, __b, __p) __arm_vbicq_m_s32(__inactive, __a, __b, __p)
> -#define vbicq_m_s16(__inactive, __a, __b, __p) __arm_vbicq_m_s16(__inactive, __a, __b, __p)
> -#define vbicq_m_u8(__inactive, __a, __b, __p) __arm_vbicq_m_u8(__inactive, __a, __b, __p)
> -#define vbicq_m_u32(__inactive, __a, __b, __p) __arm_vbicq_m_u32(__inactive, __a, __b, __p)
> -#define vbicq_m_u16(__inactive, __a, __b, __p) __arm_vbicq_m_u16(__inactive, __a, __b, __p)
>  #define vornq_m_s8(__inactive, __a, __b, __p) __arm_vornq_m_s8(__inactive, __a, __b, __p)
>  #define vornq_m_s32(__inactive, __a, __b, __p) __arm_vornq_m_s32(__inactive, __a, __b, __p)
>  #define vornq_m_s16(__inactive, __a, __b, __p) __arm_vornq_m_s16(__inactive, __a, __b, __p)
>  #define vornq_m_u8(__inactive, __a, __b, __p) __arm_vornq_m_u8(__inactive, __a, __b, __p)
>  #define vornq_m_u32(__inactive, __a, __b, __p) __arm_vornq_m_u32(__inactive, __a, __b, __p)
>  #define vornq_m_u16(__inactive, __a, __b, __p) __arm_vornq_m_u16(__inactive, __a, __b, __p)
> -#define vbicq_m_f32(__inactive, __a, __b, __p) __arm_vbicq_m_f32(__inactive, __a, __b, __p)
> -#define vbicq_m_f16(__inactive, __a, __b, __p) __arm_vbicq_m_f16(__inactive, __a, __b, __p)
>  #define vornq_m_f32(__inactive, __a, __b, __p) __arm_vornq_m_f32(__inactive, __a, __b, __p)
>  #define vornq_m_f16(__inactive, __a, __b, __p) __arm_vornq_m_f16(__inactive, __a, __b, __p)
>  #define vstrbq_s8( __addr, __value) __arm_vstrbq_s8( __addr, __value)
> @@ -484,20 +456,12 @@
>  #define viwdupq_x_wb_u8(__a, __b,  __imm, __p) __arm_viwdupq_x_wb_u8(__a, __b,  __imm, __p)
>  #define viwdupq_x_wb_u16(__a, __b,  __imm, __p) __arm_viwdupq_x_wb_u16(__a, __b,  __imm, __p)
>  #define viwdupq_x_wb_u32(__a, __b,  __imm, __p) __arm_viwdupq_x_wb_u32(__a, __b,  __imm, __p)
> -#define vbicq_x_s8(__a, __b, __p) __arm_vbicq_x_s8(__a, __b, __p)
> -#define vbicq_x_s16(__a, __b, __p) __arm_vbicq_x_s16(__a, __b, __p)
> -#define vbicq_x_s32(__a, __b, __p) __arm_vbicq_x_s32(__a, __b, __p)
> -#define vbicq_x_u8(__a, __b, __p) __arm_vbicq_x_u8(__a, __b, __p)
> -#define vbicq_x_u16(__a, __b, __p) __arm_vbicq_x_u16(__a, __b, __p)
> -#define vbicq_x_u32(__a, __b, __p) __arm_vbicq_x_u32(__a, __b, __p)
>  #define vornq_x_s8(__a, __b, __p) __arm_vornq_x_s8(__a, __b, __p)
>  #define vornq_x_s16(__a, __b, __p) __arm_vornq_x_s16(__a, __b, __p)
>  #define vornq_x_s32(__a, __b, __p) __arm_vornq_x_s32(__a, __b, __p)
>  #define vornq_x_u8(__a, __b, __p) __arm_vornq_x_u8(__a, __b, __p)
>  #define vornq_x_u16(__a, __b, __p) __arm_vornq_x_u16(__a, __b, __p)
>  #define vornq_x_u32(__a, __b, __p) __arm_vornq_x_u32(__a, __b, __p)
> -#define vbicq_x_f16(__a, __b, __p) __arm_vbicq_x_f16(__a, __b, __p)
> -#define vbicq_x_f32(__a, __b, __p) __arm_vbicq_x_f32(__a, __b, __p)
>  #define vornq_x_f16(__a, __b, __p) __arm_vornq_x_f16(__a, __b, __p)
>  #define vornq_x_f32(__a, __b, __p) __arm_vornq_x_f32(__a, __b, __p)
>  #define vadciq_s32(__a, __b,  __carry_out) __arm_vadciq_s32(__a, __b,  __carry_out)
> @@ -708,13 +672,6 @@ __arm_vornq_u8 (uint8x16_t __a, uint8x16_t __b)
>    return __builtin_mve_vornq_uv16qi (__a, __b);
>  }
>  
> -__extension__ extern __inline uint8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_u8 (uint8x16_t __a, uint8x16_t __b)
> -{
> -  return __builtin_mve_vbicq_uv16qi (__a, __b);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_s8 (int8x16_t __a, int8x16_t __b)
> @@ -722,13 +679,6 @@ __arm_vornq_s8 (int8x16_t __a, int8x16_t __b)
>    return __builtin_mve_vornq_sv16qi (__a, __b);
>  }
>  
> -__extension__ extern __inline int8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_s8 (int8x16_t __a, int8x16_t __b)
> -{
> -  return __builtin_mve_vbicq_sv16qi (__a, __b);
> -}
> -
>  __extension__ extern __inline uint16x8_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_u16 (uint16x8_t __a, uint16x8_t __b)
> @@ -736,13 +686,6 @@ __arm_vornq_u16 (uint16x8_t __a, uint16x8_t __b)
>    return __builtin_mve_vornq_uv8hi (__a, __b);
>  }
>  
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_u16 (uint16x8_t __a, uint16x8_t __b)
> -{
> -  return __builtin_mve_vbicq_uv8hi (__a, __b);
> -}
> -
>  __extension__ extern __inline int16x8_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_s16 (int16x8_t __a, int16x8_t __b)
> @@ -750,13 +693,6 @@ __arm_vornq_s16 (int16x8_t __a, int16x8_t __b)
>    return __builtin_mve_vornq_sv8hi (__a, __b);
>  }
>  
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_s16 (int16x8_t __a, int16x8_t __b)
> -{
> -  return __builtin_mve_vbicq_sv8hi (__a, __b);
> -}
> -
>  __extension__ extern __inline uint32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_u32 (uint32x4_t __a, uint32x4_t __b)
> @@ -764,13 +700,6 @@ __arm_vornq_u32 (uint32x4_t __a, uint32x4_t __b)
