[ARM][GCC][5/2x]: MVE intrinsics with binary operands.

This patch supports following MVE ACLE intrinsics with binary operands.

vqmovntq_u16, vqmovnbq_u16, vmulltq_poly_p8, vmullbq_poly_p8, vmovntq_u16, vmovnbq_u16, vmlaldavxq_u16, vmlaldavq_u16, vqmovuntq_s16, vqmovunbq_s16, vshlltq_n_u8, vshllbq_n_u8, vorrq_n_u16, vbicq_n_u16, vcmpneq_n_f16, vcmpneq_f16, vcmpltq_n_f16, vcmpltq_f16, vcmpleq_n_f16, vcmpleq_f16, vcmpgtq_n_f16, vcmpgtq_f16, vcmpgeq_n_f16, vcmpgeq_f16, vcmpeqq_n_f16, vcmpeqq_f16, vsubq_f16, vqmovntq_s16, vqmovnbq_s16, vqdmulltq_s16, vqdmulltq_n_s16, vqdmullbq_s16, vqdmullbq_n_s16, vorrq_f16, vornq_f16, vmulq_n_f16, vmulq_f16, vmovntq_s16, vmovnbq_s16, vmlsldavxq_s16, vmlsldavq_s16, vmlaldavxq_s16, vmlaldavq_s16, vminnmvq_f16, vminnmq_f16, vminnmavq_f16, vminnmaq_f16, vmaxnmvq_f16, vmaxnmq_f16, vmaxnmavq_f16, vmaxnmaq_f16, veorq_f16, vcmulq_rot90_f16, vcmulq_rot270_f16, vcmulq_rot180_f16, vcmulq_f16, vcaddq_rot90_f16, vcaddq_rot270_f16, vbicq_f16, vandq_f16, vaddq_n_f16, vabdq_f16, vshlltq_n_s8, vshllbq_n_s8, vorrq_n_s16, vbicq_n_s16, vqmovntq_u32, vqmovnbq_u32, vmulltq_poly_p16, vmullbq_poly_p16, vmovntq_u32, vmovnbq_u32, vmlaldavxq_u32, vmlaldavq_u32, vqmovuntq_s32, vqmovunbq_s32, vshlltq_n_u16, vshllbq_n_u16, vorrq_n_u32, vbicq_n_u32, vcmpneq_n_f32, vcmpneq_f32, vcmpltq_n_f32, vcmpltq_f32, vcmpleq_n_f32, vcmpleq_f32, vcmpgtq_n_f32, vcmpgtq_f32, vcmpgeq_n_f32, vcmpgeq_f32, vcmpeqq_n_f32, vcmpeqq_f32, vsubq_f32, vqmovntq_s32, vqmovnbq_s32, vqdmulltq_s32, vqdmulltq_n_s32, vqdmullbq_s32, vqdmullbq_n_s32, vorrq_f32, vornq_f32, vmulq_n_f32, vmulq_f32, vmovntq_s32, vmovnbq_s32, vmlsldavxq_s32, vmlsldavq_s32, vmlaldavxq_s32, vmlaldavq_s32, vminnmvq_f32, vminnmq_f32, vminnmavq_f32, vminnmaq_f32, vmaxnmvq_f32, vmaxnmq_f32, vmaxnmavq_f32, vmaxnmaq_f32, veorq_f32, vcmulq_rot90_f32, vcmulq_rot270_f32, vcmulq_rot180_f32, vcmulq_f32, vcaddq_rot90_f32, vcaddq_rot270_f32, vbicq_f32, vandq_f32, vaddq_n_f32, vabdq_f32, vshlltq_n_s16, vshllbq_n_s16, vorrq_n_s32, vbicq_n_s32, vrmlaldavhq_u32, vctp8q_m, vctp64q_m, vctp32q_m, vctp16q_m, vaddlvaq_u32, vrmlsldavhxq_s32, vrmlsldavhq_s32, vrmlaldavhxq_s32, vrmlaldavhq_s32, vcvttq_f16_f32, vcvtbq_f16_f32, vaddlvaq_s32.

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

The above intrinsics are defined using the already defined builtin qualifiers BINOP_NONE_NONE_IMM, BINOP_NONE_NONE_NONE, BINOP_UNONE_NONE_NONE, BINOP_UNONE_UNONE_IMM, BINOP_UNONE_UNONE_NONE, BINOP_UNONE_UNONE_UNONE.

2020-03-17  Andre Vieira  <andre.simoesdiasvieira@arm.com>
            Mihail Ionescu  <mihail.ionescu@arm.com>
            Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

	* config/arm/arm_mve.h (vqmovntq_u16): Define macro.
	(vqmovnbq_u16): Likewise.
	(vmulltq_poly_p8): Likewise.
	(vmullbq_poly_p8): Likewise.
	(vmovntq_u16): Likewise.
	(vmovnbq_u16): Likewise.
	(vmlaldavxq_u16): Likewise.
	(vmlaldavq_u16): Likewise.
	(vqmovuntq_s16): Likewise.
	(vqmovunbq_s16): Likewise.
	(vshlltq_n_u8): Likewise.
	(vshllbq_n_u8): Likewise.
	(vorrq_n_u16): Likewise.
	(vbicq_n_u16): Likewise.
	(vcmpneq_n_f16): Likewise.
	(vcmpneq_f16): Likewise.
	(vcmpltq_n_f16): Likewise.
	(vcmpltq_f16): Likewise.
	(vcmpleq_n_f16): Likewise.
	(vcmpleq_f16): Likewise.
	(vcmpgtq_n_f16): Likewise.
	(vcmpgtq_f16): Likewise.
	(vcmpgeq_n_f16): Likewise.
	(vcmpgeq_f16): Likewise.
	(vcmpeqq_n_f16): Likewise.
	(vcmpeqq_f16): Likewise.
	(vsubq_f16): Likewise.
	(vqmovntq_s16): Likewise.
	(vqmovnbq_s16): Likewise.
	(vqdmulltq_s16): Likewise.
	(vqdmulltq_n_s16): Likewise.
	(vqdmullbq_s16): Likewise.
	(vqdmullbq_n_s16): Likewise.
	(vorrq_f16): Likewise.
	(vornq_f16): Likewise.
	(vmulq_n_f16): Likewise.
	(vmulq_f16): Likewise.
	(vmovntq_s16): Likewise.
	(vmovnbq_s16): Likewise.
	(vmlsldavxq_s16): Likewise.
	(vmlsldavq_s16): Likewise.
	(vmlaldavxq_s16): Likewise.
	(vmlaldavq_s16): Likewise.
	(vminnmvq_f16): Likewise.
	(vminnmq_f16): Likewise.
	(vminnmavq_f16): Likewise.
	(vminnmaq_f16): Likewise.
	(vmaxnmvq_f16): Likewise.
	(vmaxnmq_f16): Likewise.
	(vmaxnmavq_f16): Likewise.
	(vmaxnmaq_f16): Likewise.
	(veorq_f16): Likewise.
	(vcmulq_rot90_f16): Likewise.
	(vcmulq_rot270_f16): Likewise.
	(vcmulq_rot180_f16): Likewise.
	(vcmulq_f16): Likewise.
	(vcaddq_rot90_f16): Likewise.
	(vcaddq_rot270_f16): Likewise.
	(vbicq_f16): Likewise.
	(vandq_f16): Likewise.
	(vaddq_n_f16): Likewise.
	(vabdq_f16): Likewise.
	(vshlltq_n_s8): Likewise.
	(vshllbq_n_s8): Likewise.
	(vorrq_n_s16): Likewise.
	(vbicq_n_s16): Likewise.
	(vqmovntq_u32): Likewise.
	(vqmovnbq_u32): Likewise.
	(vmulltq_poly_p16): Likewise.
	(vmullbq_poly_p16): Likewise.
	(vmovntq_u32): Likewise.
	(vmovnbq_u32): Likewise.
	(vmlaldavxq_u32): Likewise.
	(vmlaldavq_u32): Likewise.
	(vqmovuntq_s32): Likewise.
	(vqmovunbq_s32): Likewise.
	(vshlltq_n_u16): Likewise.
	(vshllbq_n_u16): Likewise.
	(vorrq_n_u32): Likewise.
	(vbicq_n_u32): Likewise.
	(vcmpneq_n_f32): Likewise.
	(vcmpneq_f32): Likewise.
	(vcmpltq_n_f32): Likewise.
	(vcmpltq_f32): Likewise.
	(vcmpleq_n_f32): Likewise.
	(vcmpleq_f32): Likewise.
	(vcmpgtq_n_f32): Likewise.
	(vcmpgtq_f32): Likewise.
	(vcmpgeq_n_f32): Likewise.
	(vcmpgeq_f32): Likewise.
	(vcmpeqq_n_f32): Likewise.
	(vcmpeqq_f32): Likewise.
	(vsubq_f32): Likewise.
	(vqmovntq_s32): Likewise.
	(vqmovnbq_s32): Likewise.
	(vqdmulltq_s32): Likewise.
	(vqdmulltq_n_s32): Likewise.
	(vqdmullbq_s32): Likewise.
	(vqdmullbq_n_s32): Likewise.
	(vorrq_f32): Likewise.
	(vornq_f32): Likewise.
	(vmulq_n_f32): Likewise.
	(vmulq_f32): Likewise.
	(vmovntq_s32): Likewise.
	(vmovnbq_s32): Likewise.
	(vmlsldavxq_s32): Likewise.
	(vmlsldavq_s32): Likewise.
	(vmlaldavxq_s32): Likewise.
	(vmlaldavq_s32): Likewise.
	(vminnmvq_f32): Likewise.
	(vminnmq_f32): Likewise.
	(vminnmavq_f32): Likewise.
	(vminnmaq_f32): Likewise.
	(vmaxnmvq_f32): Likewise.
	(vmaxnmq_f32): Likewise.
	(vmaxnmavq_f32): Likewise.
	(vmaxnmaq_f32): Likewise.
	(veorq_f32): Likewise.
	(vcmulq_rot90_f32): Likewise.
	(vcmulq_rot270_f32): Likewise.
	(vcmulq_rot180_f32): Likewise.
	(vcmulq_f32): Likewise.
	(vcaddq_rot90_f32): Likewise.
	(vcaddq_rot270_f32): Likewise.
	(vbicq_f32): Likewise.
	(vandq_f32): Likewise.
	(vaddq_n_f32): Likewise.
	(vabdq_f32): Likewise.
	(vshlltq_n_s16): Likewise.
	(vshllbq_n_s16): Likewise.
	(vorrq_n_s32): Likewise.
	(vbicq_n_s32): Likewise.
	(vrmlaldavhq_u32): Likewise.
	(vctp8q_m): Likewise.
	(vctp64q_m): Likewise.
	(vctp32q_m): Likewise.
	(vctp16q_m): Likewise.
	(vaddlvaq_u32): Likewise.
	(vrmlsldavhxq_s32): Likewise.
	(vrmlsldavhq_s32): Likewise.
	(vrmlaldavhxq_s32): Likewise.
	(vrmlaldavhq_s32): Likewise.
	(vcvttq_f16_f32): Likewise.
	(vcvtbq_f16_f32): Likewise.
	(vaddlvaq_s32): Likewise.
	(__arm_vqmovntq_u16): Define intrinsic.
	(__arm_vqmovnbq_u16): Likewise.
	(__arm_vmulltq_poly_p8): Likewise.
	(__arm_vmullbq_poly_p8): Likewise.
	(__arm_vmovntq_u16): Likewise.
	(__arm_vmovnbq_u16): Likewise.
	(__arm_vmlaldavxq_u16): Likewise.
	(__arm_vmlaldavq_u16): Likewise.
	(__arm_vqmovuntq_s16): Likewise.
	(__arm_vqmovunbq_s16): Likewise.
	(__arm_vshlltq_n_u8): Likewise.
	(__arm_vshllbq_n_u8): Likewise.
	(__arm_vorrq_n_u16): Likewise.
	(__arm_vbicq_n_u16): Likewise.
	(__arm_vcmpneq_n_f16): Likewise.
	(__arm_vcmpneq_f16): Likewise.
	(__arm_vcmpltq_n_f16): Likewise.
	(__arm_vcmpltq_f16): Likewise.
	(__arm_vcmpleq_n_f16): Likewise.
	(__arm_vcmpleq_f16): Likewise.
	(__arm_vcmpgtq_n_f16): Likewise.
	(__arm_vcmpgtq_f16): Likewise.
	(__arm_vcmpgeq_n_f16): Likewise.
	(__arm_vcmpgeq_f16): Likewise.
	(__arm_vcmpeqq_n_f16): Likewise.
	(__arm_vcmpeqq_f16): Likewise.
	(__arm_vsubq_f16): Likewise.
	(__arm_vqmovntq_s16): Likewise.
	(__arm_vqmovnbq_s16): Likewise.
	(__arm_vqdmulltq_s16): Likewise.
	(__arm_vqdmulltq_n_s16): Likewise.
	(__arm_vqdmullbq_s16): Likewise.
	(__arm_vqdmullbq_n_s16): Likewise.
	(__arm_vorrq_f16): Likewise.
	(__arm_vornq_f16): Likewise.
	(__arm_vmulq_n_f16): Likewise.
	(__arm_vmulq_f16): Likewise.
	(__arm_vmovntq_s16): Likewise.
	(__arm_vmovnbq_s16): Likewise.
	(__arm_vmlsldavxq_s16): Likewise.
	(__arm_vmlsldavq_s16): Likewise.
	(__arm_vmlaldavxq_s16): Likewise.
	(__arm_vmlaldavq_s16): Likewise.
	(__arm_vminnmvq_f16): Likewise.
	(__arm_vminnmq_f16): Likewise.
	(__arm_vminnmavq_f16): Likewise.
	(__arm_vminnmaq_f16): Likewise.
	(__arm_vmaxnmvq_f16): Likewise.
	(__arm_vmaxnmq_f16): Likewise.
	(__arm_vmaxnmavq_f16): Likewise.
	(__arm_vmaxnmaq_f16): Likewise.
	(__arm_veorq_f16): Likewise.
	(__arm_vcmulq_rot90_f16): Likewise.
	(__arm_vcmulq_rot270_f16): Likewise.
	(__arm_vcmulq_rot180_f16): Likewise.
	(__arm_vcmulq_f16): Likewise.
	(__arm_vcaddq_rot90_f16): Likewise.
	(__arm_vcaddq_rot270_f16): Likewise.
	(__arm_vbicq_f16): Likewise.
	(__arm_vandq_f16): Likewise.
	(__arm_vaddq_n_f16): Likewise.
	(__arm_vabdq_f16): Likewise.
	(__arm_vshlltq_n_s8): Likewise.
	(__arm_vshllbq_n_s8): Likewise.
	(__arm_vorrq_n_s16): Likewise.
	(__arm_vbicq_n_s16): Likewise.
	(__arm_vqmovntq_u32): Likewise.
	(__arm_vqmovnbq_u32): Likewise.
	(__arm_vmulltq_poly_p16): Likewise.
	(__arm_vmullbq_poly_p16): Likewise.
	(__arm_vmovntq_u32): Likewise.
	(__arm_vmovnbq_u32): Likewise.
	(__arm_vmlaldavxq_u32): Likewise.
	(__arm_vmlaldavq_u32): Likewise.
	(__arm_vqmovuntq_s32): Likewise.
	(__arm_vqmovunbq_s32): Likewise.
	(__arm_vshlltq_n_u16): Likewise.
	(__arm_vshllbq_n_u16): Likewise.
	(__arm_vorrq_n_u32): Likewise.
	(__arm_vbicq_n_u32): Likewise.
	(__arm_vcmpneq_n_f32): Likewise.
	(__arm_vcmpneq_f32): Likewise.
	(__arm_vcmpltq_n_f32): Likewise.
	(__arm_vcmpltq_f32): Likewise.
	(__arm_vcmpleq_n_f32): Likewise.
	(__arm_vcmpleq_f32): Likewise.
	(__arm_vcmpgtq_n_f32): Likewise.
	(__arm_vcmpgtq_f32): Likewise.
	(__arm_vcmpgeq_n_f32): Likewise.
	(__arm_vcmpgeq_f32): Likewise.
	(__arm_vcmpeqq_n_f32): Likewise.
	(__arm_vcmpeqq_f32): Likewise.
	(__arm_vsubq_f32): Likewise.
	(__arm_vqmovntq_s32): Likewise.
	(__arm_vqmovnbq_s32): Likewise.
	(__arm_vqdmulltq_s32): Likewise.
	(__arm_vqdmulltq_n_s32): Likewise.
	(__arm_vqdmullbq_s32): Likewise.
	(__arm_vqdmullbq_n_s32): Likewise.
	(__arm_vorrq_f32): Likewise.
	(__arm_vornq_f32): Likewise.
	(__arm_vmulq_n_f32): Likewise.
	(__arm_vmulq_f32): Likewise.
	(__arm_vmovntq_s32): Likewise.
	(__arm_vmovnbq_s32): Likewise.
	(__arm_vmlsldavxq_s32): Likewise.
	(__arm_vmlsldavq_s32): Likewise.
	(__arm_vmlaldavxq_s32): Likewise.
	(__arm_vmlaldavq_s32): Likewise.
	(__arm_vminnmvq_f32): Likewise.
	(__arm_vminnmq_f32): Likewise.
	(__arm_vminnmavq_f32): Likewise.
	(__arm_vminnmaq_f32): Likewise.
	(__arm_vmaxnmvq_f32): Likewise.
	(__arm_vmaxnmq_f32): Likewise.
	(__arm_vmaxnmavq_f32): Likewise.
	(__arm_vmaxnmaq_f32): Likewise.
	(__arm_veorq_f32): Likewise.
	(__arm_vcmulq_rot90_f32): Likewise.
	(__arm_vcmulq_rot270_f32): Likewise.
	(__arm_vcmulq_rot180_f32): Likewise.
	(__arm_vcmulq_f32): Likewise.
	(__arm_vcaddq_rot90_f32): Likewise.
	(__arm_vcaddq_rot270_f32): Likewise.
	(__arm_vbicq_f32): Likewise.
	(__arm_vandq_f32): Likewise.
	(__arm_vaddq_n_f32): Likewise.
	(__arm_vabdq_f32): Likewise.
	(__arm_vshlltq_n_s16): Likewise.
	(__arm_vshllbq_n_s16): Likewise.
	(__arm_vorrq_n_s32): Likewise.
	(__arm_vbicq_n_s32): Likewise.
	(__arm_vrmlaldavhq_u32): Likewise.
	(__arm_vctp8q_m): Likewise.
	(__arm_vctp64q_m): Likewise.
	(__arm_vctp32q_m): Likewise.
	(__arm_vctp16q_m): Likewise.
	(__arm_vaddlvaq_u32): Likewise.
	(__arm_vrmlsldavhxq_s32): Likewise.
	(__arm_vrmlsldavhq_s32): Likewise.
	(__arm_vrmlaldavhxq_s32): Likewise.
	(__arm_vrmlaldavhq_s32): Likewise.
	(__arm_vcvttq_f16_f32): Likewise.
	(__arm_vcvtbq_f16_f32): Likewise.
	(__arm_vaddlvaq_s32): Likewise.
	(vst4q): Define polymorphic variant.
	(vrndxq): Likewise.
	(vrndq): Likewise.
	(vrndpq): Likewise.
	(vrndnq): Likewise.
	(vrndmq): Likewise.
	(vrndaq): Likewise.
	(vrev64q): Likewise.
	(vnegq): Likewise.
	(vdupq_n): Likewise.
	(vabsq): Likewise.
	(vrev32q): Likewise.
	(vcvtbq_f32): Likewise.
	(vcvttq_f32): Likewise.
	(vcvtq): Likewise.
	(vsubq_n): Likewise.
	(vbrsrq_n): Likewise.
	(vcvtq_n): Likewise.
	(vsubq): Likewise.
	(vorrq): Likewise.
	(vabdq): Likewise.
	(vaddq_n): Likewise.
	(vandq): Likewise.
	(vbicq): Likewise.
	(vornq): Likewise.
	(vmulq_n): Likewise.
	(vmulq): Likewise.
	(vcaddq_rot270): Likewise.
	(vcmpeqq_n): Likewise.
	(vcmpeqq): Likewise.
	(vcaddq_rot90): Likewise.
	(vcmpgeq_n): Likewise.
	(vcmpgeq): Likewise.
	(vcmpgtq_n): Likewise.
	(vcmpgtq): Likewise.
	(vcmpgtq): Likewise.
	(vcmpleq_n): Likewise.
	(vcmpleq_n): Likewise.
	(vcmpleq): Likewise.
	(vcmpleq): Likewise.
	(vcmpltq_n): Likewise.
	(vcmpltq_n): Likewise.
	(vcmpltq): Likewise.
	(vcmpltq): Likewise.
	(vcmpneq_n): Likewise.
	(vcmpneq_n): Likewise.
	(vcmpneq): Likewise.
	(vcmpneq): Likewise.
	(vcmulq): Likewise.
	(vcmulq): Likewise.
	(vcmulq_rot180): Likewise.
	(vcmulq_rot180): Likewise.
	(vcmulq_rot270): Likewise.
	(vcmulq_rot270): Likewise.
	(vcmulq_rot90): Likewise.
	(vcmulq_rot90): Likewise.
	(veorq): Likewise.
	(veorq): Likewise.
	(vmaxnmaq): Likewise.
	(vmaxnmaq): Likewise.
	(vmaxnmavq): Likewise.
	(vmaxnmavq): Likewise.
	(vmaxnmq): Likewise.
	(vmaxnmq): Likewise.
	(vmaxnmvq): Likewise.
	(vmaxnmvq): Likewise.
	(vminnmaq): Likewise.
	(vminnmaq): Likewise.
	(vminnmavq): Likewise.
	(vminnmavq): Likewise.
	(vminnmq): Likewise.
	(vminnmq): Likewise.
	(vminnmvq): Likewise.
	(vminnmvq): Likewise.
	(vbicq_n): Likewise.
	(vqmovntq): Likewise.
	(vqmovntq): Likewise.
	(vqmovnbq): Likewise.
	(vqmovnbq): Likewise.
	(vmulltq_poly): Likewise.
	(vmulltq_poly): Likewise.
	(vmullbq_poly): Likewise.
	(vmullbq_poly): Likewise.
	(vmovntq): Likewise.
	(vmovntq): Likewise.
	(vmovnbq): Likewise.
	(vmovnbq): Likewise.
	(vmlaldavxq): Likewise.
	(vmlaldavxq): Likewise.
	(vqmovuntq): Likewise.
	(vqmovuntq): Likewise.
	(vshlltq_n): Likewise.
	(vshlltq_n): Likewise.
	(vshllbq_n): Likewise.
	(vshllbq_n): Likewise.
	(vorrq_n): Likewise.
	(vorrq_n): Likewise.
	(vmlaldavq): Likewise.
	(vmlaldavq): Likewise.
	(vqmovunbq): Likewise.
	(vqmovunbq): Likewise.
	(vqdmulltq_n): Likewise.
	(vqdmulltq_n): Likewise.
	(vqdmulltq): Likewise.
	(vqdmulltq): Likewise.
	(vqdmullbq_n): Likewise.
	(vqdmullbq_n): Likewise.
	(vqdmullbq): Likewise.
	(vqdmullbq): Likewise.
	(vaddlvaq): Likewise.
	(vaddlvaq): Likewise.
	(vrmlaldavhq): Likewise.
	(vrmlaldavhq): Likewise.
	(vrmlaldavhxq): Likewise.
	(vrmlaldavhxq): Likewise.
	(vrmlsldavhq): Likewise.
	(vrmlsldavhq): Likewise.
	(vrmlsldavhxq): Likewise.
	(vrmlsldavhxq): Likewise.
	(vmlsldavxq): Likewise.
	(vmlsldavxq): Likewise.
	(vmlsldavq): Likewise.
	(vmlsldavq): Likewise.
	* config/arm/arm_mve_builtins.def (BINOP_NONE_NONE_IMM): Use it.
	(BINOP_NONE_NONE_NONE): Likewise.
	(BINOP_UNONE_NONE_NONE): Likewise.
	(BINOP_UNONE_UNONE_IMM): Likewise.
	(BINOP_UNONE_UNONE_NONE): Likewise.
	(BINOP_UNONE_UNONE_UNONE): Likewise.
	* config/arm/mve.md (mve_vabdq_f<mode>): Define RTL pattern.
	(mve_vaddlvaq_<supf>v4si): Likewise.
	(mve_vaddq_n_f<mode>): Likewise.
	(mve_vandq_f<mode>): Likewise.
	(mve_vbicq_f<mode>): Likewise.
	(mve_vbicq_n_<supf><mode>): Likewise.
	(mve_vcaddq_rot270_f<mode>): Likewise.
	(mve_vcaddq_rot90_f<mode>): Likewise.
	(mve_vcmpeqq_f<mode>): Likewise.
	(mve_vcmpeqq_n_f<mode>): Likewise.
	(mve_vcmpgeq_f<mode>): Likewise.
	(mve_vcmpgeq_n_f<mode>): Likewise.
	(mve_vcmpgtq_f<mode>): Likewise.
	(mve_vcmpgtq_n_f<mode>): Likewise.
	(mve_vcmpleq_f<mode>): Likewise.
	(mve_vcmpleq_n_f<mode>): Likewise.
	(mve_vcmpltq_f<mode>): Likewise.
	(mve_vcmpltq_n_f<mode>): Likewise.
	(mve_vcmpneq_f<mode>): Likewise.
	(mve_vcmpneq_n_f<mode>): Likewise.
	(mve_vcmulq_f<mode>): Likewise.
	(mve_vcmulq_rot180_f<mode>): Likewise.
	(mve_vcmulq_rot270_f<mode>): Likewise.
	(mve_vcmulq_rot90_f<mode>): Likewise.
	(mve_vctp<mode1>q_mhi): Likewise.
	(mve_vcvtbq_f16_f32v8hf): Likewise.
	(mve_vcvttq_f16_f32v8hf): Likewise.
	(mve_veorq_f<mode>): Likewise.
	(mve_vmaxnmaq_f<mode>): Likewise.
	(mve_vmaxnmavq_f<mode>): Likewise.
	(mve_vmaxnmq_f<mode>): Likewise.
	(mve_vmaxnmvq_f<mode>): Likewise.
	(mve_vminnmaq_f<mode>): Likewise.
	(mve_vminnmavq_f<mode>): Likewise.
	(mve_vminnmq_f<mode>): Likewise.
	(mve_vminnmvq_f<mode>): Likewise.
	(mve_vmlaldavq_<supf><mode>): Likewise.
	(mve_vmlaldavxq_<supf><mode>): Likewise.
	(mve_vmlsldavq_s<mode>): Likewise.
	(mve_vmlsldavxq_s<mode>): Likewise.
	(mve_vmovnbq_<supf><mode>): Likewise.
	(mve_vmovntq_<supf><mode>): Likewise.
	(mve_vmulq_f<mode>): Likewise.
	(mve_vmulq_n_f<mode>): Likewise.
	(mve_vornq_f<mode>): Likewise.
	(mve_vorrq_f<mode>): Likewise.
	(mve_vorrq_n_<supf><mode>): Likewise.
	(mve_vqdmullbq_n_s<mode>): Likewise.
	(mve_vqdmullbq_s<mode>): Likewise.
	(mve_vqdmulltq_n_s<mode>): Likewise.
	(mve_vqdmulltq_s<mode>): Likewise.
	(mve_vqmovnbq_<supf><mode>): Likewise.
	(mve_vqmovntq_<supf><mode>): Likewise.
	(mve_vqmovunbq_s<mode>): Likewise.
	(mve_vqmovuntq_s<mode>): Likewise.
	(mve_vrmlaldavhxq_sv4si): Likewise.
	(mve_vrmlsldavhq_sv4si): Likewise.
	(mve_vrmlsldavhxq_sv4si): Likewise.
	(mve_vshllbq_n_<supf><mode>): Likewise.
	(mve_vshlltq_n_<supf><mode>): Likewise.
	(mve_vsubq_f<mode>): Likewise.
	(mve_vmulltq_poly_p<mode>): Likewise.
	(mve_vmullbq_poly_p<mode>): Likewise.
	(mve_vrmlaldavhq_<supf>v4si): Likewise.

gcc/testsuite/ChangeLog:

2020-03-17  Andre Vieira  <andre.simoesdiasvieira@arm.com>
            Mihail Ionescu  <mihail.ionescu@arm.com>
            Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

	* gcc.target/arm/mve/intrinsics/vabdq_f16.c: New test.
	* gcc.target/arm/mve/intrinsics/vabdq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddlvaq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddlvaq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddq_n_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vaddq_n_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vandq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vandq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vbicq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vbicq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vbicq_n_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vbicq_n_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vbicq_n_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vbicq_n_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcaddq_rot270_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcaddq_rot270_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcaddq_rot90_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcaddq_rot90_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpeqq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpeqq_f32.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_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_n_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgeq_n_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgtq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpgtq_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_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpleq_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_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_n_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpltq_n_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_n_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmpneq_n_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_rot180_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_rot180_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_rot270_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_rot270_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_rot90_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcmulq_rot90_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vctp16q_m.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vctp32q_m.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vctp64q_m.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vctp8q_m.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcvtbq_f16_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vcvttq_f16_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/veorq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/veorq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmaq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmaq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmavq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmavq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmvq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmaxnmvq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmaq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmaq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmavq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmavq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmvq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vminnmvq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavxq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavxq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavxq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlaldavxq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlsldavq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlsldavq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlsldavxq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmlsldavxq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovnbq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovnbq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovnbq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovnbq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovntq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovntq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovntq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmovntq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmullbq_poly_p16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmullbq_poly_p8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulltq_poly_p16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulltq_poly_p8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_n_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vmulq_n_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vornq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vornq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vorrq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vorrq_f32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vorrq_n_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vorrq_n_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vorrq_n_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vorrq_n_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmullbq_n_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmullbq_n_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmullbq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmullbq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmulltq_n_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmulltq_n_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmulltq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqdmulltq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovnbq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovnbq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovnbq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovnbq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovntq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovntq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovntq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovntq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovunbq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovunbq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovuntq_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vqmovuntq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vrmlaldavhq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vrmlaldavhq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vrmlaldavhxq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vrmlsldavhq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vrmlsldavhxq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshllbq_n_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshllbq_n_s8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshllbq_n_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshllbq_n_u8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshlltq_n_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshlltq_n_s8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshlltq_n_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vshlltq_n_u8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_f16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vsubq_f32.c: Likewise.

3 files changed, 3413 insertions, 328 deletions

diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index eb81a02d95b..db5e472e819 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -599,6 +599,149 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
 #define vshlq_n_s32(__a,  __imm) __arm_vshlq_n_s32(__a,  __imm)
 #define vrshrq_n_s32(__a,  __imm) __arm_vrshrq_n_s32(__a,  __imm)
 #define vqshlq_n_s32(__a,  __imm) __arm_vqshlq_n_s32(__a,  __imm)
+#define vqmovntq_u16(__a, __b) __arm_vqmovntq_u16(__a, __b)
+#define vqmovnbq_u16(__a, __b) __arm_vqmovnbq_u16(__a, __b)
+#define vmulltq_poly_p8(__a, __b) __arm_vmulltq_poly_p8(__a, __b)
+#define vmullbq_poly_p8(__a, __b) __arm_vmullbq_poly_p8(__a, __b)
+#define vmovntq_u16(__a, __b) __arm_vmovntq_u16(__a, __b)
+#define vmovnbq_u16(__a, __b) __arm_vmovnbq_u16(__a, __b)
+#define vmlaldavq_u16(__a, __b) __arm_vmlaldavq_u16(__a, __b)
+#define vqmovuntq_s16(__a, __b) __arm_vqmovuntq_s16(__a, __b)
+#define vqmovunbq_s16(__a, __b) __arm_vqmovunbq_s16(__a, __b)
+#define vshlltq_n_u8(__a,  __imm) __arm_vshlltq_n_u8(__a,  __imm)
+#define vshllbq_n_u8(__a,  __imm) __arm_vshllbq_n_u8(__a,  __imm)
+#define vorrq_n_u16(__a,  __imm) __arm_vorrq_n_u16(__a,  __imm)
+#define vbicq_n_u16(__a,  __imm) __arm_vbicq_n_u16(__a,  __imm)
+#define vcmpneq_n_f16(__a, __b) __arm_vcmpneq_n_f16(__a, __b)
+#define vcmpneq_f16(__a, __b) __arm_vcmpneq_f16(__a, __b)
+#define vcmpltq_n_f16(__a, __b) __arm_vcmpltq_n_f16(__a, __b)
+#define vcmpltq_f16(__a, __b) __arm_vcmpltq_f16(__a, __b)
+#define vcmpleq_n_f16(__a, __b) __arm_vcmpleq_n_f16(__a, __b)
+#define vcmpleq_f16(__a, __b) __arm_vcmpleq_f16(__a, __b)
+#define vcmpgtq_n_f16(__a, __b) __arm_vcmpgtq_n_f16(__a, __b)
+#define vcmpgtq_f16(__a, __b) __arm_vcmpgtq_f16(__a, __b)
+#define vcmpgeq_n_f16(__a, __b) __arm_vcmpgeq_n_f16(__a, __b)
+#define vcmpgeq_f16(__a, __b) __arm_vcmpgeq_f16(__a, __b)
+#define vcmpeqq_n_f16(__a, __b) __arm_vcmpeqq_n_f16(__a, __b)
+#define vcmpeqq_f16(__a, __b) __arm_vcmpeqq_f16(__a, __b)
+#define vsubq_f16(__a, __b) __arm_vsubq_f16(__a, __b)
+#define vqmovntq_s16(__a, __b) __arm_vqmovntq_s16(__a, __b)
+#define vqmovnbq_s16(__a, __b) __arm_vqmovnbq_s16(__a, __b)
+#define vqdmulltq_s16(__a, __b) __arm_vqdmulltq_s16(__a, __b)
+#define vqdmulltq_n_s16(__a, __b) __arm_vqdmulltq_n_s16(__a, __b)
+#define vqdmullbq_s16(__a, __b) __arm_vqdmullbq_s16(__a, __b)
+#define vqdmullbq_n_s16(__a, __b) __arm_vqdmullbq_n_s16(__a, __b)
+#define vorrq_f16(__a, __b) __arm_vorrq_f16(__a, __b)
+#define vornq_f16(__a, __b) __arm_vornq_f16(__a, __b)
+#define vmulq_n_f16(__a, __b) __arm_vmulq_n_f16(__a, __b)
+#define vmulq_f16(__a, __b) __arm_vmulq_f16(__a, __b)
+#define vmovntq_s16(__a, __b) __arm_vmovntq_s16(__a, __b)
+#define vmovnbq_s16(__a, __b) __arm_vmovnbq_s16(__a, __b)
+#define vmlsldavxq_s16(__a, __b) __arm_vmlsldavxq_s16(__a, __b)
+#define vmlsldavq_s16(__a, __b) __arm_vmlsldavq_s16(__a, __b)
+#define vmlaldavxq_s16(__a, __b) __arm_vmlaldavxq_s16(__a, __b)
+#define vmlaldavq_s16(__a, __b) __arm_vmlaldavq_s16(__a, __b)
+#define vminnmvq_f16(__a, __b) __arm_vminnmvq_f16(__a, __b)
+#define vminnmq_f16(__a, __b) __arm_vminnmq_f16(__a, __b)
+#define vminnmavq_f16(__a, __b) __arm_vminnmavq_f16(__a, __b)
+#define vminnmaq_f16(__a, __b) __arm_vminnmaq_f16(__a, __b)
+#define vmaxnmvq_f16(__a, __b) __arm_vmaxnmvq_f16(__a, __b)
+#define vmaxnmq_f16(__a, __b) __arm_vmaxnmq_f16(__a, __b)
+#define vmaxnmavq_f16(__a, __b) __arm_vmaxnmavq_f16(__a, __b)
+#define vmaxnmaq_f16(__a, __b) __arm_vmaxnmaq_f16(__a, __b)
+#define veorq_f16(__a, __b) __arm_veorq_f16(__a, __b)
+#define vcmulq_rot90_f16(__a, __b) __arm_vcmulq_rot90_f16(__a, __b)
+#define vcmulq_rot270_f16(__a, __b) __arm_vcmulq_rot270_f16(__a, __b)
+#define vcmulq_rot180_f16(__a, __b) __arm_vcmulq_rot180_f16(__a, __b)
+#define vcmulq_f16(__a, __b) __arm_vcmulq_f16(__a, __b)
+#define vcaddq_rot90_f16(__a, __b) __arm_vcaddq_rot90_f16(__a, __b)
+#define vcaddq_rot270_f16(__a, __b) __arm_vcaddq_rot270_f16(__a, __b)
+#define vbicq_f16(__a, __b) __arm_vbicq_f16(__a, __b)
+#define vandq_f16(__a, __b) __arm_vandq_f16(__a, __b)
+#define vaddq_n_f16(__a, __b) __arm_vaddq_n_f16(__a, __b)
+#define vabdq_f16(__a, __b) __arm_vabdq_f16(__a, __b)
+#define vshlltq_n_s8(__a,  __imm) __arm_vshlltq_n_s8(__a,  __imm)
+#define vshllbq_n_s8(__a,  __imm) __arm_vshllbq_n_s8(__a,  __imm)
+#define vorrq_n_s16(__a,  __imm) __arm_vorrq_n_s16(__a,  __imm)
+#define vbicq_n_s16(__a,  __imm) __arm_vbicq_n_s16(__a,  __imm)
+#define vqmovntq_u32(__a, __b) __arm_vqmovntq_u32(__a, __b)
+#define vqmovnbq_u32(__a, __b) __arm_vqmovnbq_u32(__a, __b)
+#define vmulltq_poly_p16(__a, __b) __arm_vmulltq_poly_p16(__a, __b)
+#define vmullbq_poly_p16(__a, __b) __arm_vmullbq_poly_p16(__a, __b)
+#define vmovntq_u32(__a, __b) __arm_vmovntq_u32(__a, __b)
+#define vmovnbq_u32(__a, __b) __arm_vmovnbq_u32(__a, __b)
+#define vmlaldavq_u32(__a, __b) __arm_vmlaldavq_u32(__a, __b)
+#define vqmovuntq_s32(__a, __b) __arm_vqmovuntq_s32(__a, __b)
+#define vqmovunbq_s32(__a, __b) __arm_vqmovunbq_s32(__a, __b)
+#define vshlltq_n_u16(__a,  __imm) __arm_vshlltq_n_u16(__a,  __imm)
+#define vshllbq_n_u16(__a,  __imm) __arm_vshllbq_n_u16(__a,  __imm)
+#define vorrq_n_u32(__a,  __imm) __arm_vorrq_n_u32(__a,  __imm)
+#define vbicq_n_u32(__a,  __imm) __arm_vbicq_n_u32(__a,  __imm)
+#define vcmpneq_n_f32(__a, __b) __arm_vcmpneq_n_f32(__a, __b)
+#define vcmpneq_f32(__a, __b) __arm_vcmpneq_f32(__a, __b)
+#define vcmpltq_n_f32(__a, __b) __arm_vcmpltq_n_f32(__a, __b)
+#define vcmpltq_f32(__a, __b) __arm_vcmpltq_f32(__a, __b)
+#define vcmpleq_n_f32(__a, __b) __arm_vcmpleq_n_f32(__a, __b)
+#define vcmpleq_f32(__a, __b) __arm_vcmpleq_f32(__a, __b)
+#define vcmpgtq_n_f32(__a, __b) __arm_vcmpgtq_n_f32(__a, __b)
+#define vcmpgtq_f32(__a, __b) __arm_vcmpgtq_f32(__a, __b)
+#define vcmpgeq_n_f32(__a, __b) __arm_vcmpgeq_n_f32(__a, __b)
+#define vcmpgeq_f32(__a, __b) __arm_vcmpgeq_f32(__a, __b)
+#define vcmpeqq_n_f32(__a, __b) __arm_vcmpeqq_n_f32(__a, __b)
+#define vcmpeqq_f32(__a, __b) __arm_vcmpeqq_f32(__a, __b)
+#define vsubq_f32(__a, __b) __arm_vsubq_f32(__a, __b)
+#define vqmovntq_s32(__a, __b) __arm_vqmovntq_s32(__a, __b)
+#define vqmovnbq_s32(__a, __b) __arm_vqmovnbq_s32(__a, __b)
+#define vqdmulltq_s32(__a, __b) __arm_vqdmulltq_s32(__a, __b)
+#define vqdmulltq_n_s32(__a, __b) __arm_vqdmulltq_n_s32(__a, __b)
+#define vqdmullbq_s32(__a, __b) __arm_vqdmullbq_s32(__a, __b)
+#define vqdmullbq_n_s32(__a, __b) __arm_vqdmullbq_n_s32(__a, __b)
+#define vorrq_f32(__a, __b) __arm_vorrq_f32(__a, __b)
+#define vornq_f32(__a, __b) __arm_vornq_f32(__a, __b)
+#define vmulq_n_f32(__a, __b) __arm_vmulq_n_f32(__a, __b)
+#define vmulq_f32(__a, __b) __arm_vmulq_f32(__a, __b)
+#define vmovntq_s32(__a, __b) __arm_vmovntq_s32(__a, __b)
+#define vmovnbq_s32(__a, __b) __arm_vmovnbq_s32(__a, __b)
+#define vmlsldavxq_s32(__a, __b) __arm_vmlsldavxq_s32(__a, __b)
+#define vmlsldavq_s32(__a, __b) __arm_vmlsldavq_s32(__a, __b)
+#define vmlaldavxq_s32(__a, __b) __arm_vmlaldavxq_s32(__a, __b)
+#define vmlaldavq_s32(__a, __b) __arm_vmlaldavq_s32(__a, __b)
+#define vminnmvq_f32(__a, __b) __arm_vminnmvq_f32(__a, __b)
+#define vminnmq_f32(__a, __b) __arm_vminnmq_f32(__a, __b)
+#define vminnmavq_f32(__a, __b) __arm_vminnmavq_f32(__a, __b)
+#define vminnmaq_f32(__a, __b) __arm_vminnmaq_f32(__a, __b)
+#define vmaxnmvq_f32(__a, __b) __arm_vmaxnmvq_f32(__a, __b)
+#define vmaxnmq_f32(__a, __b) __arm_vmaxnmq_f32(__a, __b)
+#define vmaxnmavq_f32(__a, __b) __arm_vmaxnmavq_f32(__a, __b)
+#define vmaxnmaq_f32(__a, __b) __arm_vmaxnmaq_f32(__a, __b)
+#define veorq_f32(__a, __b) __arm_veorq_f32(__a, __b)
+#define vcmulq_rot90_f32(__a, __b) __arm_vcmulq_rot90_f32(__a, __b)
+#define vcmulq_rot270_f32(__a, __b) __arm_vcmulq_rot270_f32(__a, __b)
+#define vcmulq_rot180_f32(__a, __b) __arm_vcmulq_rot180_f32(__a, __b)
+#define vcmulq_f32(__a, __b) __arm_vcmulq_f32(__a, __b)
+#define vcaddq_rot90_f32(__a, __b) __arm_vcaddq_rot90_f32(__a, __b)
+#define vcaddq_rot270_f32(__a, __b) __arm_vcaddq_rot270_f32(__a, __b)
+#define vbicq_f32(__a, __b) __arm_vbicq_f32(__a, __b)
+#define vandq_f32(__a, __b) __arm_vandq_f32(__a, __b)
+#define vaddq_n_f32(__a, __b) __arm_vaddq_n_f32(__a, __b)
+#define vabdq_f32(__a, __b) __arm_vabdq_f32(__a, __b)
+#define vshlltq_n_s16(__a,  __imm) __arm_vshlltq_n_s16(__a,  __imm)
+#define vshllbq_n_s16(__a,  __imm) __arm_vshllbq_n_s16(__a,  __imm)
+#define vorrq_n_s32(__a,  __imm) __arm_vorrq_n_s32(__a,  __imm)
+#define vbicq_n_s32(__a,  __imm) __arm_vbicq_n_s32(__a,  __imm)
+#define vrmlaldavhq_u32(__a, __b) __arm_vrmlaldavhq_u32(__a, __b)
+#define vctp8q_m(__a, __p) __arm_vctp8q_m(__a, __p)
+#define vctp64q_m(__a, __p) __arm_vctp64q_m(__a, __p)
+#define vctp32q_m(__a, __p) __arm_vctp32q_m(__a, __p)
+#define vctp16q_m(__a, __p) __arm_vctp16q_m(__a, __p)
+#define vaddlvaq_u32(__a, __b) __arm_vaddlvaq_u32(__a, __b)
+#define vrmlsldavhxq_s32(__a, __b) __arm_vrmlsldavhxq_s32(__a, __b)
+#define vrmlsldavhq_s32(__a, __b) __arm_vrmlsldavhq_s32(__a, __b)
+#define vrmlaldavhxq_s32(__a, __b) __arm_vrmlaldavhxq_s32(__a, __b)
+#define vrmlaldavhq_s32(__a, __b) __arm_vrmlaldavhq_s32(__a, __b)
+#define vcvttq_f16_f32(__a, __b) __arm_vcvttq_f16_f32(__a, __b)
+#define vcvtbq_f16_f32(__a, __b) __arm_vcvtbq_f16_f32(__a, __b)
+#define vaddlvaq_s32(__a, __b) __arm_vaddlvaq_s32(__a, __b)
 #endif
 
 __extension__ extern __inline void
@@ -3859,6 +4002,489 @@ __arm_vqshlq_n_s32 (int32x4_t __a, const int __imm)
   return __builtin_mve_vqshlq_n_sv4si (__a, __imm);
 }
 
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_u16 (uint8x16_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vqmovntq_uv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_u16 (uint8x16_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vqmovnbq_uv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
+{
+  return __builtin_mve_vmulltq_poly_pv16qi (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly_p8 (uint8x16_t __a, uint8x16_t __b)
+{
+  return __builtin_mve_vmullbq_poly_pv16qi (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_u16 (uint8x16_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vmovntq_uv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_u16 (uint8x16_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vmovnbq_uv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_u16 (uint16x8_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vmlaldavq_uv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovuntq_s16 (uint8x16_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vqmovuntq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovunbq_s16 (uint8x16_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vqmovunbq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_n_u8 (uint8x16_t __a, const int __imm)
+{
+  return __builtin_mve_vshlltq_n_uv16qi (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_n_u8 (uint8x16_t __a, const int __imm)
+{
+  return __builtin_mve_vshllbq_n_uv16qi (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_n_u16 (uint16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vorrq_n_uv8hi (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_n_u16 (uint16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vbicq_n_uv8hi (__a, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_s16 (int8x16_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vqmovntq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_s16 (int8x16_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vqmovnbq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_s16 (int16x8_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vqdmulltq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_n_s16 (int16x8_t __a, int16_t __b)
+{
+  return __builtin_mve_vqdmulltq_n_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_s16 (int16x8_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vqdmullbq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_n_s16 (int16x8_t __a, int16_t __b)
+{
+  return __builtin_mve_vqdmullbq_n_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_s16 (int8x16_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vmovntq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_s16 (int8x16_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vmovnbq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavxq_s16 (int16x8_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vmlsldavxq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavq_s16 (int16x8_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vmlsldavq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavxq_s16 (int16x8_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vmlaldavxq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_s16 (int16x8_t __a, int16x8_t __b)
+{
+  return __builtin_mve_vmlaldavq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_n_s8 (int8x16_t __a, const int __imm)
+{
+  return __builtin_mve_vshlltq_n_sv16qi (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_n_s8 (int8x16_t __a, const int __imm)
+{
+  return __builtin_mve_vshllbq_n_sv16qi (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_n_s16 (int16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vorrq_n_sv8hi (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_n_s16 (int16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vbicq_n_sv8hi (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_u32 (uint16x8_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vqmovntq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_u32 (uint16x8_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vqmovnbq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly_p16 (uint16x8_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vmulltq_poly_pv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly_p16 (uint16x8_t __a, uint16x8_t __b)
+{
+  return __builtin_mve_vmullbq_poly_pv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_u32 (uint16x8_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vmovntq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_u32 (uint16x8_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vmovnbq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_u32 (uint32x4_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vmlaldavq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovuntq_s32 (uint16x8_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vqmovuntq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovunbq_s32 (uint16x8_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vqmovunbq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_n_u16 (uint16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vshlltq_n_uv8hi (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_n_u16 (uint16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vshllbq_n_uv8hi (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_n_u32 (uint32x4_t __a, const int __imm)
+{
+  return __builtin_mve_vorrq_n_uv4si (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_n_u32 (uint32x4_t __a, const int __imm)
+{
+  return __builtin_mve_vbicq_n_uv4si (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_s32 (int16x8_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vqmovntq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_s32 (int16x8_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vqmovnbq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vqdmulltq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_n_s32 (int32x4_t __a, int32_t __b)
+{
+  return __builtin_mve_vqdmulltq_n_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vqdmullbq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_n_s32 (int32x4_t __a, int32_t __b)
+{
+  return __builtin_mve_vqdmullbq_n_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_s32 (int16x8_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vmovntq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_s32 (int16x8_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vmovnbq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavxq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vmlsldavxq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vmlsldavq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavxq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vmlaldavxq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vmlaldavq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_n_s16 (int16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vshlltq_n_sv8hi (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_n_s16 (int16x8_t __a, const int __imm)
+{
+  return __builtin_mve_vshllbq_n_sv8hi (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_n_s32 (int32x4_t __a, const int __imm)
+{
+  return __builtin_mve_vorrq_n_sv4si (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_n_s32 (int32x4_t __a, const int __imm)
+{
+  return __builtin_mve_vbicq_n_sv4si (__a, __imm);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq_u32 (uint32x4_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vrmlaldavhq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vctp8q_m (uint32_t __a, mve_pred16_t __p)
+{
+  return __builtin_mve_vctp8q_mhi (__a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vctp64q_m (uint32_t __a, mve_pred16_t __p)
+{
+  return __builtin_mve_vctp64q_mhi (__a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vctp32q_m (uint32_t __a, mve_pred16_t __p)
+{
+  return __builtin_mve_vctp32q_mhi (__a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vctp16q_m (uint32_t __a, mve_pred16_t __p)
+{
+  return __builtin_mve_vctp16q_mhi (__a, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq_u32 (uint64_t __a, uint32x4_t __b)
+{
+  return __builtin_mve_vaddlvaq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhxq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vrmlsldavhxq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vrmlsldavhq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhxq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vrmlaldavhxq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq_s32 (int32x4_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vrmlaldavhq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq_s32 (int64_t __a, int32x4_t __b)
+{
+  return __builtin_mve_vaddlvaq_sv4si (__a, __b);
+}
+
 #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point.  */
 
 __extension__ extern __inline void
@@ -4145,8 +4771,8 @@ __arm_vcvtaq_u32_f32 (float32x4_t __a)
   return __builtin_mve_vcvtaq_uv4si (__a);
 }
 
- __extension__ extern __inline int16x8_t
- __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 __arm_vcvtaq_s16_f16 (float16x8_t __a)
 {
   return __builtin_mve_vcvtaq_sv8hi (__a);
@@ -4299,6 +4925,524 @@ __arm_vcvtq_n_u32_f32 (float32x4_t __a, const int __imm6)
   return __builtin_mve_vcvtq_n_from_f_uv4si (__a, __imm6);
 }
 
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vcmpneq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmpneq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vcmpltq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmpltq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vcmpleq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmpleq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vcmpgtq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmpgtq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vcmpgeq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmpgeq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vcmpeqq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmpeqq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vsubq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vorrq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vornq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vmulq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vmulq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq_f16 (float16_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vminnmvq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vminnmq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq_f16 (float16_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vminnmavq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vminnmaq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq_f16 (float16_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vmaxnmvq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vmaxnmq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq_f16 (float16_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vmaxnmavq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vmaxnmaq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_veorq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmulq_rot90_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmulq_rot270_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmulq_rot180_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcmulq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcaddq_rot90_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vcaddq_rot270_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vbicq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vandq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_n_f16 (float16x8_t __a, float16_t __b)
+{
+  return __builtin_mve_vaddq_n_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_mve_vabdq_fv8hf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vcmpneq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmpneq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vcmpltq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmpltq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vcmpleq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmpleq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vcmpgtq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmpgtq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vcmpgeq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmpgeq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vcmpeqq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmpeqq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vsubq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vorrq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vornq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vmulq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vmulq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq_f32 (float32_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vminnmvq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vminnmq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq_f32 (float32_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vminnmavq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vminnmaq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq_f32 (float32_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vmaxnmvq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vmaxnmq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq_f32 (float32_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vmaxnmavq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vmaxnmaq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_veorq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmulq_rot90_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmulq_rot270_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmulq_rot180_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcmulq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcaddq_rot90_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcaddq_rot270_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vbicq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vandq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_n_f32 (float32x4_t __a, float32_t __b)
+{
+  return __builtin_mve_vaddq_n_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vabdq_fv4sf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvttq_f16_f32 (float16x8_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcvttq_f16_f32v8hf (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtbq_f16_f32 (float16x8_t __a, float32x4_t __b)
+{
+  return __builtin_mve_vcvtbq_f16_f32v8hf (__a, __b);
+}
+
 #endif
 
 enum {
@@ -4567,6 +5711,12 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_float16x8_t]: __arm_vnegq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
   int (*)[__ARM_mve_type_float32x4_t]: __arm_vnegq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
 
+#define vdupq_n(p0) __arm_vdupq_n(p0)
+#define __arm_vdupq_n(p0) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_float16x8_t]: __arm_vdupq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t]: __arm_vdupq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
 #define vabsq(p0) __arm_vabsq(p0)
 #define __arm_vabsq(p0) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -4677,13 +5827,15 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vsubq_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_vsubq_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_vsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vbrsrq(p0,p1) __arm_vbrsrq(p0,p1)
-#define __arm_vbrsrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_float16x8_t]: __arm_vbrsrq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), p1), \
-  int (*)[__ARM_mve_type_float32x4_t]: __arm_vbrsrq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), p1));})
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vsubq_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_vsubq_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_vsubq_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_vsubq_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_vsubq_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_vsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vsubq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vsubq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
 
 #define vshlq(p0,p1) __arm_vshlq(p0,p1)
 #define __arm_vshlq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
@@ -4714,6 +5866,370 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_n_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_n_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
 
+#define vorrq(p0,p1) __arm_vorrq(p0,p1)
+#define __arm_vorrq(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_vorrq_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_vorrq_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_vorrq_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_vorrq_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_vorrq_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_vorrq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vorrq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vorrq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vabdq(p0,p1) __arm_vabdq(p0,p1)
+#define __arm_vabdq(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_vabdq_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_vabdq_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_vabdq_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_vabdq_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_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)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vaddq(p0,p1) __arm_vaddq(p0,p1)
+#define __arm_vaddq(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_vaddq_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_vaddq_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_vaddq_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_vaddq_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_vaddq_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_vaddq_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_vaddq_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_vaddq_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_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vaddq_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_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vaddq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vaddq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vandq(p0,p1) __arm_vandq(p0,p1)
+#define __arm_vandq(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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vandq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vandq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vbicq(p0,p1) __arm_vbicq(p0,p1)
+#define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vbicq_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_vbicq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbicq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbicq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vornq(p0,p1) __arm_vornq(p0,p1)
+#define __arm_vornq(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_vornq_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_vornq_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_vornq_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_vornq_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_vornq_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_vornq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vornq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vornq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmulq_n(p0,p1) __arm_vmulq_n(p0,p1)
+#define __arm_vmulq_n(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_int8_t]: __arm_vmulq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vmulq_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_vmulq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vmulq_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_vmulq_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_vmulq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vmulq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vmulq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vmulq(p0,p1) __arm_vmulq(p0,p1)
+#define __arm_vmulq(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_vmulq_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_vmulq_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_vmulq_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_vmulq_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_vmulq_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_vmulq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmulq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmulq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcaddq_rot270(p0,p1) __arm_vcaddq_rot270(p0,p1)
+#define __arm_vcaddq_rot270(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_vcaddq_rot270_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_vcaddq_rot270_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_vcaddq_rot270_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_vcaddq_rot270_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_vcaddq_rot270_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_vcaddq_rot270_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot270_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot270_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpeqq(p0,p1) __arm_vcmpeqq(p0,p1)
+#define __arm_vcmpeqq(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_int8_t]: __arm_vcmpeqq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpeqq_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_vcmpeqq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpeqq_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_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)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpeqq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpeqq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpeqq_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_vcmpeqq_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_vcmpeqq_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_vcmpeqq_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_vcmpeqq_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_vcmpeqq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpeqq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpeqq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcaddq_rot90(p0,p1) __arm_vcaddq_rot90(p0,p1)
+#define __arm_vcaddq_rot90(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_vcaddq_rot90_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_vcaddq_rot90_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_vcaddq_rot90_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_vcaddq_rot90_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_vcaddq_rot90_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_vcaddq_rot90_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot90_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot90_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpgeq_n(p0,p1) __arm_vcmpgeq_n(p0,p1)
+#define __arm_vcmpgeq_n(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_int8_t]: __arm_vcmpgeq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_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_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
+#define __arm_vcmpgeq(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_vcmpgeq_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_vcmpgeq_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_vcmpgeq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpgtq_n(p0,p1) __arm_vcmpgtq_n(p0,p1)
+#define __arm_vcmpgtq_n(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_int8_t]: __arm_vcmpgtq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  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)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgtq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpgtq(p0,p1) __arm_vcmpgtq(p0,p1)
+#define __arm_vcmpgtq(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_vcmpgtq_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_vcmpgtq_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_vcmpgtq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgtq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgtq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmpleq(p0,p1) __arm_vcmpleq(p0,p1)
+#define __arm_vcmpleq(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_vcmpleq_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_vcmpleq_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_vcmpleq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpleq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpleq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpleq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpleq_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_vcmpleq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpleq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpleq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpltq(p0,p1) __arm_vcmpltq(p0,p1)
+#define __arm_vcmpltq(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_vcmpltq_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_vcmpltq_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_vcmpltq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vcmpltq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpltq_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_vcmpltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpltq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpltq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpltq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpltq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
+
+#define vcmpneq(p0,p1) __arm_vcmpneq(p0,p1)
+#define __arm_vcmpneq(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_int8_t]: __arm_vcmpneq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpneq_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_vcmpneq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vcmpneq_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_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)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpneq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpneq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpneq_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_vcmpneq_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_vcmpneq_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_vcmpneq_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_vcmpneq_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_vcmpneq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpneq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpneq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq(p0,p1) __arm_vcmulq(p0,p1)
+#define __arm_vcmulq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq_rot180(p0,p1) __arm_vcmulq_rot180(p0,p1)
+#define __arm_vcmulq_rot180(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot180_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot180_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq_rot270(p0,p1) __arm_vcmulq_rot270(p0,p1)
+#define __arm_vcmulq_rot270(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot270_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot270_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vcmulq_rot90(p0,p1) __arm_vcmulq_rot90(p0,p1)
+#define __arm_vcmulq_rot90(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot90_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define veorq(p0,p1) __arm_veorq(p0,p1)
+#define __arm_veorq(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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
+  int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_veorq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_veorq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmaq(p0,p1) __arm_vmaxnmaq(p0,p1)
+#define __arm_vmaxnmaq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmavq(p0,p1) __arm_vmaxnmavq(p0,p1)
+#define __arm_vmaxnmavq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmq(p0,p1) __arm_vmaxnmq(p0,p1)
+#define __arm_vmaxnmq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmvq(p0,p1) __arm_vmaxnmvq(p0,p1)
+#define __arm_vmaxnmvq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vmaxnmvq(p0,p1) __arm_vmaxnmvq(p0,p1)
+#define __arm_vmaxnmvq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vminnmaq(p0,p1) __arm_vminnmaq(p0,p1)
+#define __arm_vminnmaq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vminnmavq(p0,p1) __arm_vminnmavq(p0,p1)
+#define __arm_vminnmavq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vbrsrq(p0,p1) __arm_vbrsrq(p0,p1)
+#define __arm_vbrsrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vbrsrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vbrsrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vbrsrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vbrsrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbrsrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbrsrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1), \
+  int (*)[__ARM_mve_type_float16x8_t]: __arm_vbrsrq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), p1), \
+  int (*)[__ARM_mve_type_float32x4_t]: __arm_vbrsrq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), p1));})
+
+#define vminnmq(p0,p1) __arm_vminnmq(p0,p1)
+#define __arm_vminnmq(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_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
+#define vminnmvq(p0,p1) __arm_vminnmvq(p0,p1)
+#define __arm_vminnmvq(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_float16_t][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
+  int (*)[__ARM_mve_type_float32_t][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t)));})
+
 #define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
 #define __arm_vcmpgeq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -4729,6 +6245,422 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgeq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
 
+#define vshlq_r(p0,p1) __arm_vshlq_r(p0,p1)
+#define __arm_vshlq_r(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlq_r_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vshlq_r_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlq_r_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vshlq_n(p0,p1) __arm_vshlq_n(p0,p1)
+#define __arm_vshlq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vshlltq(p0,p1) __arm_vshlltq(p0,p1)
+#define __arm_vshlltq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlltq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlltq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlltq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
+
+#define vshllbq(p0,p1) __arm_vshllbq(p0,p1)
+#define __arm_vshllbq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vshllbq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vshllbq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  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 vrshrq(p0,p1) __arm_vrshrq(p0,p1)
+#define __arm_vrshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vrshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vrshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vrshrq(p0,p1) __arm_vrshrq(p0,p1)
+#define __arm_vrshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vrshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vrshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vrshlq(p0,p1) __arm_vrshlq(p0,p1)
+#define __arm_vrshlq(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_int32_t]: __arm_vrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_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_vrshlq_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_vrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vrmulhq(p0,p1) __arm_vrmulhq(p0,p1)
+#define __arm_vrmulhq(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_vrmulhq_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_vrmulhq_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_vrmulhq_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_vrmulhq_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_vrmulhq_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_vrmulhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vrhaddq(p0,p1) __arm_vrhaddq(p0,p1)
+#define __arm_vrhaddq(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_vrhaddq_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_vrhaddq_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_vrhaddq_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_vrhaddq_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_vrhaddq_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_vrhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqsubq(p0,p1) __arm_vqsubq(p0,p1)
+#define __arm_vqsubq(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_int8_t]: __arm_vqsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqsubq_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_vqsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqsubq_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_vqsubq_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_vqsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqsubq_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_vqsubq_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_vqsubq_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_vqsubq_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_vqsubq_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_vqsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqshluq(p0,p1) __arm_vqshluq(p0,p1)
+#define __arm_vqshluq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshluq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshluq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshluq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1));})
+
+#define vqshlq(p0,p1) __arm_vqshlq(p0,p1)
+#define __arm_vqshlq(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_vqshlq_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_vqshlq_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_vqshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqshlq_r(p0,p1) __arm_vqshlq_r(p0,p1)
+#define __arm_vqshlq_r(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshlq_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshlq_r_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshlq_r_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vqshlq_r_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vqshlq_n(p0,p1) __arm_vqshlq_n(p0,p1)
+#define __arm_vqshlq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vqshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
+#define vqrshlq(p0,p1) __arm_vqrshlq(p0,p1)
+#define __arm_vqrshlq(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_vqrshlq_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_vqrshlq_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_vqrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+
+#define vqrdmulhq(p0,p1) __arm_vqrdmulhq(p0,p1)
+#define __arm_vqrdmulhq(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_vqrdmulhq_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_vqrdmulhq_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_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqrdmulhq_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_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+
+#define vmlaldavxq(p0,p1) __arm_vmlaldavxq(p0,p1)
+#define __arm_vmlaldavxq(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_vmlaldavxq_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_vmlaldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqmovuntq(p0,p1) __arm_vqmovuntq(p0,p1)
+#define __arm_vqmovuntq(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_int16x8_t]: __arm_vqmovuntq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovuntq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqmovntq(p0,p1) __arm_vqmovntq(p0,p1)
+#define __arm_vqmovntq(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_int16x8_t]: __arm_vqmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqmovnbq(p0,p1) __arm_vqmovnbq(p0,p1)
+#define __arm_vqmovnbq(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_int16x8_t]: __arm_vqmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqdmulltq(p0,p1) __arm_vqdmulltq(p0,p1)
+#define __arm_vqdmulltq(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_int16_t]: __arm_vqdmulltq_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_vqdmulltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmulltq_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_vqdmulltq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqmovunbq(p0,p1) __arm_vqmovunbq(p0,p1)
+#define __arm_vqmovunbq(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_int16x8_t]: __arm_vqmovunbq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqdmullbq(p0,p1) __arm_vqdmullbq(p0,p1)
+#define __arm_vqdmullbq(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_int16_t]: __arm_vqdmullbq_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_vqdmullbq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmullbq_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_vqdmullbq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqdmulhq(p0,p1) __arm_vqdmulhq(p0,p1)
+#define __arm_vqdmulhq(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_int8_t]: __arm_vqdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqdmulhq_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_vqdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqdmulhq_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_vqdmulhq_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_vqdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqaddq(p0,p1) __arm_vqaddq(p0,p1)
+#define __arm_vqaddq(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_int8_t]: __arm_vqaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqaddq_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_vqaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqaddq_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_vqaddq_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_vqaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqaddq_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_vqaddq_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_vqaddq_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_vqaddq_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_vqaddq_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_vqaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmulltq_poly(p0,p1) __arm_vmulltq_poly(p0,p1)
+#define __arm_vmulltq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
+
+#define vmullbq_poly(p0,p1) __arm_vmullbq_poly(p0,p1)
+#define __arm_vmullbq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
+
+#define vmulltq_int(p0,p1) __arm_vmulltq_int(p0,p1)
+#define __arm_vmulltq_int(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_vmulltq_int_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_vmulltq_int_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_vmulltq_int_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_vmulltq_int_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_vmulltq_int_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_vmulltq_int_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vhaddq(p0,p1) __arm_vhaddq(p0,p1)
+#define __arm_vhaddq(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_int8_t]: __arm_vhaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vhaddq_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_vhaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhaddq_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_vhaddq_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_vhaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhaddq_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_vhaddq_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_vhaddq_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_vhaddq_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_vhaddq_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_vhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vhcaddq_rot270(p0,p1) __arm_vhcaddq_rot270(p0,p1)
+#define __arm_vhcaddq_rot270(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_vhcaddq_rot270_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_vhcaddq_rot270_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_vhcaddq_rot270_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vhcaddq_rot90(p0,p1) __arm_vhcaddq_rot90(p0,p1)
+#define __arm_vhcaddq_rot90(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_vhcaddq_rot90_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_vhcaddq_rot90_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_vhcaddq_rot90_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vhsubq(p0,p1) __arm_vhsubq(p0,p1)
+#define __arm_vhsubq(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_int8_t]: __arm_vhsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vhsubq_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_vhsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhsubq_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_vhsubq_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_vhsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhsubq_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_vhsubq_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_vhsubq_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_vhsubq_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_vhsubq_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_vhsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vminq(p0,p1) __arm_vminq(p0,p1)
+#define __arm_vminq(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_vminq_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_vminq_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_vminq_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_vminq_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_vminq_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_vminq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vminaq(p0,p1) __arm_vminaq(p0,p1)
+#define __arm_vminaq(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_int8x16_t]: __arm_vminaq_s8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminaq_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminaq_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmaxq(p0,p1) __arm_vmaxq(p0,p1)
+#define __arm_vmaxq(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_vmaxq_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_vmaxq_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_vmaxq_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_vmaxq_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_vmaxq_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_vmaxq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmaxaq(p0,p1) __arm_vmaxaq(p0,p1)
+#define __arm_vmaxaq(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_int8x16_t]: __arm_vmaxaq_s8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxaq_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxaq_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vmovntq(p0,p1) __arm_vmovntq(p0,p1)
+#define __arm_vmovntq(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_int16x8_t]: __arm_vmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmovnbq(p0,p1) __arm_vmovnbq(p0,p1)
+#define __arm_vmovnbq(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_int16x8_t]: __arm_vmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmulhq(p0,p1) __arm_vmulhq(p0,p1)
+#define __arm_vmulhq(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_vmulhq_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_vmulhq_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_vmulhq_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_vmulhq_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_vmulhq_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_vmulhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmullbq_int(p0,p1) __arm_vmullbq_int(p0,p1)
+#define __arm_vmullbq_int(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_vmullbq_int_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_vmullbq_int_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_vmullbq_int_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_vmullbq_int_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_vmullbq_int_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_vmullbq_int_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
 #define vcmpgtq(p0,p1) __arm_vcmpgtq(p0,p1)
 #define __arm_vcmpgtq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -4744,7 +6676,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16_t]: __arm_vcmpgtq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t)), \
   int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32_t]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
 
-#else /* MVE Interger.  */
+#else /* MVE Interger.  srinath*/
 
 #define vst4q(p0,p1) __arm_vst4q(p0,p1)
 #define __arm_vst4q(p0,p1) ({ __typeof(p0) __p0 = (p0); \
@@ -4915,12 +6847,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsubq_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_vsubq_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_vsubq_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_vsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vsubq_n(p0,p1) __arm_vsubq_n(p0,p1)
-#define __arm_vsubq_n(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_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vsubq_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_vsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
@@ -4938,43 +6865,16 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
 
-#define vrshlq_n(p0,p1) __arm_vrshlq_n(p0,p1)
-#define __arm_vrshlq_n(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_int32_t]: __arm_vrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-
 #define vrshlq(p0,p1) __arm_vrshlq(p0,p1)
 #define __arm_vrshlq(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_vrshlq_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_vrshlq_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_vrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vrshlq_n(p0,p1) __arm_vrshlq_n(p0,p1)
-#define __arm_vrshlq_n(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_int32_t]: __arm_vrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-
-#define vrshlq(p0,p1) __arm_vrshlq(p0,p1)
-#define __arm_vrshlq(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_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrshlq_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_vrshlq_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_vrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -5004,8 +6904,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrhaddq_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_vrhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
-#define vqsubq_n(p0,p1) __arm_vqsubq_n(p0,p1)
-#define __arm_vqsubq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vqsubq(p0,p1) __arm_vqsubq(p0,p1)
+#define __arm_vqsubq(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_int8_t]: __arm_vqsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
@@ -5013,12 +6913,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqsubq_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_vqsubq_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_vqsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vqsubq(p0,p1) __arm_vqsubq(p0,p1)
-#define __arm_vqsubq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqsubq_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_vqsubq_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_vqsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -5054,8 +6949,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshluq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
   int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshluq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1));})
 
-#define vrshrq_n(p0,p1) __arm_vrshrq_n(p0,p1)
-#define __arm_vrshrq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vrshrq(p0,p1) __arm_vrshrq(p0,p1)
+#define __arm_vrshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
   int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
   int (*)[__ARM_mve_type_int16x8_t]: __arm_vrshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
@@ -5074,13 +6969,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
 
-#define vqshluq_n(p0,p1) __arm_vqshluq_n(p0,p1)
-#define __arm_vqshluq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
-  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
-  int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshluq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
-  int (*)[__ARM_mve_type_int16x8_t]: __arm_vqshluq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
-  int (*)[__ARM_mve_type_int32x4_t]: __arm_vqshluq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1));})
-
 #define vqshlq_n(p0,p1) __arm_vqshlq_n(p0,p1)
 #define __arm_vqshlq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
@@ -5091,17 +6979,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
   int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
 
-#define vqrshlq_n(p0,p1) __arm_vqrshlq_n(p0,p1)
-#define __arm_vqrshlq_n(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_int32_t]: __arm_vqrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-
 #define vqrshlq(p0,p1) __arm_vqrshlq(p0,p1)
 #define __arm_vqrshlq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -5111,15 +6988,13 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqrshlq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrshlq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vqrdmulhq_n(p0,p1) __arm_vqrdmulhq_n(p0,p1)
-#define __arm_vqrdmulhq_n(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_int8_t]: __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqrdmulhq_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_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vqrshlq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
 
 #define vqrdmulhq(p0,p1) __arm_vqrdmulhq(p0,p1)
 #define __arm_vqrdmulhq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
@@ -5127,26 +7002,24 @@ 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_vqrdmulhq_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_vqrdmulhq_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_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-
-#define vqdmulhq_n(p0,p1) __arm_vqdmulhq_n(p0,p1)
-#define __arm_vqdmulhq_n(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_int8_t]: __arm_vqdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
-  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqdmulhq_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_vqdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8_t]: __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqrdmulhq_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_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
 
 #define vqdmulhq(p0,p1) __arm_vqdmulhq(p0,p1)
 #define __arm_vqdmulhq(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_int8_t]: __arm_vqdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vqdmulhq_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_vqdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqdmulhq_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_vqdmulhq_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_vqdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
 
-#define vqaddq_n(p0,p1) __arm_vqaddq_n(p0,p1)
-#define __arm_vqaddq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vqaddq(p0,p1) __arm_vqaddq(p0,p1)
+#define __arm_vqaddq(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_int8_t]: __arm_vqaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
@@ -5154,12 +7027,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vqaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vqaddq_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_vqaddq_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_vqaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vqaddq(p0,p1) __arm_vqaddq(p0,p1)
-#define __arm_vqaddq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vqaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vqaddq_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_vqaddq_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_vqaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -5167,15 +7035,6 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqaddq_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_vqaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
 
-#define vorrq_n(p0,p1) __arm_vorrq_n(p0,p1)
-#define __arm_vorrq_n(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_int32_t]: __arm_vorrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int)), \
-  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vorrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int)), \
-  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32_t]: __arm_vorrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int)), \
-  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32_t]: __arm_vorrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int)));})
-
 #define vorrq(p0,p1) __arm_vorrq(p0,p1)
 #define __arm_vorrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -5291,8 +7150,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxaq_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxaq_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
 
-#define vhsubq_n(p0,p1) __arm_vhsubq_n(p0,p1)
-#define __arm_vhsubq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vhsubq(p0,p1) __arm_vhsubq(p0,p1)
+#define __arm_vhsubq(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_int8_t]: __arm_vhsubq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
@@ -5300,12 +7159,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vhsubq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhsubq_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_vhsubq_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_vhsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vhsubq(p0,p1) __arm_vhsubq(p0,p1)
-#define __arm_vhsubq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhsubq_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_vhsubq_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_vhsubq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -5329,8 +7183,8 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vhcaddq_rot270_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_vhcaddq_rot270_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
 
-#define vhaddq_n(p0,p1) __arm_vhaddq_n(p0,p1)
-#define __arm_vhaddq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+#define vhaddq(p0,p1) __arm_vhaddq(p0,p1)
+#define __arm_vhaddq(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_int8_t]: __arm_vhaddq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
@@ -5338,12 +7192,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32_t]: __arm_vhaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
   int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8_t]: __arm_vhaddq_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_vhaddq_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_vhaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-
-#define vhaddq(p0,p1) __arm_vhaddq(p0,p1)
-#define __arm_vhaddq(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_uint32x4_t][__ARM_mve_type_uint32_t]: __arm_vhaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
   int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vhaddq_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_vhaddq_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_vhaddq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
@@ -5414,12 +7263,7 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vaddq_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_vaddq_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_vaddq_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_vaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-
-#define vaddq(p0,p1) __arm_vaddq(p0,p1)
-#define __arm_vaddq(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_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_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_vaddq_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_vaddq_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_vaddq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)), \
@@ -5591,6 +7435,129 @@ 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 vqmovntq(p0,p1) __arm_vqmovntq(p0,p1)
+#define __arm_vqmovntq(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_int16x8_t]: __arm_vqmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vqmovnbq(p0,p1) __arm_vqmovnbq(p0,p1)
+#define __arm_vqmovnbq(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_int16x8_t]: __arm_vqmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmulltq_poly(p0,p1) __arm_vmulltq_poly(p0,p1)
+#define __arm_vmulltq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
+
+#define vmullbq_poly(p0,p1) __arm_vmullbq_poly(p0,p1)
+#define __arm_vmullbq_poly(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  __typeof(p1) __p1 = (p1); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_p8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_p16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)));})
+
+#define vmovntq(p0,p1) __arm_vmovntq(p0,p1)
+#define __arm_vmovntq(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_int16x8_t]: __arm_vmovntq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovntq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovntq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovntq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmovnbq(p0,p1) __arm_vmovnbq(p0,p1)
+#define __arm_vmovnbq(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_int16x8_t]: __arm_vmovnbq_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vmovnbq_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t)), \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovnbq_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovnbq_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vmlaldavxq(p0,p1) __arm_vmlaldavxq(p0,p1)
+#define __arm_vmlaldavxq(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_vmlaldavxq_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_vmlaldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqmovuntq(p0,p1) __arm_vqmovuntq(p0,p1)
+#define __arm_vqmovuntq(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_int16x8_t]: __arm_vqmovuntq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovuntq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vshlltq(p0,p1) __arm_vshlltq(p0,p1)
+#define __arm_vshlltq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlltq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vshlltq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlltq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+  int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlltq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1));})
+
+#define vshllbq(p0,p1) __arm_vshllbq(p0,p1)
+#define __arm_vshllbq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+  int (*)[__ARM_mve_type_int8x16_t]: __arm_vshllbq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+  int (*)[__ARM_mve_type_int16x8_t]: __arm_vshllbq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+  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); \
+  _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+  int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovunbq_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
+  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqdmulltq(p0,p1) __arm_vqdmulltq(p0,p1)
+#define __arm_vqdmulltq(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_int16_t]: __arm_vqdmulltq_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_vqdmulltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmulltq_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_vqdmulltq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vqdmullbq(p0,p1) __arm_vqdmullbq(p0,p1)
+#define __arm_vqdmullbq(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_int16_t]: __arm_vqdmullbq_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_vqdmullbq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmullbq_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_vqdmullbq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
+
+#define vcmpgeq_n(p0,p1) __arm_vcmpgeq_n(p0,p1)
+#define __arm_vcmpgeq_n(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_int8_t]: __arm_vcmpgeq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8_t)), \
+  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpgeq_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_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
+
 #define vcmpgeq(p0,p1) __arm_vcmpgeq(p0,p1)
 #define __arm_vcmpgeq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
   __typeof(p1) __p1 = (p1); \
@@ -5646,6 +7613,46 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16_t]: __arm_vcmpltq_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_vcmpltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_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)));})
+
 #endif /* MVE Floating point.  */
 
 #ifdef __cplusplus
diff --git a/gcc/config/arm/arm_mve_builtins.def b/gcc/config/arm/arm_mve_builtins.def
index 550a67f920b..7129b99bc99 100644
--- a/gcc/config/arm/arm_mve_builtins.def
+++ b/gcc/config/arm/arm_mve_builtins.def
@@ -18,198 +18,276 @@
     along with GCC; see the file COPYING3.  If not see
     <http://www.gnu.org/licenses/>.  */
 
-VAR5 (STORE1, vst4q, v16qi, v8hi, v4si, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndxq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndpq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndnq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndmq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrndaq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vrev64q_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vnegq_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vdupq_n_f, v8hf, v4sf)
-VAR2 (UNOP_NONE_NONE, vabsq_f, v8hf, v4sf)
-VAR1 (UNOP_NONE_NONE, vrev32q_f, v8hf)
-VAR1 (UNOP_NONE_NONE, vcvttq_f32_f16, v4sf)
-VAR1 (UNOP_NONE_NONE, vcvtbq_f32_f16, v4sf)
-VAR2 (UNOP_NONE_SNONE, vcvtq_to_f_s, v8hf, v4sf)
-VAR2 (UNOP_NONE_UNONE, vcvtq_to_f_u, v8hf, v4sf)
-VAR3 (UNOP_SNONE_SNONE, vrev64q_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vqnegq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vqabsq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vnegq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vmvnq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vdupq_n_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vclzq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vclsq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vaddvq_s, v16qi, v8hi, v4si)
-VAR3 (UNOP_SNONE_SNONE, vabsq_s, v16qi, v8hi, v4si)
-VAR2 (UNOP_SNONE_SNONE, vrev32q_s, v16qi, v8hi)
-VAR2 (UNOP_SNONE_SNONE, vmovltq_s, v16qi, v8hi)
-VAR2 (UNOP_SNONE_SNONE, vmovlbq_s, v16qi, v8hi)
-VAR2 (UNOP_SNONE_NONE, vcvtq_from_f_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtpq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtnq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtmq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_NONE, vcvtaq_s, v8hi, v4si)
-VAR2 (UNOP_SNONE_IMM, vmvnq_n_s, v8hi, v4si)
-VAR1 (UNOP_SNONE_SNONE, vrev16q_s, v16qi)
-VAR1 (UNOP_SNONE_SNONE, vaddlvq_s, v4si)
-VAR3 (UNOP_UNONE_UNONE, vrev64q_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vmvnq_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vdupq_n_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vclzq_u, v16qi, v8hi, v4si)
-VAR3 (UNOP_UNONE_UNONE, vaddvq_u, v16qi, v8hi, v4si)
-VAR2 (UNOP_UNONE_UNONE, vrev32q_u, v16qi, v8hi)
-VAR2 (UNOP_UNONE_UNONE, vmovltq_u, v16qi, v8hi)
-VAR2 (UNOP_UNONE_UNONE, vmovlbq_u, v16qi, v8hi)
-VAR2 (UNOP_UNONE_NONE, vcvtq_from_f_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtpq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtnq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtmq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_NONE, vcvtaq_u, v8hi, v4si)
-VAR2 (UNOP_UNONE_IMM, vmvnq_n_u, v8hi, v4si)
-VAR1 (UNOP_UNONE_UNONE, vrev16q_u, v16qi)
-VAR1 (UNOP_UNONE_UNONE, vaddlvq_u, v4si)
-VAR1 (UNOP_UNONE_UNONE, vctp16q, hi)
-VAR1 (UNOP_UNONE_UNONE, vctp32q, hi)
-VAR1 (UNOP_UNONE_UNONE, vctp64q, hi)
-VAR1 (UNOP_UNONE_UNONE, vctp8q, hi)
-VAR1 (UNOP_UNONE_UNONE, vpnot, hi)
-VAR2 (BINOP_NONE_NONE_NONE, vsubq_n_f, v8hf, v4sf)
-VAR2 (BINOP_NONE_NONE_NONE, vbrsrq_n_f, v8hf, v4sf)
-VAR2 (BINOP_NONE_NONE_IMM, vcvtq_n_to_f_s, v8hf, v4sf)
-VAR2 (BINOP_NONE_UNONE_IMM, vcvtq_n_to_f_u, v8hf, v4sf)
-VAR2 (BINOP_NONE_UNONE_UNONE, vcreateq_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_IMM, vcvtq_n_from_f_u, v8hi, v4si)
-VAR2 (BINOP_NONE_NONE_IMM, vcvtq_n_from_f_s, v8hi, v4si)
-VAR4 (BINOP_UNONE_UNONE_UNONE, vcreateq_u, v16qi, v8hi, v4si, v2di)
-VAR4 (BINOP_NONE_UNONE_UNONE, vcreateq_s, v16qi, v8hi, v4si, v2di)
-VAR3 (BINOP_UNONE_UNONE_IMM, vshrq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vshrq_n_s, v16qi, v8hi, v4si)
-VAR1 (BINOP_NONE_NONE_UNONE, vaddlvq_p_s, v4si)
-VAR1 (BINOP_UNONE_UNONE_UNONE, vaddlvq_p_u, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpneq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpneq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vsubq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vsubq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vrmulhq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vrhaddq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqsubq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqsubq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqaddq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vqaddq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vorrq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vornq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulltq_int_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmullbq_int_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmulhq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmladavq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vminvq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vminq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmaxvq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vmaxq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhsubq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhsubq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhaddq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vhaddq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, veorq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpneq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmphiq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmphiq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpeqq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpeqq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpcsq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpcsq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcaddq_rot90_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcaddq_rot270_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vbicq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vandq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vaddvq_p_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vaddvaq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vaddq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vabdq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vshlq_r_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vrshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vrshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqshlq_r_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqrshlq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vqrshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vminavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vminaq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vmaxavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vmaxaq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_NONE, vbrsrq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_IMM, vshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_IMM, vrshrq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_IMM, vqshlq_n_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpneq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpltq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpltq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpleq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpleq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgtq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgtq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgeq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgeq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpeqq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpeqq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_IMM, vqshluq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_UNONE, vaddvq_p_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vsubq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vsubq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vshlq_r_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrshlq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vrhaddq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqsubq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqsubq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqshlq_r_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrshlq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrshlq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrdmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqrdmulhq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqdmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqdmulhq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqaddq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vqaddq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vorrq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vornq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulltq_int_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmullbq_int_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmulhq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmlsdavxq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmlsdavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmladavxq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmladavq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vminvq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vminq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmaxvq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vmaxq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhsubq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhsubq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhcaddq_rot90_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhcaddq_rot270_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhaddq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vhaddq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, veorq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vcaddq_rot90_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vcaddq_rot270_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vbrsrq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vbicq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vandq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vaddvaq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vaddq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_NONE, vabdq_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vshlq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vrshrq_n_s, v16qi, v8hi, v4si)
-VAR3 (BINOP_NONE_NONE_IMM, vqshlq_n_s, v16qi, v8hi, v4si)
+VAR5(STORE1, vst4q, v16qi, v8hi, v4si, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndxq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndpq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndnq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndmq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrndaq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vrev64q_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vnegq_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vdupq_n_f, v8hf, v4sf)
+VAR2(UNOP_NONE_NONE, vabsq_f, v8hf, v4sf)
+VAR1(UNOP_NONE_NONE, vrev32q_f, v8hf)
+VAR1(UNOP_NONE_NONE, vcvttq_f32_f16, v4sf)
+VAR1(UNOP_NONE_NONE, vcvtbq_f32_f16, v4sf)
+VAR2(UNOP_NONE_SNONE, vcvtq_to_f_s, v8hf, v4sf)
+VAR2(UNOP_NONE_UNONE, vcvtq_to_f_u, v8hf, v4sf)
+VAR3(UNOP_SNONE_SNONE, vrev64q_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vqnegq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vqabsq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vnegq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vmvnq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vdupq_n_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vclzq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vclsq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vaddvq_s, v16qi, v8hi, v4si)
+VAR3(UNOP_SNONE_SNONE, vabsq_s, v16qi, v8hi, v4si)
+VAR2(UNOP_SNONE_SNONE, vrev32q_s, v16qi, v8hi)
+VAR2(UNOP_SNONE_SNONE, vmovltq_s, v16qi, v8hi)
+VAR2(UNOP_SNONE_SNONE, vmovlbq_s, v16qi, v8hi)
+VAR2(UNOP_SNONE_NONE, vcvtq_from_f_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtpq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtnq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtmq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_NONE, vcvtaq_s, v8hi, v4si)
+VAR2(UNOP_SNONE_IMM, vmvnq_n_s, v8hi, v4si)
+VAR1(UNOP_SNONE_SNONE, vrev16q_s, v16qi)
+VAR1(UNOP_SNONE_SNONE, vaddlvq_s, v4si)
+VAR3(UNOP_UNONE_UNONE, vrev64q_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vmvnq_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vdupq_n_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vclzq_u, v16qi, v8hi, v4si)
+VAR3(UNOP_UNONE_UNONE, vaddvq_u, v16qi, v8hi, v4si)
+VAR2(UNOP_UNONE_UNONE, vrev32q_u, v16qi, v8hi)
+VAR2(UNOP_UNONE_UNONE, vmovltq_u, v16qi, v8hi)
+VAR2(UNOP_UNONE_UNONE, vmovlbq_u, v16qi, v8hi)
+VAR2(UNOP_UNONE_NONE, vcvtq_from_f_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtpq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtnq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtmq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_NONE, vcvtaq_u, v8hi, v4si)
+VAR2(UNOP_UNONE_IMM, vmvnq_n_u, v8hi, v4si)
+VAR1(UNOP_UNONE_UNONE, vrev16q_u, v16qi)
+VAR1(UNOP_UNONE_UNONE, vaddlvq_u, v4si)
+VAR1(UNOP_UNONE_UNONE, vctp16q, hi)
+VAR1(UNOP_UNONE_UNONE, vctp32q, hi)
+VAR1(UNOP_UNONE_UNONE, vctp64q, hi)
+VAR1(UNOP_UNONE_UNONE, vctp8q, hi)
+VAR1(UNOP_UNONE_UNONE, vpnot, hi)
+VAR2(BINOP_NONE_NONE_NONE, vsubq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vbrsrq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_IMM, vcvtq_n_to_f_s, v8hf, v4sf)
+VAR2(BINOP_NONE_UNONE_IMM, vcvtq_n_to_f_u, v8hf, v4sf)
+VAR2(BINOP_NONE_UNONE_UNONE, vcreateq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_IMM, vcvtq_n_from_f_u, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_IMM, vcvtq_n_from_f_s, v8hi, v4si)
+VAR4(BINOP_UNONE_UNONE_UNONE, vcreateq_u, v16qi, v8hi, v4si, v2di)
+VAR4(BINOP_NONE_UNONE_UNONE, vcreateq_s, v16qi, v8hi, v4si, v2di)
+VAR3(BINOP_UNONE_UNONE_IMM, vshrq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vshrq_n_s, v16qi, v8hi, v4si)
+VAR1(BINOP_NONE_NONE_UNONE, vaddlvq_p_s, v4si)
+VAR1(BINOP_UNONE_UNONE_UNONE, vaddlvq_p_u, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpneq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpneq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vsubq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vsubq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vrmulhq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vrhaddq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqsubq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqsubq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqaddq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vqaddq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vorrq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vornq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulltq_int_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmullbq_int_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmulhq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmladavq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vminvq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vminq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmaxvq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vmaxq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhsubq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhsubq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhaddq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vhaddq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, veorq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpneq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmphiq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmphiq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpeqq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpeqq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpcsq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcmpcsq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcaddq_rot90_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vcaddq_rot270_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vbicq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vandq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vaddvq_p_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vaddvaq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vaddq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_UNONE, vabdq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vshlq_r_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vrshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vrshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqshlq_r_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqrshlq_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vqrshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vminavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vminaq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vmaxavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vmaxaq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_NONE, vbrsrq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_IMM, vshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_IMM, vrshrq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_UNONE_IMM, vqshlq_n_u, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpneq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpltq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpltq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpleq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpleq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgtq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgtq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgeq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpgeq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpeqq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_NONE, vcmpeqq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_UNONE_NONE_IMM, vqshluq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_UNONE, vaddvq_p_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vsubq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vsubq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vshlq_r_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrshlq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vrhaddq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqsubq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqsubq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqshlq_r_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrshlq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrshlq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrdmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqrdmulhq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqdmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqdmulhq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqaddq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vqaddq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vorrq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vornq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulltq_int_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmullbq_int_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmulhq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmlsdavxq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmlsdavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmladavxq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmladavq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vminvq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vminq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmaxvq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vmaxq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhsubq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhsubq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhcaddq_rot90_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhcaddq_rot270_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhaddq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vhaddq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, veorq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vcaddq_rot90_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vcaddq_rot270_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vbrsrq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vbicq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vandq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vaddvaq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vaddq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_NONE, vabdq_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vshlq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vrshrq_n_s, v16qi, v8hi, v4si)
+VAR3(BINOP_NONE_NONE_IMM, vqshlq_n_s, v16qi, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vqmovntq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vqmovnbq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmulltq_poly_p, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmullbq_poly_p, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmovntq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmovnbq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_UNONE, vmlaldavq_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_NONE, vqmovuntq_s, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_NONE, vqmovunbq_s, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_IMM, vshlltq_n_u, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_IMM, vshllbq_n_u, v16qi, v8hi)
+VAR2(BINOP_UNONE_UNONE_IMM, vorrq_n_u, v8hi, v4si)
+VAR2(BINOP_UNONE_UNONE_IMM, vbicq_n_u, v8hi, v4si)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpneq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpneq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpltq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpltq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpleq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpleq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgtq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgtq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgeq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpgeq_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpeqq_n_f, v8hf, v4sf)
+VAR2(BINOP_UNONE_NONE_NONE, vcmpeqq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vsubq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vqmovntq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqmovnbq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmulltq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmulltq_n_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmullbq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vqdmullbq_n_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vorrq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vornq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmulq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmulq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmovntq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmovnbq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlsldavxq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlsldavq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlaldavxq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vmlaldavq_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_NONE, vminnmvq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vminnmq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vminnmavq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vminnmaq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmvq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmavq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vmaxnmaq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, veorq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_rot90_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_rot270_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_rot180_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcmulq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcaddq_rot90_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vcaddq_rot270_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vbicq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vandq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vaddq_n_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_NONE, vabdq_f, v8hf, v4sf)
+VAR2(BINOP_NONE_NONE_IMM, vshlltq_n_s, v16qi, v8hi)
+VAR2(BINOP_NONE_NONE_IMM, vshllbq_n_s, v16qi, v8hi)
+VAR2(BINOP_NONE_NONE_IMM, vorrq_n_s, v8hi, v4si)
+VAR2(BINOP_NONE_NONE_IMM, vbicq_n_s, v8hi, v4si)
+VAR1(BINOP_UNONE_UNONE_UNONE, vrmlaldavhq_u, v4si)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp8q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp64q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp32q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vctp16q_m, hi)
+VAR1(BINOP_UNONE_UNONE_UNONE, vaddlvaq_u, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlsldavhxq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlsldavhq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlaldavhxq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vrmlaldavhq_s, v4si)
+VAR1(BINOP_NONE_NONE_NONE, vcvttq_f16_f32, v8hf)
+VAR1(BINOP_NONE_NONE_NONE, vcvtbq_f16_f32, v8hf)
+VAR1(BINOP_NONE_NONE_NONE, vaddlvaq_s, v4si)
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 8e817b890da..24fb8167d6a 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -66,7 +66,26 @@
 			 VMLADAVXQ_S VMLSDAVQ_S VMLSDAVXQ_S VQDMULHQ_N_S
 			 VQDMULHQ_S VQRDMULHQ_N_S VQRDMULHQ_S VQSHLUQ_N_S
 			 VCMPCSQ_N_U VCMPCSQ_U VCMPHIQ_N_U VCMPHIQ_U VABDQ_M_S
-			 VABDQ_M_U])
+			 VABDQ_M_U VABDQ_F VADDQ_N_F VANDQ_F VBICQ_F
+			 VCADDQ_ROT270_F VCADDQ_ROT90_F VCMPEQQ_F VCMPEQQ_N_F
+			 VCMPGEQ_F VCMPGEQ_N_F VCMPGTQ_F VCMPGTQ_N_F VCMPLEQ_F
+			 VCMPLEQ_N_F VCMPLTQ_F VCMPLTQ_N_F VCMPNEQ_F VCMPNEQ_N_F
+			 VCMULQ_F VCMULQ_ROT180_F VCMULQ_ROT270_F VCMULQ_ROT90_F
+			 VEORQ_F VMAXNMAQ_F VMAXNMAVQ_F VMAXNMQ_F VMAXNMVQ_F
+			 VMINNMAQ_F VMINNMAVQ_F VMINNMQ_F VMINNMVQ_F VMULQ_F
+			 VMULQ_N_F VORNQ_F VORRQ_F VSUBQ_F VADDLVAQ_U
+			 VADDLVAQ_S VBICQ_N_U VBICQ_N_S VCTP8Q_M VCTP16Q_M
+			 VCTP32Q_M VCTP64Q_M VCVTBQ_F16_F32 VCVTTQ_F16_F32
+			 VMLALDAVQ_U VMLALDAVXQ_U VMLALDAVXQ_S VMLALDAVQ_S
+			 VMLSLDAVQ_S VMLSLDAVXQ_S VMOVNBQ_U VMOVNBQ_S
+			 VMOVNTQ_U VMOVNTQ_S VORRQ_N_S VORRQ_N_U VQDMULLBQ_N_S
+			 VQDMULLBQ_S VQDMULLTQ_N_S VQDMULLTQ_S VQMOVNBQ_U
+			 VQMOVNBQ_S VQMOVUNBQ_S VQMOVUNTQ_S VRMLALDAVHXQ_S
+			 VRMLSLDAVHQ_S VRMLSLDAVHXQ_S VSHLLBQ_S
+			 VSHLLBQ_U VSHLLTQ_U VSHLLTQ_S VQMOVNTQ_U VQMOVNTQ_S
+			 VSHLLBQ_N_S VSHLLBQ_N_U VSHLLTQ_N_U VSHLLTQ_N_S
+			 VRMLALDAVHQ_U VRMLALDAVHQ_S VMULLTQ_POLY_P
+			 VMULLBQ_POLY_P])
 
 (define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF")
 			    (V8HF "V8HI") (V4SF "V4SI")])
@@ -119,10 +138,19 @@
 		       (VSHLQ_N_S "s") (VSHLQ_N_U "u") (VSHLQ_R_S "s")
 		       (VSHLQ_R_U "u") (VSUBQ_N_S "s") (VSUBQ_N_U "u")
 		       (VSUBQ_S "s") (VSUBQ_U "u") (VADDVAQ_S "s")
-		       (VADDVAQ_U "u")])
+		       (VADDVAQ_U "u") (VADDLVAQ_S "s") (VADDLVAQ_U "u")
+		       (VBICQ_N_S "s") (VBICQ_N_U "u") (VMLALDAVQ_U "u")
+		       (VMLALDAVQ_S "s") (VMLALDAVXQ_U "u") (VMLALDAVXQ_S "s")
+		       (VMOVNBQ_U "u") (VMOVNBQ_S "s") (VMOVNTQ_U "u")
+		       (VMOVNTQ_S "s") (VORRQ_N_S "s") (VORRQ_N_U "u")
+		       (VQMOVNBQ_U "u") (VQMOVNBQ_S "s") (VQMOVNTQ_S "s")
+		       (VQMOVNTQ_U "u") (VSHLLBQ_N_U "u") (VSHLLBQ_N_S "s")
+		       (VSHLLTQ_N_U "u") (VSHLLTQ_N_S "s") (VRMLALDAVHQ_U "u")
+		       (VRMLALDAVHQ_S "s")])
 
 (define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32")
-			(VCTP64Q "64")])
+			(VCTP64Q "64") (VCTP8Q_M "8") (VCTP16Q_M "16")
+			(VCTP32Q_M "32") (VCTP64Q_M "64")])
 (define_mode_attr MVE_pred2 [(V16QI "mve_imm_8") (V8HI "mve_imm_16")
 			     (V4SI "mve_imm_32")])
 (define_mode_attr MVE_constraint2 [(V16QI "Rb") (V8HI "Rd") (V4SI "Rf")])
@@ -146,6 +174,7 @@
 (define_int_iterator VCVTMQ [VCVTMQ_S VCVTMQ_U])
 (define_int_iterator VADDLVQ [VADDLVQ_U VADDLVQ_S])
 (define_int_iterator VCTPQ [VCTP8Q VCTP16Q VCTP32Q VCTP64Q])
+(define_int_iterator VCTPQ_M [VCTP8Q_M VCTP16Q_M VCTP32Q_M VCTP64Q_M])
 (define_int_iterator VCVTQ_N_TO_F [VCVTQ_N_TO_F_S VCVTQ_N_TO_F_U])
 (define_int_iterator VCREATEQ [VCREATEQ_U VCREATEQ_S])
 (define_int_iterator VSHRQ_N [VSHRQ_N_S VSHRQ_N_U])
@@ -200,7 +229,18 @@
 (define_int_iterator VSHLQ_R [VSHLQ_R_S VSHLQ_R_U])
 (define_int_iterator VSUBQ [VSUBQ_S VSUBQ_U])
 (define_int_iterator VSUBQ_N [VSUBQ_N_S VSUBQ_N_U])
-
+(define_int_iterator VADDLVAQ [VADDLVAQ_S VADDLVAQ_U])
+(define_int_iterator VBICQ_N [VBICQ_N_S VBICQ_N_U])
+(define_int_iterator VMLALDAVQ [VMLALDAVQ_U VMLALDAVQ_S])
+(define_int_iterator VMLALDAVXQ [VMLALDAVXQ_U VMLALDAVXQ_S])
+(define_int_iterator VMOVNBQ [VMOVNBQ_U VMOVNBQ_S])
+(define_int_iterator VMOVNTQ [VMOVNTQ_S VMOVNTQ_U])
+(define_int_iterator VORRQ_N [VORRQ_N_U VORRQ_N_S])
+(define_int_iterator VQMOVNBQ [VQMOVNBQ_U VQMOVNBQ_S])
+(define_int_iterator VQMOVNTQ [VQMOVNTQ_U VQMOVNTQ_S])
+(define_int_iterator VSHLLBQ_N [VSHLLBQ_N_S VSHLLBQ_N_U])
+(define_int_iterator VSHLLTQ_N [VSHLLTQ_N_U VSHLLTQ_N_S])
+(define_int_iterator VRMLALDAVHQ [VRMLALDAVHQ_U VRMLALDAVHQ_S])
 
 (define_insn "*mve_mov<mode>"
   [(set (match_operand:MVE_types 0 "nonimmediate_operand" "=w,w,r,w,w,r,w,Us")
@@ -2057,3 +2097,963 @@
   "vsub.i%#<V_sz_elem>\t%q0, %q1, %q2"
   [(set_attr "type" "mve_move")
 ])
+
+;;
+;; [vabdq_f])
+;;
+(define_insn "mve_vabdq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VABDQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vabd.f%#<V_sz_elem>	%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vaddlvaq_s vaddlvaq_u])
+;;
+(define_insn "mve_vaddlvaq_<supf>v4si"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:DI 1 "s_register_operand" "0")
+		    (match_operand:V4SI 2 "s_register_operand" "w")]
+	 VADDLVAQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vaddlva.<supf>32 %Q0, %R0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vaddq_n_f])
+;;
+(define_insn "mve_vaddq_n_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VADDQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vadd.f%#<V_sz_elem>	%q0, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vandq_f])
+;;
+(define_insn "mve_vandq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VANDQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vand %q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vbicq_f])
+;;
+(define_insn "mve_vbicq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VBICQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vbic %q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vbicq_n_s, vbicq_n_u])
+;;
+(define_insn "mve_vbicq_n_<supf><mode>"
+  [
+   (set (match_operand:MVE_5 0 "s_register_operand" "=w")
+	(unspec:MVE_5 [(match_operand:MVE_5 1 "s_register_operand" "0")
+		       (match_operand:SI 2 "immediate_operand" "i")]
+	 VBICQ_N))
+  ]
+  "TARGET_HAVE_MVE"
+  "vbic.i%#<V_sz_elem>	%q0, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcaddq_rot270_f])
+;;
+(define_insn "mve_vcaddq_rot270_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCADDQ_ROT270_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcadd.f%#<V_sz_elem>	%q0, %q1, %q2, #270"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcaddq_rot90_f])
+;;
+(define_insn "mve_vcaddq_rot90_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCADDQ_ROT90_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcadd.f%#<V_sz_elem>	%q0, %q1, %q2, #90"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpeqq_f])
+;;
+(define_insn "mve_vcmpeqq_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMPEQQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	eq, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpeqq_n_f])
+;;
+(define_insn "mve_vcmpeqq_n_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VCMPEQQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	eq, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpgeq_f])
+;;
+(define_insn "mve_vcmpgeq_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMPGEQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	ge, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpgeq_n_f])
+;;
+(define_insn "mve_vcmpgeq_n_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VCMPGEQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	ge, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpgtq_f])
+;;
+(define_insn "mve_vcmpgtq_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMPGTQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	gt, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpgtq_n_f])
+;;
+(define_insn "mve_vcmpgtq_n_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VCMPGTQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	gt, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpleq_f])
+;;
+(define_insn "mve_vcmpleq_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMPLEQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	le, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpleq_n_f])
+;;
+(define_insn "mve_vcmpleq_n_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VCMPLEQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	le, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpltq_f])
+;;
+(define_insn "mve_vcmpltq_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMPLTQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	lt, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpltq_n_f])
+;;
+(define_insn "mve_vcmpltq_n_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VCMPLTQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	lt, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpneq_f])
+;;
+(define_insn "mve_vcmpneq_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMPNEQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	ne, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmpneq_n_f])
+;;
+(define_insn "mve_vcmpneq_n_f<mode>"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:MVE_0 1 "s_register_operand" "w")
+		    (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VCMPNEQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmp.f%#<V_sz_elem>	ne, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmulq_f])
+;;
+(define_insn "mve_vcmulq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMULQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmul.f%#<V_sz_elem>	%q0, %q1, %q2, #0"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmulq_rot180_f])
+;;
+(define_insn "mve_vcmulq_rot180_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMULQ_ROT180_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmul.f%#<V_sz_elem>	%q0, %q1, %q2, #180"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmulq_rot270_f])
+;;
+(define_insn "mve_vcmulq_rot270_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMULQ_ROT270_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmul.f%#<V_sz_elem>	%q0, %q1, %q2, #270"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcmulq_rot90_f])
+;;
+(define_insn "mve_vcmulq_rot90_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VCMULQ_ROT90_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcmul.f%#<V_sz_elem>	%q0, %q1, %q2, #90"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vctp8q_m vctp16q_m vctp32q_m vctp64q_m])
+;;
+(define_insn "mve_vctp<mode1>q_mhi"
+  [
+   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
+	(unspec:HI [(match_operand:SI 1 "s_register_operand" "r")
+		    (match_operand:HI 2 "vpr_register_operand" "Up")]
+	 VCTPQ_M))
+  ]
+  "TARGET_HAVE_MVE"
+  "vpst\;vctpt.<mode1> %1"
+  [(set_attr "type" "mve_move")
+   (set_attr "length""8")])
+
+;;
+;; [vcvtbq_f16_f32])
+;;
+(define_insn "mve_vcvtbq_f16_f32v8hf"
+  [
+   (set (match_operand:V8HF 0 "s_register_operand" "=w")
+	(unspec:V8HF [(match_operand:V8HF 1 "s_register_operand" "0")
+		      (match_operand:V4SF 2 "s_register_operand" "w")]
+	 VCVTBQ_F16_F32))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcvtb.f16.f32 %q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcvttq_f16_f32])
+;;
+(define_insn "mve_vcvttq_f16_f32v8hf"
+  [
+   (set (match_operand:V8HF 0 "s_register_operand" "=w")
+	(unspec:V8HF [(match_operand:V8HF 1 "s_register_operand" "0")
+		      (match_operand:V4SF 2 "s_register_operand" "w")]
+	 VCVTTQ_F16_F32))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vcvtt.f16.f32 %q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [veorq_f])
+;;
+(define_insn "mve_veorq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VEORQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "veor %q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmaxnmaq_f])
+;;
+(define_insn "mve_vmaxnmaq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "0")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMAXNMAQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vmaxnma.f%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmaxnmavq_f])
+;;
+(define_insn "mve_vmaxnmavq_f<mode>"
+  [
+   (set (match_operand:<V_elem> 0 "s_register_operand" "=r")
+	(unspec:<V_elem> [(match_operand:<V_elem> 1 "s_register_operand" "0")
+			  (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMAXNMAVQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vmaxnmav.f%#<V_sz_elem>	%0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmaxnmq_f])
+;;
+(define_insn "mve_vmaxnmq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMAXNMQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vmaxnm.f%#<V_sz_elem>	%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmaxnmvq_f])
+;;
+(define_insn "mve_vmaxnmvq_f<mode>"
+  [
+   (set (match_operand:<V_elem> 0 "s_register_operand" "=r")
+	(unspec:<V_elem> [(match_operand:<V_elem> 1 "s_register_operand" "0")
+			  (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMAXNMVQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vmaxnmv.f%#<V_sz_elem>	%0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vminnmaq_f])
+;;
+(define_insn "mve_vminnmaq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "0")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMINNMAQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vminnma.f%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vminnmavq_f])
+;;
+(define_insn "mve_vminnmavq_f<mode>"
+  [
+   (set (match_operand:<V_elem> 0 "s_register_operand" "=r")
+	(unspec:<V_elem> [(match_operand:<V_elem> 1 "s_register_operand" "0")
+			  (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMINNMAVQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vminnmav.f%#<V_sz_elem>	%0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vminnmq_f])
+;;
+(define_insn "mve_vminnmq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMINNMQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vminnm.f%#<V_sz_elem>	%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vminnmvq_f])
+;;
+(define_insn "mve_vminnmvq_f<mode>"
+  [
+   (set (match_operand:<V_elem> 0 "s_register_operand" "=r")
+	(unspec:<V_elem> [(match_operand:<V_elem> 1 "s_register_operand" "0")
+			  (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMINNMVQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vminnmv.f%#<V_sz_elem>	%0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmlaldavq_u, vmlaldavq_s])
+;;
+(define_insn "mve_vmlaldavq_<supf><mode>"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:MVE_5 1 "s_register_operand" "w")
+		    (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VMLALDAVQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmlaldav.<supf>%#<V_sz_elem>	%Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmlaldavxq_s])
+;;
+(define_insn "mve_vmlaldavxq_s<mode>"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:MVE_5 1 "s_register_operand" "w")
+		    (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VMLALDAVXQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmlaldavx.s%#<V_sz_elem> %Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmlsldavq_s])
+;;
+(define_insn "mve_vmlsldavq_s<mode>"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:MVE_5 1 "s_register_operand" "w")
+		    (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VMLSLDAVQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmlsldav.s%#<V_sz_elem> %Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmlsldavxq_s])
+;;
+(define_insn "mve_vmlsldavxq_s<mode>"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:MVE_5 1 "s_register_operand" "w")
+		    (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VMLSLDAVXQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmlsldavx.s%#<V_sz_elem> %Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmovnbq_u, vmovnbq_s])
+;;
+(define_insn "mve_vmovnbq_<supf><mode>"
+  [
+   (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+	(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
+				 (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VMOVNBQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmovnb.i%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmovntq_s, vmovntq_u])
+;;
+(define_insn "mve_vmovntq_<supf><mode>"
+  [
+   (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+	(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
+				 (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VMOVNTQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmovnt.i%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmulq_f])
+;;
+(define_insn "mve_vmulq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VMULQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vmul.f%#<V_sz_elem>	%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmulq_n_f])
+;;
+(define_insn "mve_vmulq_n_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VMULQ_N_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vmul.f%#<V_sz_elem>	%q0, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vornq_f])
+;;
+(define_insn "mve_vornq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VORNQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vorn %q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vorrq_f])
+;;
+(define_insn "mve_vorrq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VORRQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vorr %q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vorrq_n_u, vorrq_n_s])
+;;
+(define_insn "mve_vorrq_n_<supf><mode>"
+  [
+   (set (match_operand:MVE_5 0 "s_register_operand" "=w")
+	(unspec:MVE_5 [(match_operand:MVE_5 1 "s_register_operand" "0")
+		       (match_operand:SI 2 "immediate_operand" "i")]
+	 VORRQ_N))
+  ]
+  "TARGET_HAVE_MVE"
+  "vorr.i%#<V_sz_elem>	%q0, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqdmullbq_n_s])
+;;
+(define_insn "mve_vqdmullbq_n_s<mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_5 1 "s_register_operand" "w")
+				  (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VQDMULLBQ_N_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqdmullb.s%#<V_sz_elem>	%q0, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqdmullbq_s])
+;;
+(define_insn "mve_vqdmullbq_s<mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_5 1 "s_register_operand" "w")
+				  (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VQDMULLBQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqdmullb.s%#<V_sz_elem>	%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqdmulltq_n_s])
+;;
+(define_insn "mve_vqdmulltq_n_s<mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_5 1 "s_register_operand" "w")
+				  (match_operand:<V_elem> 2 "s_register_operand" "r")]
+	 VQDMULLTQ_N_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqdmullt.s%#<V_sz_elem>	%q0, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqdmulltq_s])
+;;
+(define_insn "mve_vqdmulltq_s<mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_5 1 "s_register_operand" "w")
+				  (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VQDMULLTQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqdmullt.s%#<V_sz_elem>	%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqmovnbq_u, vqmovnbq_s])
+;;
+(define_insn "mve_vqmovnbq_<supf><mode>"
+  [
+   (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+	(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
+				 (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VQMOVNBQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqmovnb.<supf>%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqmovntq_u, vqmovntq_s])
+;;
+(define_insn "mve_vqmovntq_<supf><mode>"
+  [
+   (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+	(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
+				 (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VQMOVNTQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqmovnt.<supf>%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqmovunbq_s])
+;;
+(define_insn "mve_vqmovunbq_s<mode>"
+  [
+   (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+	(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
+				 (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VQMOVUNBQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqmovunb.s%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vqmovuntq_s])
+;;
+(define_insn "mve_vqmovuntq_s<mode>"
+  [
+   (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+	(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
+				 (match_operand:MVE_5 2 "s_register_operand" "w")]
+	 VQMOVUNTQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vqmovunt.s%#<V_sz_elem>	%q0, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vrmlaldavhxq_s])
+;;
+(define_insn "mve_vrmlaldavhxq_sv4si"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:V4SI 1 "s_register_operand" "w")
+		    (match_operand:V4SI 2 "s_register_operand" "w")]
+	 VRMLALDAVHXQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vrmlaldavhx.s32 %Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vrmlsldavhq_s])
+;;
+(define_insn "mve_vrmlsldavhq_sv4si"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:V4SI 1 "s_register_operand" "w")
+		    (match_operand:V4SI 2 "s_register_operand" "w")]
+	 VRMLSLDAVHQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vrmlsldavh.s32\t%Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vrmlsldavhxq_s])
+;;
+(define_insn "mve_vrmlsldavhxq_sv4si"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:V4SI 1 "s_register_operand" "w")
+		    (match_operand:V4SI 2 "s_register_operand" "w")]
+	 VRMLSLDAVHXQ_S))
+  ]
+  "TARGET_HAVE_MVE"
+  "vrmlsldavhx.s32\t%Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vshllbq_n_s, vshllbq_n_u])
+;;
+(define_insn "mve_vshllbq_n_<supf><mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_3 1 "s_register_operand" "w")
+				  (match_operand:SI 2 "immediate_operand" "i")]
+	 VSHLLBQ_N))
+  ]
+  "TARGET_HAVE_MVE"
+  "vshllb.<supf>%#<V_sz_elem>\t%q0, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vshlltq_n_u, vshlltq_n_s])
+;;
+(define_insn "mve_vshlltq_n_<supf><mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_3 1 "s_register_operand" "w")
+				  (match_operand:SI 2 "immediate_operand" "i")]
+	 VSHLLTQ_N))
+  ]
+  "TARGET_HAVE_MVE"
+  "vshllt.<supf>%#<V_sz_elem>\t%q0, %q1, %2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vsubq_f])
+;;
+(define_insn "mve_vsubq_f<mode>"
+  [
+   (set (match_operand:MVE_0 0 "s_register_operand" "=w")
+	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
+		       (match_operand:MVE_0 2 "s_register_operand" "w")]
+	 VSUBQ_F))
+  ]
+  "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+  "vsub.f%#<V_sz_elem>\t%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmulltq_poly_p])
+;;
+(define_insn "mve_vmulltq_poly_p<mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_3 1 "s_register_operand" "w")
+				  (match_operand:MVE_3 2 "s_register_operand" "w")]
+	 VMULLTQ_POLY_P))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmullt.p%#<V_sz_elem>\t%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vmullbq_poly_p])
+;;
+(define_insn "mve_vmullbq_poly_p<mode>"
+  [
+   (set (match_operand:<V_double_width> 0 "s_register_operand" "=w")
+	(unspec:<V_double_width> [(match_operand:MVE_3 1 "s_register_operand" "w")
+				  (match_operand:MVE_3 2 "s_register_operand" "w")]
+	 VMULLBQ_POLY_P))
+  ]
+  "TARGET_HAVE_MVE"
+  "vmullb.p%#<V_sz_elem>\t%q0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vrmlaldavhq_u vrmlaldavhq_s])
+;;
+(define_insn "mve_vrmlaldavhq_<supf>v4si"
+  [
+   (set (match_operand:DI 0 "s_register_operand" "=r")
+	(unspec:DI [(match_operand:V4SI 1 "s_register_operand" "w")
+		    (match_operand:V4SI 2 "s_register_operand" "w")]
+	 VRMLALDAVHQ))
+  ]
+  "TARGET_HAVE_MVE"
+  "vrmlaldavh.<supf>32 %Q0, %R0, %q1, %q2"
+  [(set_attr "type" "mve_move")
+])