diff mbox series

[commited,trunk,6/9] arm: Fix MVE header pointer overloads this time (and a bit more tidying)

Message ID 20230518105915.1304768-6-stam.markianos-wright@arm.com
State Accepted
Headers
Series [commited,trunk,1/9] arm: Mve testsuite improvements |

Checks

Context Check Description
snail/gcc-patch-check success Github commit url

Commit Message

Stamatis Markianos-Wright May 18, 2023, 10:59 a.m. UTC 
  Hi all,

Previously we had fixed the overloading of scalar arguments to intrinsics
with the introduction of a new `__ARM_mve_coerce3` _ Generic association.
This allowed users to give types other than int32_t, e.g. int, short, long,
etc., which previously would emit a nonsensical error message from the
_Generic.

Here I adjust that handling slightly and I am also doing the same thing, but
for pointer types:
(un)signed char* can be now used instead of (u)int8_t*
(un)signed short* can be now used instead of (u)int16_t*
(un)signed int* and long* can be now used instead of (u)int32_t*
(un)signed long long* can be now used instead of (u)int64_t*
__fp16* and _Float16* can be now used instead of float16_t*
float* can be now used instead of float32_t*

This required me to break down the _coerce_ generics for the specific
pointer types.
On the scalar types, the change in this patch is minor, renaming the
_coerce_ generics and passing all scalars through the `__typeof` for
consistency with each-other.

No test regressions in the GCC testsuite or CMSIS-NN.

gcc/ChangeLog:

	* config/arm/arm_mve.h: (__ARM_mve_typeid): Add more pointer types.
	(__ARM_mve_coerce1): Remove.
	(__ARM_mve_coerce2): Remove.
	(__ARM_mve_coerce3): Remove.
	(__ARM_mve_coerce_i_scalar): New.
	(__ARM_mve_coerce_s8_ptr): New.
	(__ARM_mve_coerce_u8_ptr): New.
	(__ARM_mve_coerce_s16_ptr): New.
	(__ARM_mve_coerce_u16_ptr): New.
	(__ARM_mve_coerce_s32_ptr): New.
	(__ARM_mve_coerce_u32_ptr): New.
	(__ARM_mve_coerce_s64_ptr): New.
	(__ARM_mve_coerce_u64_ptr): New.
	(__ARM_mve_coerce_f_scalar): New.
	(__ARM_mve_coerce_f16_ptr): New.
	(__ARM_mve_coerce_f32_ptr): New.
	(__arm_vst4q): Change _coerce_ overloads.
	(__arm_vbicq): Change _coerce_ overloads.
	(__arm_vld1q): Change _coerce_ overloads.
	(__arm_vld1q_z): Change _coerce_ overloads.
	(__arm_vld2q): Change _coerce_ overloads.
	(__arm_vld4q): Change _coerce_ overloads.
	(__arm_vldrhq_gather_offset): Change _coerce_ overloads.
	(__arm_vldrhq_gather_offset_z): Change _coerce_ overloads.
	(__arm_vldrhq_gather_shifted_offset): Change _coerce_ overloads.
	(__arm_vldrhq_gather_shifted_offset_z): Change _coerce_ overloads.
	(__arm_vldrwq_gather_offset): Change _coerce_ overloads.
	(__arm_vldrwq_gather_offset_z): Change _coerce_ overloads.
	(__arm_vldrwq_gather_shifted_offset): Change _coerce_ overloads.
	(__arm_vldrwq_gather_shifted_offset_z): Change _coerce_ overloads.
	(__arm_vst1q_p): Change _coerce_ overloads.
	(__arm_vst2q): Change _coerce_ overloads.
	(__arm_vst1q): Change _coerce_ overloads.
	(__arm_vstrhq): Change _coerce_ overloads.
	(__arm_vstrhq_p): Change _coerce_ overloads.
	(__arm_vstrhq_scatter_offset_p): Change _coerce_ overloads.
	(__arm_vstrhq_scatter_offset): Change _coerce_ overloads.
	(__arm_vstrhq_scatter_shifted_offset_p): Change _coerce_ overloads.
	(__arm_vstrhq_scatter_shifted_offset): Change _coerce_ overloads.
	(__arm_vstrwq_p): Change _coerce_ overloads.
	(__arm_vstrwq): Change _coerce_ overloads.
	(__arm_vstrwq_scatter_offset): Change _coerce_ overloads.
	(__arm_vstrwq_scatter_offset_p): Change _coerce_ overloads.
	(__arm_vstrwq_scatter_shifted_offset): Change _coerce_ overloads.
	(__arm_vstrwq_scatter_shifted_offset_p): Change _coerce_ overloads.
	(__arm_vsetq_lane): Change _coerce_ overloads.
	(__arm_vldrbq_gather_offset): Change _coerce_ overloads.
	(__arm_vdwdupq_x_u8): Change _coerce_ overloads.
	(__arm_vdwdupq_x_u16): Change _coerce_ overloads.
	(__arm_vdwdupq_x_u32): Change _coerce_ overloads.
	(__arm_viwdupq_x_u8): Change _coerce_ overloads.
	(__arm_viwdupq_x_u16): Change _coerce_ overloads.
	(__arm_viwdupq_x_u32): Change _coerce_ overloads.
	(__arm_vidupq_x_u8): Change _coerce_ overloads.
	(__arm_vddupq_x_u8): Change _coerce_ overloads.
	(__arm_vidupq_x_u16): Change _coerce_ overloads.
	(__arm_vddupq_x_u16): Change _coerce_ overloads.
	(__arm_vidupq_x_u32): Change _coerce_ overloads.
	(__arm_vddupq_x_u32): Change _coerce_ overloads.
	(__arm_vldrdq_gather_offset): Change _coerce_ overloads.
	(__arm_vldrdq_gather_offset_z): Change _coerce_ overloads.
	(__arm_vldrdq_gather_shifted_offset): Change _coerce_ overloads.
	(__arm_vldrdq_gather_shifted_offset_z): Change _coerce_ overloads.
	(__arm_vldrbq_gather_offset_z): Change _coerce_ overloads.
	(__arm_vidupq_u16): Change _coerce_ overloads.
	(__arm_vidupq_u32): Change _coerce_ overloads.
	(__arm_vidupq_u8): Change _coerce_ overloads.
	(__arm_vddupq_u16): Change _coerce_ overloads.
	(__arm_vddupq_u32): Change _coerce_ overloads.
	(__arm_vddupq_u8): Change _coerce_ overloads.
	(__arm_viwdupq_m): Change _coerce_ overloads.
	(__arm_viwdupq_u16): Change _coerce_ overloads.
	(__arm_viwdupq_u32): Change _coerce_ overloads.
	(__arm_viwdupq_u8): Change _coerce_ overloads.
	(__arm_vdwdupq_m): Change _coerce_ overloads.
	(__arm_vdwdupq_u16): Change _coerce_ overloads.
	(__arm_vdwdupq_u32): Change _coerce_ overloads.
	(__arm_vdwdupq_u8): Change _coerce_ overloads.
	(__arm_vstrbq): Change _coerce_ overloads.
	(__arm_vstrbq_p): Change _coerce_ overloads.
	(__arm_vstrbq_scatter_offset_p): Change _coerce_ overloads.
	(__arm_vstrdq_scatter_offset_p): Change _coerce_ overloads.
	(__arm_vstrdq_scatter_offset): Change _coerce_ overloads.
	(__arm_vstrdq_scatter_shifted_offset_p): Change _coerce_ overloads.
	(__arm_vstrdq_scatter_shifted_offset): Change _coerce_ overloads.

gcc/testsuite/ChangeLog:

	* gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c: Add testcases.
	* gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c: Add testcases.
---
 gcc/config/arm/arm_mve.h                      | 914 +++++++++---------
 .../mve_intrinsic_type_overloads-fp.c         |  55 +-
 .../mve_intrinsic_type_overloads-int.c        |  74 +-
 3 files changed, 577 insertions(+), 466 deletions(-)
diff mbox series

Patch

diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 30cec519791..30485e74cdd 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -10727,16 +10727,29 @@  enum {
 	short: __ARM_mve_type_int_n, \
 	int: __ARM_mve_type_int_n, \
 	long: __ARM_mve_type_int_n, \
+	long long: __ARM_mve_type_int_n, \
 	_Float16: __ARM_mve_type_fp_n, \
 	__fp16: __ARM_mve_type_fp_n, \
 	float: __ARM_mve_type_fp_n, \
 	double: __ARM_mve_type_fp_n, \
-	long long: __ARM_mve_type_int_n, \
 	unsigned char: __ARM_mve_type_int_n, \
 	unsigned short: __ARM_mve_type_int_n, \
 	unsigned int: __ARM_mve_type_int_n, \
 	unsigned long: __ARM_mve_type_int_n, \
 	unsigned long long: __ARM_mve_type_int_n, \
+	signed char*: __ARM_mve_type_int8_t_ptr, \
+	short*: __ARM_mve_type_int16_t_ptr, \
+	int*: __ARM_mve_type_int32_t_ptr, \
+	long*: __ARM_mve_type_int32_t_ptr, \
+	long long*: __ARM_mve_type_int64_t_ptr, \
+	_Float16*: __ARM_mve_type_float16_t_ptr, \
+	__fp16*: __ARM_mve_type_float16_t_ptr, \
+	float*: __ARM_mve_type_float32_t_ptr, \
+	unsigned char*: __ARM_mve_type_uint8_t_ptr, \
+	unsigned short*: __ARM_mve_type_uint16_t_ptr, \
+	unsigned int*: __ARM_mve_type_uint32_t_ptr, \
+	unsigned long*: __ARM_mve_type_uint32_t_ptr, \
+	unsigned long long*: __ARM_mve_type_uint64_t_ptr, \
 	default: __ARM_mve_unsupported_type))
 #else
 #define __ARM_mve_typeid(x) _Generic(x, \
@@ -10795,32 +10808,67 @@  enum {
 	unsigned int: __ARM_mve_type_int_n, \
 	unsigned long: __ARM_mve_type_int_n, \
 	unsigned long long: __ARM_mve_type_int_n, \
+	signed char*: __ARM_mve_type_int8_t_ptr, \
+	short*: __ARM_mve_type_int16_t_ptr, \
+	int*: __ARM_mve_type_int32_t_ptr, \
+	long*: __ARM_mve_type_int32_t_ptr, \
+	long long*: __ARM_mve_type_int64_t_ptr, \
+	unsigned char*: __ARM_mve_type_uint8_t_ptr, \
+	unsigned short*: __ARM_mve_type_uint16_t_ptr, \
+	unsigned int*: __ARM_mve_type_uint32_t_ptr, \
+	unsigned long*: __ARM_mve_type_uint32_t_ptr, \
+	unsigned long long*: __ARM_mve_type_uint64_t_ptr, \
 	default: __ARM_mve_unsupported_type))
 #endif /* MVE Floating point.  */
 
 extern void *__ARM_undef;
 #define __ARM_mve_coerce(param, type) \
     _Generic(param, type: param, default: *(type *)__ARM_undef)
-#define __ARM_mve_coerce1(param, type) \
-    _Generic(param, type: param, const type: param, default: *(type *)__ARM_undef)
-#define __ARM_mve_coerce2(param, type) \
-    _Generic(param, type: param, __fp16: param, default: _Generic (param, _Float16: param, float16_t: param, float32_t: param, default: *(type *)__ARM_undef))
-#define __ARM_mve_coerce3(param, type) \
-    _Generic(param, type: param, default: _Generic (param, int8_t: param, int16_t: param, int32_t: param, int64_t: param, uint8_t: param, uint16_t: param, uint32_t: param, uint64_t: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_i_scalar(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, int8_t: param, int16_t: param, int32_t: param, int64_t: param, uint8_t: param, uint16_t: param, uint32_t: param, uint64_t: param, default: *(type *)__ARM_undef))
+
+#define __ARM_mve_coerce_s8_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, signed char*: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_u8_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, unsigned char*: param, default: *(type *)__ARM_undef))
+
+#define __ARM_mve_coerce_s16_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, short*: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_u16_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, unsigned short*: param, default: *(type *)__ARM_undef))
+
+#define __ARM_mve_coerce_s32_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, int*: param, long*: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_u32_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, unsigned int*: param, unsigned long*: param, default: *(type *)__ARM_undef))
+
+#define __ARM_mve_coerce_s64_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, long long*: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_u64_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, unsigned long long*: param, default: *(type *)__ARM_undef))
+
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point.  */
+#define __ARM_mve_coerce_f_scalar(param, type) \
+    _Generic(param, type: param, const type: param, __fp16: param, default: _Generic (param, _Float16: param, float16_t: param, float32_t: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_f16_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, __fp16*: param, _Float16*: param, default: *(type *)__ARM_undef))
+#define __ARM_mve_coerce_f32_ptr(param, type) \
+    _Generic(param, type: param, const type: param, default: _Generic (param, float*: param, default: *(type *)__ARM_undef))
+#endif
 
 #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point.  */
 
 #define __arm_vst4q(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_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__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(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce_s16_ptr(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce_u16_ptr(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \
+  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_vcvtbq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -10847,10 +10895,10 @@  extern void *__ARM_undef;
 #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_coerce3 (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_coerce3 (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_coerce3 (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_coerce3 (p1, int)), \
+  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)), \
@@ -11188,236 +11236,236 @@  extern void *__ARM_undef;
 
 #define __arm_vld1q(p0) (\
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce1(p0, uint32_t *)), \
-  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_f16 (__ARM_mve_coerce1(p0, float16_t *)), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_f32 (__ARM_mve_coerce1(p0, float32_t *))))
+  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \
+  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)), \
+  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *)), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *))))
 
 #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_coerce1(p0, int8_t *), p1), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce1(p0, int16_t *), p1), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce1(p0, uint8_t *), p1), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \
-  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_z_f16 (__ARM_mve_coerce1(p0, float16_t *), p1), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1)))
+  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), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), p1), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), p1), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1), \
+  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_z_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), p1), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_z_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1)))
 
 #define __arm_vld2q(p0) ( \
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce1(p0, uint32_t *)), \
-  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld2q_f16 (__ARM_mve_coerce1(p0, float16_t *)), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld2q_f32 (__ARM_mve_coerce1(p0, float32_t *))))
+  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \
+  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)), \
+  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld2q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *)), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld2q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *))))
 
 #define __arm_vld4q(p0) ( \
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce1(p0, uint32_t *)), \
-  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld4q_f16 (__ARM_mve_coerce1(p0, float16_t *)), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld4q_f32 (__ARM_mve_coerce1(p0, float32_t *))))
+  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \
+  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)), \
+  int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld4q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *)), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld4q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *))))
 
 #define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));})
 
 #define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
 
 #define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));})
 
 #define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
 
 #define __arm_vldrwq_gather_offset(p0,p1) ( \
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce1(p0, float32_t *), p1)))
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1)))
 
 #define __arm_vldrwq_gather_offset_z(p0,p1,p2) ( \
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1, p2), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1, p2)))
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1, p2), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1, p2)))
 
 #define __arm_vldrwq_gather_shifted_offset(p0,p1) ( \
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce1(p0, float32_t *), p1)))
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1)))
 
 #define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ( \
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1, p2), \
-  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1, p2)))
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1, p2), \
+  int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1, p2)))
 
 #define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_p_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #define __arm_vst2q(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_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x2_t]: __arm_vst2q_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x2_t)), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x2_t]: __arm_vst2q_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x2_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x2_t]: __arm_vst2q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x2_t)), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x2_t]: __arm_vst2q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x2_t)));})
 
 #define __arm_vst1q(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_vst1q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vstrhq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)));})
 
 #define __arm_vstrhq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2));})
 
 #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
 
 #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
 
 #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
 
 #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
 
 #define __arm_vstrwq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_p_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #define __arm_vstrwq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
 
 #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
 
 #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
 
 #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
 
 #define __arm_vstrwq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
@@ -11434,44 +11482,44 @@  extern void *__ARM_undef;
 #define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_f32 (__ARM_mve_coerce(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_f32 (__ARM_mve_coerce_f32_ptr(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t)));})
 
 #define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_p_f32 (__ARM_mve_coerce(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_p_f32 (__ARM_mve_coerce_f32_ptr(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
 
 #define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
 
 #define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
 
 #define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
 
 #define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
-  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
 
 #define __arm_vuninitializedq(p0) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -11600,16 +11648,16 @@  extern void *__ARM_undef;
 #define __arm_vsetq_lane(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_vsetq_lane_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_vsetq_lane_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_vsetq_lane_s32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_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_vsetq_lane_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_vsetq_lane_u32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vsetq_lane_f16 (__ARM_mve_coerce2(p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
-  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vsetq_lane_f32 (__ARM_mve_coerce2(p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t]: __arm_vsetq_lane_s8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vsetq_lane_s16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vsetq_lane_s32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_u8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vsetq_lane_f16 (__ARM_mve_coerce_f_scalar(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \
+  int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vsetq_lane_f32 (__ARM_mve_coerce_f_scalar(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));})
 
 #else /* MVE Integer.  */
 
@@ -11625,12 +11673,12 @@  extern void *__ARM_undef;
 
 #define __arm_vst4q(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_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)));})
 
 #define __arm_vornq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -11699,10 +11747,10 @@  extern void *__ARM_undef;
 #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_coerce3 (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_coerce3 (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_coerce3 (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_coerce3 (p1, int)), \
+  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)), \
@@ -11789,12 +11837,12 @@  extern void *__ARM_undef;
 
 #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_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  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)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vstrwq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
@@ -11803,144 +11851,144 @@  extern void *__ARM_undef;
 
 #define __arm_vld1q(p0) (\
   _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce1(p0, uint32_t *))))
+  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \
+  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *))))
 
 #define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
 #define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
 #define __arm_vldrwq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vldrwq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_vldrwq_gather_shifted_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_vst1q(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_vst1q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
 #define __arm_vst2q(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_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)));})
 
 #define __arm_vstrhq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vstrhq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
 #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 
 #define __arm_vstrwq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vstrwq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
 #define __arm_vstrdq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
@@ -11955,58 +12003,58 @@  extern void *__ARM_undef;
 #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __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_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 #define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 #define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vuninitializedq(p0) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -12092,29 +12140,29 @@  extern void *__ARM_undef;
   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_coerce1(p0, int8_t *), p1), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce1(p0, int16_t *), p1), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce1(p0, uint8_t *), p1), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1)))
+  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), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), p1), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), p1), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1)))
 
 #define __arm_vld2q(p0) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce1(p0, uint32_t *))))
+  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \
+  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *))))
 
 
 #define __arm_vld4q(p0) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \
-  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \
-  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \
-  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce1(p0, uint32_t *))))
+  int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \
+  int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \
+  int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \
+  int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *))))
 
 #define __arm_vgetq_lane(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -12130,14 +12178,14 @@  extern void *__ARM_undef;
 #define __arm_vsetq_lane(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_vsetq_lane_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_vsetq_lane_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_vsetq_lane_s32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_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_vsetq_lane_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_vsetq_lane_u32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2));})
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t]: __arm_vsetq_lane_s8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vsetq_lane_s16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vsetq_lane_s32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_u8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2));})
 
 #endif /* MVE Integer.  */
 
@@ -12146,62 +12194,62 @@  extern void *__ARM_undef;
 #define __arm_vdwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u8 ((uint32_t) __p1, p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_vdwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u16 ((uint32_t) __p1, p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_vdwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u32 ((uint32_t) __p1, p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_viwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u8 ((uint32_t) __p1, p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_viwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u16 ((uint32_t) __p1, p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_viwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u32 ((uint32_t) __p1, p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_vidupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u8 ((uint32_t) __p1, p2, p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vddupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u8 ((uint32_t) __p1, p2, p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vidupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u16 ((uint32_t) __p1, p2, p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vddupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u16 ((uint32_t) __p1, p2, p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vidupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u32 ((uint32_t) __p1, p2, p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vddupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u32 ((uint32_t) __p1, p2, p3), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vhcaddq_rot270_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
@@ -12234,20 +12282,20 @@  extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_wb_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
 
 #define __arm_vldrdq_gather_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce1(p0, int64_t *), p1), \
-  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1)))
+  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1), \
+  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1)))
 
 #define __arm_vldrdq_gather_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce1(p0, int64_t *), p1, p2), \
-  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1, p2)))
+  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1, p2), \
+  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1, p2)))
 
 #define __arm_vldrdq_gather_shifted_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce1(p0, int64_t *), p1), \
-  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1)))
+  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1), \
+  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1)))
 
 #define __arm_vldrdq_gather_shifted_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce1(p0, int64_t *), p1, p2), \
-  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1, p2)))
+  int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1, p2), \
+  int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1, p2)))
 
 #define __arm_vadciq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -12303,12 +12351,12 @@  extern void *__ARM_undef;
 
 #define __arm_vldrbq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
   _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_u8 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce1(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_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_s16 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_s32 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  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_vhcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -12364,12 +12412,12 @@  extern void *__ARM_undef;
 
 #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_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16(__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32(__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8(__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16(__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32(__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  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)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16(__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32(__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8(__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16(__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32(__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vidupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
  __typeof(p1) __p1 = (p1); \
@@ -12377,9 +12425,9 @@  extern void *__ARM_undef;
  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint32_t) __p1, p2, p3), \
  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint32_t) __p1, p2, p3), \
  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2, p3), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vddupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
  __typeof(p1) __p1 = (p1); \
@@ -12387,89 +12435,89 @@  extern void *__ARM_undef;
  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint32_t) __p1, p2, p3), \
  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint32_t) __p1, p2, p3), \
  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2, p3), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));})
 
 #define __arm_vidupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u16 ((uint32_t) __p0, p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vidupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u32 ((uint32_t) __p0, p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vidupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u8 ((uint32_t) __p0, p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vddupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u16 ((uint32_t) __p0, p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vddupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u32 ((uint32_t) __p0, p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_vddupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u8 ((uint32_t) __p0, p1), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));})
 
 #define __arm_viwdupq_m(p0,p1,p2,p3,p4) ({ __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_int_n]: __arm_viwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_viwdupq_u16(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u16 (__ARM_mve_coerce3(p0, int), p1, (const int) p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1, (const int) p2));})
+  int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u16 (__ARM_mve_coerce_i_scalar(__p0, int), p1, (const int) p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, (const int) p2));})
 
 #define __arm_viwdupq_u32(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u32 (__ARM_mve_coerce3(p0, int), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u32 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_viwdupq_u8(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u8 (__ARM_mve_coerce3(p0, int), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u8 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_vdwdupq_m(p0,p1,p2,p3,p4) ({ __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_int_n]: __arm_vdwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));})
 
 #define __arm_vdwdupq_u16(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u16 (__ARM_mve_coerce3(p0, int), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u16 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_vdwdupq_u32(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u32 (__ARM_mve_coerce3(p0, int), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u32 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_vdwdupq_u8(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u8 (__ARM_mve_coerce3(p0, int), p1, p2), \
-  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
+  int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u8 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \
+  int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));})
 
 #define __arm_vshlcq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -12514,22 +12562,22 @@  extern void *__ARM_undef;
 
 #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(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_s16 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_s32 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+  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)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_s16 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_s32 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
 #define __arm_vstrbq_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_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_p_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_p_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_p_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_p_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_p_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_p_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_p_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_p_s16 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_p_s32 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_p_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_p_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_vstrbq_p_u32 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
 
 #define __arm_vstrdq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
@@ -12545,47 +12593,47 @@  extern void *__ARM_undef;
   __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_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_s16 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_s32 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_u16 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
 
 #define __arm_vstrbq_scatter_offset_p(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_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_p_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_p_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_p_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_p_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_p_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_p_s16 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_p_s32 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_p_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_p_u16 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_p_u32 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
 #define __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_p_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
-  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_p_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
+  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_p_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
+  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_p_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
 
 #define __arm_vstrdq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \
-  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
+  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \
+  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
 
 #define __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
-  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
+  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
+  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
 
 #define __arm_vstrdq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \
-  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
+  int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \
+  int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
 
 #endif /* __cplusplus  */
 #endif /* __ARM_FEATURE_MVE  */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c
index a2787a47859..a1e786ecd9f 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c
@@ -1,6 +1,7 @@ 
 /* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
 /* { dg-add-options arm_v8_1m_mve_fp } */
-/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long" } */
+/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -Wno-incompatible-pointer-types" { target c } } */
+/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -fpermissive" { target c++ } } */
 #include "arm_mve.h"
 
 float f1;
@@ -10,35 +11,14 @@  float32_t f4;
 __fp16 f5;
 _Float16 f6;
 
-int i1;
-short i2;
-long i3;
-long long i4;
-int8_t i5;
-int16_t i6;
-int32_t i7;
-int64_t i8;
-
 float16x8_t floatvec;
-int16x8_t intvec;
 
-void test(void)
+/* Test a few different supported ways of passing a scalar int value.
+The intrinsic vmulq was chosen arbitrarily, but it is representative of
+all intrinsics that take a non-const scalar value.  */
+void
+test_scalars (void)
 {
-    /* Test a few different supported ways of passing an int value.  The
-    intrinsic vmulq was chosen arbitrarily, but it is representative of
-    all intrinsics that take a non-const scalar value.  */
-    intvec = vmulq(intvec, 2);
-    intvec = vmulq(intvec, (int32_t) 2);
-    intvec = vmulq(intvec, (short) 2);
-    intvec = vmulq(intvec, i1);
-    intvec = vmulq(intvec, i2);
-    intvec = vmulq(intvec, i3);
-    intvec = vmulq(intvec, i4);
-    intvec = vmulq(intvec, i5);
-    intvec = vmulq(intvec, i6);
-    intvec = vmulq(intvec, i7);
-    intvec = vmulq(intvec, i8);
-
     /* Test a few different supported ways of passing a float value.  */
     floatvec = vmulq(floatvec, 0.5);
     floatvec = vmulq(floatvec, 0.5f);
@@ -53,4 +33,25 @@  void test(void)
     floatvec = vmulq(floatvec, (_Float16) 0.15);
 }
 
+/* Next, test a number of valid pointer overloads.  */
+void
+foo11 (__fp16 * addr, float16x8_t value)
+{
+  vst1q (addr, value);
+}
+
+#ifndef __cplusplus
+void
+foo12 (_Float16 * addr, float16x8_t value)
+{
+  vst1q (addr, value);
+}
+#endif
+
+void
+foo13 (float * addr, float32x4_t value)
+{
+  vst1q (addr, value);
+}
+
 /* { dg-final { scan-assembler-not "__ARM_undef" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c
index 7b88f462e17..7947dc024bc 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c
@@ -1,7 +1,7 @@ 
 /* { dg-require-effective-target arm_v8_1m_mve_ok } */
 /* { dg-add-options arm_v8_1m_mve } */
-/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long" } */
-
+/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -Wno-incompatible-pointer-types" { target c } } */
+/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -fpermissive" { target c++ } } */
 #include "arm_mve.h"
 
 int i1;
@@ -15,11 +15,12 @@  int64_t i8;
 
 int16x8_t intvec;
 
-void test(void)
+/* Test a few different supported ways of passing a scalar int value.
+The intrinsic vmulq was chosen arbitrarily, but it is representative of
+all intrinsics that take a non-const scalar value.  */
+void
+test_scalars (void)
 {
-    /* Test a few different supported ways of passing an int value.  The
-    intrinsic vmulq was chosen arbitrarily, but it is representative of
-    all intrinsics that take a non-const scalar value.  */
     intvec = vmulq(intvec, 2);
     intvec = vmulq(intvec, (int32_t) 2);
     intvec = vmulq(intvec, (short) 2);
@@ -33,4 +34,65 @@  void test(void)
     intvec = vmulq(intvec, i8);
 }
 
+/* Next, test a number of valid pointer overloads.  */
+void
+foo1 (signed char * addr, int8x16_t value)
+{
+  vst1q (addr, value);
+}
+
+void
+foo2 (short * addr, int16x8_t value)
+{
+  vst1q (addr, value);
+}
+
+void
+foo3 (int * addr, int32x4_t value)
+{
+  vst1q (addr, value); /* { dg-warning "invalid conversion" "" { target c++ } } */
+}
+
+void
+foo4 (long * addr, int32x4_t value)
+{
+  vst1q (addr, value);
+}
+
+void
+foo5 (long long * addr, uint64x2_t value)
+{
+  vldrdq_gather_offset (addr, value);
+}
+
+void
+foo6 (unsigned char * addr, uint8x16_t value)
+{
+  vst1q (addr, value);
+}
+
+void
+foo7 (unsigned short * addr, uint16x8_t value)
+{
+  vst1q (addr, value);
+}
+
+void
+foo8 (unsigned int * addr, uint32x4_t value)
+{
+  vst1q (addr, value); /* { dg-warning "invalid conversion" "" { target c++ } } */
+}
+
+void
+foo9 (unsigned long * addr, uint32x4_t value)
+{
+  vst1q (addr, value);
+}
+
+void
+foo10 (unsigned long long * addr, uint64x2_t value)
+{
+  vldrdq_gather_offset (addr, value);
+}
+
 /* { dg-final { scan-assembler-not "__ARM_undef" } } */