>    return __builtin_mve_vornq_uv4si (__a, __b);
>  }
>  
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_u32 (uint32x4_t __a, uint32x4_t __b)
> -{
> -  return __builtin_mve_vbicq_uv4si (__a, __b);
> -}
> -
>  __extension__ extern __inline int32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_s32 (int32x4_t __a, int32x4_t __b)
> @@ -778,41 +707,6 @@ __arm_vornq_s32 (int32x4_t __a, int32x4_t __b)
>    return __builtin_mve_vornq_sv4si (__a, __b);
>  }
>  
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_s32 (int32x4_t __a, int32x4_t __b)
> -{
> -  return __builtin_mve_vbicq_sv4si (__a, __b);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_n_u16 (uint16x8_t __a, const int __imm)
> -{
> -  return __builtin_mve_vbicq_n_uv8hi (__a, __imm);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_n_s16 (int16x8_t __a, const int __imm)
> -{
> -  return __builtin_mve_vbicq_n_sv8hi (__a, __imm);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_n_u32 (uint32x4_t __a, const int __imm)
> -{
> -  return __builtin_mve_vbicq_n_uv4si (__a, __imm);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_n_s32 (int32x4_t __a, const int __imm)
> -{
> -  return __builtin_mve_vbicq_n_sv4si (__a, __imm);
> -}
> -
>  __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vctp8q_m (uint32_t __a, mve_pred16_t __p)
> @@ -841,34 +735,6 @@ __arm_vctp16q_m (uint32_t __a, mve_pred16_t __p)
>    return __builtin_mve_vctp16q_mv8bi (__a, __p);
>  }
>  
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n_s16 (int16x8_t __a, const int __imm, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_n_sv8hi (__a, __imm, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n_s32 (int32x4_t __a, const int __imm, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_n_sv4si (__a, __imm, __p);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n_u16 (uint16x8_t __a, const int __imm, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_n_uv8hi (__a, __imm, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n_u32 (uint32x4_t __a, const int __imm, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_n_uv4si (__a, __imm, __p);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vshlcq_s8 (int8x16_t __a, uint32_t * __b, const int __imm)
> @@ -923,48 +789,6 @@ __arm_vshlcq_u32 (uint32x4_t __a, uint32_t * __b, const int __imm)
>    return __res;
>  }
>  
> -__extension__ extern __inline int8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_sv16qi (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_sv4si (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_s16 (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_sv8hi (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_u8 (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_uv16qi (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_uv4si (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_uv8hi (__inactive, __a, __b, __p);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> @@ -2834,48 +2658,6 @@ __arm_viwdupq_x_wb_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16
>    return __res;
>  }
>  
> -__extension__ extern __inline int8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_sv16qi (__arm_vuninitializedq_s8 (), __a, __b, __p);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_s16 (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __b, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_s32 (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_u8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_uv16qi (__arm_vuninitializedq_u8 (), __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_u16 (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_u32 (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __b, __p);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_x_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> @@ -3645,13 +3427,6 @@ __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_vbicq_f16 (float16x8_t __a, float16x8_t __b)
> -{
> -  return __builtin_mve_vbicq_fv8hf (__a, __b);
> -}
> -
>  __extension__ extern __inline float32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_f32 (float32x4_t __a, float32x4_t __b)
> @@ -3659,27 +3434,6 @@ __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_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_vbicq_m_f32 (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_fv4sf (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline float16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_f16 (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_fv8hf (__inactive, __a, __b, __p);
> -}
> -
>  __extension__ extern __inline float32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_m_f32 (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
> @@ -3924,20 +3678,6 @@ __arm_vstrwq_scatter_base_wb_p_f32 (uint32x4_t * __addr, const int __offset, flo
>    *__addr = __builtin_mve_vstrwq_scatter_base_wb_p_fv4sf (*__addr, __offset, __value, __p);
>  }
>  
> -__extension__ extern __inline float16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_fv8hf (__arm_vuninitializedq_f16 (), __a, __b, __p);
> -}
> -
> -__extension__ extern __inline float32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x_f32 (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
> -{
> -  return __builtin_mve_vbicq_m_fv4sf (__arm_vuninitializedq_f32 (), __a, __b, __p);
> -}
> -
>  __extension__ extern __inline float16x8_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
> @@ -4119,13 +3859,6 @@ __arm_vornq (uint8x16_t __a, uint8x16_t __b)
>   return __arm_vornq_u8 (__a, __b);
>  }
>  
> -__extension__ extern __inline uint8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (uint8x16_t __a, uint8x16_t __b)
> -{
> - return __arm_vbicq_u8 (__a, __b);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq (int8x16_t __a, int8x16_t __b)
> @@ -4133,13 +3866,6 @@ __arm_vornq (int8x16_t __a, int8x16_t __b)
>   return __arm_vornq_s8 (__a, __b);
>  }
>  
> -__extension__ extern __inline int8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (int8x16_t __a, int8x16_t __b)
> -{
> - return __arm_vbicq_s8 (__a, __b);
> -}
> -
>  __extension__ extern __inline uint16x8_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq (uint16x8_t __a, uint16x8_t __b)
> @@ -4147,13 +3873,6 @@ __arm_vornq (uint16x8_t __a, uint16x8_t __b)
>   return __arm_vornq_u16 (__a, __b);
>  }
>  
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (uint16x8_t __a, uint16x8_t __b)
> -{
> - return __arm_vbicq_u16 (__a, __b);
> -}
> -
>  __extension__ extern __inline int16x8_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq (int16x8_t __a, int16x8_t __b)
> @@ -4161,13 +3880,6 @@ __arm_vornq (int16x8_t __a, int16x8_t __b)
>   return __arm_vornq_s16 (__a, __b);
>  }
>  
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (int16x8_t __a, int16x8_t __b)
> -{
> - return __arm_vbicq_s16 (__a, __b);
> -}
> -
>  __extension__ extern __inline uint32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq (uint32x4_t __a, uint32x4_t __b)
> @@ -4175,13 +3887,6 @@ __arm_vornq (uint32x4_t __a, uint32x4_t __b)
>   return __arm_vornq_u32 (__a, __b);
>  }
>  
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (uint32x4_t __a, uint32x4_t __b)
> -{
> - return __arm_vbicq_u32 (__a, __b);
> -}
> -
>  __extension__ extern __inline int32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq (int32x4_t __a, int32x4_t __b)
> @@ -4189,69 +3894,6 @@ __arm_vornq (int32x4_t __a, int32x4_t __b)
>   return __arm_vornq_s32 (__a, __b);
>  }
>  
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (int32x4_t __a, int32x4_t __b)
> -{
> - return __arm_vbicq_s32 (__a, __b);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (uint16x8_t __a, const int __imm)
> -{
> - return __arm_vbicq_n_u16 (__a, __imm);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (int16x8_t __a, const int __imm)
> -{
> - return __arm_vbicq_n_s16 (__a, __imm);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (uint32x4_t __a, const int __imm)
> -{
> - return __arm_vbicq_n_u32 (__a, __imm);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (int32x4_t __a, const int __imm)
> -{
> - return __arm_vbicq_n_s32 (__a, __imm);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n (int16x8_t __a, const int __imm, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_n_s16 (__a, __imm, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n (int32x4_t __a, const int __imm, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_n_s32 (__a, __imm, __p);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n (uint16x8_t __a, const int __imm, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_n_u16 (__a, __imm, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m_n (uint32x4_t __a, const int __imm, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_n_u32 (__a, __imm, __p);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vshlcq (int8x16_t __a, uint32_t * __b, const int __imm)
> @@ -4294,48 +3936,6 @@ __arm_vshlcq (uint32x4_t __a, uint32_t * __b, const int __imm)
>   return __arm_vshlcq_u32 (__a, __b, __imm);
>  }
>  
> -__extension__ extern __inline int8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_s8 (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_s32 (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_s16 (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_u8 (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_u32 (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_u16 (__inactive, __a, __b, __p);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> @@ -5778,48 +5378,6 @@ __arm_viwdupq_x_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t
>   return __arm_viwdupq_x_wb_u32 (__a, __b, __imm, __p);
>  }
>  
> -__extension__ extern __inline int8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_s8 (__a, __b, __p);
> -}
> -
> -__extension__ extern __inline int16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_s16 (__a, __b, __p);
> -}
> -
> -__extension__ extern __inline int32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_s32 (__a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint8x16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_u8 (__a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_u16 (__a, __b, __p);
> -}
> -
> -__extension__ extern __inline uint32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_u32 (__a, __b, __p);
> -}
> -
>  __extension__ extern __inline int8x16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
> @@ -6361,13 +5919,6 @@ __arm_vornq (float16x8_t __a, float16x8_t __b)
>   return __arm_vornq_f16 (__a, __b);
>  }
>  
> -__extension__ extern __inline float16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (float16x8_t __a, float16x8_t __b)
> -{
> - return __arm_vbicq_f16 (__a, __b);
> -}
> -
>  __extension__ extern __inline float32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq (float32x4_t __a, float32x4_t __b)
> @@ -6375,27 +5926,6 @@ __arm_vornq (float32x4_t __a, float32x4_t __b)
>   return __arm_vornq_f32 (__a, __b);
>  }
>  
> -__extension__ extern __inline float32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq (float32x4_t __a, float32x4_t __b)
> -{
> - return __arm_vbicq_f32 (__a, __b);
> -}
> -
> -__extension__ extern __inline float32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_f32 (__inactive, __a, __b, __p);
> -}
> -
> -__extension__ extern __inline float16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_m_f16 (__inactive, __a, __b, __p);
> -}
> -
>  __extension__ extern __inline float32x4_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
> @@ -6578,20 +6108,6 @@ __arm_vstrwq_scatter_base_wb_p (uint32x4_t * __addr, const int __offset, float32
>   __arm_vstrwq_scatter_base_wb_p_f32 (__addr, __offset, __value, __p);
>  }
>  
> -__extension__ extern __inline float16x8_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_f16 (__a, __b, __p);
> -}
> -
> -__extension__ extern __inline float32x4_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vbicq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
> -{
> - return __arm_vbicq_x_f32 (__a, __b, __p);
> -}
> -
>  __extension__ extern __inline float16x8_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vornq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
> @@ -7027,22 +6543,6 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce_f16_ptr(__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_f32_ptr(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
>  
> -#define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
> -  __typeof(p1) __p1 = (p1); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  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 __arm_vornq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
>    __typeof(p1) __p1 = (p1); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
> @@ -7055,13 +6555,6 @@ extern void *__ARM_undef;
>    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 __arm_vbicq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
> -  int (*)[__ARM_mve_type_int16x8_t]: __arm_vbicq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1, p2), \
> -  int (*)[__ARM_mve_type_int32x4_t]: __arm_vbicq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1, p2), \
> -  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
> -  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
> -
>  #define __arm_vshlcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
>    int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlcq_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
> @@ -7071,19 +6564,6 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
>    int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
>  
> -#define __arm_vbicq_m(p0,p1,p2,p3) ({ __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_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
> -  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
> -  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbicq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
> -  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbicq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
> -
>  #define __arm_vornq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
>    __typeof(p1) __p1 = (p1); \
>    __typeof(p2) __p2 = (p2); \
> @@ -7387,18 +6867,6 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_wb_p_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
>    int (*)[__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_base_wb_p_f32 (p0, p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
>  
> -#define __arm_vbicq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
> -  __typeof(p2) __p2 = (p2); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
> -  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_x_s8   (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_x_s16  (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_x_s32  (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
> -  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
> -  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbicq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
> -  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbicq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
> -
>  #define __arm_vornq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
>    __typeof(p2) __p2 = (p2); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
> @@ -7469,20 +6937,6 @@ extern void *__ARM_undef;
>    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)));})
>  
> -#define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
> -  __typeof(p1) __p1 = (p1); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \
> -  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)));})
> -
>  #define __arm_vshlcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
>    int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlcq_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
> @@ -7492,24 +6946,6 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
>    int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
>  
> -#define __arm_vbicq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
> -  int (*)[__ARM_mve_type_int16x8_t]: __arm_vbicq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1, p2), \
> -  int (*)[__ARM_mve_type_int32x4_t]: __arm_vbicq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1, p2), \
> -  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
> -  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
> -
> -#define __arm_vbicq_m(p0,p1,p2,p3) ({ __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_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
> -  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
> -
>  #define __arm_vornq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
>    __typeof(p1) __p1 = (p1); \
>    __typeof(p2) __p2 = (p2); \
> @@ -7750,16 +7186,6 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vornq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
>    int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vornq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
>  
> -#define __arm_vbicq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
> -  __typeof(p2) __p2 = (p2); \
> -  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
> -  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_x_s8   (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_x_s16  (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_x_s32  (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
> -  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
> -
>  #define __arm_vld1q_z(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
>    int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), p1), \
>    int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), p1), \
> diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
> index 41c7e73a161..c0dd4b9019e 100644
> --- a/gcc/config/arm/mve.md
> +++ b/gcc/config/arm/mve.md
> @@ -803,7 +803,7 @@ (define_expand "mve_vandq_s<mode>"
>  ;;
>  ;; [vbicq_s, vbicq_u])
>  ;;
> -(define_insn "mve_vbicq_u<mode>"
> +(define_insn "@mve_vbicq_u<mode>"
>    [
>     (set (match_operand:MVE_2 0 "s_register_operand" "=w")
>  	(and:MVE_2 (not:MVE_2 (match_operand:MVE_2 2 "s_register_operand" "w"))
> @@ -815,7 +815,7 @@ (define_insn "mve_vbicq_u<mode>"
>    (set_attr "type" "mve_move")
>  ])
>  
> -(define_expand "mve_vbicq_s<mode>"
> +(define_expand "@mve_vbicq_s<mode>"
>    [
>     (set (match_operand:MVE_2 0 "s_register_operand")
>  	(and:MVE_2 (not:MVE_2 (match_operand:MVE_2 2 "s_register_operand"))
> @@ -1209,7 +1209,7 @@ (define_insn "mve_vandq_f<mode>"
>  ;;
>  ;; [vbicq_f])
>  ;;
> -(define_insn "mve_vbicq_f<mode>"
> +(define_insn "@mve_vbicq_f<mode>"
>    [
>     (set (match_operand:MVE_0 0 "s_register_operand" "=w")
>  	(and:MVE_0 (not:MVE_0 (match_operand:MVE_0 1 "s_register_operand" "w"))