[gcc/devel/c++-coroutines] [ARM][PATCH]: Add support for MVE ACLE intrinsics polymorphic variants for +mve.fp option.

[Iain D Sandoe]

https://gcc.gnu.org/g:e81d0d9ec7a337dd6a649390e1824930dc57847d

commit e81d0d9ec7a337dd6a649390e1824930dc57847d
Author: Srinath Parvathaneni <srinath.parvathaneni@arm.com>
Date:   Tue Mar 31 10:53:25 2020 +0100

    [ARM][PATCH]: Add support for MVE ACLE intrinsics polymorphic variants for +mve.fp option.
    
    For the following MVE ACLE intrinsics, polymorphic variant supports only +mve option, support for +mve.fp is missing.
    
    vabavq_p_s16, vabavq_p_s32, vabavq_p_s8, vabavq_p_u16, vabavq_p_u32, vabavq_p_u8, vabavq_s16, vabavq_s32, vabavq_s8, vabavq_u16, vabavq_u32, vabavq_u8, vaddlvaq_p_s32, vaddlvaq_p_u32, vaddlvaq_s32, vaddlvaq_u32, vaddlvq_p_s32, vaddlvq_p_u32, vaddlvq_u32, vaddvaq_p_s16, vaddvaq_p_s32, vaddvaq_p_s8, vaddvaq_p_u16, vaddvaq_p_u32, vaddvaq_p_u8, vaddvaq_s16, vaddvaq_s32, vaddvaq_s8, vaddvaq_u16, vaddvaq_u32, vaddvaq_u8, vaddvq_p_s16, vaddvq_p_s32, vaddvq_p_s8, vaddvq_p_u16, vaddvq_p_u32, vaddvq_p_u8, vaddvq_s8, vaddvq_u16, vaddvq_u32, vaddvq_u8, vcmpcsq_m_n_u16, vcmpcsq_m_n_u32, vcmpcsq_m_n_u8, vcmpcsq_m_u16, vcmpcsq_m_u32, vcmpcsq_m_u8, vcmpcsq_n_u16, vcmpcsq_n_u32, vcmpcsq_n_u8, vcmpcsq_u16, vcmpcsq_u32, vcmpcsq_u8, vcmpeqq_n_f16, vcmpeqq_n_f32, vcmpgeq_m_n_s16, vcmpgeq_m_n_s32, vcmpgeq_m_n_s8, vcmpgtq_m_n_f16, vcmpgtq_m_n_f32, vcmpgtq_n_f16, vcmpgtq_n_f32, vcmphiq_m_n_u16, vcmphiq_m_n_u32, vcmphiq_m_n_u8, vcmphiq_m_u16, vcmphiq_m_u32, vcmphiq_m_u8, vcmphiq_n_u16, vcmphiq_n_u32, vcmphiq_n_u8, vcmphiq_u16, vcmphiq_u32, vcmphiq_u8, vcmpleq_m_n_f16, vcmpleq_m_n_f32, vcmpleq_n_f16, vcmpleq_n_f32, vcmpltq_m_n_f16, vcmpltq_m_n_f32, vcmpneq_m_n_f16, vcmpneq_m_n_f32, vcmpneq_n_f16, vcmpneq_n_f32, vmaxavq_p_s16, vmaxavq_p_s32, vmaxavq_p_s8, vmaxavq_s16, vmaxavq_s32, vmaxavq_s8, vmaxq_x_s16, vmaxq_x_s32, vmaxq_x_s8, vmaxq_x_u16, vmaxq_x_u32, vmaxq_x_u8, vmaxvq_p_s16, vmaxvq_p_s32, vmaxvq_p_s8, vmaxvq_p_u16, vmaxvq_p_u32, vmaxvq_p_u8, vmaxvq_s16, vmaxvq_s32, vmaxvq_s8, vmaxvq_u16, vmaxvq_u32, vmaxvq_u8, vminavq_p_s16, vminavq_p_s32, vminavq_p_s8, vminavq_s16, vminavq_s32, vminavq_s8, vminq_x_s16, vminq_x_s32, vminq_x_s8, vminq_x_u16, vminq_x_u32, vminq_x_u8, vminvq_p_s16, vminvq_p_s32, vminvq_p_s8, vminvq_p_u16, vminvq_p_u32, vminvq_p_u8, vminvq_s16, vminvq_s32, vminvq_s8, vminvq_u16, vminvq_u32, vminvq_u8, vmladavaq_p_s16, vmladavaq_p_s32, vmladavaq_p_s8, vmladavaq_p_u16, vmladavaq_p_u32, vmladavaq_p_u8, vmladavaq_s16, vmladavaq_s32, vmladavaq_s8, vmladavaq_u16, vmladavaq_u32, vmladavaq_u8, vmladavaxq_s16, vmladavaxq_s32, vmladavaxq_s8, vmladavq_p_s16, vmladavq_p_s32, vmladavq_p_s8, vmladavq_p_u16, vmladavq_p_u32, vmladavq_p_u8, vmladavq_s16, vmladavq_s32, vmladavq_s8, vmladavq_u16, vmladavq_u32, vmladavq_u8, vmladavxq_p_s16, vmladavxq_p_s32, vmladavxq_p_s8, vmladavxq_s16, vmladavxq_s32, vmladavxq_s8, vmlaldavaq_s16, vmlaldavaq_s32, vmlaldavaq_u16, vmlaldavaq_u32, vmlaldavaxq_s16, vmlaldavaxq_s32, vmlaldavq_p_s16, vmlaldavq_p_s32, vmlaldavq_p_u16, vmlaldavq_p_u32, vmlaldavq_s16, vmlaldavq_s32, vmlaldavq_u16, vmlaldavq_u32, vmlaldavxq_p_s16, vmlaldavxq_p_s32, vmlsdavaq_s16, vmlsdavaq_s32, vmlsdavaq_s8, vmlsdavaxq_s16, vmlsdavaxq_s32, vmlsdavaxq_s8, vmlsdavq_p_s16, vmlsdavq_p_s32, vmlsdavq_p_s8, vmlsdavq_s16, vmlsdavq_s32, vmlsdavq_s8, vmlsdavxq_p_s16, vmlsdavxq_p_s32, vmlsdavxq_p_s8, vmlsdavxq_s16, vmlsdavxq_s32, vmlsdavxq_s8, vmlsldavaq_s16, vmlsldavaq_s32, vmlsldavaxq_s16, vmlsldavaxq_s32, vmlsldavq_p_s16, vmlsldavq_p_s32, vmlsldavq_s16, vmlsldavq_s32, vmlsldavxq_p_s16, vmlsldavxq_p_s32, vmlsldavxq_s16, vmlsldavxq_s32, vmovlbq_x_s16, vmovlbq_x_s8, vmovlbq_x_u16, vmovlbq_x_u8, vmovltq_x_s16, vmovltq_x_s8, vmovltq_x_u16, vmovltq_x_u8, vmulhq_x_s16, vmulhq_x_s32, vmulhq_x_s8, vmulhq_x_u16, vmulhq_x_u32, vmulhq_x_u8, vmullbq_int_x_s16, vmullbq_int_x_s32, vmullbq_int_x_s8, vmullbq_int_x_u16, vmullbq_int_x_u32, vmullbq_int_x_u8, vmullbq_poly_x_p16, vmullbq_poly_x_p8, vmulltq_int_x_s16, vmulltq_int_x_s32, vmulltq_int_x_s8, vmulltq_int_x_u16, vmulltq_int_x_u32, vmulltq_int_x_u8, vmulltq_poly_x_p16, vmulltq_poly_x_p8, vrmlaldavhaq_s32, vrmlaldavhaq_u32, vrmlaldavhaxq_s32, vrmlaldavhq_p_s32, vrmlaldavhq_p_u32, vrmlaldavhq_s32, vrmlaldavhq_u32, vrmlaldavhxq_p_s32, vrmlaldavhxq_s32, vrmlsldavhaq_s32, vrmlsldavhaxq_s32, vrmlsldavhq_p_s32, vrmlsldavhq_s32, vrmlsldavhxq_p_s32, vrmlsldavhxq_s32, vstrbq_p_s16, vstrbq_p_s32, vstrbq_p_s8, vstrbq_p_u16, vstrbq_p_u32, vstrbq_p_u8, vstrbq_s16, vstrbq_s32, vstrbq_s8, vstrbq_scatter_offset_p_s16, vstrbq_scatter_offset_p_s32, vstrbq_scatter_offset_p_s8, vstrbq_scatter_offset_p_u16, vstrbq_scatter_offset_p_u32, vstrbq_scatter_offset_p_u8, vstrbq_scatter_offset_s16, vstrbq_scatter_offset_s32, vstrbq_scatter_offset_s8, vstrbq_scatter_offset_u16, vstrbq_scatter_offset_u32, vstrbq_scatter_offset_u8, vstrbq_u16, vstrbq_u32, vstrbq_u8, vstrdq_scatter_base_p_s64, vstrdq_scatter_base_p_u64, vstrdq_scatter_base_s64, vstrdq_scatter_base_u64, vstrdq_scatter_offset_p_s64, vstrdq_scatter_offset_p_u64, vstrdq_scatter_offset_s64, vstrdq_scatter_offset_u64, vstrdq_scatter_shifted_offset_p_s64,
    vstrdq_scatter_shifted_offset_p_u64, vstrdq_scatter_shifted_offset_s64,
    vstrdq_scatter_shifted_offset_u64.
    
    This patch adds the support for MVE ACLE intrinsics polymorphic variants with +mve.fp option.
    
    Please refer to M-profile Vector Extension (MVE) intrinsics [1]  for more details.
    [1] https://developer.arm.com/architectures/instruction-sets/simd-isas/helium/mve-intrinsics
    
    2020-03-31  Srinath Parvathaneni  <srinath.parvathaneni@arm.com>
    
            * config/arm/arm_mve.h (vaddlvq): Move the polymorphic variant to the
            common section of both MVE Integer and MVE Floating Point.
            (vaddvq): Likewise.
            (vaddlvq_p): Likewise.
            (vaddvaq): Likewise.
            (vaddvq_p): Likewise.
            (vcmpcsq): Likewise.
            (vmlsdavxq): Likewise.
            (vmlsdavq): Likewise.
            (vmladavxq): Likewise.
            (vmladavq): Likewise.
            (vminvq): Likewise.
            (vminavq): Likewise.
            (vmaxvq): Likewise.
            (vmaxavq): Likewise.
            (vmlaldavq): Likewise.
            (vcmphiq): Likewise.
            (vaddlvaq): Likewise.
            (vrmlaldavhq): Likewise.
            (vrmlaldavhxq): Likewise.
            (vrmlsldavhq): Likewise.
            (vrmlsldavhxq): Likewise.
            (vmlsldavxq): Likewise.
            (vmlsldavq): Likewise.
            (vabavq): Likewise.
            (vrmlaldavhaq): Likewise.
            (vcmpgeq_m_n): Likewise.
            (vmlsdavxq_p): Likewise.
            (vmlsdavq_p): Likewise.
            (vmlsdavaxq): Likewise.
            (vmlsdavaq): Likewise.
            (vaddvaq_p): Likewise.
            (vcmpcsq_m_n): Likewise.
            (vcmpcsq_m): Likewise.
            (vmladavxq_p): Likewise.
            (vmladavq_p): Likewise.
            (vmladavaxq): Likewise.
            (vmladavaq): Likewise.
            (vminvq_p): Likewise.
            (vminavq_p): Likewise.
            (vmaxvq_p): Likewise.
            (vmaxavq_p): Likewise.
            (vcmphiq_m): Likewise.
            (vaddlvaq_p): Likewise.
            (vmlaldavaq): Likewise.
            (vmlaldavaxq): Likewise.
            (vmlaldavq_p): Likewise.
            (vmlaldavxq_p): Likewise.
            (vmlsldavaq): Likewise.
            (vmlsldavaxq): Likewise.
            (vmlsldavq_p): Likewise.
            (vmlsldavxq_p): Likewise.
            (vrmlaldavhaxq): Likewise.
            (vrmlaldavhq_p): Likewise.
            (vrmlaldavhxq_p): Likewise.
            (vrmlsldavhaq): Likewise.
            (vrmlsldavhaxq): Likewise.
            (vrmlsldavhq_p): Likewise.
            (vrmlsldavhxq_p): Likewise.
            (vabavq_p): Likewise.
            (vmladavaq_p): Likewise.
            (vstrbq_scatter_offset): Likewise.
            (vstrbq_p): Likewise.
            (vstrbq_scatter_offset_p): Likewise.
            (vstrdq_scatter_base_p): Likewise.
            (vstrdq_scatter_base): Likewise.
            (vstrdq_scatter_offset_p): Likewise.
            (vstrdq_scatter_offset): Likewise.
            (vstrdq_scatter_shifted_offset_p): Likewise.
            (vstrdq_scatter_shifted_offset): Likewise.
            (vmaxq_x): Likewise.
            (vminq_x): Likewise.
            (vmovlbq_x): Likewise.
            (vmovltq_x): Likewise.
            (vmulhq_x): Likewise.
            (vmullbq_int_x): Likewise.
            (vmullbq_poly_x): Likewise.
            (vmulltq_int_x): Likewise.
            (vmulltq_poly_x): Likewise.
            (vstrbq): Likewise.
    
    gcc/testsuite/ChangeLog:
    
    2020-03-31  Srinath Parvathaneni  <srinath.parvathaneni@arm.com>
    
            * gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u16.c: Modify.
            * gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c: Likewise.
            * gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c: Likewise.

Diff:
---
 gcc/ChangeLog                                      |   83 ++
 gcc/config/arm/arm_mve.h                           | 1517 ++++++++++----------
 gcc/testsuite/ChangeLog                            |   25 +
 .../arm/mve/intrinsics/vcmpcsq_m_n_u16.c           |    2 +-
 .../arm/mve/intrinsics/vcmpcsq_m_n_u32.c           |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c  |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c  |    2 +-
 .../arm/mve/intrinsics/vcmpgeq_m_n_s16.c           |    2 +-
 .../arm/mve/intrinsics/vcmpgeq_m_n_s32.c           |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c |    2 +-
 .../arm/mve/intrinsics/vcmpgtq_m_n_f16.c           |    2 +-
 .../arm/mve/intrinsics/vcmpgtq_m_n_f32.c           |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c  |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c  |    2 +-
 .../arm/mve/intrinsics/vcmpleq_m_n_f16.c           |    2 +-
 .../arm/mve/intrinsics/vcmpleq_m_n_f32.c           |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c  |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c  |    2 +-
 .../arm/mve/intrinsics/vcmpltq_m_n_f16.c           |    2 +-
 .../arm/mve/intrinsics/vcmpltq_m_n_f32.c           |    2 +-
 .../arm/mve/intrinsics/vcmpneq_m_n_f16.c           |    2 +-
 .../arm/mve/intrinsics/vcmpneq_m_n_f32.c           |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c  |    2 +-
 .../gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c  |    2 +-
 25 files changed, 882 insertions(+), 787 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 88e279eb474..097a222f66d 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,86 @@
+2020-03-31  Srinath Parvathaneni  <srinath.parvathaneni@arm.com>
+
+	* config/arm/arm_mve.h (vaddlvq): Move the polymorphic variant to the
+	common section of both MVE Integer and MVE Floating Point.
+	(vaddvq): Likewise.
+	(vaddlvq_p): Likewise.
+	(vaddvaq): Likewise.
+	(vaddvq_p): Likewise.
+	(vcmpcsq): Likewise.
+	(vmlsdavxq): Likewise.
+	(vmlsdavq): Likewise.
+	(vmladavxq): Likewise.
+	(vmladavq): Likewise.
+	(vminvq): Likewise.
+	(vminavq): Likewise.
+	(vmaxvq): Likewise.
+	(vmaxavq): Likewise.
+	(vmlaldavq): Likewise.
+	(vcmphiq): Likewise.
+	(vaddlvaq): Likewise.
+	(vrmlaldavhq): Likewise.
+	(vrmlaldavhxq): Likewise.
+	(vrmlsldavhq): Likewise.
+	(vrmlsldavhxq): Likewise.
+	(vmlsldavxq): Likewise.
+	(vmlsldavq): Likewise.
+	(vabavq): Likewise.
+	(vrmlaldavhaq): Likewise.
+	(vcmpgeq_m_n): Likewise.
+	(vmlsdavxq_p): Likewise.
+	(vmlsdavq_p): Likewise.
+	(vmlsdavaxq): Likewise.
+	(vmlsdavaq): Likewise.
+	(vaddvaq_p): Likewise.
+	(vcmpcsq_m_n): Likewise.
+	(vcmpcsq_m): Likewise.
+	(vmladavxq_p): Likewise.
+	(vmladavq_p): Likewise.
+	(vmladavaxq): Likewise.
+	(vmladavaq): Likewise.
+	(vminvq_p): Likewise.
+	(vminavq_p): Likewise.
+	(vmaxvq_p): Likewise.
+	(vmaxavq_p): Likewise.
+	(vcmphiq_m): Likewise.
+	(vaddlvaq_p): Likewise.
+	(vmlaldavaq): Likewise.
+	(vmlaldavaxq): Likewise.
+	(vmlaldavq_p): Likewise.
+	(vmlaldavxq_p): Likewise.
+	(vmlsldavaq): Likewise.
+	(vmlsldavaxq): Likewise.
+	(vmlsldavq_p): Likewise.
+	(vmlsldavxq_p): Likewise.
+	(vrmlaldavhaxq): Likewise.
+	(vrmlaldavhq_p): Likewise.
+	(vrmlaldavhxq_p): Likewise.
+	(vrmlsldavhaq): Likewise.
+	(vrmlsldavhaxq): Likewise.
+	(vrmlsldavhq_p): Likewise.
+	(vrmlsldavhxq_p): Likewise.
+	(vabavq_p): Likewise.
+	(vmladavaq_p): Likewise.
+	(vstrbq_scatter_offset): Likewise.
+	(vstrbq_p): Likewise.
+	(vstrbq_scatter_offset_p): Likewise.
+	(vstrdq_scatter_base_p): Likewise.
+	(vstrdq_scatter_base): Likewise.
+	(vstrdq_scatter_offset_p): Likewise.
+	(vstrdq_scatter_offset): Likewise.
+	(vstrdq_scatter_shifted_offset_p): Likewise.
+	(vstrdq_scatter_shifted_offset): Likewise.
+	(vmaxq_x): Likewise.
+	(vminq_x): Likewise.
+	(vmovlbq_x): Likewise.
+	(vmovltq_x): Likewise.
+	(vmulhq_x): Likewise.
+	(vmullbq_int_x): Likewise.
+	(vmullbq_poly_x): Likewise.
+	(vmulltq_int_x): Likewise.
+	(vmulltq_poly_x): Likewise.
+	(vstrbq): Likewise.
+
 2020-03-31  Jakub Jelinek  <jakub@redhat.com>
 
 	PR target/94368
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 14b6ec857bf..03ce0dd7e67 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -23568,22 +23568,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
   int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
 
-#define vaddlvq(p0) __arm_vaddlvq(p0)
-#define __arm_vaddlvq(p0) ({ __typeof(p0) __p0 = (p0); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-
-#define vaddvq(p0) __arm_vaddvq(p0)
-#define __arm_vaddvq(p0) ({ __typeof(p0) __p0 = (p0); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int8x16_t]: __arm_vaddvq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16x8_t]: __arm_vaddvq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddvq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vaddvq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vaddvq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddvq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-
 #define vmovlbq(p0) __arm_vmovlbq(p0)
 #define __arm_vmovlbq(p0) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -23658,12 +23642,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
 
-#define vaddlvq_p(p0,p1) __arm_vaddlvq_p(p0,p1)
-#define __arm_vaddlvq_p(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
-  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-
 #define vcmpneq(p0,p1) __arm_vcmpneq(p0,p1)
 #define __arm_vcmpneq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -24141,38 +24119,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
-#define vaddvaq(p0,p1) __arm_vaddvaq(p0,p1)
-#define __arm_vaddvaq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t]: __arm_vaddvaq_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t]: __arm_vaddvaq_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vaddvaq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t]: __arm_vaddvaq_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vaddvq_p(p0,p1) __arm_vaddvq_p(p0,p1)
-#define __arm_vaddvq_p(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int8x16_t]: __arm_vaddvq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
-  int (*)[__ARM_mve_type_int16x8_t]: __arm_vaddvq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
-  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddvq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
-  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vaddvq_p_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
-  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vaddvq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
-  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-
-#define vcmpcsq(p0,p1) __arm_vcmpcsq(p0,p1)
-#define __arm_vcmpcsq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpcsq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpcsq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpcsq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpcsq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpcsq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpcsq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
 #define vcmpeqq(p0,p1) __arm_vcmpeqq(p0,p1)
 #define __arm_vcmpeqq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -24190,82 +24136,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpeqq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpeqq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
 
-#define vmlsdavxq(p0,p1) __arm_vmlsdavxq(p0,p1)
-#define __arm_vmlsdavxq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavxq_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_vmlsdavxq_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_vmlsdavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vmlsdavq(p0,p1) __arm_vmlsdavq(p0,p1)
-#define __arm_vmlsdavq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavq_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_vmlsdavq_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_vmlsdavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vmladavxq(p0,p1) __arm_vmladavxq(p0,p1)
-#define __arm_vmladavxq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavxq_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_vmladavxq_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_vmladavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavxq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavxq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavxq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vmladavq(p0,p1) __arm_vmladavq(p0,p1)
-#define __arm_vmladavq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavq_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_vmladavq_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_vmladavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vminvq(p0,p1) __arm_vminvq(p0,p1)
-#define __arm_vminvq(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][__ARM_mve_type_int8x16_t]: __arm_vminvq_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vminvq_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vminvq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vminvq_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vminvq_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vminvq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vminavq(p0,p1) __arm_vminavq(p0,p1)
-#define __arm_vminavq(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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vminavq_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vminavq_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vminavq_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vmaxvq(p0,p1) __arm_vmaxvq(p0,p1)
-#define __arm_vmaxvq(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][__ARM_mve_type_int8x16_t]: __arm_vmaxvq_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxvq_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxvq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxvq_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxvq_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxvq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vmaxavq(p0,p1) __arm_vmaxavq(p0,p1)
-#define __arm_vmaxavq(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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vmaxavq_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxavq_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxavq_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
 #define vcmpneq(p0,p1) __arm_vcmpneq(p0,p1)
 #define __arm_vcmpneq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -24364,15 +24234,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshllbq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshllbq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
 
-#define vmlaldavq(p0,p1) __arm_vmlaldavq(p0,p1)
-#define __arm_vmlaldavq(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_int16x8_t]: __arm_vmlaldavq_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_vmlaldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
 #define vqmovunbq(p0,p1) __arm_vqmovunbq(p0,p1)
 #define __arm_vqmovunbq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -24428,17 +24289,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgtq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgtq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
 
-#define vcmphiq(p0,p1) __arm_vcmphiq(p0,p1)
-#define __arm_vcmphiq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmphiq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmphiq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmphiq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmphiq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmphiq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmphiq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
 #define vcmpleq(p0,p1) __arm_vcmpleq(p0,p1)
 #define __arm_vcmpleq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -24495,58 +24345,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpneq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpneq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
 
-#define vaddlvaq(p0,p1) __arm_vaddlvaq(p0,p1)
-#define __arm_vaddlvaq(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_int64_t][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vrmlaldavhq(p0,p1) __arm_vrmlaldavhq(p0,p1)
-#define __arm_vrmlaldavhq(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_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq(p0,p1)
-#define __arm_vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq_s32(p0,p1)
-
-#define vrmlsldavhq(p0,p1) __arm_vrmlsldavhq(p0,p1)
-#define __arm_vrmlsldavhq(p0,p1) __arm_vrmlsldavhq_s32(p0,p1)
-
-#define vrmlsldavhq(p0,p1) __arm_vrmlsldavhq(p0,p1)
-#define __arm_vrmlsldavhq(p0,p1) __arm_vrmlsldavhq_s32(p0,p1)
-
-#define vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq(p0,p1)
-#define __arm_vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq_s32(p0,p1)
-
-#define vmlsldavxq(p0,p1) __arm_vmlsldavxq(p0,p1)
-#define __arm_vmlsldavxq(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_int16x8_t]: __arm_vmlsldavxq_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_vmlsldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vmlsldavq(p0,p1) __arm_vmlsldavq(p0,p1)
-#define __arm_vmlsldavq(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_int16x8_t]: __arm_vmlsldavq_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_vmlsldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vabavq(p0,p1,p2) __arm_vabavq(p0,p1,p2)
-#define __arm_vabavq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabavq_s8 (__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabavq_s16 (__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabavq_s32 (__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabavq_u8 (__p0, __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_u16 (__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_u32 (__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-
 #define vshlcq(p0,p1,p2) __arm_vshlcq(p0,p1,p2)
 #define __arm_vshlcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -24557,14 +24355,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
 
-#define vrmlaldavhaq(p0,p1,p2) __arm_vrmlaldavhaq(p0,p1,p2)
-#define __arm_vrmlaldavhaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-
 #define vcmpeqq_m(p0,p1,p2) __arm_vcmpeqq_m(p0,p1,p2)
 #define __arm_vcmpeqq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -24790,12 +24580,7 @@ extern void *__ARM_undef;
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgeq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpgeq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpgeq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vcmpgeq_m_n(p0,p1,p2) __arm_vcmpgeq_m_n(p0,p1,p2)
-#define __arm_vcmpgeq_m_n(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_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpgeq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgeq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgeq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
@@ -24911,202 +24696,38 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminaq_m_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminaq_m_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
 
-#define vrmlaldavhaq(p0,p1,p2) __arm_vrmlaldavhaq(p0,p1,p2)
-#define __arm_vrmlaldavhaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vcmpltq_m(p0,p1,p2) __arm_vcmpltq_m(p0,p1,p2)
+#define __arm_vcmpltq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpltq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpltq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpltq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpltq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpltq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpltq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
 
-#define vmlsdavxq_p(p0,p1,p2) __arm_vmlsdavxq_p(p0,p1,p2)
-#define __arm_vmlsdavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vcmpleq_m(p0,p1,p2) __arm_vcmpleq_m(p0,p1,p2)
+#define __arm_vcmpleq_m(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavxq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpleq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpleq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpleq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpleq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpleq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpleq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
 
-#define vmlsdavq_p(p0,p1,p2) __arm_vmlsdavq_p(p0,p1,p2)
-#define __arm_vmlsdavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vcmpgtq_m(p0,p1,p2) __arm_vcmpgtq_m(p0,p1,p2)
+#define __arm_vcmpgtq_m(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vmlsdavaxq(p0,p1,p2) __arm_vmlsdavaxq(p0,p1,p2)
-#define __arm_vmlsdavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavaxq_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaxq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaxq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-
-#define vmlsdavaq(p0,p1,p2) __arm_vmlsdavaq(p0,p1,p2)
-#define __arm_vmlsdavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavaq_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-
-#define vaddvaq_p(p0,p1,p2) __arm_vaddvaq_p(p0,p1,p2)
-#define __arm_vaddvaq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t]: __arm_vaddvaq_p_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t]: __arm_vaddvaq_p_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vaddvaq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t]: __arm_vaddvaq_p_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vcmpcsq_m_n(p0,p1,p2) __arm_vcmpcsq_m_n(p0,p1,p2)
-#define __arm_vcmpcsq_m_n(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpcsq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpcsq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpcsq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpcsq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpcsq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpcsq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2));})
-
-#define vcmpcsq_m(p0,p1,p2) __arm_vcmpcsq_m(p0,p1,p2)
-#define __arm_vcmpcsq_m(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpcsq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpcsq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpcsq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vmladavxq_p(p0,p1,p2) __arm_vmladavxq_p(p0,p1,p2)
-#define __arm_vmladavxq_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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavxq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vmladavq_p(p0,p1,p2) __arm_vmladavq_p(p0,p1,p2)
-#define __arm_vmladavq_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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavq_p_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vmladavaxq(p0,p1,p2) __arm_vmladavaxq(p0,p1,p2)
-#define __arm_vmladavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaxq_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaxq_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaxq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaxq_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaxq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaxq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-
-#define vmladavaq(p0,p1,p2) __arm_vmladavaq(p0,p1,p2)
-#define __arm_vmladavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaq_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaq_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaq_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-
-#define vminvq_p(p0,p1,p2) __arm_vminvq_p(p0,p1,p2)
-#define __arm_vminvq_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][__ARM_mve_type_int8x16_t]: __arm_vminvq_p_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vminvq_p_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vminvq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vminvq_p_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vminvq_p_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vminvq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vminavq_p(p0,p1,p2) __arm_vminavq_p(p0,p1,p2)
-#define __arm_vminavq_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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vminavq_p_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vminavq_p_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vminavq_p_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vmaxvq_p(p0,p1,p2) __arm_vmaxvq_p(p0,p1,p2)
-#define __arm_vmaxvq_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][__ARM_mve_type_int8x16_t]: __arm_vmaxvq_p_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxvq_p_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxvq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxvq_p_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxvq_p_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxvq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vmaxavq_p(p0,p1,p2) __arm_vmaxavq_p(p0,p1,p2)
-#define __arm_vmaxavq_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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vmaxavq_p_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxavq_p_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxavq_p_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vcmpltq_m(p0,p1,p2) __arm_vcmpltq_m(p0,p1,p2)
-#define __arm_vcmpltq_m(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpltq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpltq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpltq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpltq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpltq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpltq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
-
-#define vcmpleq_m(p0,p1,p2) __arm_vcmpleq_m(p0,p1,p2)
-#define __arm_vcmpleq_m(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpleq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpleq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpleq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpleq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpleq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpleq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
-
-#define vcmphiq_m(p0,p1,p2) __arm_vcmphiq_m(p0,p1,p2)
-#define __arm_vcmphiq_m(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_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmphiq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmphiq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmphiq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmphiq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmphiq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmphiq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vcmpgtq_m(p0,p1,p2) __arm_vcmpgtq_m(p0,p1,p2)
-#define __arm_vcmpgtq_m(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgtq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpgtq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpgtq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgtq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgtq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgtq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgtq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vcmpgtq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vcmpgtq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpgtq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgtq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vcmpgtq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
 
 #define vshrntq(p0,p1,p2) __arm_vshrntq(p0,p1,p2)
 #define __arm_vshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
@@ -25269,182 +24890,74 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovunbq_m_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_m_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
 
-#define vaddlvaq_p(p0,p1,p2) __arm_vaddlvaq_p(p0,p1,p2)
-#define __arm_vaddlvaq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vsubq_m(p0,p1,p2,p3) __arm_vsubq_m(p0,p1,p2,p3)
+#define __arm_vsubq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_p_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vsubq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vsubq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vsubq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vsubq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vsubq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vsubq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vsubq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vsubq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsubq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vsubq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsubq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
-#define vmlaldavaq(p0,p1,p2) __arm_vmlaldavaq(p0,p1,p2)
-#define __arm_vmlaldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vabdq_m(p0,p1,p2,p3) __arm_vabdq_m(p0,p1,p2,p3)
+#define __arm_vabdq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavaq_s16 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavaq_u16 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
-  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabdq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabdq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
-#define vmlaldavaxq(p0,p1,p2) __arm_vmlaldavaxq(p0,p1,p2)
-#define __arm_vmlaldavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vandq_m(p0,p1,p2,p3) __arm_vandq_m(p0,p1,p2,p3)
+#define __arm_vandq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavaxq_s16 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaxq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vandq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vandq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vandq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vandq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vandq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vandq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
-#define vmlaldavq_p(p0,p1,p2) __arm_vmlaldavq_p(p0,p1,p2)
-#define __arm_vmlaldavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vbicq_m(p0,p1,p2,p3) __arm_vbicq_m(p0,p1,p2,p3)
+#define __arm_vbicq_m(p0,p1,p2,p3) ({ __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_int16x8_t]: __arm_vmlaldavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
-#define vmlaldavxq_p(p0,p1,p2) __arm_vmlaldavxq_p(p0,p1,p2)
-#define __arm_vmlaldavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define vbrsrq_m(p0,p1,p2,p3) __arm_vbrsrq_m(p0,p1,p2,p3)
+#define __arm_vbrsrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbrsrq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __p2, p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbrsrq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __p2, p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbrsrq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __p2, p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbrsrq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __p2, p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbrsrq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __p2, p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbrsrq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __p2, p3));})
 
-#define vmlsldavaq(p0,p1,p2) __arm_vmlsldavaq(p0,p1,p2)
-#define __arm_vmlsldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-
-#define vmlsldavaxq(p0,p1,p2) __arm_vmlsldavaxq(p0,p1,p2)
-#define __arm_vmlsldavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaxq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaxq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-
-#define vmlsldavq_p(p0,p1,p2) __arm_vmlsldavq_p(p0,p1,p2)
-#define __arm_vmlsldavq_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_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vmlsldavxq_p(p0,p1,p2) __arm_vmlsldavxq_p(p0,p1,p2)
-#define __arm_vmlsldavxq_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_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vrmlaldavhaxq(p0,p1,p2) __arm_vrmlaldavhaxq(p0,p1,p2)
-#define __arm_vrmlaldavhaxq(p0,p1,p2) __arm_vrmlaldavhaxq_s32(p0,p1,p2)
-
-#define vrmlaldavhq_p(p0,p1,p2) __arm_vrmlaldavhq_p(p0,p1,p2)
-#define __arm_vrmlaldavhq_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_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vrmlaldavhxq_p(p0,p1,p2) __arm_vrmlaldavhxq_p(p0,p1,p2)
-#define __arm_vrmlaldavhxq_p(p0,p1,p2) __arm_vrmlaldavhxq_p_s32(p0,p1,p2)
-
-#define vrmlsldavhaq(p0,p1,p2) __arm_vrmlsldavhaq(p0,p1,p2)
-#define __arm_vrmlsldavhaq(p0,p1,p2) __arm_vrmlsldavhaq_s32(p0,p1,p2)
-
-#define vrmlsldavhaxq(p0,p1,p2) __arm_vrmlsldavhaxq(p0,p1,p2)
-#define __arm_vrmlsldavhaxq(p0,p1,p2) __arm_vrmlsldavhaxq_s32(p0,p1,p2)
-
-#define vrmlsldavhq_p(p0,p1,p2) __arm_vrmlsldavhq_p(p0,p1,p2)
-#define __arm_vrmlsldavhq_p(p0,p1,p2) __arm_vrmlsldavhq_p_s32(p0,p1,p2)
-
-#define vrmlsldavhxq_p(p0,p1,p2) __arm_vrmlsldavhxq_p(p0,p1,p2)
-#define __arm_vrmlsldavhxq_p(p0,p1,p2) __arm_vrmlsldavhxq_p_s32(p0,p1,p2)
-
-#define vsubq_m(p0,p1,p2,p3) __arm_vsubq_m(p0,p1,p2,p3)
-#define __arm_vsubq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vsubq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vsubq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vsubq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vsubq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vsubq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vsubq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vsubq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vsubq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsubq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vsubq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsubq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vabavq_p(p0,p1,p2,p3) __arm_vabavq_p(p0,p1,p2,p3)
-#define __arm_vabavq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabavq_p_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabavq_p_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabavq_p_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabavq_p_u8(__p0, __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_p_u16(__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_p_u32(__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vabdq_m(p0,p1,p2,p3) __arm_vabdq_m(p0,p1,p2,p3)
-#define __arm_vabdq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabdq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabdq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vandq_m(p0,p1,p2,p3) __arm_vandq_m(p0,p1,p2,p3)
-#define __arm_vandq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vandq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vandq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vandq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vandq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vandq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vandq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vbicq_m(p0,p1,p2,p3) __arm_vbicq_m(p0,p1,p2,p3)
-#define __arm_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vbrsrq_m(p0,p1,p2,p3) __arm_vbrsrq_m(p0,p1,p2,p3)
-#define __arm_vbrsrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbrsrq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __p2, p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbrsrq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __p2, p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbrsrq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __p2, p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbrsrq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __p2, p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbrsrq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __p2, p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbrsrq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __p2, p3));})
-
-#define vcaddq_rot270_m(p0,p1,p2,p3) __arm_vcaddq_rot270_m(p0,p1,p2,p3)
-#define __arm_vcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+#define vcaddq_rot270_m(p0,p1,p2,p3) __arm_vcaddq_rot270_m(p0,p1,p2,p3)
+#define __arm_vcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
@@ -25479,18 +24992,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_veorq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_veorq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
-#define vmladavaq_p(p0,p1,p2,p3) __arm_vmladavaq_p(p0,p1,p2,p3)
-#define __arm_vmladavaq_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_int32_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaq_p_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaq_p_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaq_p_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
 #define vornq_m(p0,p1,p2,p3) __arm_vornq_m(p0,p1,p2,p3)
 #define __arm_vornq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -25562,18 +25063,6 @@ extern void *__ARM_undef;
   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)));})
 
-#define vstrbq_scatter_offset(p0,p1,p2) __arm_vstrbq_scatter_offset(p0,p1,p2)
-#define __arm_vstrbq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_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)));})
-
 #define vstrwq_scatter_base(p0,p1,p2) __arm_vstrwq_scatter_base(p0,p1,p2)
 #define __arm_vstrwq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
@@ -25591,29 +25080,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
   int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
-#define vstrbq_p(p0,p1,p2) __arm_vstrbq_p(p0,p1,p2)
-#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));})
-
-#define vstrbq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrbq_scatter_offset_p(p0,p1,p2,p3)
-#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));})
-
 #define vstrwq_scatter_base_p(p0,p1,p2,p3) __arm_vstrwq_scatter_base_p(p0,p1,p2,p3)
 #define __arm_vstrwq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
@@ -25796,50 +25262,6 @@ extern void *__ARM_undef;
   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));})
 
-#define vstrdq_scatter_base_p(p0,p1,p2,p3) __arm_vstrdq_scatter_base_p(p0,p1,p2,p3)
-#define __arm_vstrdq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_p_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
-  int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_p_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
-
-#define vstrdq_scatter_base(p0,p1,p2) __arm_vstrdq_scatter_base(p0,p1,p2)
-#define __arm_vstrdq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t)), \
-  int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
-
-#define vstrdq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3)
-#define __arm_vstrdq_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(__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));})
-
-#define vstrdq_scatter_offset(p0,p1,p2) __arm_vstrdq_scatter_offset(p0,p1,p2)
-#define __arm_vstrdq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __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)));})
-
-#define vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3)
-#define __arm_vstrdq_scatter_shifted_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(__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));})
-
-#define vstrdq_scatter_shifted_offset(p0,p1,p2) __arm_vstrdq_scatter_shifted_offset(p0,p1,p2)
-#define __arm_vstrdq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
-  __typeof(p1) __p1 = (p1); \
-  __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)));})
-
 #define vstrhq_scatter_offset(p0,p1,p2) __arm_vstrhq_scatter_offset(p0,p1,p2)
 #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -26085,117 +25507,32 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_veorq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_veorq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
 
-#define vmaxq_x(p1,p2,p3) __arm_vmaxq_x(p1,p2,p3)
-#define __arm_vmaxq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+#define vmulq_x(p1,p2,p3) __arm_vmulq_x(p1,p2,p3)
+#define __arm_vmulq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmaxq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxq_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxq_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxq_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vmulq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vmulq_x_n_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vmulq_x_n_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vmulq_x_n_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vmulq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vmulq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
 
-#define vminq_x(p1,p2,p3) __arm_vminq_x(p1,p2,p3)
-#define __arm_vminq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vminq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vminq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vminq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vminq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vmovlbq_x(p1,p2) __arm_vmovlbq_x(p1,p2)
-#define __arm_vmovlbq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovlbq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
-
-#define vmovltq_x(p1,p2) __arm_vmovltq_x(p1,p2)
-#define __arm_vmovltq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovltq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
-  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
-
-#define vmulhq_x(p1,p2,p3) __arm_vmulhq_x(p1,p2,p3)
-#define __arm_vmulhq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulhq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulhq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulhq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulhq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulhq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulhq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vmullbq_int_x(p1,p2,p3) __arm_vmullbq_int_x(p1,p2,p3)
-#define __arm_vmullbq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmullbq_int_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmullbq_int_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmullbq_int_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_int_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmullbq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vmullbq_poly_x(p1,p2,p3) __arm_vmullbq_poly_x(p1,p2,p3)
-#define __arm_vmullbq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
-#define vmulltq_int_x(p1,p2,p3) __arm_vmulltq_int_x(p1,p2,p3)
-#define __arm_vmulltq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulltq_int_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulltq_int_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulltq_int_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_int_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulltq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-
-#define vmulltq_poly_x(p1,p2,p3) __arm_vmulltq_poly_x(p1,p2,p3)
-#define __arm_vmulltq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-
-#define vmulq_x(p1,p2,p3) __arm_vmulq_x(p1,p2,p3)
-#define __arm_vmulq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
-  __typeof(p2) __p2 = (p2); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
-  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vmulq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t), p3), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vmulq_x_n_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vmulq_x_n_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vmulq_x_n_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vmulq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vmulq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
-
-#define vnegq_x(p1,p2) __arm_vnegq_x(p1,p2)
-#define __arm_vnegq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
-  int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
-  int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
-  int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vornq_x(p1,p2,p3) __arm_vornq_x(p1,p2,p3)
-#define __arm_vornq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+#define vnegq_x(p1,p2) __arm_vnegq_x(p1,p2)
+#define __arm_vnegq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vornq_x(p1,p2,p3) __arm_vornq_x(p1,p2,p3)
+#define __arm_vornq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
   __typeof(p2) __p2 = (p2); \
   _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vornq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
@@ -27555,6 +26892,656 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2, p3), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2, p3));})
 
+#define vabavq(p0,p1,p2) __arm_vabavq(p0,p1,p2)
+#define __arm_vabavq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabavq_s8 (__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabavq_s16 (__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabavq_s32 (__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabavq_u8 (__p0, __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_u16 (__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_u32 (__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
+#define vabavq_p(p0,p1,p2,p3) __arm_vabavq_p(p0,p1,p2,p3)
+#define __arm_vabavq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabavq_p_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabavq_p_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabavq_p_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabavq_p_u8(__p0, __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_p_u16(__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_p_u32(__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vaddlvaq(p0,p1) __arm_vaddlvaq(p0,p1)
+#define __arm_vaddlvaq(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_int64_t][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vaddlvaq_p(p0,p1,p2) __arm_vaddlvaq_p(p0,p1,p2)
+#define __arm_vaddlvaq_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_int64_t][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_p_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vaddlvq(p0) __arm_vaddlvq(p0)
+#define __arm_vaddlvq(p0) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+
+#define vaddlvq_p(p0,p1) __arm_vaddlvq_p(p0,p1)
+#define __arm_vaddlvq_p(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vaddvaq(p0,p1) __arm_vaddvaq(p0,p1)
+#define __arm_vaddvaq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t]: __arm_vaddvaq_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t]: __arm_vaddvaq_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vaddvaq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t]: __arm_vaddvaq_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vaddvaq_p(p0,p1,p2) __arm_vaddvaq_p(p0,p1,p2)
+#define __arm_vaddvaq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t]: __arm_vaddvaq_p_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t]: __arm_vaddvaq_p_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vaddvaq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t]: __arm_vaddvaq_p_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vaddvq(p0) __arm_vaddvq(p0)
+#define __arm_vaddvq(p0) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vaddvq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vaddvq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddvq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vaddvq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vaddvq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddvq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
+
+#define vaddvq_p(p0,p1) __arm_vaddvq_p(p0,p1)
+#define __arm_vaddvq_p(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vaddvq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vaddvq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddvq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vaddvq_p_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vaddvq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vcmpcsq(p0,p1) __arm_vcmpcsq(p0,p1)
+#define __arm_vcmpcsq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpcsq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpcsq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpcsq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpcsq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpcsq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpcsq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
+
+#define vcmpcsq_m(p0,p1,p2) __arm_vcmpcsq_m(p0,p1,p2)
+#define __arm_vcmpcsq_m(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_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmpcsq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpcsq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpcsq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpcsq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmpcsq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmpcsq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2));})
+
+#define vcmphiq(p0,p1) __arm_vcmphiq(p0,p1)
+#define __arm_vcmphiq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmphiq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmphiq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmphiq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmphiq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmphiq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmphiq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
+
+#define vcmphiq_m(p0,p1,p2) __arm_vcmphiq_m(p0,p1,p2)
+#define __arm_vcmphiq_m(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_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmphiq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16_t]: __arm_vcmphiq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vcmphiq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vcmphiq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmphiq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmphiq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vmaxavq(p0,p1) __arm_vmaxavq(p0,p1)
+#define __arm_vmaxavq(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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vmaxavq_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxavq_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxavq_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmaxavq_p(p0,p1,p2) __arm_vmaxavq_p(p0,p1,p2)
+#define __arm_vmaxavq_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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vmaxavq_p_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxavq_p_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxavq_p_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmaxq_x(p1,p2,p3) __arm_vmaxq_x(p1,p2,p3)
+#define __arm_vmaxq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmaxq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxq_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxq_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxq_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vmaxvq(p0,p1) __arm_vmaxvq(p0,p1)
+#define __arm_vmaxvq(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][__ARM_mve_type_int8x16_t]: __arm_vmaxvq_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxvq_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxvq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxvq_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxvq_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxvq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmaxvq_p(p0,p1,p2) __arm_vmaxvq_p(p0,p1,p2)
+#define __arm_vmaxvq_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][__ARM_mve_type_int8x16_t]: __arm_vmaxvq_p_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vmaxvq_p_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vmaxvq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vmaxvq_p_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxvq_p_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxvq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vminavq(p0,p1) __arm_vminavq(p0,p1)
+#define __arm_vminavq(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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vminavq_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vminavq_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vminavq_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vminavq_p(p0,p1,p2) __arm_vminavq_p(p0,p1,p2)
+#define __arm_vminavq_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_uint8_t][__ARM_mve_type_int8x16_t]: __arm_vminavq_p_s8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_int16x8_t]: __arm_vminavq_p_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_int32x4_t]: __arm_vminavq_p_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vminq_x(p1,p2,p3) __arm_vminq_x(p1,p2,p3)
+#define __arm_vminq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vminq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vminq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vminq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vminq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vminvq(p0,p1) __arm_vminvq(p0,p1)
+#define __arm_vminvq(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][__ARM_mve_type_int8x16_t]: __arm_vminvq_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vminvq_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vminvq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vminvq_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vminvq_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vminvq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vminvq_p(p0,p1,p2) __arm_vminvq_p(p0,p1,p2)
+#define __arm_vminvq_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][__ARM_mve_type_int8x16_t]: __arm_vminvq_p_s8 (__ARM_mve_coerce(__p0, int8_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16_t][__ARM_mve_type_int16x8_t]: __arm_vminvq_p_s16 (__ARM_mve_coerce(__p0, int16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t]: __arm_vminvq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8_t][__ARM_mve_type_uint8x16_t]: __arm_vminvq_p_u8 (__ARM_mve_coerce(__p0, uint8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16_t][__ARM_mve_type_uint16x8_t]: __arm_vminvq_p_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t]: __arm_vminvq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vmladavaq(p0,p1,p2) __arm_vmladavaq(p0,p1,p2)
+#define __arm_vmladavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaq_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaq_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaq_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
+#define vmladavaq_p(p0,p1,p2,p3) __arm_vmladavaq_p(p0,p1,p2,p3)
+#define __arm_vmladavaq_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_int32_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaq_p_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaq_p_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaq_p_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vmladavaxq(p0,p1,p2) __arm_vmladavaxq(p0,p1,p2)
+#define __arm_vmladavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaxq_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaxq_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaxq_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaxq_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaxq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaxq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
+#define vmladavq(p0,p1) __arm_vmladavq(p0,p1)
+#define __arm_vmladavq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavq_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_vmladavq_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_vmladavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmladavq_p(p0,p1,p2) __arm_vmladavq_p(p0,p1,p2)
+#define __arm_vmladavq_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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavq_p_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vmladavxq(p0,p1) __arm_vmladavxq(p0,p1)
+#define __arm_vmladavxq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavxq_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_vmladavxq_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_vmladavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavxq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavxq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavxq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmladavxq_p(p0,p1,p2) __arm_vmladavxq_p(p0,p1,p2)
+#define __arm_vmladavxq_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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavxq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmlaldavaq(p0,p1,p2) __arm_vmlaldavaq(p0,p1,p2)
+#define __arm_vmlaldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavaq_s16 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavaq_u16 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
+#define vmlaldavaxq(p0,p1,p2) __arm_vmlaldavaxq(p0,p1,p2)
+#define __arm_vmlaldavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavaxq_s16 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaxq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
+
+#define vmlaldavq(p0,p1) __arm_vmlaldavq(p0,p1)
+#define __arm_vmlaldavq(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_int16x8_t]: __arm_vmlaldavq_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_vmlaldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmlaldavq_p(p0,p1,p2) __arm_vmlaldavq_p(p0,p1,p2)
+#define __arm_vmlaldavq_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_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vmlaldavxq_p(p0,p1,p2) __arm_vmlaldavxq_p(p0,p1,p2)
+#define __arm_vmlaldavxq_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_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmlsdavaq(p0,p1,p2) __arm_vmlsdavaq(p0,p1,p2)
+#define __arm_vmlsdavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavaq_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
+
+#define vmlsdavaxq(p0,p1,p2) __arm_vmlsdavaxq(p0,p1,p2)
+#define __arm_vmlsdavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavaxq_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaxq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaxq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
+
+#define vmlsdavq(p0,p1) __arm_vmlsdavq(p0,p1)
+#define __arm_vmlsdavq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavq_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_vmlsdavq_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_vmlsdavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmlsdavq_p(p0,p1,p2) __arm_vmlsdavq_p(p0,p1,p2)
+#define __arm_vmlsdavq_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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmlsdavxq(p0,p1) __arm_vmlsdavxq(p0,p1)
+#define __arm_vmlsdavxq(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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavxq_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_vmlsdavxq_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_vmlsdavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmlsdavxq_p(p0,p1,p2) __arm_vmlsdavxq_p(p0,p1,p2)
+#define __arm_vmlsdavxq_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_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmlsdavxq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmlsldavaq(p0,p1,p2) __arm_vmlsldavaq(p0,p1,p2)
+#define __arm_vmlsldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
+
+#define vmlsldavaxq(p0,p1,p2) __arm_vmlsldavaxq(p0,p1,p2)
+#define __arm_vmlsldavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaxq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaxq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
+
+#define vmlsldavq(p0,p1) __arm_vmlsldavq(p0,p1)
+#define __arm_vmlsldavq(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_int16x8_t]: __arm_vmlsldavq_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_vmlsldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmlsldavq_p(p0,p1,p2) __arm_vmlsldavq_p(p0,p1,p2)
+#define __arm_vmlsldavq_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_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmlsldavxq(p0,p1) __arm_vmlsldavxq(p0,p1)
+#define __arm_vmlsldavxq(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_int16x8_t]: __arm_vmlsldavxq_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_vmlsldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmlsldavxq_p(p0,p1,p2) __arm_vmlsldavxq_p(p0,p1,p2)
+#define __arm_vmlsldavxq_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_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
+
+#define vmovlbq_x(p1,p2) __arm_vmovlbq_x(p1,p2)
+#define __arm_vmovlbq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovlbq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
+
+#define vmovltq_x(p1,p2) __arm_vmovltq_x(p1,p2)
+#define __arm_vmovltq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovltq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
+
+#define vmulhq_x(p1,p2,p3) __arm_vmulhq_x(p1,p2,p3)
+#define __arm_vmulhq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulhq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulhq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulhq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulhq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulhq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulhq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vmullbq_int_x(p1,p2,p3) __arm_vmullbq_int_x(p1,p2,p3)
+#define __arm_vmullbq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmullbq_int_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmullbq_int_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmullbq_int_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_int_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmullbq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vmullbq_poly_x(p1,p2,p3) __arm_vmullbq_poly_x(p1,p2,p3)
+#define __arm_vmullbq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
+
+#define vmulltq_int_x(p1,p2,p3) __arm_vmulltq_int_x(p1,p2,p3)
+#define __arm_vmulltq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulltq_int_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulltq_int_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulltq_int_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_int_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulltq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define vmulltq_poly_x(p1,p2,p3) __arm_vmulltq_poly_x(p1,p2,p3)
+#define __arm_vmulltq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
+
+#define vrmlaldavhaq(p0,p1,p2) __arm_vrmlaldavhaq(p0,p1,p2)
+#define __arm_vrmlaldavhaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int64_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint64_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
+#define vrmlaldavhaxq(p0,p1,p2) __arm_vrmlaldavhaxq(p0,p1,p2)
+#define __arm_vrmlaldavhaxq(p0,p1,p2) __arm_vrmlaldavhaxq_s32(p0,p1,p2)
+
+#define vrmlaldavhq(p0,p1) __arm_vrmlaldavhq(p0,p1)
+#define __arm_vrmlaldavhq(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_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vrmlaldavhq_p(p0,p1,p2) __arm_vrmlaldavhq_p(p0,p1,p2)
+#define __arm_vrmlaldavhq_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_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq(p0,p1)
+#define __arm_vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq_s32(p0,p1)
+
+#define vrmlaldavhxq_p(p0,p1,p2) __arm_vrmlaldavhxq_p(p0,p1,p2)
+#define __arm_vrmlaldavhxq_p(p0,p1,p2) __arm_vrmlaldavhxq_p_s32(p0,p1,p2)
+
+#define vrmlsldavhaq(p0,p1,p2) __arm_vrmlsldavhaq(p0,p1,p2)
+#define __arm_vrmlsldavhaq(p0,p1,p2) __arm_vrmlsldavhaq_s32(p0,p1,p2)
+
+#define vrmlsldavhaxq(p0,p1,p2) __arm_vrmlsldavhaxq(p0,p1,p2)
+#define __arm_vrmlsldavhaxq(p0,p1,p2) __arm_vrmlsldavhaxq_s32(p0,p1,p2)
+
+#define vrmlsldavhq(p0,p1) __arm_vrmlsldavhq(p0,p1)
+#define __arm_vrmlsldavhq(p0,p1) __arm_vrmlsldavhq_s32(p0,p1)
+
+#define vrmlsldavhq_p(p0,p1,p2) __arm_vrmlsldavhq_p(p0,p1,p2)
+#define __arm_vrmlsldavhq_p(p0,p1,p2) __arm_vrmlsldavhq_p_s32(p0,p1,p2)
+
+#define vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq(p0,p1)
+#define __arm_vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq_s32(p0,p1)
+
+#define vrmlsldavhxq_p(p0,p1,p2) __arm_vrmlsldavhxq_p(p0,p1,p2)
+#define __arm_vrmlsldavhxq_p(p0,p1,p2) __arm_vrmlsldavhxq_p_s32(p0,p1,p2)
+
+#define vstrbq(p0,p1) __arm_vstrbq(p0,p1)
+#define __arm_vstrbq(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_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)));})
+
+#define vstrbq_p(p0,p1,p2) __arm_vstrbq_p(p0,p1,p2)
+#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));})
+
+#define vstrbq_scatter_offset(p0,p1,p2) __arm_vstrbq_scatter_offset(p0,p1,p2)
+#define __arm_vstrbq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_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)));})
+
+#define vstrbq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrbq_scatter_offset_p(p0,p1,p2,p3)
+#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));})
+
+#define vstrdq_scatter_base(p0,p1,p2) __arm_vstrdq_scatter_base(p0,p1,p2)
+#define __arm_vstrdq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t)), \
+  int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
+
+#define vstrdq_scatter_base_p(p0,p1,p2,p3) __arm_vstrdq_scatter_base_p(p0,p1,p2,p3)
+#define __arm_vstrdq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
+  int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_p_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
+  int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_p_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
+
+#define vstrdq_scatter_offset(p0,p1,p2) __arm_vstrdq_scatter_offset(p0,p1,p2)
+#define __arm_vstrdq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __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)));})
+
+#define vstrdq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3)
+#define __arm_vstrdq_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(__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));})
+
+#define vstrdq_scatter_shifted_offset(p0,p1,p2) __arm_vstrdq_scatter_shifted_offset(p0,p1,p2)
+#define __arm_vstrdq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  __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)));})
+
+#define vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3)
+#define __arm_vstrdq_scatter_shifted_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(__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));})
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index aa269f6071f..b6b87d2b3f1 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,28 @@
+2020-03-31  Srinath Parvathaneni  <srinath.parvathaneni@arm.com>
+
+	* gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u16.c: Modify.
+	* gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c: Likewise.
+	* gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c: Likewise.
+
 2020-03-31  Jakub Jelinek  <jakub@redhat.com>
 
 	PR target/94368
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u16.c
index b9ea8d9152c..a1640133012 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u16.c
@@ -16,7 +16,7 @@ foo (uint16x8_t a, uint16_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (uint16x8_t a, uint16_t b, mve_pred16_t p)
 {
-  return vcmpcsq_m_n (a, b, p);
+  return vcmpcsq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u32.c
index aa41fcb32d0..d269ec7e3ab 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u32.c
@@ -16,7 +16,7 @@ foo (uint32x4_t a, uint32_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (uint32x4_t a, uint32_t b, mve_pred16_t p)
 {
-  return vcmpcsq_m_n (a, b, p);
+  return vcmpcsq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c
index 370701c8593..52c16b3e70f 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpcsq_m_n_u8.c
@@ -16,7 +16,7 @@ foo (uint8x16_t a, uint8_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (uint8x16_t a, uint8_t b, mve_pred16_t p)
 {
-  return vcmpcsq_m_n (a, b, p);
+  return vcmpcsq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c
index 7dbc352cc1f..f97209d2322 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f16.c
@@ -15,7 +15,7 @@ foo (float16x8_t a, float16_t b)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b)
 {
-  return vcmpeqq_n (a, b);
+  return vcmpeqq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f16"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c
index 3cd9224ef21..c80843288b2 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpeqq_n_f32.c
@@ -15,7 +15,7 @@ foo (float32x4_t a, float32_t b)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b)
 {
-  return vcmpeqq_n (a, b);
+  return vcmpeqq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f32"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s16.c
index f5df1c78226..c0ad38f6c6f 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s16.c
@@ -16,7 +16,7 @@ foo (int16x8_t a, int16_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (int16x8_t a, int16_t b, mve_pred16_t p)
 {
-  return vcmpgeq_m_n (a, b, p);
+  return vcmpgeq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s32.c
index 6730046a959..8974ce4d11a 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s32.c
@@ -16,7 +16,7 @@ foo (int32x4_t a, int32_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (int32x4_t a, int32_t b, mve_pred16_t p)
 {
-  return vcmpgeq_m_n (a, b, p);
+  return vcmpgeq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c
index 76162c77d7e..981aa1b516c 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgeq_m_n_s8.c
@@ -16,7 +16,7 @@ foo (int8x16_t a, int8_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (int8x16_t a, int8_t b, mve_pred16_t p)
 {
-  return vcmpgeq_m_n (a, b, p);
+  return vcmpgeq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16.c
index be8131e60ec..80c86f65825 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f16.c
@@ -16,7 +16,7 @@ foo (float16x8_t a, float16_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
 {
-  return vcmpgtq_m_n (a, b, p);
+  return vcmpgtq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32.c
index 7ef00a2003a..9b7aaadfe71 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_m_n_f32.c
@@ -16,7 +16,7 @@ foo (float32x4_t a, float32_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
 {
-  return vcmpgtq_m_n (a, b, p);
+  return vcmpgtq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c
index e536848c2ef..98e152cd999 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f16.c
@@ -15,7 +15,7 @@ foo (float16x8_t a, float16_t b)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b)
 {
-  return vcmpgtq_n (a, b);
+  return vcmpgtq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f16"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c
index 554dd6000c4..5691e2f9d35 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpgtq_n_f32.c
@@ -15,7 +15,7 @@ foo (float32x4_t a, float32_t b)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b)
 {
-  return vcmpgtq_n (a, b);
+  return vcmpgtq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f32"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16.c
index 77f3cc7d72c..42049fd57a4 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f16.c
@@ -16,7 +16,7 @@ foo (float16x8_t a, float16_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
 {
-  return vcmpleq_m_n (a, b, p);
+  return vcmpleq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32.c
index 2080fb2453e..c68bd4e5900 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_m_n_f32.c
@@ -16,7 +16,7 @@ foo (float32x4_t a, float32_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
 {
-  return vcmpleq_m_n (a, b, p);
+  return vcmpleq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c
index 7ea8ff0f322..3fa3c5e0310 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f16.c
@@ -15,7 +15,7 @@ foo (float16x8_t a, float16_t b)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b)
 {
-  return vcmpleq_n (a, b);
+  return vcmpleq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f16"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c
index e332ec3b197..8349de7b68c 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpleq_n_f32.c
@@ -15,7 +15,7 @@ foo (float32x4_t a, float32_t b)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b)
 {
-  return vcmpleq_n (a, b);
+  return vcmpleq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f32"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16.c
index 6f1ab88166f..45d0f51b4d7 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f16.c
@@ -16,7 +16,7 @@ foo (float16x8_t a, float16_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
 {
-  return vcmpltq_m_n (a, b, p);
+  return vcmpltq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32.c
index c9714bec6a1..16e37ccaf8d 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpltq_m_n_f32.c
@@ -16,7 +16,7 @@ foo (float32x4_t a, float32_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
 {
-  return vcmpltq_m_n (a, b, p);
+  return vcmpltq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16.c
index 6d9ed03c0f2..c127b3a68f6 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f16.c
@@ -16,7 +16,7 @@ foo (float16x8_t a, float16_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b, mve_pred16_t p)
 {
-  return vcmpneq_m_n (a, b, p);
+  return vcmpneq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32.c
index 33446bf4850..a8423d45708 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_m_n_f32.c
@@ -16,7 +16,7 @@ foo (float32x4_t a, float32_t b, mve_pred16_t p)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b, mve_pred16_t p)
 {
-  return vcmpneq_m_n (a, b, p);
+  return vcmpneq_m (a, b, p);
 }
 
 /* { dg-final { scan-assembler "vpst" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c
index 4f66335c8f0..e9e2a9c7b04 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c
@@ -15,7 +15,7 @@ foo (float16x8_t a, float16_t b)
 mve_pred16_t
 foo1 (float16x8_t a, float16_t b)
 {
-  return vcmpneq_n (a, b);
+  return vcmpneq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f16"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c
index 363ea0fe17e..eb64b17969c 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c
@@ -15,7 +15,7 @@ foo (float32x4_t a, float32_t b)
 mve_pred16_t
 foo1 (float32x4_t a, float32_t b)
 {
-  return vcmpneq_n (a, b);
+  return vcmpneq (a, b);
 }
 
 /* { dg-final { scan-assembler "vcmp.f32"  }  } */