arm: [MVE intrinsics] rework vaddvaq

Implement vaddvaq using the new MVE builtins framework.

2022-10-25  Christophe Lyon  <christophe.lyon@arm.com>

	gcc/
	* config/arm/arm-mve-builtins-base.cc (vaddvaq): New.
	* config/arm/arm-mve-builtins-base.def (vaddvaq): New.
	* config/arm/arm-mve-builtins-base.h (vaddvaq): New.
	* config/arm/arm_mve.h (vaddvaq): Remove.
	(vaddvaq_p): Remove.
	(vaddvaq_u8): Remove.
	(vaddvaq_s8): Remove.
	(vaddvaq_u16): Remove.
	(vaddvaq_s16): Remove.
	(vaddvaq_u32): Remove.
	(vaddvaq_s32): Remove.
	(vaddvaq_p_u8): Remove.
	(vaddvaq_p_s8): Remove.
	(vaddvaq_p_u16): Remove.
	(vaddvaq_p_s16): Remove.
	(vaddvaq_p_u32): Remove.
	(vaddvaq_p_s32): Remove.
	(__arm_vaddvaq_u8): Remove.
	(__arm_vaddvaq_s8): Remove.
	(__arm_vaddvaq_u16): Remove.
	(__arm_vaddvaq_s16): Remove.
	(__arm_vaddvaq_u32): Remove.
	(__arm_vaddvaq_s32): Remove.
	(__arm_vaddvaq_p_u8): Remove.
	(__arm_vaddvaq_p_s8): Remove.
	(__arm_vaddvaq_p_u16): Remove.
	(__arm_vaddvaq_p_s16): Remove.
	(__arm_vaddvaq_p_u32): Remove.
	(__arm_vaddvaq_p_s32): Remove.
	(__arm_vaddvaq): Remove.
	(__arm_vaddvaq_p): Remove.

4 files changed, 3 insertions, 202 deletions

diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc
index 7f90fc6..e87069b 100644
--- a/gcc/config/arm/arm-mve-builtins-base.cc
+++ b/gcc/config/arm/arm-mve-builtins-base.cc
@@ -245,6 +245,7 @@ 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_WITH_RTX_M_N (vaddq, PLUS, VADDQ)
 FUNCTION_PRED_P_S_U (vaddvq, VADDVQ)
+FUNCTION_PRED_P_S_U (vaddvaq, VADDVAQ)
 FUNCTION_WITH_RTX_M (vandq, AND, VANDQ)
 FUNCTION_WITHOUT_N_NO_U_F (vclsq, VCLSQ)
 FUNCTION (vclzq, unspec_based_mve_function_exact_insn, (CLZ, CLZ, CLZ, -1, -1, -1, VCLZQ_M_S, VCLZQ_M_U, -1, -1, -1 ,-1))
diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def
index d32745f..413fe4a 100644
--- a/gcc/config/arm/arm-mve-builtins-base.def
+++ b/gcc/config/arm/arm-mve-builtins-base.def
@@ -21,6 +21,7 @@
 DEF_MVE_FUNCTION (vabdq, binary, all_integer, mx_or_none)
 DEF_MVE_FUNCTION (vabsq, unary, all_signed, mx_or_none)
 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 (vclsq, unary, all_signed, mx_or_none)
diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h
index 9080542..5338b77 100644
--- a/gcc/config/arm/arm-mve-builtins-base.h
+++ b/gcc/config/arm/arm-mve-builtins-base.h
@@ -26,6 +26,7 @@ namespace functions {
 extern const function_base *const vabdq;
 extern const function_base *const vabsq;
 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 vclsq;
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 11f1033..7478357 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -54,7 +54,6 @@
 #define vcaddq_rot90(__a, __b) __arm_vcaddq_rot90(__a, __b)
 #define vcaddq_rot270(__a, __b) __arm_vcaddq_rot270(__a, __b)
 #define vbicq(__a, __b) __arm_vbicq(__a, __b)
-#define vaddvaq(__a, __b) __arm_vaddvaq(__a, __b)
 #define vbrsrq(__a, __b) __arm_vbrsrq(__a, __b)
 #define vqshluq(__a, __imm) __arm_vqshluq(__a, __imm)
 #define vmlsdavxq(__a, __b) __arm_vmlsdavxq(__a, __b)
@@ -89,7 +88,6 @@
 #define vmlaq(__a, __b, __c) __arm_vmlaq(__a, __b, __c)
 #define vmladavq_p(__a, __b, __p) __arm_vmladavq_p(__a, __b, __p)
 #define vmladavaq(__a, __b, __c) __arm_vmladavaq(__a, __b, __c)
-#define vaddvaq_p(__a, __b, __p) __arm_vaddvaq_p(__a, __b, __p)
 #define vsriq(__a, __b, __imm) __arm_vsriq(__a, __b, __imm)
 #define vsliq(__a, __b, __imm) __arm_vsliq(__a, __b, __imm)
 #define vmlsdavxq_p(__a, __b, __p) __arm_vmlsdavxq_p(__a, __b, __p)
@@ -390,7 +388,6 @@
 #define vcaddq_rot90_u8(__a, __b) __arm_vcaddq_rot90_u8(__a, __b)
 #define vcaddq_rot270_u8(__a, __b) __arm_vcaddq_rot270_u8(__a, __b)
 #define vbicq_u8(__a, __b) __arm_vbicq_u8(__a, __b)
-#define vaddvaq_u8(__a, __b) __arm_vaddvaq_u8(__a, __b)
 #define vbrsrq_n_u8(__a, __b) __arm_vbrsrq_n_u8(__a, __b)
 #define vqshluq_n_s8(__a,  __imm) __arm_vqshluq_n_s8(__a,  __imm)
 #define vornq_s8(__a, __b) __arm_vornq_s8(__a, __b)
@@ -406,7 +403,6 @@
 #define vcaddq_rot270_s8(__a, __b) __arm_vcaddq_rot270_s8(__a, __b)
 #define vbrsrq_n_s8(__a, __b) __arm_vbrsrq_n_s8(__a, __b)
 #define vbicq_s8(__a, __b) __arm_vbicq_s8(__a, __b)
-#define vaddvaq_s8(__a, __b) __arm_vaddvaq_s8(__a, __b)
 #define vornq_u16(__a, __b) __arm_vornq_u16(__a, __b)
 #define vmulltq_int_u16(__a, __b) __arm_vmulltq_int_u16(__a, __b)
 #define vmullbq_int_u16(__a, __b) __arm_vmullbq_int_u16(__a, __b)
@@ -414,7 +410,6 @@
 #define vcaddq_rot90_u16(__a, __b) __arm_vcaddq_rot90_u16(__a, __b)
 #define vcaddq_rot270_u16(__a, __b) __arm_vcaddq_rot270_u16(__a, __b)
 #define vbicq_u16(__a, __b) __arm_vbicq_u16(__a, __b)
-#define vaddvaq_u16(__a, __b) __arm_vaddvaq_u16(__a, __b)
 #define vbrsrq_n_u16(__a, __b) __arm_vbrsrq_n_u16(__a, __b)
 #define vqshluq_n_s16(__a,  __imm) __arm_vqshluq_n_s16(__a,  __imm)
 #define vornq_s16(__a, __b) __arm_vornq_s16(__a, __b)
@@ -430,7 +425,6 @@
 #define vcaddq_rot270_s16(__a, __b) __arm_vcaddq_rot270_s16(__a, __b)
 #define vbrsrq_n_s16(__a, __b) __arm_vbrsrq_n_s16(__a, __b)
 #define vbicq_s16(__a, __b) __arm_vbicq_s16(__a, __b)
-#define vaddvaq_s16(__a, __b) __arm_vaddvaq_s16(__a, __b)
 #define vornq_u32(__a, __b) __arm_vornq_u32(__a, __b)
 #define vmulltq_int_u32(__a, __b) __arm_vmulltq_int_u32(__a, __b)
 #define vmullbq_int_u32(__a, __b) __arm_vmullbq_int_u32(__a, __b)
@@ -438,7 +432,6 @@
 #define vcaddq_rot90_u32(__a, __b) __arm_vcaddq_rot90_u32(__a, __b)
 #define vcaddq_rot270_u32(__a, __b) __arm_vcaddq_rot270_u32(__a, __b)
 #define vbicq_u32(__a, __b) __arm_vbicq_u32(__a, __b)
-#define vaddvaq_u32(__a, __b) __arm_vaddvaq_u32(__a, __b)
 #define vbrsrq_n_u32(__a, __b) __arm_vbrsrq_n_u32(__a, __b)
 #define vqshluq_n_s32(__a,  __imm) __arm_vqshluq_n_s32(__a,  __imm)
 #define vornq_s32(__a, __b) __arm_vornq_s32(__a, __b)
@@ -454,7 +447,6 @@
 #define vcaddq_rot270_s32(__a, __b) __arm_vcaddq_rot270_s32(__a, __b)
 #define vbrsrq_n_s32(__a, __b) __arm_vbrsrq_n_s32(__a, __b)
 #define vbicq_s32(__a, __b) __arm_vbicq_s32(__a, __b)
-#define vaddvaq_s32(__a, __b) __arm_vaddvaq_s32(__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 vmlaldavq_u16(__a, __b) __arm_vmlaldavq_u16(__a, __b)
@@ -543,7 +535,6 @@
 #define vmlaq_n_u8(__a, __b, __c) __arm_vmlaq_n_u8(__a, __b, __c)
 #define vmladavq_p_u8(__a, __b, __p) __arm_vmladavq_p_u8(__a, __b, __p)
 #define vmladavaq_u8(__a, __b, __c) __arm_vmladavaq_u8(__a, __b, __c)
-#define vaddvaq_p_u8(__a, __b, __p) __arm_vaddvaq_p_u8(__a, __b, __p)
 #define vsriq_n_u8(__a, __b,  __imm) __arm_vsriq_n_u8(__a, __b,  __imm)
 #define vsliq_n_u8(__a, __b,  __imm) __arm_vsliq_n_u8(__a, __b,  __imm)
 #define vmvnq_m_s8(__inactive, __a, __p) __arm_vmvnq_m_s8(__inactive, __a, __p)
@@ -551,7 +542,6 @@
