arm: [MVE intrinsics] rework vmullbq_poly vmulltq_poly

Implement vmull[bt]q_poly using the new MVE builtins framework.

2023-08-14  Christophe Lyon  <christophe.lyon@linaro.org>

	gcc/
	* config/arm/arm-mve-builtins-base.cc (vmullbq_poly)
	(vmulltq_poly): New.
	* config/arm/arm-mve-builtins-base.def (vmullbq_poly)
	(vmulltq_poly): New.
	* config/arm/arm-mve-builtins-base.h (vmullbq_poly)
	(vmulltq_poly): New.
	* config/arm/arm_mve.h (vmulltq_poly): Remove.
	(vmullbq_poly): Remove.
	(vmullbq_poly_m): Remove.
	(vmulltq_poly_m): Remove.
	(vmullbq_poly_x): Remove.
	(vmulltq_poly_x): Remove.
	(vmulltq_poly_p8): Remove.
	(vmullbq_poly_p8): Remove.
	(vmulltq_poly_p16): Remove.
	(vmullbq_poly_p16): Remove.
	(vmullbq_poly_m_p8): Remove.
	(vmullbq_poly_m_p16): Remove.
	(vmulltq_poly_m_p8): Remove.
	(vmulltq_poly_m_p16): Remove.
	(vmullbq_poly_x_p8): Remove.
	(vmullbq_poly_x_p16): Remove.
	(vmulltq_poly_x_p8): Remove.
	(vmulltq_poly_x_p16): Remove.
	(__arm_vmulltq_poly_p8): Remove.
	(__arm_vmullbq_poly_p8): Remove.
	(__arm_vmulltq_poly_p16): Remove.
	(__arm_vmullbq_poly_p16): Remove.
	(__arm_vmullbq_poly_m_p8): Remove.
	(__arm_vmullbq_poly_m_p16): Remove.
	(__arm_vmulltq_poly_m_p8): Remove.
	(__arm_vmulltq_poly_m_p16): Remove.
	(__arm_vmullbq_poly_x_p8): Remove.
	(__arm_vmullbq_poly_x_p16): Remove.
	(__arm_vmulltq_poly_x_p8): Remove.
	(__arm_vmulltq_poly_x_p16): Remove.
	(__arm_vmulltq_poly): Remove.
	(__arm_vmullbq_poly): Remove.
	(__arm_vmullbq_poly_m): Remove.
	(__arm_vmulltq_poly_m): Remove.
	(__arm_vmullbq_poly_x): Remove.
	(__arm_vmulltq_poly_x): Remove.

4 files changed, 6 insertions, 248 deletions

diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc
index 3620c56..ed5eba6 100644
--- a/gcc/config/arm/arm-mve-builtins-base.cc
+++ b/gcc/config/arm/arm-mve-builtins-base.cc
@@ -331,6 +331,8 @@ FUNCTION_WITHOUT_N_NO_F (vmovntq, VMOVNTQ)
 FUNCTION_WITHOUT_N_NO_F (vmulhq, VMULHQ)
 FUNCTION (vmullbq_int, unspec_mve_function_exact_insn_vmull, (VMULLBQ_INT_S, VMULLBQ_INT_U, VMULLBQ_INT_M_S, VMULLBQ_INT_M_U))
 FUNCTION (vmulltq_int, unspec_mve_function_exact_insn_vmull, (VMULLTQ_INT_S, VMULLTQ_INT_U, VMULLTQ_INT_M_S, VMULLTQ_INT_M_U))
+FUNCTION (vmullbq_poly, unspec_mve_function_exact_insn_vmull_poly, (VMULLBQ_POLY_P, VMULLBQ_POLY_M_P))
+FUNCTION (vmulltq_poly, unspec_mve_function_exact_insn_vmull_poly, (VMULLTQ_POLY_P, VMULLTQ_POLY_M_P))
 FUNCTION_WITH_RTX_M_N (vmulq, MULT, VMULQ)
 FUNCTION_WITH_RTX_M_N_NO_F (vmvnq, NOT, VMVNQ)
 FUNCTION (vnegq, unspec_based_mve_function_exact_insn, (NEG, NEG, NEG, -1, -1, -1, VNEGQ_M_S, -1, VNEGQ_M_F, -1, -1, -1))
diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def
index db811be..01dfbde 100644
--- a/gcc/config/arm/arm-mve-builtins-base.def
+++ b/gcc/config/arm/arm-mve-builtins-base.def
@@ -80,6 +80,8 @@ DEF_MVE_FUNCTION (vmovntq, binary_move_narrow, integer_16_32, m_or_none)
 DEF_MVE_FUNCTION (vmulhq, binary, all_integer, mx_or_none)
 DEF_MVE_FUNCTION (vmullbq_int, binary_widen, all_integer, mx_or_none)
 DEF_MVE_FUNCTION (vmulltq_int, binary_widen, all_integer, mx_or_none)
+DEF_MVE_FUNCTION (vmullbq_poly, binary_widen_poly, poly_8_16, mx_or_none)
+DEF_MVE_FUNCTION (vmulltq_poly, binary_widen_poly, poly_8_16, mx_or_none)
 DEF_MVE_FUNCTION (vmulq, binary_opt_n, all_integer, mx_or_none)
 DEF_MVE_FUNCTION (vmvnq, mvn, all_integer, mx_or_none)
 DEF_MVE_FUNCTION (vnegq, 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 5652fb7..c574c32 100644
--- a/gcc/config/arm/arm-mve-builtins-base.h
+++ b/gcc/config/arm/arm-mve-builtins-base.h
@@ -104,6 +104,8 @@ extern const function_base *const vmovntq;
 extern const function_base *const vmulhq;
 extern const function_base *const vmullbq_int;
 extern const function_base *const vmulltq_int;
+extern const function_base *const vmullbq_poly;
+extern const function_base *const vmulltq_poly;
 extern const function_base *const vmulq;
 extern const function_base *const vmvnq;
 extern const function_base *const vnegq;
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 837864a..b82d94e 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -44,14 +44,10 @@
 #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 vmulltq_poly(__a, __b) __arm_vmulltq_poly(__a, __b)
-#define vmullbq_poly(__a, __b) __arm_vmullbq_poly(__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 vmullbq_poly_m(__inactive, __a, __b, __p) __arm_vmullbq_poly_m(__inactive, __a, __b, __p)
-#define vmulltq_poly_m(__inactive, __a, __b, __p) __arm_vmulltq_poly_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)
 #define vstrwq_scatter_base(__addr, __offset, __value) __arm_vstrwq_scatter_base(__addr, __offset, __value)
@@ -125,8 +121,6 @@
 #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 vmullbq_poly_x(__a, __b, __p) __arm_vmullbq_poly_x(__a, __b, __p)
-#define vmulltq_poly_x(__a, __b, __p) __arm_vmulltq_poly_x(__a, __b, __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)
@@ -220,14 +214,10 @@
 #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 vmulltq_poly_p8(__a, __b) __arm_vmulltq_poly_p8(__a, __b)
-#define vmullbq_poly_p8(__a, __b) __arm_vmullbq_poly_p8(__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 vmulltq_poly_p16(__a, __b) __arm_vmulltq_poly_p16(__a, __b)
-#define vmullbq_poly_p16(__a, __b) __arm_vmullbq_poly_p16(__a, __b)
 #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)
@@ -292,10 +282,6 @@
 #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 vmullbq_poly_m_p8(__inactive, __a, __b, __p) __arm_vmullbq_poly_m_p8(__inactive, __a, __b, __p)
-#define vmullbq_poly_m_p16(__inactive, __a, __b, __p) __arm_vmullbq_poly_m_p16(__inactive, __a, __b, __p)
-#define vmulltq_poly_m_p8(__inactive, __a, __b, __p) __arm_vmulltq_poly_m_p8(__inactive, __a, __b, __p)
-#define vmulltq_poly_m_p16(__inactive, __a, __b, __p) __arm_vmulltq_poly_m_p16(__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 vcvtq_m_n_s32_f32(__inactive, __a,  __imm6, __p) __arm_vcvtq_m_n_s32_f32(__inactive, __a,  __imm6, __p)
@@ -602,10 +588,6 @@
 #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 vmullbq_poly_x_p8(__a, __b, __p) __arm_vmullbq_poly_x_p8(__a, __b, __p)
-#define vmullbq_poly_x_p16(__a, __b, __p) __arm_vmullbq_poly_x_p16(__a, __b, __p)
-#define vmulltq_poly_x_p8(__a, __b, __p) __arm_vmulltq_poly_x_p8(__a, __b, __p)
-#define vmulltq_poly_x_p16(__a, __b, __p) __arm_vmulltq_poly_x_p16(__a, __b, __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)
@@ -943,20 +925,6 @@ __arm_vbicq_s32 (int32x4_t __a, int32x4_t __b)
 
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
-{
-  return __builtin_mve_vmulltq_poly_pv16qi (__a, __b);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
-{
-  return __builtin_mve_vmullbq_poly_pv16qi (__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);
@@ -971,20 +939,6 @@ __arm_vbicq_n_s16 (int16x8_t __a, const int __imm)
 
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_p16 (uint16x8_t __a, uint16x8_t __b)
-{
-  return __builtin_mve_vmulltq_poly_pv8hi (__a, __b);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_p16 (uint16x8_t __a, uint16x8_t __b)
-{
-  return __builtin_mve_vmullbq_poly_pv8hi (__a, __b);
-}
-
-__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);
@@ -1191,34 +1145,6 @@ __arm_vornq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pr
   return __builtin_mve_vornq_m_uv8hi (__inactive, __a, __b, __p);
 }
 
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_m_p8 (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmullbq_poly_m_pv16qi (__inactive, __a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_m_p16 (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmullbq_poly_m_pv8hi (__inactive, __a, __b, __p);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_m_p8 (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmulltq_poly_m_pv16qi (__inactive, __a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_m_p16 (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmulltq_poly_m_pv8hi (__inactive, __a, __b, __p);
-}
-
 __extension__ extern __inline void
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vstrbq_scatter_offset_s8 (int8_t * __base, uint8x16_t __offset, int8x16_t __value)
@@ -3130,34 +3056,6 @@ __arm_viwdupq_x_wb_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16
   return __res;
 }
 
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_x_p8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmullbq_poly_m_pv16qi (__arm_vuninitializedq_u16 (), __a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_x_p16 (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmullbq_poly_m_pv8hi (__arm_vuninitializedq_u32 (), __a, __b, __p);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_x_p8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmulltq_poly_m_pv16qi (__arm_vuninitializedq_u16 (), __a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_x_p16 (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
-  return __builtin_mve_vmulltq_poly_m_pv8hi (__arm_vuninitializedq_u32 (), __a, __b, __p);
-}
-
 __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)
@@ -5293,20 +5191,6 @@ __arm_vbicq (int32x4_t __a, int32x4_t __b)
 
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly (uint8x16_t __a, uint8x16_t __b)
-{
- return __arm_vmulltq_poly_p8 (__a, __b);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly (uint8x16_t __a, uint8x16_t __b)
-{
- return __arm_vmullbq_poly_p8 (__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);
@@ -5321,20 +5205,6 @@ __arm_vbicq (int16x8_t __a, const int __imm)
 
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly (uint16x8_t __a, uint16x8_t __b)
-{
- return __arm_vmulltq_poly_p16 (__a, __b);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly (uint16x8_t __a, uint16x8_t __b)
-{
- return __arm_vmullbq_poly_p16 (__a, __b);
-}
-
-__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);
@@ -5501,34 +5371,6 @@ __arm_vornq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16
  return __arm_vornq_m_u16 (__inactive, __a, __b, __p);
 }
 
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_m (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
- return __arm_vmullbq_poly_m_p8 (__inactive, __a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_m (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
- return __arm_vmullbq_poly_m_p16 (__inactive, __a, __b, __p);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_m (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
- return __arm_vmulltq_poly_m_p8 (__inactive, __a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_m (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
- return __arm_vmulltq_poly_m_p16 (__inactive, __a, __b, __p);
-}
-
 __extension__ extern __inline void
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vstrbq_scatter_offset (int8_t * __base, uint8x16_t __offset, int8x16_t __value)
@@ -7013,34 +6855,6 @@ __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 uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
- return __arm_vmullbq_poly_x_p8 (__a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmullbq_poly_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
- return __arm_vmullbq_poly_x_p16 (__a, __b, __p);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
-{
- return __arm_vmulltq_poly_x_p8 (__a, __b, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vmulltq_poly_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
-{
- return __arm_vmulltq_poly_x_p16 (__a, __b, __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)
@@ -8746,18 +8560,6 @@ 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_vmulltq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
-
-#define __arm_vmullbq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
-
 #define __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), \
@@ -9290,18 +9092,6 @@ extern void *__ARM_undef;
   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_vmulltq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
-
-#define __arm_vmullbq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
-
 #define __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), \
@@ -9577,18 +9367,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vuninitializedq_u32 (), \
   int (*)[__ARM_mve_type_uint64x2_t]: __arm_vuninitializedq_u64 ());})
 
-#define __arm_vmullbq_poly_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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_x_p8 (__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_vmullbq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
-#define __arm_vmulltq_poly_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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_x_p8 (__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_vmulltq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_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, \
@@ -9814,20 +9592,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
   int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_u32 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
-#define __arm_vmulltq_poly_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_uint16x8_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_m_p8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_m_p16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
-#define __arm_vmullbq_poly_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_uint16x8_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_m_p8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_m_p16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
 #define __arm_vldrbq_gather_offset(p0,p1) ({ __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_s8(__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
@@ -9946,18 +9710,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2, p3), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2, p3));})
 
-#define __arm_vmullbq_poly_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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_x_p8 (__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_vmullbq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
-#define __arm_vmulltq_poly_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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_x_p8 (__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_vmulltq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
 #define __arm_vstrbq(p0,p1) ({ __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_int8x16_t]: __arm_vstrbq_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \