arm: [MVE intrinsics] rework vfmaq vfmasq vfmsq

Implement vfmaq, vfmasq, vfmsq using the new MVE builtins framework.

2022-12-12  Christophe Lyon  <christophe.lyon@arm.com>

	gcc/
	* config/arm/arm-mve-builtins-base.cc (vfmaq, vfmasq, vfmsq): New.
	* config/arm/arm-mve-builtins-base.def (vfmaq, vfmasq, vfmsq): New.
	* config/arm/arm-mve-builtins-base.h (vfmaq, vfmasq, vfmsq): New.
	* config/arm/arm-mve-builtins.cc
	(function_instance::has_inactive_argument): Handle vfmaq, vfmasq,
	vfmsq.
	* config/arm/arm_mve.h (vfmaq): Remove.
	(vfmasq): Remove.
	(vfmsq): Remove.
	(vfmaq_m): Remove.
	(vfmasq_m): Remove.
	(vfmsq_m): Remove.
	(vfmaq_f16): Remove.
	(vfmaq_n_f16): Remove.
	(vfmasq_n_f16): Remove.
	(vfmsq_f16): Remove.
	(vfmaq_f32): Remove.
	(vfmaq_n_f32): Remove.
	(vfmasq_n_f32): Remove.
	(vfmsq_f32): Remove.
	(vfmaq_m_f32): Remove.
	(vfmaq_m_f16): Remove.
	(vfmaq_m_n_f32): Remove.
	(vfmaq_m_n_f16): Remove.
	(vfmasq_m_n_f32): Remove.
	(vfmasq_m_n_f16): Remove.
	(vfmsq_m_f32): Remove.
	(vfmsq_m_f16): Remove.
	(__arm_vfmaq_f16): Remove.
	(__arm_vfmaq_n_f16): Remove.
	(__arm_vfmasq_n_f16): Remove.
	(__arm_vfmsq_f16): Remove.
	(__arm_vfmaq_f32): Remove.
	(__arm_vfmaq_n_f32): Remove.
	(__arm_vfmasq_n_f32): Remove.
	(__arm_vfmsq_f32): Remove.
	(__arm_vfmaq_m_f32): Remove.
	(__arm_vfmaq_m_f16): Remove.
	(__arm_vfmaq_m_n_f32): Remove.
	(__arm_vfmaq_m_n_f16): Remove.
	(__arm_vfmasq_m_n_f32): Remove.
	(__arm_vfmasq_m_n_f16): Remove.
	(__arm_vfmsq_m_f32): Remove.
	(__arm_vfmsq_m_f16): Remove.
	(__arm_vfmaq): Remove.
	(__arm_vfmasq): Remove.
	(__arm_vfmsq): Remove.
	(__arm_vfmaq_m): Remove.
	(__arm_vfmasq_m): Remove.
	(__arm_vfmsq_m): Remove.

diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc
index 6286d4a147a1e88cfd71d50f99ee88c40e0bdf50..91d397d6208ed1f24e37f118a5fb924094560f4a 100644 (file)
--- a/gcc/config/arm/arm-mve-builtins-base.cc
+++ b/gcc/config/arm/arm-mve-builtins-base.cc
@@ -273,6 +273,9 @@ FUNCTION (vcmphiq, unspec_based_mve_function_exact_insn_vcmp, (UNKNOWN, GTU, UNK
 FUNCTION_WITHOUT_M_N (vcreateq, VCREATEQ)
 FUNCTION_ONLY_N (vdupq, VDUPQ)
 FUNCTION_WITH_RTX_M (veorq, XOR, VEORQ)
+FUNCTION (vfmaq, unspec_mve_function_exact_insn, (-1, -1, VFMAQ_F, -1, -1, VFMAQ_N_F, -1, -1, VFMAQ_M_F, -1, -1, VFMAQ_M_N_F))
+FUNCTION (vfmasq, unspec_mve_function_exact_insn, (-1, -1, -1, -1, -1, VFMASQ_N_F, -1, -1, -1, -1, -1, VFMASQ_M_N_F))
+FUNCTION (vfmsq, unspec_mve_function_exact_insn, (-1, -1, VFMSQ_F, -1, -1, -1, -1, -1, VFMSQ_M_F, -1, -1, -1))
 FUNCTION_WITH_M_N_NO_F (vhaddq, VHADDQ)
 FUNCTION_WITH_M_N_NO_F (vhsubq, VHSUBQ)
 FUNCTION_PRED_P_S (vmaxavq, VMAXAVQ)

diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def
index 141d057924ed22d57086f339145abdfdca8dc230..8894f9e53727837ca423aac2877b195720d8f070 100644 (file)
--- a/gcc/config/arm/arm-mve-builtins-base.def
+++ b/gcc/config/arm/arm-mve-builtins-base.def
@@ -158,6 +158,9 @@ DEF_MVE_FUNCTION (vcmpneq, cmp, all_float, m_or_none)
 DEF_MVE_FUNCTION (vcreateq, create, all_float, none)
 DEF_MVE_FUNCTION (vdupq, unary_n, all_float, mx_or_none)
 DEF_MVE_FUNCTION (veorq, binary, all_float, mx_or_none)
+DEF_MVE_FUNCTION (vfmaq, ternary_opt_n, all_float, m_or_none)
+DEF_MVE_FUNCTION (vfmasq, ternary_n, all_float, m_or_none)
+DEF_MVE_FUNCTION (vfmsq, ternary, all_float, m_or_none)
 DEF_MVE_FUNCTION (vmaxnmaq, binary, all_float, m_or_none)
 DEF_MVE_FUNCTION (vmaxnmavq, binary_maxvminv, all_float, p_or_none)
 DEF_MVE_FUNCTION (vmaxnmq, 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 b1783a2c917603beb8855b4acaaf2e8ab9838e3f..dabb52e800daa6242a1dcc904ae99bf510b7225d 100644 (file)
--- a/gcc/config/arm/arm-mve-builtins-base.h
+++ b/gcc/config/arm/arm-mve-builtins-base.h
@@ -46,6 +46,9 @@ extern const function_base *const vcmpneq;
 extern const function_base *const vcreateq;
 extern const function_base *const vdupq;
 extern const function_base *const veorq;
+extern const function_base *const vfmaq;
+extern const function_base *const vfmasq;
+extern const function_base *const vfmsq;
 extern const function_base *const vhaddq;
 extern const function_base *const vhsubq;
 extern const function_base *const vmaxaq;

diff --git a/gcc/config/arm/arm-mve-builtins.cc b/gcc/config/arm/arm-mve-builtins.cc
index c157a3ec8a3a906e3c96ba09a96a12b4f05a6a7f..87fcbc31f2f6e8bcc51de6aee36384b1edd1c779 100644 (file)
--- a/gcc/config/arm/arm-mve-builtins.cc
+++ b/gcc/config/arm/arm-mve-builtins.cc
@@ -678,6 +678,9 @@ function_instance::has_inactive_argument () const
       || base == functions::vcmpltq
       || base == functions::vcmpcsq
       || base == functions::vcmphiq
+      || base == functions::vfmaq
+      || base == functions::vfmasq
+      || base == functions::vfmsq
       || base == functions::vmaxaq
       || base == functions::vmaxnmaq
       || base == functions::vminaq

diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 69ded8703cdfd9b5e30fff130c97e16f3655f559..747cdc3509d380748cac8d80e0e3985a01bb0712 100644 (file)
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -184,9 +184,6 @@
 #define vcmlaq_rot180(__a, __b, __c) __arm_vcmlaq_rot180(__a, __b, __c)
 #define vcmlaq_rot270(__a, __b, __c) __arm_vcmlaq_rot270(__a, __b, __c)
 #define vcmlaq_rot90(__a, __b, __c) __arm_vcmlaq_rot90(__a, __b, __c)
-#define vfmaq(__a, __b, __c) __arm_vfmaq(__a, __b, __c)
-#define vfmasq(__a, __b, __c) __arm_vfmasq(__a, __b, __c)
-#define vfmsq(__a, __b, __c) __arm_vfmsq(__a, __b, __c)
 #define vcvtmq_m(__inactive, __a, __p) __arm_vcvtmq_m(__inactive, __a, __p)
 #define vcvtnq_m(__inactive, __a, __p) __arm_vcvtnq_m(__inactive, __a, __p)
 #define vcvtpq_m(__inactive, __a, __p) __arm_vcvtpq_m(__inactive, __a, __p)
@@ -199,9 +196,6 @@
 #define vcmulq_rot180_m(__inactive, __a, __b, __p) __arm_vcmulq_rot180_m(__inactive, __a, __b, __p)
 #define vcmulq_rot270_m(__inactive, __a, __b, __p) __arm_vcmulq_rot270_m(__inactive, __a, __b, __p)
 #define vcmulq_rot90_m(__inactive, __a, __b, __p) __arm_vcmulq_rot90_m(__inactive, __a, __b, __p)
-#define vfmaq_m(__a, __b, __c, __p) __arm_vfmaq_m(__a, __b, __c, __p)
-#define vfmasq_m(__a, __b, __c, __p) __arm_vfmasq_m(__a, __b, __c, __p)
-#define vfmsq_m(__a, __b, __c, __p) __arm_vfmsq_m(__a, __b, __c, __p)
 #define vcmulq_x(__a, __b, __p) __arm_vcmulq_x(__a, __b, __p)
 #define vcmulq_rot90_x(__a, __b, __p) __arm_vcmulq_rot90_x(__a, __b, __p)
 #define vcmulq_rot180_x(__a, __b, __p) __arm_vcmulq_rot180_x(__a, __b, __p)
@@ -375,10 +369,6 @@
 #define vcmlaq_rot180_f16(__a, __b, __c) __arm_vcmlaq_rot180_f16(__a, __b, __c)
 #define vcmlaq_rot270_f16(__a, __b, __c) __arm_vcmlaq_rot270_f16(__a, __b, __c)
 #define vcmlaq_rot90_f16(__a, __b, __c) __arm_vcmlaq_rot90_f16(__a, __b, __c)
-#define vfmaq_f16(__a, __b, __c) __arm_vfmaq_f16(__a, __b, __c)
-#define vfmaq_n_f16(__a, __b, __c) __arm_vfmaq_n_f16(__a, __b, __c)
-#define vfmasq_n_f16(__a, __b, __c) __arm_vfmasq_n_f16(__a, __b, __c)
-#define vfmsq_f16(__a, __b, __c) __arm_vfmsq_f16(__a, __b, __c)
 #define vcvtmq_m_s16_f16(__inactive, __a, __p) __arm_vcvtmq_m_s16_f16(__inactive, __a, __p)
 #define vcvtnq_m_s16_f16(__inactive, __a, __p) __arm_vcvtnq_m_s16_f16(__inactive, __a, __p)
 #define vcvtpq_m_s16_f16(__inactive, __a, __p) __arm_vcvtpq_m_s16_f16(__inactive, __a, __p)
@@ -392,10 +382,6 @@
 #define vcmlaq_rot180_f32(__a, __b, __c) __arm_vcmlaq_rot180_f32(__a, __b, __c)
 #define vcmlaq_rot270_f32(__a, __b, __c) __arm_vcmlaq_rot270_f32(__a, __b, __c)
 #define vcmlaq_rot90_f32(__a, __b, __c) __arm_vcmlaq_rot90_f32(__a, __b, __c)
-#define vfmaq_f32(__a, __b, __c) __arm_vfmaq_f32(__a, __b, __c)
-#define vfmaq_n_f32(__a, __b, __c) __arm_vfmaq_n_f32(__a, __b, __c)
-#define vfmasq_n_f32(__a, __b, __c) __arm_vfmasq_n_f32(__a, __b, __c)
-#define vfmsq_f32(__a, __b, __c) __arm_vfmsq_f32(__a, __b, __c)
 #define vcvtmq_m_s32_f32(__inactive, __a, __p) __arm_vcvtmq_m_s32_f32(__inactive, __a, __p)
 #define vcvtnq_m_s32_f32(__inactive, __a, __p) __arm_vcvtnq_m_s32_f32(__inactive, __a, __p)
 #define vcvtpq_m_s32_f32(__inactive, __a, __p) __arm_vcvtpq_m_s32_f32(__inactive, __a, __p)
@@ -493,14 +479,6 @@
 #define vcvtq_m_n_s16_f16(__inactive, __a,  __imm6, __p) __arm_vcvtq_m_n_s16_f16(__inactive, __a,  __imm6, __p)
 #define vcvtq_m_n_u32_f32(__inactive, __a,  __imm6, __p) __arm_vcvtq_m_n_u32_f32(__inactive, __a,  __imm6, __p)
 #define vcvtq_m_n_u16_f16(__inactive, __a,  __imm6, __p) __arm_vcvtq_m_n_u16_f16(__inactive, __a,  __imm6, __p)
-#define vfmaq_m_f32(__a, __b, __c, __p) __arm_vfmaq_m_f32(__a, __b, __c, __p)
-#define vfmaq_m_f16(__a, __b, __c, __p) __arm_vfmaq_m_f16(__a, __b, __c, __p)
-#define vfmaq_m_n_f32(__a, __b, __c, __p) __arm_vfmaq_m_n_f32(__a, __b, __c, __p)
-#define vfmaq_m_n_f16(__a, __b, __c, __p) __arm_vfmaq_m_n_f16(__a, __b, __c, __p)
-#define vfmasq_m_n_f32(__a, __b, __c, __p) __arm_vfmasq_m_n_f32(__a, __b, __c, __p)
-#define vfmasq_m_n_f16(__a, __b, __c, __p) __arm_vfmasq_m_n_f16(__a, __b, __c, __p)
-#define vfmsq_m_f32(__a, __b, __c, __p) __arm_vfmsq_m_f32(__a, __b, __c, __p)
-#define vfmsq_m_f16(__a, __b, __c, __p) __arm_vfmsq_m_f16(__a, __b, __c, __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)
@@ -5540,34 +5518,6 @@ __arm_vcmlaq_rot90_f16 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
   return __builtin_mve_vcmlaq_rot90v8hf (__a, __b, __c);
 }
 
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_f16 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
-{
-  return __builtin_mve_vfmaq_fv8hf (__a, __b, __c);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_n_f16 (float16x8_t __a, float16x8_t __b, float16_t __c)
-{
-  return __builtin_mve_vfmaq_n_fv8hf (__a, __b, __c);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq_n_f16 (float16x8_t __a, float16x8_t __b, float16_t __c)
-{
-  return __builtin_mve_vfmasq_n_fv8hf (__a, __b, __c);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq_f16 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
-{
-  return __builtin_mve_vfmsq_fv8hf (__a, __b, __c);
-}
-
 __extension__ extern __inline int16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vcvtmq_m_s16_f16 (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
@@ -5659,34 +5609,6 @@ __arm_vcmlaq_rot90_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
   return __builtin_mve_vcmlaq_rot90v4sf (__a, __b, __c);
 }
 
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
-{
-  return __builtin_mve_vfmaq_fv4sf (__a, __b, __c);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c)
-{
-  return __builtin_mve_vfmaq_n_fv4sf (__a, __b, __c);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c)
-{
-  return __builtin_mve_vfmasq_n_fv4sf (__a, __b, __c);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
-{
-  return __builtin_mve_vfmsq_fv4sf (__a, __b, __c);
-}
-
 __extension__ extern __inline int32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vcvtmq_m_s32_f32 (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
@@ -5960,62 +5882,6 @@ __arm_vcvtq_m_n_u16_f16 (uint16x8_t __inactive, float16x8_t __a, const int __imm
   return __builtin_mve_vcvtq_m_n_from_f_uv8hi (__inactive, __a, __imm6, __p);
 }
 
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmaq_m_fv4sf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m_f16 (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmaq_m_fv8hf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmaq_m_n_fv4sf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m_n_f16 (float16x8_t __a, float16x8_t __b, float16_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmaq_m_n_fv8hf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq_m_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmasq_m_n_fv4sf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq_m_n_f16 (float16x8_t __a, float16x8_t __b, float16_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmasq_m_n_fv8hf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq_m_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmsq_m_fv4sf (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq_m_f16 (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
-{
-  return __builtin_mve_vfmsq_m_fv8hf (__a, __b, __c, __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)
@@ -10356,34 +10222,6 @@ __arm_vcmlaq_rot90 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
  return __arm_vcmlaq_rot90_f16 (__a, __b, __c);
 }
 
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq (float16x8_t __a, float16x8_t __b, float16x8_t __c)
-{
- return __arm_vfmaq_f16 (__a, __b, __c);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq (float16x8_t __a, float16x8_t __b, float16_t __c)
-{
- return __arm_vfmaq_n_f16 (__a, __b, __c);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq (float16x8_t __a, float16x8_t __b, float16_t __c)
-{
- return __arm_vfmasq_n_f16 (__a, __b, __c);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq (float16x8_t __a, float16x8_t __b, float16x8_t __c)
-{
- return __arm_vfmsq_f16 (__a, __b, __c);
-}
-
 __extension__ extern __inline int16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vcvtmq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
@@ -10475,34 +10313,6 @@ __arm_vcmlaq_rot90 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
  return __arm_vcmlaq_rot90_f32 (__a, __b, __c);
 }
 
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq (float32x4_t __a, float32x4_t __b, float32x4_t __c)
-{
- return __arm_vfmaq_f32 (__a, __b, __c);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq (float32x4_t __a, float32x4_t __b, float32_t __c)
-{
- return __arm_vfmaq_n_f32 (__a, __b, __c);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq (float32x4_t __a, float32x4_t __b, float32_t __c)
-{
- return __arm_vfmasq_n_f32 (__a, __b, __c);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq (float32x4_t __a, float32x4_t __b, float32x4_t __c)
-{
- return __arm_vfmsq_f32 (__a, __b, __c);
-}
-
 __extension__ extern __inline int32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vcvtmq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
@@ -10776,62 +10586,6 @@ __arm_vcvtq_m_n (uint16x8_t __inactive, float16x8_t __a, const int __imm6, mve_p
  return __arm_vcvtq_m_n_u16_f16 (__inactive, __a, __imm6, __p);
 }
 
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
-{
- return __arm_vfmaq_m_f32 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
-{
- return __arm_vfmaq_m_f16 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m (float32x4_t __a, float32x4_t __b, float32_t __c, mve_pred16_t __p)
-{
- return __arm_vfmaq_m_n_f32 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmaq_m (float16x8_t __a, float16x8_t __b, float16_t __c, mve_pred16_t __p)
-{
- return __arm_vfmaq_m_n_f16 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq_m (float32x4_t __a, float32x4_t __b, float32_t __c, mve_pred16_t __p)
-{
- return __arm_vfmasq_m_n_f32 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmasq_m (float16x8_t __a, float16x8_t __b, float16_t __c, mve_pred16_t __p)
-{
- return __arm_vfmasq_m_n_f16 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
-{
- return __arm_vfmsq_m_f32 (__a, __b, __c, __p);
-}
-
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vfmsq_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
-{
- return __arm_vfmsq_m_f16 (__a, __b, __c, __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)
@@ -11859,29 +11613,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtpq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtpq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
-#define __arm_vfmaq(p0,p1,p2) ({ __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_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(p2, double)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(p2, double)), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-
-#define __arm_vfmsq(p0,p1,p2) ({ __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_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmsq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmsq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-
-#define __arm_vfmasq(p0,p1,p2) ({ __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_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(p2, double)), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(p2, double)));})
-
 #define __arm_vpselq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
@@ -11991,29 +11722,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_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_vcmulq_rot90_m_f32(__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
 
-#define __arm_vfmaq_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_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmaq_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_vfmaq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(p2, double), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(p2, double), p3));})
-
-#define __arm_vfmasq_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_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce2(p2, double), p3), \
-  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce2(p2, double), p3));})
-
-#define __arm_vfmsq_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_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmsq_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_vfmsq_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); \