 #define vmlsdavq_p_s8(__a, __b, __p) __arm_vmlsdavq_p_s8(__a, __b, __p)
 #define vmladavxq_p_s8(__a, __b, __p) __arm_vmladavxq_p_s8(__a, __b, __p)
 #define vmladavq_p_s8(__a, __b, __p) __arm_vmladavq_p_s8(__a, __b, __p)
-#define vaddvaq_p_s8(__a, __b, __p) __arm_vaddvaq_p_s8(__a, __b, __p)
 #define vqrdmlsdhxq_s8(__inactive, __a, __b) __arm_vqrdmlsdhxq_s8(__inactive, __a, __b)
 #define vqrdmlsdhq_s8(__inactive, __a, __b) __arm_vqrdmlsdhq_s8(__inactive, __a, __b)
 #define vqrdmlashq_n_s8(__a, __b, __c) __arm_vqrdmlashq_n_s8(__a, __b, __c)
@@ -579,7 +569,6 @@
 #define vmlaq_n_u16(__a, __b, __c) __arm_vmlaq_n_u16(__a, __b, __c)
 #define vmladavq_p_u16(__a, __b, __p) __arm_vmladavq_p_u16(__a, __b, __p)
 #define vmladavaq_u16(__a, __b, __c) __arm_vmladavaq_u16(__a, __b, __c)
-#define vaddvaq_p_u16(__a, __b, __p) __arm_vaddvaq_p_u16(__a, __b, __p)
 #define vsriq_n_u16(__a, __b,  __imm) __arm_vsriq_n_u16(__a, __b,  __imm)
 #define vsliq_n_u16(__a, __b,  __imm) __arm_vsliq_n_u16(__a, __b,  __imm)
 #define vmvnq_m_s16(__inactive, __a, __p) __arm_vmvnq_m_s16(__inactive, __a, __p)
@@ -587,7 +576,6 @@
 #define vmlsdavq_p_s16(__a, __b, __p) __arm_vmlsdavq_p_s16(__a, __b, __p)
 #define vmladavxq_p_s16(__a, __b, __p) __arm_vmladavxq_p_s16(__a, __b, __p)
 #define vmladavq_p_s16(__a, __b, __p) __arm_vmladavq_p_s16(__a, __b, __p)
-#define vaddvaq_p_s16(__a, __b, __p) __arm_vaddvaq_p_s16(__a, __b, __p)
 #define vqrdmlsdhxq_s16(__inactive, __a, __b) __arm_vqrdmlsdhxq_s16(__inactive, __a, __b)
 #define vqrdmlsdhq_s16(__inactive, __a, __b) __arm_vqrdmlsdhq_s16(__inactive, __a, __b)
 #define vqrdmlashq_n_s16(__a, __b, __c) __arm_vqrdmlashq_n_s16(__a, __b, __c)
@@ -615,7 +603,6 @@
 #define vmlaq_n_u32(__a, __b, __c) __arm_vmlaq_n_u32(__a, __b, __c)
 #define vmladavq_p_u32(__a, __b, __p) __arm_vmladavq_p_u32(__a, __b, __p)
 #define vmladavaq_u32(__a, __b, __c) __arm_vmladavaq_u32(__a, __b, __c)
-#define vaddvaq_p_u32(__a, __b, __p) __arm_vaddvaq_p_u32(__a, __b, __p)
 #define vsriq_n_u32(__a, __b,  __imm) __arm_vsriq_n_u32(__a, __b,  __imm)
 #define vsliq_n_u32(__a, __b,  __imm) __arm_vsliq_n_u32(__a, __b,  __imm)
 #define vmvnq_m_s32(__inactive, __a, __p) __arm_vmvnq_m_s32(__inactive, __a, __p)
@@ -623,7 +610,6 @@
 #define vmlsdavq_p_s32(__a, __b, __p) __arm_vmlsdavq_p_s32(__a, __b, __p)
 #define vmladavxq_p_s32(__a, __b, __p) __arm_vmladavxq_p_s32(__a, __b, __p)
 #define vmladavq_p_s32(__a, __b, __p) __arm_vmladavq_p_s32(__a, __b, __p)
-#define vaddvaq_p_s32(__a, __b, __p) __arm_vaddvaq_p_s32(__a, __b, __p)
 #define vqrdmlsdhxq_s32(__inactive, __a, __b) __arm_vqrdmlsdhxq_s32(__inactive, __a, __b)
 #define vqrdmlsdhq_s32(__inactive, __a, __b) __arm_vqrdmlsdhq_s32(__inactive, __a, __b)
 #define vqrdmlashq_n_s32(__a, __b, __c) __arm_vqrdmlashq_n_s32(__a, __b, __c)
@@ -1753,13 +1739,6 @@ __arm_vbicq_u8 (uint8x16_t __a, uint8x16_t __b)
   return __builtin_mve_vbicq_uv16qi (__a, __b);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_u8 (uint32_t __a, uint8x16_t __b)
-{
-  return __builtin_mve_vaddvaq_uv16qi (__a, __b);
-}
-
 __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vbrsrq_n_u8 (uint8x16_t __a, int32_t __b)
@@ -1865,13 +1844,6 @@ __arm_vbicq_s8 (int8x16_t __a, int8x16_t __b)
   return __builtin_mve_vbicq_sv16qi (__a, __b);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_s8 (int32_t __a, int8x16_t __b)
-{
-  return __builtin_mve_vaddvaq_sv16qi (__a, __b);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vornq_u16 (uint16x8_t __a, uint16x8_t __b)
@@ -1923,13 +1895,6 @@ __arm_vbicq_u16 (uint16x8_t __a, uint16x8_t __b)
   return __builtin_mve_vbicq_uv8hi (__a, __b);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_u16 (uint32_t __a, uint16x8_t __b)
-{
-  return __builtin_mve_vaddvaq_uv8hi (__a, __b);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vbrsrq_n_u16 (uint16x8_t __a, int32_t __b)
@@ -2035,13 +2000,6 @@ __arm_vbicq_s16 (int16x8_t __a, int16x8_t __b)
   return __builtin_mve_vbicq_sv8hi (__a, __b);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_s16 (int32_t __a, int16x8_t __b)
-{
-  return __builtin_mve_vaddvaq_sv8hi (__a, __b);
-}
-
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vornq_u32 (uint32x4_t __a, uint32x4_t __b)
@@ -2093,13 +2051,6 @@ __arm_vbicq_u32 (uint32x4_t __a, uint32x4_t __b)
   return __builtin_mve_vbicq_uv4si (__a, __b);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_u32 (uint32_t __a, uint32x4_t __b)
-{
-  return __builtin_mve_vaddvaq_uv4si (__a, __b);
-}
-
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vbrsrq_n_u32 (uint32x4_t __a, int32_t __b)
@@ -2205,13 +2156,6 @@ __arm_vbicq_s32 (int32x4_t __a, int32x4_t __b)
   return __builtin_mve_vbicq_sv4si (__a, __b);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_s32 (int32_t __a, int32x4_t __b)
-{
-  return __builtin_mve_vaddvaq_sv4si (__a, __b);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vmulltq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
@@ -2658,13 +2602,6 @@ __arm_vmladavaq_u8 (uint32_t __a, uint8x16_t __b, uint8x16_t __c)
   return __builtin_mve_vmladavaq_uv16qi (__a, __b, __c);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p_u8 (uint32_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vaddvaq_p_uv16qi (__a, __b, __p);
-}
-
 __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vsriq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __imm)
@@ -2714,13 +2651,6 @@ __arm_vmladavq_p_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
   return __builtin_mve_vmladavq_p_sv16qi (__a, __b, __p);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p_s8 (int32_t __a, int8x16_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vaddvaq_p_sv16qi (__a, __b, __p);
-}
-
 __extension__ extern __inline int8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vqrdmlsdhxq_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
@@ -2910,13 +2840,6 @@ __arm_vmladavaq_u16 (uint32_t __a, uint16x8_t __b, uint16x8_t __c)
   return __builtin_mve_vmladavaq_uv8hi (__a, __b, __c);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p_u16 (uint32_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vaddvaq_p_uv8hi (__a, __b, __p);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vsriq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __imm)
@@ -2966,13 +2889,6 @@ __arm_vmladavq_p_s16 (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
   return __builtin_mve_vmladavq_p_sv8hi (__a, __b, __p);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p_s16 (int32_t __a, int16x8_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vaddvaq_p_sv8hi (__a, __b, __p);
-}
-
 __extension__ extern __inline int16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vqrdmlsdhxq_s16 (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
@@ -3162,13 +3078,6 @@ __arm_vmladavaq_u32 (uint32_t __a, uint32x4_t __b, uint32x4_t __c)
   return __builtin_mve_vmladavaq_uv4si (__a, __b, __c);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p_u32 (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vaddvaq_p_uv4si (__a, __b, __p);
-}
-
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vsriq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __imm)
@@ -3218,13 +3127,6 @@ __arm_vmladavq_p_s32 (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
   return __builtin_mve_vmladavq_p_sv4si (__a, __b, __p);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p_s32 (int32_t __a, int32x4_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vaddvaq_p_sv4si (__a, __b, __p);
-}
-
 __extension__ extern __inline int32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vqrdmlsdhxq_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
@@ -9859,13 +9761,6 @@ __arm_vbicq (uint8x16_t __a, uint8x16_t __b)
  return __arm_vbicq_u8 (__a, __b);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq (uint32_t __a, uint8x16_t __b)
-{
- return __arm_vaddvaq_u8 (__a, __b);
-}
-
 __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vbrsrq (uint8x16_t __a, int32_t __b)
@@ -9971,13 +9866,6 @@ __arm_vbicq (int8x16_t __a, int8x16_t __b)
  return __arm_vbicq_s8 (__a, __b);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq (int32_t __a, int8x16_t __b)
-{
- return __arm_vaddvaq_s8 (__a, __b);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vornq (uint16x8_t __a, uint16x8_t __b)
@@ -10027,13 +9915,6 @@ __arm_vbicq (uint16x8_t __a, uint16x8_t __b)
  return __arm_vbicq_u16 (__a, __b);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq (uint32_t __a, uint16x8_t __b)
-{
- return __arm_vaddvaq_u16 (__a, __b);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vbrsrq (uint16x8_t __a, int32_t __b)
@@ -10139,13 +10020,6 @@ __arm_vbicq (int16x8_t __a, int16x8_t __b)
  return __arm_vbicq_s16 (__a, __b);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq (int32_t __a, int16x8_t __b)
-{
- return __arm_vaddvaq_s16 (__a, __b);
-}
-
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vornq (uint32x4_t __a, uint32x4_t __b)
@@ -10195,13 +10069,6 @@ __arm_vbicq (uint32x4_t __a, uint32x4_t __b)
  return __arm_vbicq_u32 (__a, __b);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq (uint32_t __a, uint32x4_t __b)
-{
- return __arm_vaddvaq_u32 (__a, __b);
-}
-
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vbrsrq (uint32x4_t __a, int32_t __b)
@@ -10307,13 +10174,6 @@ __arm_vbicq (int32x4_t __a, int32x4_t __b)
  return __arm_vbicq_s32 (__a, __b);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq (int32_t __a, int32x4_t __b)
-{
- return __arm_vaddvaq_s32 (__a, __b);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vmulltq_poly (uint8x16_t __a, uint8x16_t __b)
@@ -10720,13 +10580,6 @@ __arm_vmladavaq (uint32_t __a, uint8x16_t __b, uint8x16_t __c)
  return __arm_vmladavaq_u8 (__a, __b, __c);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p (uint32_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
- return __arm_vaddvaq_p_u8 (__a, __b, __p);
-}
-
 __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vsriq (uint8x16_t __a, uint8x16_t __b, const int __imm)
@@ -10776,13 +10629,6 @@ __arm_vmladavq_p (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
  return __arm_vmladavq_p_s8 (__a, __b, __p);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p (int32_t __a, int8x16_t __b, mve_pred16_t __p)
-{
- return __arm_vaddvaq_p_s8 (__a, __b, __p);
-}
-
 __extension__ extern __inline int8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vqrdmlsdhxq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
@@ -10972,13 +10818,6 @@ __arm_vmladavaq (uint32_t __a, uint16x8_t __b, uint16x8_t __c)
  return __arm_vmladavaq_u16 (__a, __b, __c);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p (uint32_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
- return __arm_vaddvaq_p_u16 (__a, __b, __p);
-}
-
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vsriq (uint16x8_t __a, uint16x8_t __b, const int __imm)
@@ -11028,13 +10867,6 @@ __arm_vmladavq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
  return __arm_vmladavq_p_s16 (__a, __b, __p);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p (int32_t __a, int16x8_t __b, mve_pred16_t __p)
-{
- return __arm_vaddvaq_p_s16 (__a, __b, __p);
-}
-
 __extension__ extern __inline int16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vqrdmlsdhxq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
@@ -11224,13 +11056,6 @@ __arm_vmladavaq (uint32_t __a, uint32x4_t __b, uint32x4_t __c)
  return __arm_vmladavaq_u32 (__a, __b, __c);
 }
 
-__extension__ extern __inline uint32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
-{
- return __arm_vaddvaq_p_u32 (__a, __b, __p);
-}
-
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vsriq (uint32x4_t __a, uint32x4_t __b, const int __imm)
@@ -11280,13 +11105,6 @@ __arm_vmladavq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
  return __arm_vmladavq_p_s32 (__a, __b, __p);
 }
 
-__extension__ extern __inline int32_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vaddvaq_p (int32_t __a, int32x4_t __b, mve_pred16_t __p)
-{
- return __arm_vaddvaq_p_s32 (__a, __b, __p);
-}
-
 __extension__ extern __inline int32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vqrdmlsdhxq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
@@ -19404,26 +19222,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
 
-#define __arm_vaddvaq(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_int_n][__ARM_mve_type_int8x16_t]: __arm_vaddvaq_s8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vaddvaq_s16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vaddvaq_s32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vaddvaq_u8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_u16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_u32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define __arm_vaddvaq_p(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_int_n][__ARM_mve_type_int8x16_t]: __arm_vaddvaq_p_s8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vaddvaq_p_s16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vaddvaq_p_s32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vaddvaq_p_u8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_p_u16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_p_u32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
 #define __arm_vmladavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \