#include <stdbool.h>
#endif
-#ifdef __cplusplus
-extern "C" {
-#endif
-
#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
typedef __fp16 float16_t;
typedef float float32_t;
typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
#ifndef __ARM_MVE_PRESERVE_USER_NAMESPACE
+#define vst4q(__addr, __value) __arm_vst4q(__addr, __value)
+#define vdupq_n(__a) __arm_vdupq_n(__a)
+#define vabsq(__a) __arm_vabsq(__a)
+#define vclsq(__a) __arm_vclsq(__a)
+#define vclzq(__a) __arm_vclzq(__a)
+#define vnegq(__a) __arm_vnegq(__a)
+#define vaddlvq(__a) __arm_vaddlvq(__a)
+#define vaddvq(__a) __arm_vaddvq(__a)
+#define vmovlbq(__a) __arm_vmovlbq(__a)
+#define vmovltq(__a) __arm_vmovltq(__a)
+#define vmvnq(__a) __arm_vmvnq(__a)
+#define vrev16q(__a) __arm_vrev16q(__a)
+#define vrev32q(__a) __arm_vrev32q(__a)
+#define vrev64q(__a) __arm_vrev64q(__a)
+#define vqabsq(__a) __arm_vqabsq(__a)
+#define vqnegq(__a) __arm_vqnegq(__a)
+#define vshrq(__a, __imm) __arm_vshrq(__a, __imm)
+#define vaddlvq_p(__a, __p) __arm_vaddlvq_p(__a, __p)
+#define vcmpneq(__a, __b) __arm_vcmpneq(__a, __b)
+#define vshlq(__a, __b) __arm_vshlq(__a, __b)
+#define vsubq(__a, __b) __arm_vsubq(__a, __b)
+#define vrmulhq(__a, __b) __arm_vrmulhq(__a, __b)
+#define vrhaddq(__a, __b) __arm_vrhaddq(__a, __b)
+#define vqsubq(__a, __b) __arm_vqsubq(__a, __b)
+#define vqaddq(__a, __b) __arm_vqaddq(__a, __b)
+#define vorrq(__a, __b) __arm_vorrq(__a, __b)
+#define vornq(__a, __b) __arm_vornq(__a, __b)
+#define vmulq(__a, __b) __arm_vmulq(__a, __b)
+#define vmulltq_int(__a, __b) __arm_vmulltq_int(__a, __b)
+#define vmullbq_int(__a, __b) __arm_vmullbq_int(__a, __b)
+#define vmulhq(__a, __b) __arm_vmulhq(__a, __b)
+#define vmladavq(__a, __b) __arm_vmladavq(__a, __b)
+#define vminvq(__a, __b) __arm_vminvq(__a, __b)
+#define vminq(__a, __b) __arm_vminq(__a, __b)
+#define vmaxvq(__a, __b) __arm_vmaxvq(__a, __b)
+#define vmaxq(__a, __b) __arm_vmaxq(__a, __b)
+#define vhsubq(__a, __b) __arm_vhsubq(__a, __b)
+#define vhaddq(__a, __b) __arm_vhaddq(__a, __b)
+#define veorq(__a, __b) __arm_veorq(__a, __b)
+#define vcmphiq(__a, __b) __arm_vcmphiq(__a, __b)
+#define vcmpeqq(__a, __b) __arm_vcmpeqq(__a, __b)
+#define vcmpcsq(__a, __b) __arm_vcmpcsq(__a, __b)
+#define vcaddq_rot90(__a, __b) __arm_vcaddq_rot90(__a, __b)
+#define vcaddq_rot270(__a, __b) __arm_vcaddq_rot270(__a, __b)
+#define vbicq(__a, __b) __arm_vbicq(__a, __b)
+#define vandq(__a, __b) __arm_vandq(__a, __b)
+#define vaddvq_p(__a, __p) __arm_vaddvq_p(__a, __p)
+#define vaddvaq(__a, __b) __arm_vaddvaq(__a, __b)
+#define vaddq(__a, __b) __arm_vaddq(__a, __b)
+#define vabdq(__a, __b) __arm_vabdq(__a, __b)
+#define vshlq_r(__a, __b) __arm_vshlq_r(__a, __b)
+#define vrshlq(__a, __b) __arm_vrshlq(__a, __b)
+#define vqshlq(__a, __b) __arm_vqshlq(__a, __b)
+#define vqshlq_r(__a, __b) __arm_vqshlq_r(__a, __b)
+#define vqrshlq(__a, __b) __arm_vqrshlq(__a, __b)
+#define vminavq(__a, __b) __arm_vminavq(__a, __b)
+#define vminaq(__a, __b) __arm_vminaq(__a, __b)
+#define vmaxavq(__a, __b) __arm_vmaxavq(__a, __b)
+#define vmaxaq(__a, __b) __arm_vmaxaq(__a, __b)
+#define vbrsrq(__a, __b) __arm_vbrsrq(__a, __b)
+#define vshlq_n(__a, __imm) __arm_vshlq_n(__a, __imm)
+#define vrshrq(__a, __imm) __arm_vrshrq(__a, __imm)
+#define vqshlq_n(__a, __imm) __arm_vqshlq_n(__a, __imm)
+#define vcmpltq(__a, __b) __arm_vcmpltq(__a, __b)
+#define vcmpleq(__a, __b) __arm_vcmpleq(__a, __b)
+#define vcmpgtq(__a, __b) __arm_vcmpgtq(__a, __b)
+#define vcmpgeq(__a, __b) __arm_vcmpgeq(__a, __b)
+#define vqshluq(__a, __imm) __arm_vqshluq(__a, __imm)
+#define vqrdmulhq(__a, __b) __arm_vqrdmulhq(__a, __b)
+#define vqdmulhq(__a, __b) __arm_vqdmulhq(__a, __b)
+#define vmlsdavxq(__a, __b) __arm_vmlsdavxq(__a, __b)
+#define vmlsdavq(__a, __b) __arm_vmlsdavq(__a, __b)
+#define vmladavxq(__a, __b) __arm_vmladavxq(__a, __b)
+#define vhcaddq_rot90(__a, __b) __arm_vhcaddq_rot90(__a, __b)
+#define vhcaddq_rot270(__a, __b) __arm_vhcaddq_rot270(__a, __b)
+#define vqmovntq(__a, __b) __arm_vqmovntq(__a, __b)
+#define vqmovnbq(__a, __b) __arm_vqmovnbq(__a, __b)
+#define vmulltq_poly(__a, __b) __arm_vmulltq_poly(__a, __b)
+#define vmullbq_poly(__a, __b) __arm_vmullbq_poly(__a, __b)
+#define vmovntq(__a, __b) __arm_vmovntq(__a, __b)
+#define vmovnbq(__a, __b) __arm_vmovnbq(__a, __b)
+#define vmlaldavq(__a, __b) __arm_vmlaldavq(__a, __b)
+#define vqmovuntq(__a, __b) __arm_vqmovuntq(__a, __b)
+#define vqmovunbq(__a, __b) __arm_vqmovunbq(__a, __b)
+#define vshlltq(__a, __imm) __arm_vshlltq(__a, __imm)
+#define vshllbq(__a, __imm) __arm_vshllbq(__a, __imm)
+#define vqdmulltq(__a, __b) __arm_vqdmulltq(__a, __b)
+#define vqdmullbq(__a, __b) __arm_vqdmullbq(__a, __b)
+#define vmlsldavxq(__a, __b) __arm_vmlsldavxq(__a, __b)
+#define vmlsldavq(__a, __b) __arm_vmlsldavq(__a, __b)
+#define vmlaldavxq(__a, __b) __arm_vmlaldavxq(__a, __b)
+#define vrmlaldavhq(__a, __b) __arm_vrmlaldavhq(__a, __b)
+#define vaddlvaq(__a, __b) __arm_vaddlvaq(__a, __b)
+#define vrmlsldavhxq(__a, __b) __arm_vrmlsldavhxq(__a, __b)
+#define vrmlsldavhq(__a, __b) __arm_vrmlsldavhq(__a, __b)
+#define vrmlaldavhxq(__a, __b) __arm_vrmlaldavhxq(__a, __b)
+#define vabavq(__a, __b, __c) __arm_vabavq(__a, __b, __c)
+#define vbicq_m_n(__a, __imm, __p) __arm_vbicq_m_n(__a, __imm, __p)
+#define vqrshrnbq(__a, __b, __imm) __arm_vqrshrnbq(__a, __b, __imm)
+#define vqrshrunbq(__a, __b, __imm) __arm_vqrshrunbq(__a, __b, __imm)
+#define vrmlaldavhaq(__a, __b, __c) __arm_vrmlaldavhaq(__a, __b, __c)
+#define vshlcq(__a, __b, __imm) __arm_vshlcq(__a, __b, __imm)
+#define vpselq(__a, __b, __p) __arm_vpselq(__a, __b, __p)
+#define vrev64q_m(__inactive, __a, __p) __arm_vrev64q_m(__inactive, __a, __p)
+#define vqrdmlashq(__a, __b, __c) __arm_vqrdmlashq(__a, __b, __c)
+#define vqrdmlahq(__a, __b, __c) __arm_vqrdmlahq(__a, __b, __c)
+#define vqdmlahq(__a, __b, __c) __arm_vqdmlahq(__a, __b, __c)
+#define vmvnq_m(__inactive, __a, __p) __arm_vmvnq_m(__inactive, __a, __p)
+#define vmlasq(__a, __b, __c) __arm_vmlasq(__a, __b, __c)
+#define vmlaq(__a, __b, __c) __arm_vmlaq(__a, __b, __c)
+#define vmladavq_p(__a, __b, __p) __arm_vmladavq_p(__a, __b, __p)
+#define vmladavaq(__a, __b, __c) __arm_vmladavaq(__a, __b, __c)
+#define vminvq_p(__a, __b, __p) __arm_vminvq_p(__a, __b, __p)
+#define vmaxvq_p(__a, __b, __p) __arm_vmaxvq_p(__a, __b, __p)
+#define vdupq_m(__inactive, __a, __p) __arm_vdupq_m(__inactive, __a, __p)
+#define vcmpneq_m(__a, __b, __p) __arm_vcmpneq_m(__a, __b, __p)
+#define vcmphiq_m(__a, __b, __p) __arm_vcmphiq_m(__a, __b, __p)
+#define vcmpeqq_m(__a, __b, __p) __arm_vcmpeqq_m(__a, __b, __p)
+#define vcmpcsq_m(__a, __b, __p) __arm_vcmpcsq_m(__a, __b, __p)
+#define vcmpcsq_m_n(__a, __b, __p) __arm_vcmpcsq_m_n(__a, __b, __p)
+#define vclzq_m(__inactive, __a, __p) __arm_vclzq_m(__inactive, __a, __p)
+#define vaddvaq_p(__a, __b, __p) __arm_vaddvaq_p(__a, __b, __p)
+#define vsriq(__a, __b, __imm) __arm_vsriq(__a, __b, __imm)
+#define vsliq(__a, __b, __imm) __arm_vsliq(__a, __b, __imm)
+#define vshlq_m_r(__a, __b, __p) __arm_vshlq_m_r(__a, __b, __p)
+#define vrshlq_m_n(__a, __b, __p) __arm_vrshlq_m_n(__a, __b, __p)
+#define vqshlq_m_r(__a, __b, __p) __arm_vqshlq_m_r(__a, __b, __p)
+#define vqrshlq_m_n(__a, __b, __p) __arm_vqrshlq_m_n(__a, __b, __p)
+#define vminavq_p(__a, __b, __p) __arm_vminavq_p(__a, __b, __p)
+#define vminaq_m(__a, __b, __p) __arm_vminaq_m(__a, __b, __p)
+#define vmaxavq_p(__a, __b, __p) __arm_vmaxavq_p(__a, __b, __p)
+#define vmaxaq_m(__a, __b, __p) __arm_vmaxaq_m(__a, __b, __p)
+#define vcmpltq_m(__a, __b, __p) __arm_vcmpltq_m(__a, __b, __p)
+#define vcmpleq_m(__a, __b, __p) __arm_vcmpleq_m(__a, __b, __p)
+#define vcmpgtq_m(__a, __b, __p) __arm_vcmpgtq_m(__a, __b, __p)
+#define vcmpgeq_m(__a, __b, __p) __arm_vcmpgeq_m(__a, __b, __p)
+#define vqnegq_m(__inactive, __a, __p) __arm_vqnegq_m(__inactive, __a, __p)
+#define vqabsq_m(__inactive, __a, __p) __arm_vqabsq_m(__inactive, __a, __p)
+#define vnegq_m(__inactive, __a, __p) __arm_vnegq_m(__inactive, __a, __p)
+#define vmlsdavxq_p(__a, __b, __p) __arm_vmlsdavxq_p(__a, __b, __p)
+#define vmlsdavq_p(__a, __b, __p) __arm_vmlsdavq_p(__a, __b, __p)
+#define vmladavxq_p(__a, __b, __p) __arm_vmladavxq_p(__a, __b, __p)
+#define vclsq_m(__inactive, __a, __p) __arm_vclsq_m(__inactive, __a, __p)
+#define vabsq_m(__inactive, __a, __p) __arm_vabsq_m(__inactive, __a, __p)
+#define vqrdmlsdhxq(__inactive, __a, __b) __arm_vqrdmlsdhxq(__inactive, __a, __b)
+#define vqrdmlsdhq(__inactive, __a, __b) __arm_vqrdmlsdhq(__inactive, __a, __b)
+#define vqrdmladhxq(__inactive, __a, __b) __arm_vqrdmladhxq(__inactive, __a, __b)
+#define vqrdmladhq(__inactive, __a, __b) __arm_vqrdmladhq(__inactive, __a, __b)
+#define vqdmlsdhxq(__inactive, __a, __b) __arm_vqdmlsdhxq(__inactive, __a, __b)
+#define vqdmlsdhq(__inactive, __a, __b) __arm_vqdmlsdhq(__inactive, __a, __b)
+#define vqdmladhxq(__inactive, __a, __b) __arm_vqdmladhxq(__inactive, __a, __b)
+#define vqdmladhq(__inactive, __a, __b) __arm_vqdmladhq(__inactive, __a, __b)
+#define vmlsdavaxq(__a, __b, __c) __arm_vmlsdavaxq(__a, __b, __c)
+#define vmlsdavaq(__a, __b, __c) __arm_vmlsdavaq(__a, __b, __c)
+#define vmladavaxq(__a, __b, __c) __arm_vmladavaxq(__a, __b, __c)
+#define vrmlaldavhaxq(__a, __b, __c) __arm_vrmlaldavhaxq(__a, __b, __c)
+#define vrmlsldavhaq(__a, __b, __c) __arm_vrmlsldavhaq(__a, __b, __c)
+#define vrmlsldavhaxq(__a, __b, __c) __arm_vrmlsldavhaxq(__a, __b, __c)
+#define vaddlvaq_p(__a, __b, __p) __arm_vaddlvaq_p(__a, __b, __p)
+#define vrev16q_m(__inactive, __a, __p) __arm_vrev16q_m(__inactive, __a, __p)
+#define vrmlaldavhq_p(__a, __b, __p) __arm_vrmlaldavhq_p(__a, __b, __p)
+#define vrmlaldavhxq_p(__a, __b, __p) __arm_vrmlaldavhxq_p(__a, __b, __p)
+#define vrmlsldavhq_p(__a, __b, __p) __arm_vrmlsldavhq_p(__a, __b, __p)
+#define vrmlsldavhxq_p(__a, __b, __p) __arm_vrmlsldavhxq_p(__a, __b, __p)
+#define vorrq_m_n(__a, __imm, __p) __arm_vorrq_m_n(__a, __imm, __p)
+#define vqrshrntq(__a, __b, __imm) __arm_vqrshrntq(__a, __b, __imm)
+#define vqshrnbq(__a, __b, __imm) __arm_vqshrnbq(__a, __b, __imm)
+#define vqshrntq(__a, __b, __imm) __arm_vqshrntq(__a, __b, __imm)
+#define vrshrnbq(__a, __b, __imm) __arm_vrshrnbq(__a, __b, __imm)
+#define vrshrntq(__a, __b, __imm) __arm_vrshrntq(__a, __b, __imm)
+#define vshrnbq(__a, __b, __imm) __arm_vshrnbq(__a, __b, __imm)
+#define vshrntq(__a, __b, __imm) __arm_vshrntq(__a, __b, __imm)
+#define vmlaldavaq(__a, __b, __c) __arm_vmlaldavaq(__a, __b, __c)
+#define vmlaldavaxq(__a, __b, __c) __arm_vmlaldavaxq(__a, __b, __c)
+#define vmlsldavaq(__a, __b, __c) __arm_vmlsldavaq(__a, __b, __c)
+#define vmlsldavaxq(__a, __b, __c) __arm_vmlsldavaxq(__a, __b, __c)
+#define vmlaldavq_p(__a, __b, __p) __arm_vmlaldavq_p(__a, __b, __p)
+#define vmlaldavxq_p(__a, __b, __p) __arm_vmlaldavxq_p(__a, __b, __p)
+#define vmlsldavq_p(__a, __b, __p) __arm_vmlsldavq_p(__a, __b, __p)
+#define vmlsldavxq_p(__a, __b, __p) __arm_vmlsldavxq_p(__a, __b, __p)
+#define vmovlbq_m(__inactive, __a, __p) __arm_vmovlbq_m(__inactive, __a, __p)
+#define vmovltq_m(__inactive, __a, __p) __arm_vmovltq_m(__inactive, __a, __p)
+#define vmovnbq_m(__a, __b, __p) __arm_vmovnbq_m(__a, __b, __p)
+#define vmovntq_m(__a, __b, __p) __arm_vmovntq_m(__a, __b, __p)
+#define vqmovnbq_m(__a, __b, __p) __arm_vqmovnbq_m(__a, __b, __p)
+#define vqmovntq_m(__a, __b, __p) __arm_vqmovntq_m(__a, __b, __p)
+#define vrev32q_m(__inactive, __a, __p) __arm_vrev32q_m(__inactive, __a, __p)
+#define vqrshruntq(__a, __b, __imm) __arm_vqrshruntq(__a, __b, __imm)
+#define vqshrunbq(__a, __b, __imm) __arm_vqshrunbq(__a, __b, __imm)
+#define vqshruntq(__a, __b, __imm) __arm_vqshruntq(__a, __b, __imm)
+#define vqmovunbq_m(__a, __b, __p) __arm_vqmovunbq_m(__a, __b, __p)
+#define vqmovuntq_m(__a, __b, __p) __arm_vqmovuntq_m(__a, __b, __p)
+#define vsriq_m(__a, __b, __imm, __p) __arm_vsriq_m(__a, __b, __imm, __p)
+#define vsubq_m(__inactive, __a, __b, __p) __arm_vsubq_m(__inactive, __a, __b, __p)
+#define vqshluq_m(__inactive, __a, __imm, __p) __arm_vqshluq_m(__inactive, __a, __imm, __p)
+#define vabavq_p(__a, __b, __c, __p) __arm_vabavq_p(__a, __b, __c, __p)
+#define vshlq_m(__inactive, __a, __b, __p) __arm_vshlq_m(__inactive, __a, __b, __p)
+#define vabdq_m(__inactive, __a, __b, __p) __arm_vabdq_m(__inactive, __a, __b, __p)
+#define vaddq_m(__inactive, __a, __b, __p) __arm_vaddq_m(__inactive, __a, __b, __p)
+#define vandq_m(__inactive, __a, __b, __p) __arm_vandq_m(__inactive, __a, __b, __p)
+#define vbicq_m(__inactive, __a, __b, __p) __arm_vbicq_m(__inactive, __a, __b, __p)
+#define vbrsrq_m(__inactive, __a, __b, __p) __arm_vbrsrq_m(__inactive, __a, __b, __p)
+#define vcaddq_rot270_m(__inactive, __a, __b, __p) __arm_vcaddq_rot270_m(__inactive, __a, __b, __p)
+#define vcaddq_rot90_m(__inactive, __a, __b, __p) __arm_vcaddq_rot90_m(__inactive, __a, __b, __p)
+#define veorq_m(__inactive, __a, __b, __p) __arm_veorq_m(__inactive, __a, __b, __p)
+#define vhaddq_m(__inactive, __a, __b, __p) __arm_vhaddq_m(__inactive, __a, __b, __p)
+#define vhcaddq_rot270_m(__inactive, __a, __b, __p) __arm_vhcaddq_rot270_m(__inactive, __a, __b, __p)
+#define vhcaddq_rot90_m(__inactive, __a, __b, __p) __arm_vhcaddq_rot90_m(__inactive, __a, __b, __p)
+#define vhsubq_m(__inactive, __a, __b, __p) __arm_vhsubq_m(__inactive, __a, __b, __p)
+#define vmaxq_m(__inactive, __a, __b, __p) __arm_vmaxq_m(__inactive, __a, __b, __p)
+#define vminq_m(__inactive, __a, __b, __p) __arm_vminq_m(__inactive, __a, __b, __p)
+#define vmladavaq_p(__a, __b, __c, __p) __arm_vmladavaq_p(__a, __b, __c, __p)
+#define vmladavaxq_p(__a, __b, __c, __p) __arm_vmladavaxq_p(__a, __b, __c, __p)
+#define vmlaq_m(__a, __b, __c, __p) __arm_vmlaq_m(__a, __b, __c, __p)
+#define vmlasq_m(__a, __b, __c, __p) __arm_vmlasq_m(__a, __b, __c, __p)
+#define vmlsdavaq_p(__a, __b, __c, __p) __arm_vmlsdavaq_p(__a, __b, __c, __p)
+#define vmlsdavaxq_p(__a, __b, __c, __p) __arm_vmlsdavaxq_p(__a, __b, __c, __p)
+#define vmulhq_m(__inactive, __a, __b, __p) __arm_vmulhq_m(__inactive, __a, __b, __p)
+#define vmullbq_int_m(__inactive, __a, __b, __p) __arm_vmullbq_int_m(__inactive, __a, __b, __p)
+#define vmulltq_int_m(__inactive, __a, __b, __p) __arm_vmulltq_int_m(__inactive, __a, __b, __p)
+#define vmulq_m(__inactive, __a, __b, __p) __arm_vmulq_m(__inactive, __a, __b, __p)
+#define vornq_m(__inactive, __a, __b, __p) __arm_vornq_m(__inactive, __a, __b, __p)
+#define vorrq_m(__inactive, __a, __b, __p) __arm_vorrq_m(__inactive, __a, __b, __p)
+#define vqaddq_m(__inactive, __a, __b, __p) __arm_vqaddq_m(__inactive, __a, __b, __p)
+#define vqdmladhq_m(__inactive, __a, __b, __p) __arm_vqdmladhq_m(__inactive, __a, __b, __p)
+#define vqdmladhxq_m(__inactive, __a, __b, __p) __arm_vqdmladhxq_m(__inactive, __a, __b, __p)
+#define vqdmlahq_m(__a, __b, __c, __p) __arm_vqdmlahq_m(__a, __b, __c, __p)
+#define vqdmlsdhq_m(__inactive, __a, __b, __p) __arm_vqdmlsdhq_m(__inactive, __a, __b, __p)
+#define vqdmlsdhxq_m(__inactive, __a, __b, __p) __arm_vqdmlsdhxq_m(__inactive, __a, __b, __p)
+#define vqdmulhq_m(__inactive, __a, __b, __p) __arm_vqdmulhq_m(__inactive, __a, __b, __p)
+#define vqrdmladhq_m(__inactive, __a, __b, __p) __arm_vqrdmladhq_m(__inactive, __a, __b, __p)
+#define vqrdmladhxq_m(__inactive, __a, __b, __p) __arm_vqrdmladhxq_m(__inactive, __a, __b, __p)
+#define vqrdmlahq_m(__a, __b, __c, __p) __arm_vqrdmlahq_m(__a, __b, __c, __p)
+#define vqrdmlashq_m(__a, __b, __c, __p) __arm_vqrdmlashq_m(__a, __b, __c, __p)
+#define vqrdmlsdhq_m(__inactive, __a, __b, __p) __arm_vqrdmlsdhq_m(__inactive, __a, __b, __p)
+#define vqrdmlsdhxq_m(__inactive, __a, __b, __p) __arm_vqrdmlsdhxq_m(__inactive, __a, __b, __p)
+#define vqrdmulhq_m(__inactive, __a, __b, __p) __arm_vqrdmulhq_m(__inactive, __a, __b, __p)
+#define vqrshlq_m(__inactive, __a, __b, __p) __arm_vqrshlq_m(__inactive, __a, __b, __p)
+#define vqshlq_m_n(__inactive, __a, __imm, __p) __arm_vqshlq_m_n(__inactive, __a, __imm, __p)
+#define vqshlq_m(__inactive, __a, __b, __p) __arm_vqshlq_m(__inactive, __a, __b, __p)
+#define vqsubq_m(__inactive, __a, __b, __p) __arm_vqsubq_m(__inactive, __a, __b, __p)
+#define vrhaddq_m(__inactive, __a, __b, __p) __arm_vrhaddq_m(__inactive, __a, __b, __p)
+#define vrmulhq_m(__inactive, __a, __b, __p) __arm_vrmulhq_m(__inactive, __a, __b, __p)
+#define vrshlq_m(__inactive, __a, __b, __p) __arm_vrshlq_m(__inactive, __a, __b, __p)
+#define vrshrq_m(__inactive, __a, __imm, __p) __arm_vrshrq_m(__inactive, __a, __imm, __p)
+#define vshlq_m_n(__inactive, __a, __imm, __p) __arm_vshlq_m_n(__inactive, __a, __imm, __p)
+#define vshrq_m(__inactive, __a, __imm, __p) __arm_vshrq_m(__inactive, __a, __imm, __p)
+#define vsliq_m(__a, __b, __imm, __p) __arm_vsliq_m(__a, __b, __imm, __p)
+#define vmlaldavaq_p(__a, __b, __c, __p) __arm_vmlaldavaq_p(__a, __b, __c, __p)
+#define vmlaldavaxq_p(__a, __b, __c, __p) __arm_vmlaldavaxq_p(__a, __b, __c, __p)
+#define vmlsldavaq_p(__a, __b, __c, __p) __arm_vmlsldavaq_p(__a, __b, __c, __p)
+#define vmlsldavaxq_p(__a, __b, __c, __p) __arm_vmlsldavaxq_p(__a, __b, __c, __p)
+#define vmullbq_poly_m(__inactive, __a, __b, __p) __arm_vmullbq_poly_m(__inactive, __a, __b, __p)
+#define vmulltq_poly_m(__inactive, __a, __b, __p) __arm_vmulltq_poly_m(__inactive, __a, __b, __p)
+#define vqdmullbq_m(__inactive, __a, __b, __p) __arm_vqdmullbq_m(__inactive, __a, __b, __p)
+#define vqdmulltq_m(__inactive, __a, __b, __p) __arm_vqdmulltq_m(__inactive, __a, __b, __p)
+#define vqrshrnbq_m(__a, __b, __imm, __p) __arm_vqrshrnbq_m(__a, __b, __imm, __p)
+#define vqrshrntq_m(__a, __b, __imm, __p) __arm_vqrshrntq_m(__a, __b, __imm, __p)
+#define vqrshrunbq_m(__a, __b, __imm, __p) __arm_vqrshrunbq_m(__a, __b, __imm, __p)
+#define vqrshruntq_m(__a, __b, __imm, __p) __arm_vqrshruntq_m(__a, __b, __imm, __p)
+#define vqshrnbq_m(__a, __b, __imm, __p) __arm_vqshrnbq_m(__a, __b, __imm, __p)
+#define vqshrntq_m(__a, __b, __imm, __p) __arm_vqshrntq_m(__a, __b, __imm, __p)
+#define vqshrunbq_m(__a, __b, __imm, __p) __arm_vqshrunbq_m(__a, __b, __imm, __p)
+#define vqshruntq_m(__a, __b, __imm, __p) __arm_vqshruntq_m(__a, __b, __imm, __p)
+#define vrmlaldavhaq_p(__a, __b, __c, __p) __arm_vrmlaldavhaq_p(__a, __b, __c, __p)
+#define vrmlaldavhaxq_p(__a, __b, __c, __p) __arm_vrmlaldavhaxq_p(__a, __b, __c, __p)
+#define vrmlsldavhaq_p(__a, __b, __c, __p) __arm_vrmlsldavhaq_p(__a, __b, __c, __p)
+#define vrmlsldavhaxq_p(__a, __b, __c, __p) __arm_vrmlsldavhaxq_p(__a, __b, __c, __p)
+#define vrshrnbq_m(__a, __b, __imm, __p) __arm_vrshrnbq_m(__a, __b, __imm, __p)
+#define vrshrntq_m(__a, __b, __imm, __p) __arm_vrshrntq_m(__a, __b, __imm, __p)
+#define vshllbq_m(__inactive, __a, __imm, __p) __arm_vshllbq_m(__inactive, __a, __imm, __p)
+#define vshlltq_m(__inactive, __a, __imm, __p) __arm_vshlltq_m(__inactive, __a, __imm, __p)
+#define vshrnbq_m(__a, __b, __imm, __p) __arm_vshrnbq_m(__a, __b, __imm, __p)
+#define vshrntq_m(__a, __b, __imm, __p) __arm_vshrntq_m(__a, __b, __imm, __p)
+#define vstrbq_scatter_offset(__base, __offset, __value) __arm_vstrbq_scatter_offset(__base, __offset, __value)
+#define vstrbq(__addr, __value) __arm_vstrbq(__addr, __value)
+#define vstrwq_scatter_base(__addr, __offset, __value) __arm_vstrwq_scatter_base(__addr, __offset, __value)
+#define vldrbq_gather_offset(__base, __offset) __arm_vldrbq_gather_offset(__base, __offset)
+#define vstrbq_p(__addr, __value, __p) __arm_vstrbq_p(__addr, __value, __p)
+#define vstrbq_scatter_offset_p(__base, __offset, __value, __p) __arm_vstrbq_scatter_offset_p(__base, __offset, __value, __p)
+#define vstrwq_scatter_base_p(__addr, __offset, __value, __p) __arm_vstrwq_scatter_base_p(__addr, __offset, __value, __p)
+#define vldrbq_gather_offset_z(__base, __offset, __p) __arm_vldrbq_gather_offset_z(__base, __offset, __p)
+#define vld1q(__base) __arm_vld1q(__base)
+#define vldrhq_gather_offset(__base, __offset) __arm_vldrhq_gather_offset(__base, __offset)
+#define vldrhq_gather_offset_z(__base, __offset, __p) __arm_vldrhq_gather_offset_z(__base, __offset, __p)
+#define vldrhq_gather_shifted_offset(__base, __offset) __arm_vldrhq_gather_shifted_offset(__base, __offset)
+#define vldrhq_gather_shifted_offset_z(__base, __offset, __p) __arm_vldrhq_gather_shifted_offset_z(__base, __offset, __p)
+#define vldrdq_gather_offset(__base, __offset) __arm_vldrdq_gather_offset(__base, __offset)
+#define vldrdq_gather_offset_z(__base, __offset, __p) __arm_vldrdq_gather_offset_z(__base, __offset, __p)
+#define vldrdq_gather_shifted_offset(__base, __offset) __arm_vldrdq_gather_shifted_offset(__base, __offset)
+#define vldrdq_gather_shifted_offset_z(__base, __offset, __p) __arm_vldrdq_gather_shifted_offset_z(__base, __offset, __p)
+#define vldrwq_gather_offset(__base, __offset) __arm_vldrwq_gather_offset(__base, __offset)
+#define vldrwq_gather_offset_z(__base, __offset, __p) __arm_vldrwq_gather_offset_z(__base, __offset, __p)
+#define vldrwq_gather_shifted_offset(__base, __offset) __arm_vldrwq_gather_shifted_offset(__base, __offset)
+#define vldrwq_gather_shifted_offset_z(__base, __offset, __p) __arm_vldrwq_gather_shifted_offset_z(__base, __offset, __p)
+#define vst1q(__addr, __value) __arm_vst1q(__addr, __value)
+#define vstrhq_scatter_offset(__base, __offset, __value) __arm_vstrhq_scatter_offset(__base, __offset, __value)
+#define vstrhq_scatter_offset_p(__base, __offset, __value, __p) __arm_vstrhq_scatter_offset_p(__base, __offset, __value, __p)
+#define vstrhq_scatter_shifted_offset(__base, __offset, __value) __arm_vstrhq_scatter_shifted_offset(__base, __offset, __value)
+#define vstrhq_scatter_shifted_offset_p(__base, __offset, __value, __p) __arm_vstrhq_scatter_shifted_offset_p(__base, __offset, __value, __p)
+#define vstrhq(__addr, __value) __arm_vstrhq(__addr, __value)
+#define vstrhq_p(__addr, __value, __p) __arm_vstrhq_p(__addr, __value, __p)
+#define vstrwq(__addr, __value) __arm_vstrwq(__addr, __value)
+#define vstrwq_p(__addr, __value, __p) __arm_vstrwq_p(__addr, __value, __p)
+#define vstrdq_scatter_base_p(__addr, __offset, __value, __p) __arm_vstrdq_scatter_base_p(__addr, __offset, __value, __p)
+#define vstrdq_scatter_base(__addr, __offset, __value) __arm_vstrdq_scatter_base(__addr, __offset, __value)
+#define vstrdq_scatter_offset_p(__base, __offset, __value, __p) __arm_vstrdq_scatter_offset_p(__base, __offset, __value, __p)
+#define vstrdq_scatter_offset(__base, __offset, __value) __arm_vstrdq_scatter_offset(__base, __offset, __value)
+#define vstrdq_scatter_shifted_offset_p(__base, __offset, __value, __p) __arm_vstrdq_scatter_shifted_offset_p(__base, __offset, __value, __p)
+#define vstrdq_scatter_shifted_offset(__base, __offset, __value) __arm_vstrdq_scatter_shifted_offset(__base, __offset, __value)
+#define vstrwq_scatter_offset_p(__base, __offset, __value, __p) __arm_vstrwq_scatter_offset_p(__base, __offset, __value, __p)
+#define vstrwq_scatter_offset(__base, __offset, __value) __arm_vstrwq_scatter_offset(__base, __offset, __value)
+#define vstrwq_scatter_shifted_offset_p(__base, __offset, __value, __p) __arm_vstrwq_scatter_shifted_offset_p(__base, __offset, __value, __p)
+#define vstrwq_scatter_shifted_offset(__base, __offset, __value) __arm_vstrwq_scatter_shifted_offset(__base, __offset, __value)
+#define vuninitializedq(__v) __arm_vuninitializedq(__v)
+#define vreinterpretq_s16(__a) __arm_vreinterpretq_s16(__a)
+#define vreinterpretq_s32(__a) __arm_vreinterpretq_s32(__a)
+#define vreinterpretq_s64(__a) __arm_vreinterpretq_s64(__a)
+#define vreinterpretq_s8(__a) __arm_vreinterpretq_s8(__a)
+#define vreinterpretq_u16(__a) __arm_vreinterpretq_u16(__a)
+#define vreinterpretq_u32(__a) __arm_vreinterpretq_u32(__a)
+#define vreinterpretq_u64(__a) __arm_vreinterpretq_u64(__a)
+#define vreinterpretq_u8(__a) __arm_vreinterpretq_u8(__a)
+#define vddupq_m(__inactive, __a, __imm, __p) __arm_vddupq_m(__inactive, __a, __imm, __p)
+#define vddupq_u8(__a, __imm) __arm_vddupq_u8(__a, __imm)
+#define vddupq_u32(__a, __imm) __arm_vddupq_u32(__a, __imm)
+#define vddupq_u16(__a, __imm) __arm_vddupq_u16(__a, __imm)
+#define vdwdupq_m(__inactive, __a, __b, __imm, __p) __arm_vdwdupq_m(__inactive, __a, __b, __imm, __p)
+#define vdwdupq_u8(__a, __b, __imm) __arm_vdwdupq_u8(__a, __b, __imm)
+#define vdwdupq_u32(__a, __b, __imm) __arm_vdwdupq_u32(__a, __b, __imm)
+#define vdwdupq_u16(__a, __b, __imm) __arm_vdwdupq_u16(__a, __b, __imm)
+#define vidupq_m(__inactive, __a, __imm, __p) __arm_vidupq_m(__inactive, __a, __imm, __p)
+#define vidupq_u8(__a, __imm) __arm_vidupq_u8(__a, __imm)
+#define vidupq_u32(__a, __imm) __arm_vidupq_u32(__a, __imm)
+#define vidupq_u16(__a, __imm) __arm_vidupq_u16(__a, __imm)
+#define viwdupq_m(__inactive, __a, __b, __imm, __p) __arm_viwdupq_m(__inactive, __a, __b, __imm, __p)
+#define viwdupq_u8(__a, __b, __imm) __arm_viwdupq_u8(__a, __b, __imm)
+#define viwdupq_u32(__a, __b, __imm) __arm_viwdupq_u32(__a, __b, __imm)
+#define viwdupq_u16(__a, __b, __imm) __arm_viwdupq_u16(__a, __b, __imm)
+#define vstrdq_scatter_base_wb(__addr, __offset, __value) __arm_vstrdq_scatter_base_wb(__addr, __offset, __value)
+#define vstrdq_scatter_base_wb_p(__addr, __offset, __value, __p) __arm_vstrdq_scatter_base_wb_p(__addr, __offset, __value, __p)
+#define vstrwq_scatter_base_wb_p(__addr, __offset, __value, __p) __arm_vstrwq_scatter_base_wb_p(__addr, __offset, __value, __p)
+#define vstrwq_scatter_base_wb(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb(__addr, __offset, __value)
+#define vddupq_x_u8(__a, __imm, __p) __arm_vddupq_x_u8(__a, __imm, __p)
+#define vddupq_x_u16(__a, __imm, __p) __arm_vddupq_x_u16(__a, __imm, __p)
+#define vddupq_x_u32(__a, __imm, __p) __arm_vddupq_x_u32(__a, __imm, __p)
+#define vdwdupq_x_u8(__a, __b, __imm, __p) __arm_vdwdupq_x_u8(__a, __b, __imm, __p)
+#define vdwdupq_x_u16(__a, __b, __imm, __p) __arm_vdwdupq_x_u16(__a, __b, __imm, __p)
+#define vdwdupq_x_u32(__a, __b, __imm, __p) __arm_vdwdupq_x_u32(__a, __b, __imm, __p)
+#define vidupq_x_u8(__a, __imm, __p) __arm_vidupq_x_u8(__a, __imm, __p)
+#define vidupq_x_u16(__a, __imm, __p) __arm_vidupq_x_u16(__a, __imm, __p)
+#define vidupq_x_u32(__a, __imm, __p) __arm_vidupq_x_u32(__a, __imm, __p)
+#define viwdupq_x_u8(__a, __b, __imm, __p) __arm_viwdupq_x_u8(__a, __b, __imm, __p)
+#define viwdupq_x_u16(__a, __b, __imm, __p) __arm_viwdupq_x_u16(__a, __b, __imm, __p)
+#define viwdupq_x_u32(__a, __b, __imm, __p) __arm_viwdupq_x_u32(__a, __b, __imm, __p)
+#define vminq_x(__a, __b, __p) __arm_vminq_x(__a, __b, __p)
+#define vmaxq_x(__a, __b, __p) __arm_vmaxq_x(__a, __b, __p)
+#define vabdq_x(__a, __b, __p) __arm_vabdq_x(__a, __b, __p)
+#define vabsq_x(__a, __p) __arm_vabsq_x(__a, __p)
+#define vaddq_x(__a, __b, __p) __arm_vaddq_x(__a, __b, __p)
+#define vclsq_x(__a, __p) __arm_vclsq_x(__a, __p)
+#define vclzq_x(__a, __p) __arm_vclzq_x(__a, __p)
+#define vnegq_x(__a, __p) __arm_vnegq_x(__a, __p)
+#define vmulhq_x(__a, __b, __p) __arm_vmulhq_x(__a, __b, __p)
+#define vmullbq_poly_x(__a, __b, __p) __arm_vmullbq_poly_x(__a, __b, __p)
+#define vmullbq_int_x(__a, __b, __p) __arm_vmullbq_int_x(__a, __b, __p)
+#define vmulltq_poly_x(__a, __b, __p) __arm_vmulltq_poly_x(__a, __b, __p)
+#define vmulltq_int_x(__a, __b, __p) __arm_vmulltq_int_x(__a, __b, __p)
+#define vmulq_x(__a, __b, __p) __arm_vmulq_x(__a, __b, __p)
+#define vsubq_x(__a, __b, __p) __arm_vsubq_x(__a, __b, __p)
+#define vcaddq_rot90_x(__a, __b, __p) __arm_vcaddq_rot90_x(__a, __b, __p)
+#define vcaddq_rot270_x(__a, __b, __p) __arm_vcaddq_rot270_x(__a, __b, __p)
+#define vhaddq_x(__a, __b, __p) __arm_vhaddq_x(__a, __b, __p)
+#define vhcaddq_rot90_x(__a, __b, __p) __arm_vhcaddq_rot90_x(__a, __b, __p)
+#define vhcaddq_rot270_x(__a, __b, __p) __arm_vhcaddq_rot270_x(__a, __b, __p)
+#define vhsubq_x(__a, __b, __p) __arm_vhsubq_x(__a, __b, __p)
+#define vrhaddq_x(__a, __b, __p) __arm_vrhaddq_x(__a, __b, __p)
+#define vrmulhq_x(__a, __b, __p) __arm_vrmulhq_x(__a, __b, __p)
+#define vandq_x(__a, __b, __p) __arm_vandq_x(__a, __b, __p)
+#define vbicq_x(__a, __b, __p) __arm_vbicq_x(__a, __b, __p)
+#define vbrsrq_x(__a, __b, __p) __arm_vbrsrq_x(__a, __b, __p)
+#define veorq_x(__a, __b, __p) __arm_veorq_x(__a, __b, __p)
+#define vmovlbq_x(__a, __p) __arm_vmovlbq_x(__a, __p)
+#define vmovltq_x(__a, __p) __arm_vmovltq_x(__a, __p)
+#define vmvnq_x(__a, __p) __arm_vmvnq_x(__a, __p)
+#define vornq_x(__a, __b, __p) __arm_vornq_x(__a, __b, __p)
+#define vorrq_x(__a, __b, __p) __arm_vorrq_x(__a, __b, __p)
+#define vrev16q_x(__a, __p) __arm_vrev16q_x(__a, __p)
+#define vrev32q_x(__a, __p) __arm_vrev32q_x(__a, __p)
+#define vrev64q_x(__a, __p) __arm_vrev64q_x(__a, __p)
+#define vrshlq_x(__a, __b, __p) __arm_vrshlq_x(__a, __b, __p)
+#define vshllbq_x(__a, __imm, __p) __arm_vshllbq_x(__a, __imm, __p)
+#define vshlltq_x(__a, __imm, __p) __arm_vshlltq_x(__a, __imm, __p)
+#define vshlq_x(__a, __b, __p) __arm_vshlq_x(__a, __b, __p)
+#define vshlq_x_n(__a, __imm, __p) __arm_vshlq_x_n(__a, __imm, __p)
+#define vrshrq_x(__a, __imm, __p) __arm_vrshrq_x(__a, __imm, __p)
+#define vshrq_x(__a, __imm, __p) __arm_vshrq_x(__a, __imm, __p)
+#define vadciq(__a, __b, __carry_out) __arm_vadciq(__a, __b, __carry_out)
+#define vadciq_m(__inactive, __a, __b, __carry_out, __p) __arm_vadciq_m(__inactive, __a, __b, __carry_out, __p)
+#define vadcq(__a, __b, __carry) __arm_vadcq(__a, __b, __carry)
+#define vadcq_m(__inactive, __a, __b, __carry, __p) __arm_vadcq_m(__inactive, __a, __b, __carry, __p)
+#define vsbciq(__a, __b, __carry_out) __arm_vsbciq(__a, __b, __carry_out)
+#define vsbciq_m(__inactive, __a, __b, __carry_out, __p) __arm_vsbciq_m(__inactive, __a, __b, __carry_out, __p)
+#define vsbcq(__a, __b, __carry) __arm_vsbcq(__a, __b, __carry)
+#define vsbcq_m(__inactive, __a, __b, __carry, __p) __arm_vsbcq_m(__inactive, __a, __b, __carry, __p)
+#define vst1q_p(__addr, __value, __p) __arm_vst1q_p(__addr, __value, __p)
+#define vst2q(__addr, __value) __arm_vst2q(__addr, __value)
+#define vld1q_z(__base, __p) __arm_vld1q_z(__base, __p)
+#define vld2q(__addr) __arm_vld2q(__addr)
+#define vld4q(__addr) __arm_vld4q(__addr)
+#define vsetq_lane(__a, __b, __idx) __arm_vsetq_lane(__a, __b, __idx)
+#define vgetq_lane(__a, __idx) __arm_vgetq_lane(__a, __idx)
+#define vshlcq_m(__a, __b, __imm, __p) __arm_vshlcq_m(__a, __b, __imm, __p)
+#define vrndxq(__a) __arm_vrndxq(__a)
+#define vrndq(__a) __arm_vrndq(__a)
+#define vrndpq(__a) __arm_vrndpq(__a)
+#define vrndnq(__a) __arm_vrndnq(__a)
+#define vrndmq(__a) __arm_vrndmq(__a)
+#define vrndaq(__a) __arm_vrndaq(__a)
+#define vcvttq_f32(__a) __arm_vcvttq_f32(__a)
+#define vcvtbq_f32(__a) __arm_vcvtbq_f32(__a)
+#define vcvtq(__a) __arm_vcvtq(__a)
+#define vcvtq_n(__a, __imm6) __arm_vcvtq_n(__a, __imm6)
+#define vminnmvq(__a, __b) __arm_vminnmvq(__a, __b)
+#define vminnmq(__a, __b) __arm_vminnmq(__a, __b)
+#define vminnmavq(__a, __b) __arm_vminnmavq(__a, __b)
+#define vminnmaq(__a, __b) __arm_vminnmaq(__a, __b)
+#define vmaxnmvq(__a, __b) __arm_vmaxnmvq(__a, __b)
+#define vmaxnmq(__a, __b) __arm_vmaxnmq(__a, __b)
+#define vmaxnmavq(__a, __b) __arm_vmaxnmavq(__a, __b)
+#define vmaxnmaq(__a, __b) __arm_vmaxnmaq(__a, __b)
+#define vcmulq_rot90(__a, __b) __arm_vcmulq_rot90(__a, __b)
+#define vcmulq_rot270(__a, __b) __arm_vcmulq_rot270(__a, __b)
+#define vcmulq_rot180(__a, __b) __arm_vcmulq_rot180(__a, __b)
+#define vcmulq(__a, __b) __arm_vcmulq(__a, __b)
+#define vcvtaq_m(__inactive, __a, __p) __arm_vcvtaq_m(__inactive, __a, __p)
+#define vcvtq_m(__inactive, __a, __p) __arm_vcvtq_m(__inactive, __a, __p)
+#define vcvtbq_m(__a, __b, __p) __arm_vcvtbq_m(__a, __b, __p)
+#define vcvttq_m(__a, __b, __p) __arm_vcvttq_m(__a, __b, __p)
+#define vcmlaq(__a, __b, __c) __arm_vcmlaq(__a, __b, __c)
+#define vcmlaq_rot180(__a, __b, __c) __arm_vcmlaq_rot180(__a, __b, __c)
+#define vcmlaq_rot270(__a, __b, __c) __arm_vcmlaq_rot270(__a, __b, __c)
+#define vcmlaq_rot90(__a, __b, __c) __arm_vcmlaq_rot90(__a, __b, __c)
+#define vfmaq(__a, __b, __c) __arm_vfmaq(__a, __b, __c)
+#define vfmasq(__a, __b, __c) __arm_vfmasq(__a, __b, __c)
+#define vfmsq(__a, __b, __c) __arm_vfmsq(__a, __b, __c)
+#define vcvtmq_m(__inactive, __a, __p) __arm_vcvtmq_m(__inactive, __a, __p)
+#define vcvtnq_m(__inactive, __a, __p) __arm_vcvtnq_m(__inactive, __a, __p)
+#define vcvtpq_m(__inactive, __a, __p) __arm_vcvtpq_m(__inactive, __a, __p)
+#define vmaxnmaq_m(__a, __b, __p) __arm_vmaxnmaq_m(__a, __b, __p)
+#define vmaxnmavq_p(__a, __b, __p) __arm_vmaxnmavq_p(__a, __b, __p)
+#define vmaxnmvq_p(__a, __b, __p) __arm_vmaxnmvq_p(__a, __b, __p)
+#define vminnmaq_m(__a, __b, __p) __arm_vminnmaq_m(__a, __b, __p)
+#define vminnmavq_p(__a, __b, __p) __arm_vminnmavq_p(__a, __b, __p)
+#define vminnmvq_p(__a, __b, __p) __arm_vminnmvq_p(__a, __b, __p)
+#define vrndaq_m(__inactive, __a, __p) __arm_vrndaq_m(__inactive, __a, __p)
+#define vrndmq_m(__inactive, __a, __p) __arm_vrndmq_m(__inactive, __a, __p)
+#define vrndnq_m(__inactive, __a, __p) __arm_vrndnq_m(__inactive, __a, __p)
+#define vrndpq_m(__inactive, __a, __p) __arm_vrndpq_m(__inactive, __a, __p)
+#define vrndq_m(__inactive, __a, __p) __arm_vrndq_m(__inactive, __a, __p)
+#define vrndxq_m(__inactive, __a, __p) __arm_vrndxq_m(__inactive, __a, __p)
+#define vcvtq_m_n(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n(__inactive, __a, __imm6, __p)
+#define vcmlaq_m(__a, __b, __c, __p) __arm_vcmlaq_m(__a, __b, __c, __p)
+#define vcmlaq_rot180_m(__a, __b, __c, __p) __arm_vcmlaq_rot180_m(__a, __b, __c, __p)
+#define vcmlaq_rot270_m(__a, __b, __c, __p) __arm_vcmlaq_rot270_m(__a, __b, __c, __p)
+#define vcmlaq_rot90_m(__a, __b, __c, __p) __arm_vcmlaq_rot90_m(__a, __b, __c, __p)
+#define vcmulq_m(__inactive, __a, __b, __p) __arm_vcmulq_m(__inactive, __a, __b, __p)
+#define vcmulq_rot180_m(__inactive, __a, __b, __p) __arm_vcmulq_rot180_m(__inactive, __a, __b, __p)
+#define vcmulq_rot270_m(__inactive, __a, __b, __p) __arm_vcmulq_rot270_m(__inactive, __a, __b, __p)
+#define vcmulq_rot90_m(__inactive, __a, __b, __p) __arm_vcmulq_rot90_m(__inactive, __a, __b, __p)
+#define vfmaq_m(__a, __b, __c, __p) __arm_vfmaq_m(__a, __b, __c, __p)
+#define vfmasq_m(__a, __b, __c, __p) __arm_vfmasq_m(__a, __b, __c, __p)
+#define vfmsq_m(__a, __b, __c, __p) __arm_vfmsq_m(__a, __b, __c, __p)
+#define vmaxnmq_m(__inactive, __a, __b, __p) __arm_vmaxnmq_m(__inactive, __a, __b, __p)
+#define vminnmq_m(__inactive, __a, __b, __p) __arm_vminnmq_m(__inactive, __a, __b, __p)
+#define vreinterpretq_f16(__a) __arm_vreinterpretq_f16(__a)
+#define vreinterpretq_f32(__a) __arm_vreinterpretq_f32(__a)
+#define vminnmq_x(__a, __b, __p) __arm_vminnmq_x(__a, __b, __p)
+#define vmaxnmq_x(__a, __b, __p) __arm_vmaxnmq_x(__a, __b, __p)
+#define vcmulq_x(__a, __b, __p) __arm_vcmulq_x(__a, __b, __p)
+#define vcmulq_rot90_x(__a, __b, __p) __arm_vcmulq_rot90_x(__a, __b, __p)
+#define vcmulq_rot180_x(__a, __b, __p) __arm_vcmulq_rot180_x(__a, __b, __p)
+#define vcmulq_rot270_x(__a, __b, __p) __arm_vcmulq_rot270_x(__a, __b, __p)
+#define vcvtq_x(__a, __p) __arm_vcvtq_x(__a, __p)
+#define vcvtq_x_n(__a, __imm6, __p) __arm_vcvtq_x_n(__a, __imm6, __p)
+#define vrndq_x(__a, __p) __arm_vrndq_x(__a, __p)
+#define vrndnq_x(__a, __p) __arm_vrndnq_x(__a, __p)
+#define vrndmq_x(__a, __p) __arm_vrndmq_x(__a, __p)
+#define vrndpq_x(__a, __p) __arm_vrndpq_x(__a, __p)
+#define vrndaq_x(__a, __p) __arm_vrndaq_x(__a, __p)
+#define vrndxq_x(__a, __p) __arm_vrndxq_x(__a, __p)
+
+
#define vst4q_s8( __addr, __value) __arm_vst4q_s8( __addr, __value)
#define vst4q_s16( __addr, __value) __arm_vst4q_s16( __addr, __value)
#define vst4q_s32( __addr, __value) __arm_vst4q_s32( __addr, __value)
}
#endif
-enum {
- __ARM_mve_type_fp_n = 1,
- __ARM_mve_type_int_n,
- __ARM_mve_type_float16_t_ptr,
- __ARM_mve_type_float16x8_t,
- __ARM_mve_type_float16x8x2_t,
- __ARM_mve_type_float16x8x4_t,
- __ARM_mve_type_float32_t_ptr,
- __ARM_mve_type_float32x4_t,
- __ARM_mve_type_float32x4x2_t,
- __ARM_mve_type_float32x4x4_t,
- __ARM_mve_type_int16_t_ptr,
- __ARM_mve_type_int16x8_t,
- __ARM_mve_type_int16x8x2_t,
- __ARM_mve_type_int16x8x4_t,
- __ARM_mve_type_int32_t_ptr,
- __ARM_mve_type_int32x4_t,
- __ARM_mve_type_int32x4x2_t,
- __ARM_mve_type_int32x4x4_t,
- __ARM_mve_type_int64_t_ptr,
- __ARM_mve_type_int64x2_t,
- __ARM_mve_type_int8_t_ptr,
- __ARM_mve_type_int8x16_t,
- __ARM_mve_type_int8x16x2_t,
- __ARM_mve_type_int8x16x4_t,
- __ARM_mve_type_uint16_t_ptr,
- __ARM_mve_type_uint16x8_t,
- __ARM_mve_type_uint16x8x2_t,
- __ARM_mve_type_uint16x8x4_t,
- __ARM_mve_type_uint32_t_ptr,
- __ARM_mve_type_uint32x4_t,
- __ARM_mve_type_uint32x4x2_t,
- __ARM_mve_type_uint32x4x4_t,
- __ARM_mve_type_uint64_t_ptr,
- __ARM_mve_type_uint64x2_t,
- __ARM_mve_type_uint8_t_ptr,
- __ARM_mve_type_uint8x16_t,
- __ARM_mve_type_uint8x16x2_t,
- __ARM_mve_type_uint8x16x4_t,
- __ARM_mve_unsupported_type
-};
+#ifdef __cplusplus
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (int8_t * __addr, int8x16x4_t __value)
+{
+ __arm_vst4q_s8 (__addr, __value);
+}
-#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
-#define __ARM_mve_typeid(x) _Generic(x, \
- float16_t: __ARM_mve_type_fp_n, \
- float16_t *: __ARM_mve_type_float16_t_ptr, \
- float16_t const *: __ARM_mve_type_float16_t_ptr, \
- float16x8_t: __ARM_mve_type_float16x8_t, \
- float16x8x2_t: __ARM_mve_type_float16x8x2_t, \
- float16x8x4_t: __ARM_mve_type_float16x8x4_t, \
- float32_t: __ARM_mve_type_fp_n, \
- float32_t *: __ARM_mve_type_float32_t_ptr, \
- float32_t const *: __ARM_mve_type_float32_t_ptr, \
- float32x4_t: __ARM_mve_type_float32x4_t, \
- float32x4x2_t: __ARM_mve_type_float32x4x2_t, \
- float32x4x4_t: __ARM_mve_type_float32x4x4_t, \
- int16_t: __ARM_mve_type_int_n, \
- int16_t *: __ARM_mve_type_int16_t_ptr, \
- int16_t const *: __ARM_mve_type_int16_t_ptr, \
- int16x8_t: __ARM_mve_type_int16x8_t, \
- int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
- int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
- int32_t: __ARM_mve_type_int_n, \
- int32_t *: __ARM_mve_type_int32_t_ptr, \
- int32_t const *: __ARM_mve_type_int32_t_ptr, \
- int32x4_t: __ARM_mve_type_int32x4_t, \
- int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
- int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
- int64_t: __ARM_mve_type_int_n, \
- int64_t *: __ARM_mve_type_int64_t_ptr, \
- int64_t const *: __ARM_mve_type_int64_t_ptr, \
- int64x2_t: __ARM_mve_type_int64x2_t, \
- int8_t: __ARM_mve_type_int_n, \
- int8_t *: __ARM_mve_type_int8_t_ptr, \
- int8_t const *: __ARM_mve_type_int8_t_ptr, \
- int8x16_t: __ARM_mve_type_int8x16_t, \
- int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
- int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
- uint16_t: __ARM_mve_type_int_n, \
- uint16_t *: __ARM_mve_type_uint16_t_ptr, \
- uint16_t const *: __ARM_mve_type_uint16_t_ptr, \
- uint16x8_t: __ARM_mve_type_uint16x8_t, \
- uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
- uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
- uint32_t: __ARM_mve_type_int_n, \
- uint32_t *: __ARM_mve_type_uint32_t_ptr, \
- uint32_t const *: __ARM_mve_type_uint32_t_ptr, \
- uint32x4_t: __ARM_mve_type_uint32x4_t, \
- uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
- uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
- uint64_t: __ARM_mve_type_int_n, \
- uint64_t *: __ARM_mve_type_uint64_t_ptr, \
- uint64_t const *: __ARM_mve_type_uint64_t_ptr, \
- uint64x2_t: __ARM_mve_type_uint64x2_t, \
- uint8_t: __ARM_mve_type_int_n, \
- uint8_t *: __ARM_mve_type_uint8_t_ptr, \
- uint8_t const *: __ARM_mve_type_uint8_t_ptr, \
- uint8x16_t: __ARM_mve_type_uint8x16_t, \
- uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
- uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
- default: _Generic(x, \
- signed char: __ARM_mve_type_int_n, \
- short: __ARM_mve_type_int_n, \
- int: __ARM_mve_type_int_n, \
- long: __ARM_mve_type_int_n, \
- long long: __ARM_mve_type_int_n, \
- unsigned char: __ARM_mve_type_int_n, \
- unsigned short: __ARM_mve_type_int_n, \
- unsigned int: __ARM_mve_type_int_n, \
- unsigned long: __ARM_mve_type_int_n, \
- unsigned long long: __ARM_mve_type_int_n, \
- default: __ARM_mve_unsupported_type))
-#else
-#define __ARM_mve_typeid(x) _Generic(x, \
- int16_t: __ARM_mve_type_int_n, \
- int16_t *: __ARM_mve_type_int16_t_ptr, \
- int16_t const *: __ARM_mve_type_int16_t_ptr, \
- int16x8_t: __ARM_mve_type_int16x8_t, \
- int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
- int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
- int32_t: __ARM_mve_type_int_n, \
- int32_t *: __ARM_mve_type_int32_t_ptr, \
- int32_t const *: __ARM_mve_type_int32_t_ptr, \
- int32x4_t: __ARM_mve_type_int32x4_t, \
- int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
- int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
- int64_t: __ARM_mve_type_int_n, \
- int64_t *: __ARM_mve_type_int64_t_ptr, \
- int64_t const *: __ARM_mve_type_int64_t_ptr, \
- int64x2_t: __ARM_mve_type_int64x2_t, \
- int8_t: __ARM_mve_type_int_n, \
- int8_t *: __ARM_mve_type_int8_t_ptr, \
- int8_t const *: __ARM_mve_type_int8_t_ptr, \
- int8x16_t: __ARM_mve_type_int8x16_t, \
- int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
- int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
- uint16_t: __ARM_mve_type_int_n, \
- uint16_t *: __ARM_mve_type_uint16_t_ptr, \
- uint16_t const *: __ARM_mve_type_uint16_t_ptr, \
- uint16x8_t: __ARM_mve_type_uint16x8_t, \
- uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
- uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
- uint32_t: __ARM_mve_type_int_n, \
- uint32_t *: __ARM_mve_type_uint32_t_ptr, \
- uint32_t const *: __ARM_mve_type_uint32_t_ptr, \
- uint32x4_t: __ARM_mve_type_uint32x4_t, \
- uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
- uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
- uint64_t: __ARM_mve_type_int_n, \
- uint64_t *: __ARM_mve_type_uint64_t_ptr, \
- uint64_t const *: __ARM_mve_type_uint64_t_ptr, \
- uint64x2_t: __ARM_mve_type_uint64x2_t, \
- uint8_t: __ARM_mve_type_int_n, \
- uint8_t *: __ARM_mve_type_uint8_t_ptr, \
- uint8_t const *: __ARM_mve_type_uint8_t_ptr, \
- uint8x16_t: __ARM_mve_type_uint8x16_t, \
- uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
- uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
- default: _Generic(x, \
- signed char: __ARM_mve_type_int_n, \
- short: __ARM_mve_type_int_n, \
- int: __ARM_mve_type_int_n, \
- long: __ARM_mve_type_int_n, \
- long long: __ARM_mve_type_int_n, \
- unsigned char: __ARM_mve_type_int_n, \
- unsigned short: __ARM_mve_type_int_n, \
- unsigned int: __ARM_mve_type_int_n, \
- unsigned long: __ARM_mve_type_int_n, \
- unsigned long long: __ARM_mve_type_int_n, \
- default: __ARM_mve_unsupported_type))
-#endif /* MVE Floating point. */
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (int16_t * __addr, int16x8x4_t __value)
+{
+ __arm_vst4q_s16 (__addr, __value);
+}
-extern void *__ARM_undef;
-#define __ARM_mve_coerce(param, type) \
- _Generic(param, type: param, default: *(type *)__ARM_undef)
-#define __ARM_mve_coerce1(param, type) \
- _Generic(param, type: param, const type: param, default: *(type *)__ARM_undef)
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (int32_t * __addr, int32x4x4_t __value)
+{
+ __arm_vst4q_s32 (__addr, __value);
+}
-#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (uint8_t * __addr, uint8x16x4_t __value)
+{
+ __arm_vst4q_u8 (__addr, __value);
+}
-#define vst4q(p0,p1) __arm_vst4q(p0,p1)
-#define __arm_vst4q(p0,p1) ({ __typeof(p0) __p0 = (p0); \
- __typeof(p1) __p1 = (p1); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
- int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
- int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
- int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
- int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
- int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \
- int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \
- int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (uint16_t * __addr, uint16x8x4_t __value)
+{
+ __arm_vst4q_u16 (__addr, __value);
+}
-#define vrndxq(p0) __arm_vrndxq(p0)
-#define __arm_vrndxq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndxq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndxq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (uint32_t * __addr, uint32x4x4_t __value)
+{
+ __arm_vst4q_u32 (__addr, __value);
+}
-#define vrndq(p0) __arm_vrndq(p0)
-#define __arm_vrndq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (int8_t __a)
+{
+ return __arm_vdupq_n_s8 (__a);
+}
-#define vrndpq(p0) __arm_vrndpq(p0)
-#define __arm_vrndpq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndpq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndpq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (int16_t __a)
+{
+ return __arm_vdupq_n_s16 (__a);
+}
-#define vrndnq(p0) __arm_vrndnq(p0)
-#define __arm_vrndnq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndnq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndnq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (int32_t __a)
+{
+ return __arm_vdupq_n_s32 (__a);
+}
-#define vrndmq(p0) __arm_vrndmq(p0)
-#define __arm_vrndmq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndmq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndmq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq (int8x16_t __a)
+{
+ return __arm_vabsq_s8 (__a);
+}
-#define vrndaq(p0) __arm_vrndaq(p0)
-#define __arm_vrndaq(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndaq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq (int16x8_t __a)
+{
+ return __arm_vabsq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq (int32x4_t __a)
+{
+ return __arm_vabsq_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq (int8x16_t __a)
+{
+ return __arm_vclsq_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq (int16x8_t __a)
+{
+ return __arm_vclsq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq (int32x4_t __a)
+{
+ return __arm_vclsq_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq (int8x16_t __a)
+{
+ return __arm_vclzq_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq (int16x8_t __a)
+{
+ return __arm_vclzq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq (int32x4_t __a)
+{
+ return __arm_vclzq_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq (int8x16_t __a)
+{
+ return __arm_vnegq_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq (int16x8_t __a)
+{
+ return __arm_vnegq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq (int32x4_t __a)
+{
+ return __arm_vnegq_s32 (__a);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvq (int32x4_t __a)
+{
+ return __arm_vaddlvq_s32 (__a);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq (int8x16_t __a)
+{
+ return __arm_vaddvq_s8 (__a);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq (int16x8_t __a)
+{
+ return __arm_vaddvq_s16 (__a);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq (int32x4_t __a)
+{
+ return __arm_vaddvq_s32 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq (int8x16_t __a)
+{
+ return __arm_vmovlbq_s8 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq (int16x8_t __a)
+{
+ return __arm_vmovlbq_s16 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq (int8x16_t __a)
+{
+ return __arm_vmovltq_s8 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq (int16x8_t __a)
+{
+ return __arm_vmovltq_s16 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq (int8x16_t __a)
+{
+ return __arm_vmvnq_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq (int16x8_t __a)
+{
+ return __arm_vmvnq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq (int32x4_t __a)
+{
+ return __arm_vmvnq_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev16q (int8x16_t __a)
+{
+ return __arm_vrev16q_s8 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q (int8x16_t __a)
+{
+ return __arm_vrev32q_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q (int16x8_t __a)
+{
+ return __arm_vrev32q_s16 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (int8x16_t __a)
+{
+ return __arm_vrev64q_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (int16x8_t __a)
+{
+ return __arm_vrev64q_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (int32x4_t __a)
+{
+ return __arm_vrev64q_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqabsq (int8x16_t __a)
+{
+ return __arm_vqabsq_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqabsq (int16x8_t __a)
+{
+ return __arm_vqabsq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqabsq (int32x4_t __a)
+{
+ return __arm_vqabsq_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqnegq (int8x16_t __a)
+{
+ return __arm_vqnegq_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqnegq (int16x8_t __a)
+{
+ return __arm_vqnegq_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqnegq (int32x4_t __a)
+{
+ return __arm_vqnegq_s32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (uint8x16_t __a)
+{
+ return __arm_vrev64q_u8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (uint16x8_t __a)
+{
+ return __arm_vrev64q_u16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (uint32x4_t __a)
+{
+ return __arm_vrev64q_u32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq (uint8x16_t __a)
+{
+ return __arm_vmvnq_u8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq (uint16x8_t __a)
+{
+ return __arm_vmvnq_u16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq (uint32x4_t __a)
+{
+ return __arm_vmvnq_u32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (uint8_t __a)
+{
+ return __arm_vdupq_n_u8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (uint16_t __a)
+{
+ return __arm_vdupq_n_u16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (uint32_t __a)
+{
+ return __arm_vdupq_n_u32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq (uint8x16_t __a)
+{
+ return __arm_vclzq_u8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq (uint16x8_t __a)
+{
+ return __arm_vclzq_u16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq (uint32x4_t __a)
+{
+ return __arm_vclzq_u32 (__a);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq (uint8x16_t __a)
+{
+ return __arm_vaddvq_u8 (__a);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq (uint16x8_t __a)
+{
+ return __arm_vaddvq_u16 (__a);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq (uint32x4_t __a)
+{
+ return __arm_vaddvq_u32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q (uint8x16_t __a)
+{
+ return __arm_vrev32q_u8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q (uint16x8_t __a)
+{
+ return __arm_vrev32q_u16 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq (uint8x16_t __a)
+{
+ return __arm_vmovltq_u8 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq (uint16x8_t __a)
+{
+ return __arm_vmovltq_u16 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq (uint8x16_t __a)
+{
+ return __arm_vmovlbq_u8 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq (uint16x8_t __a)
+{
+ return __arm_vmovlbq_u16 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev16q (uint8x16_t __a)
+{
+ return __arm_vrev16q_u8 (__a);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvq (uint32x4_t __a)
+{
+ return __arm_vaddlvq_u32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq (int8x16_t __a, const int __imm)
+{
+ return __arm_vshrq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq (int16x8_t __a, const int __imm)
+{
+ return __arm_vshrq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq (int32x4_t __a, const int __imm)
+{
+ return __arm_vshrq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq (uint8x16_t __a, const int __imm)
+{
+ return __arm_vshrq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq (uint16x8_t __a, const int __imm)
+{
+ return __arm_vshrq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq (uint32x4_t __a, const int __imm)
+{
+ return __arm_vshrq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvq_p (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddlvq_p_s32 (__a, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvq_p (uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddlvq_p_u32 (__a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcmpneq_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcmpneq_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcmpneq_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vcmpneq_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vcmpneq_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vcmpneq_u32 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vshlq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vshlq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vshlq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq (uint8x16_t __a, int8x16_t __b)
+{
+ return __arm_vshlq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq (uint16x8_t __a, int16x8_t __b)
+{
+ return __arm_vshlq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq (uint32x4_t __a, int32x4_t __b)
+{
+ return __arm_vshlq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vsubq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vsubq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vrmulhq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vrhaddq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vqsubq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vqsubq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vqaddq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vqaddq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vorrq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vornq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmulq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vmulq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmulltq_int_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmullbq_int_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmulhq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmladavq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq (uint8_t __a, uint8x16_t __b)
+{
+ return __arm_vminvq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vminq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq (uint8_t __a, uint8x16_t __b)
+{
+ return __arm_vmaxvq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmaxq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vhsubq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vhsubq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vhaddq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vhaddq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_veorq_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vcmpneq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vcmphiq_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vcmphiq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vcmpeqq_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vcmpeqq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vcmpcsq_u8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vcmpcsq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vcaddq_rot90_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vcaddq_rot270_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vbicq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vandq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq_p (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddvq_p_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq (uint32_t __a, uint8x16_t __b)
+{
+ return __arm_vaddvaq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (uint8x16_t __a, uint8_t __b)
+{
+ return __arm_vaddq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vabdq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_r (uint8x16_t __a, int32_t __b)
+{
+ return __arm_vshlq_r_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (uint8x16_t __a, int8x16_t __b)
+{
+ return __arm_vrshlq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (uint8x16_t __a, int32_t __b)
+{
+ return __arm_vrshlq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq (uint8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqshlq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_r (uint8x16_t __a, int32_t __b)
+{
+ return __arm_vqshlq_r_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (uint8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrshlq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (uint8x16_t __a, int32_t __b)
+{
+ return __arm_vqrshlq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminavq (uint8_t __a, int8x16_t __b)
+{
+ return __arm_vminavq_s8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminaq (uint8x16_t __a, int8x16_t __b)
+{
+ return __arm_vminaq_s8 (__a, __b);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxavq (uint8_t __a, int8x16_t __b)
+{
+ return __arm_vmaxavq_s8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxaq (uint8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmaxaq_s8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (uint8x16_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_n (uint8x16_t __a, const int __imm)
+{
+ return __arm_vshlq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq (uint8x16_t __a, const int __imm)
+{
+ return __arm_vrshrq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_n (uint8x16_t __a, const int __imm)
+{
+ return __arm_vqshlq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vcmpneq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcmpltq_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vcmpltq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcmpleq_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vcmpleq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcmpgtq_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vcmpgtq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcmpgeq_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vcmpgeq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcmpeqq_s8 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vcmpeqq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshluq (int8x16_t __a, const int __imm)
+{
+ return __arm_vqshluq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq_p (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddvq_p_s8 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vsubq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vsubq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_r (int8x16_t __a, int32_t __b)
+{
+ return __arm_vshlq_r_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vrshlq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (int8x16_t __a, int32_t __b)
+{
+ return __arm_vrshlq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vrmulhq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vrhaddq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqsubq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vqsubq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqshlq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_r (int8x16_t __a, int32_t __b)
+{
+ return __arm_vqshlq_r_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrshlq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (int8x16_t __a, int32_t __b)
+{
+ return __arm_vqrshlq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrdmulhq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vqrdmulhq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqdmulhq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vqdmulhq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqaddq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vqaddq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vorrq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vornq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmulq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vmulq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmulltq_int_s8 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmullbq_int_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmulhq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavxq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmlsdavxq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmlsdavq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavxq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmladavxq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmladavq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq (int8_t __a, int8x16_t __b)
+{
+ return __arm_vminvq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vminq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq (int8_t __a, int8x16_t __b)
+{
+ return __arm_vmaxvq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vmaxq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vhsubq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vhsubq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90 (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vhcaddq_rot90_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270 (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vhcaddq_rot270_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vhaddq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vhaddq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_veorq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcaddq_rot90_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vcaddq_rot270_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (int8x16_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vbicq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vandq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq (int32_t __a, int8x16_t __b)
+{
+ return __arm_vaddvaq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (int8x16_t __a, int8_t __b)
+{
+ return __arm_vaddq_n_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vabdq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_n (int8x16_t __a, const int __imm)
+{
+ return __arm_vshlq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq (int8x16_t __a, const int __imm)
+{
+ return __arm_vrshrq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_n (int8x16_t __a, const int __imm)
+{
+ return __arm_vqshlq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vsubq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vsubq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vrmulhq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vrhaddq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vqsubq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vqsubq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vqaddq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vqaddq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vorrq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vornq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmulq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vmulq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmulltq_int_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmullbq_int_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmulhq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmladavq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq (uint16_t __a, uint16x8_t __b)
+{
+ return __arm_vminvq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vminq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq (uint16_t __a, uint16x8_t __b)
+{
+ return __arm_vmaxvq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmaxq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vhsubq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vhsubq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vhaddq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vhaddq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_veorq_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vcmpneq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vcmphiq_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vcmphiq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vcmpeqq_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vcmpeqq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vcmpcsq_u16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vcmpcsq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vcaddq_rot90_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vcaddq_rot270_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vbicq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vandq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq_p (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddvq_p_u16 (__a, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq (uint32_t __a, uint16x8_t __b)
+{
+ return __arm_vaddvaq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (uint16x8_t __a, uint16_t __b)
+{
+ return __arm_vaddq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vabdq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_r (uint16x8_t __a, int32_t __b)
+{
+ return __arm_vshlq_r_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (uint16x8_t __a, int16x8_t __b)
+{
+ return __arm_vrshlq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (uint16x8_t __a, int32_t __b)
+{
+ return __arm_vrshlq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq (uint16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqshlq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_r (uint16x8_t __a, int32_t __b)
+{
+ return __arm_vqshlq_r_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (uint16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrshlq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (uint16x8_t __a, int32_t __b)
+{
+ return __arm_vqrshlq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminavq (uint16_t __a, int16x8_t __b)
+{
+ return __arm_vminavq_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminaq (uint16x8_t __a, int16x8_t __b)
+{
+ return __arm_vminaq_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxavq (uint16_t __a, int16x8_t __b)
+{
+ return __arm_vmaxavq_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxaq (uint16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmaxaq_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (uint16x8_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_n (uint16x8_t __a, const int __imm)
+{
+ return __arm_vshlq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq (uint16x8_t __a, const int __imm)
+{
+ return __arm_vrshrq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_n (uint16x8_t __a, const int __imm)
+{
+ return __arm_vqshlq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vcmpneq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcmpltq_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vcmpltq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcmpleq_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vcmpleq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcmpgtq_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vcmpgtq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcmpgeq_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vcmpgeq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcmpeqq_s16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vcmpeqq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshluq (int16x8_t __a, const int __imm)
+{
+ return __arm_vqshluq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq_p (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddvq_p_s16 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vsubq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vsubq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_r (int16x8_t __a, int32_t __b)
+{
+ return __arm_vshlq_r_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vrshlq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (int16x8_t __a, int32_t __b)
+{
+ return __arm_vrshlq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vrmulhq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vrhaddq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqsubq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vqsubq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqshlq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_r (int16x8_t __a, int32_t __b)
+{
+ return __arm_vqshlq_r_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrshlq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (int16x8_t __a, int32_t __b)
+{
+ return __arm_vqrshlq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrdmulhq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vqrdmulhq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmulhq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vqdmulhq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqaddq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vqaddq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vorrq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vornq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmulq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vmulq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmulltq_int_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmullbq_int_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmulhq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavxq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmlsdavxq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmlsdavq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavxq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmladavxq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmladavq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq (int16_t __a, int16x8_t __b)
+{
+ return __arm_vminvq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vminq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq (int16_t __a, int16x8_t __b)
+{
+ return __arm_vmaxvq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmaxq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vhsubq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vhsubq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90 (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vhcaddq_rot90_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270 (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vhcaddq_rot270_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vhaddq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vhaddq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_veorq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcaddq_rot90_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vcaddq_rot270_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (int16x8_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vbicq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vandq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq (int32_t __a, int16x8_t __b)
+{
+ return __arm_vaddvaq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vaddq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vabdq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_n (int16x8_t __a, const int __imm)
+{
+ return __arm_vshlq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq (int16x8_t __a, const int __imm)
+{
+ return __arm_vrshrq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_n (int16x8_t __a, const int __imm)
+{
+ return __arm_vqshlq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vsubq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vsubq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vrmulhq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vrhaddq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vqsubq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vqsubq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vqaddq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vqaddq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vorrq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vornq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmulq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vmulq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmulltq_int_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmullbq_int_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmulhq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmladavq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq (uint32_t __a, uint32x4_t __b)
+{
+ return __arm_vminvq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vminq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq (uint32_t __a, uint32x4_t __b)
+{
+ return __arm_vmaxvq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmaxq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vhsubq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vhsubq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vhaddq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vhaddq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_veorq_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vcmpneq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vcmphiq_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vcmphiq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vcmpeqq_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vcmpeqq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vcmpcsq_u32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vcmpcsq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vcaddq_rot90_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vcaddq_rot270_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vbicq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vandq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq_p (uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddvq_p_u32 (__a, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq (uint32_t __a, uint32x4_t __b)
+{
+ return __arm_vaddvaq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (uint32x4_t __a, uint32_t __b)
+{
+ return __arm_vaddq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vabdq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_r (uint32x4_t __a, int32_t __b)
+{
+ return __arm_vshlq_r_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (uint32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrshlq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (uint32x4_t __a, int32_t __b)
+{
+ return __arm_vrshlq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq (uint32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqshlq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_r (uint32x4_t __a, int32_t __b)
+{
+ return __arm_vqshlq_r_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (uint32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrshlq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (uint32x4_t __a, int32_t __b)
+{
+ return __arm_vqrshlq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminavq (uint32_t __a, int32x4_t __b)
+{
+ return __arm_vminavq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminaq (uint32x4_t __a, int32x4_t __b)
+{
+ return __arm_vminaq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxavq (uint32_t __a, int32x4_t __b)
+{
+ return __arm_vmaxavq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxaq (uint32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmaxaq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (uint32x4_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_n (uint32x4_t __a, const int __imm)
+{
+ return __arm_vshlq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq (uint32x4_t __a, const int __imm)
+{
+ return __arm_vrshrq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_n (uint32x4_t __a, const int __imm)
+{
+ return __arm_vqshlq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vcmpneq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcmpltq_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vcmpltq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcmpleq_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vcmpleq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcmpgtq_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vcmpgtq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcmpgeq_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vcmpgeq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcmpeqq_s32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vcmpeqq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshluq (int32x4_t __a, const int __imm)
+{
+ return __arm_vqshluq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvq_p (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vaddvq_p_s32 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vsubq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vsubq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_r (int32x4_t __a, int32_t __b)
+{
+ return __arm_vshlq_r_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrshlq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vrshlq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrmulhq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrhaddq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqsubq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqsubq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqshlq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_r (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqshlq_r_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrshlq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqrshlq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrdmulhq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqrdmulhq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmulhq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqdmulhq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqaddq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqaddq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vorrq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vornq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmulq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vmulq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmulltq_int_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmullbq_int_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmulhq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmlsdavxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmlsdavq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmladavxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmladavq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq (int32_t __a, int32x4_t __b)
+{
+ return __arm_vminvq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vminq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq (int32_t __a, int32x4_t __b)
+{
+ return __arm_vmaxvq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmaxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vhsubq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vhsubq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90 (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vhcaddq_rot90_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270 (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vhcaddq_rot270_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vhaddq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vhaddq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_veorq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcaddq_rot90_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vcaddq_rot270_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vbicq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vandq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq (int32_t __a, int32x4_t __b)
+{
+ return __arm_vaddvaq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vaddq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vabdq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_n (int32x4_t __a, const int __imm)
+{
+ return __arm_vshlq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq (int32x4_t __a, const int __imm)
+{
+ return __arm_vrshrq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_n (int32x4_t __a, const int __imm)
+{
+ return __arm_vqshlq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq (uint8x16_t __a, uint16x8_t __b)
+{
+ return __arm_vqmovntq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq (uint8x16_t __a, uint16x8_t __b)
+{
+ return __arm_vqmovnbq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmulltq_poly_p8 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vmullbq_poly_p8 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq (uint8x16_t __a, uint16x8_t __b)
+{
+ return __arm_vmovntq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq (uint8x16_t __a, uint16x8_t __b)
+{
+ return __arm_vmovnbq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmlaldavq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovuntq (uint8x16_t __a, int16x8_t __b)
+{
+ return __arm_vqmovuntq_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovunbq (uint8x16_t __a, int16x8_t __b)
+{
+ return __arm_vqmovunbq_s16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq (uint8x16_t __a, const int __imm)
+{
+ return __arm_vshlltq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq (uint8x16_t __a, const int __imm)
+{
+ return __arm_vshllbq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (uint16x8_t __a, const int __imm)
+{
+ return __arm_vorrq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (uint16x8_t __a, const int __imm)
+{
+ return __arm_vbicq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq (int8x16_t __a, int16x8_t __b)
+{
+ return __arm_vqmovntq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq (int8x16_t __a, int16x8_t __b)
+{
+ return __arm_vqmovnbq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmulltq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vqdmulltq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmullbq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq (int16x8_t __a, int16_t __b)
+{
+ return __arm_vqdmullbq_n_s16 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq (int8x16_t __a, int16x8_t __b)
+{
+ return __arm_vmovntq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq (int8x16_t __a, int16x8_t __b)
+{
+ return __arm_vmovnbq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavxq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmlsldavxq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmlsldavq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavxq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmlaldavxq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vmlaldavq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq (int8x16_t __a, const int __imm)
+{
+ return __arm_vshlltq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq (int8x16_t __a, const int __imm)
+{
+ return __arm_vshllbq_n_s8 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (int16x8_t __a, const int __imm)
+{
+ return __arm_vorrq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (int16x8_t __a, const int __imm)
+{
+ return __arm_vbicq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq (uint16x8_t __a, uint32x4_t __b)
+{
+ return __arm_vqmovntq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq (uint16x8_t __a, uint32x4_t __b)
+{
+ return __arm_vqmovnbq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmulltq_poly_p16 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vmullbq_poly_p16 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq (uint16x8_t __a, uint32x4_t __b)
+{
+ return __arm_vmovntq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq (uint16x8_t __a, uint32x4_t __b)
+{
+ return __arm_vmovnbq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vmlaldavq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovuntq (uint16x8_t __a, int32x4_t __b)
+{
+ return __arm_vqmovuntq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovunbq (uint16x8_t __a, int32x4_t __b)
+{
+ return __arm_vqmovunbq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq (uint16x8_t __a, const int __imm)
+{
+ return __arm_vshlltq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq (uint16x8_t __a, const int __imm)
+{
+ return __arm_vshllbq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (uint32x4_t __a, const int __imm)
+{
+ return __arm_vorrq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (uint32x4_t __a, const int __imm)
+{
+ return __arm_vbicq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq (int16x8_t __a, int32x4_t __b)
+{
+ return __arm_vqmovntq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq (int16x8_t __a, int32x4_t __b)
+{
+ return __arm_vqmovnbq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmulltq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqdmulltq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmullbq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq (int32x4_t __a, int32_t __b)
+{
+ return __arm_vqdmullbq_n_s32 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq (int16x8_t __a, int32x4_t __b)
+{
+ return __arm_vmovntq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq (int16x8_t __a, int32x4_t __b)
+{
+ return __arm_vmovnbq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmlsldavxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmlsldavq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmlaldavxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vmlaldavq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq (int16x8_t __a, const int __imm)
+{
+ return __arm_vshlltq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq (int16x8_t __a, const int __imm)
+{
+ return __arm_vshllbq_n_s16 (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (int32x4_t __a, const int __imm)
+{
+ return __arm_vorrq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (int32x4_t __a, const int __imm)
+{
+ return __arm_vbicq_n_s32 (__a, __imm);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vrmlaldavhq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq (uint64_t __a, uint32x4_t __b)
+{
+ return __arm_vaddlvaq_u32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrmlsldavhxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrmlsldavhq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhxq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrmlaldavhxq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vrmlaldavhq_s32 (__a, __b);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq (int64_t __a, int32x4_t __b)
+{
+ return __arm_vaddlvaq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq (uint32_t __a, int8x16_t __b, int8x16_t __c)
+{
+ return __arm_vabavq_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq (uint32_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vabavq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq (uint32_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vabavq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq (uint32_t __a, uint8x16_t __b, uint8x16_t __c)
+{
+ return __arm_vabavq_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq (uint32_t __a, uint16x8_t __b, uint16x8_t __c)
+{
+ return __arm_vabavq_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq (uint32_t __a, uint32x4_t __b, uint32x4_t __c)
+{
+ return __arm_vabavq_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m_n (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m_n (int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_n_s32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m_n (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m_n (uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqrshrnbq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vqrshrnbq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqrshrnbq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vqrshrnbq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrunbq (uint8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqrshrunbq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrunbq (uint16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqrshrunbq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhaq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vrmlaldavhaq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhaq (uint64_t __a, uint32x4_t __b, uint32x4_t __c)
+{
+ return __arm_vrmlaldavhaq_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq (int8x16_t __a, uint32_t * __b, const int __imm)
+{
+ return __arm_vshlcq_s8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq (uint8x16_t __a, uint32_t * __b, const int __imm)
+{
+ return __arm_vshlcq_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq (int16x8_t __a, uint32_t * __b, const int __imm)
+{
+ return __arm_vshlcq_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq (uint16x8_t __a, uint32_t * __b, const int __imm)
+{
+ return __arm_vshlcq_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq (int32x4_t __a, uint32_t * __b, const int __imm)
+{
+ return __arm_vshlcq_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq (uint32x4_t __a, uint32_t * __b, const int __imm)
+{
+ return __arm_vshlcq_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
+{
+ return __arm_vqrdmlashq_n_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
+{
+ return __arm_vqrdmlahq_n_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
+{
+ return __arm_vqdmlahq_n_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
+{
+ return __arm_vmlasq_n_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq (uint8x16_t __a, uint8x16_t __b, uint8_t __c)
+{
+ return __arm_vmlaq_n_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq_p (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavq_p_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq (uint32_t __a, uint8x16_t __b, uint8x16_t __c)
+{
+ return __arm_vmladavaq_u8 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq_p (uint8_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminvq_p_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq_p (uint8_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxvq_p_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (uint8x16_t __inactive, uint8_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq_m (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmphiq_m_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq_m (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmphiq_m_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq_m (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpcsq_m_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq_m (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpcsq_m_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_m (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq_p (uint32_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddvaq_p_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq (uint8x16_t __a, uint8x16_t __b, const int __imm)
+{
+ return __arm_vsriq_n_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq (uint8x16_t __a, uint8x16_t __b, const int __imm)
+{
+ return __arm_vsliq_n_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_r (uint8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_r_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m_n (uint8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_r (uint8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_r_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m_n (uint8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminavq_p (uint8_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminavq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminaq_m (uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminaq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxavq_p (uint8_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxavq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxaq_m (uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxaq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_r (int8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_r_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m_n (int8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_r (int8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_r_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m_n (int8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqnegq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vqnegq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqabsq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vqabsq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavxq_p (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsdavxq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavq_p (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsdavq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavxq_p (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavxq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq_p (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq_p (int8_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminvq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq_p (int8_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxvq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (int8x16_t __inactive, int8_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vclsq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq_p (int32_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddvaq_p_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhxq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrdmlsdhxq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrdmlsdhq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq (int8x16_t __a, int8x16_t __b, int8_t __c)
+{
+ return __arm_vqrdmlashq_n_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq (int8x16_t __a, int8x16_t __b, int8_t __c)
+{
+ return __arm_vqrdmlahq_n_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhxq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrdmladhxq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqrdmladhq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhxq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqdmlsdhxq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqdmlsdhq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq (int8x16_t __a, int8x16_t __b, int8_t __c)
+{
+ return __arm_vqdmlahq_n_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhxq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqdmladhxq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhq (int8x16_t __inactive, int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vqdmladhq_s8 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaxq (int32_t __a, int8x16_t __b, int8x16_t __c)
+{
+ return __arm_vmlsdavaxq_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaq (int32_t __a, int8x16_t __b, int8x16_t __c)
+{
+ return __arm_vmlsdavaq_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq (int8x16_t __a, int8x16_t __b, int8_t __c)
+{
+ return __arm_vmlasq_n_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq (int8x16_t __a, int8x16_t __b, int8_t __c)
+{
+ return __arm_vmlaq_n_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaxq (int32_t __a, int8x16_t __b, int8x16_t __c)
+{
+ return __arm_vmladavaxq_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq (int32_t __a, int8x16_t __b, int8x16_t __c)
+{
+ return __arm_vmladavaq_s8 (__a, __b, __c);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq (int8x16_t __a, int8x16_t __b, const int __imm)
+{
+ return __arm_vsriq_n_s8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq (int8x16_t __a, int8x16_t __b, const int __imm)
+{
+ return __arm_vsliq_n_s8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (uint16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
+{
+ return __arm_vqrdmlashq_n_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
+{
+ return __arm_vqrdmlahq_n_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
+{
+ return __arm_vqdmlahq_n_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (uint16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
+{
+ return __arm_vmlasq_n_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
+{
+ return __arm_vmlaq_n_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq_p (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavq_p_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq (uint32_t __a, uint16x8_t __b, uint16x8_t __c)
+{
+ return __arm_vmladavaq_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq_p (uint16_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminvq_p_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq_p (uint16_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxvq_p_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (uint16x8_t __inactive, uint16_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq_m (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmphiq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq_m (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmphiq_m_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq_m (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpcsq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq_m (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpcsq_m_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_m (uint16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_m_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq_p (uint32_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddvaq_p_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq (uint16x8_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vsriq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq (uint16x8_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vsliq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_r (uint16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_r_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m_n (uint16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_r (uint16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_r_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m_n (uint16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminavq_p (uint16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminavq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminaq_m (uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminaq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxavq_p (uint16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxavq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxaq_m (uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxaq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_r (int16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_r_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m_n (int16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_r (int16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_r_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m_n (int16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqnegq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vqnegq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqabsq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vqabsq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavxq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsdavxq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsdavq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavxq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavxq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq_p (int16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminvq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq_p (int16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxvq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (int16x8_t __inactive, int16_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vclsq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq_p (int32_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddvaq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhxq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrdmlsdhxq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrdmlsdhq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq (int16x8_t __a, int16x8_t __b, int16_t __c)
+{
+ return __arm_vqrdmlashq_n_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq (int16x8_t __a, int16x8_t __b, int16_t __c)
+{
+ return __arm_vqrdmlahq_n_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhxq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrdmladhxq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqrdmladhq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhxq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmlsdhxq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmlsdhq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq (int16x8_t __a, int16x8_t __b, int16_t __c)
+{
+ return __arm_vqdmlahq_n_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhxq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmladhxq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhq (int16x8_t __inactive, int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vqdmladhq_s16 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaxq (int32_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmlsdavaxq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaq (int32_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmlsdavaq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq (int16x8_t __a, int16x8_t __b, int16_t __c)
+{
+ return __arm_vmlasq_n_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq (int16x8_t __a, int16x8_t __b, int16_t __c)
+{
+ return __arm_vmlaq_n_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaxq (int32_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmladavaxq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq (int32_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmladavaq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq (int16x8_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vsriq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq (int16x8_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vsliq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (uint32x4_t __inactive, uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_u32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
+{
+ return __arm_vqrdmlashq_n_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
+{
+ return __arm_vqrdmlahq_n_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
+{
+ return __arm_vqdmlahq_n_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (uint32x4_t __inactive, uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_u32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
+{
+ return __arm_vmlasq_n_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
+{
+ return __arm_vmlaq_n_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq_p (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq (uint32_t __a, uint32x4_t __b, uint32x4_t __c)
+{
+ return __arm_vmladavaq_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq_p (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminvq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq_p (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxvq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (uint32x4_t __inactive, uint32_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_u32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq_m (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmphiq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmphiq_m (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmphiq_m_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq_m (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpcsq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpcsq_m (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpcsq_m_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_m (uint32x4_t __inactive, uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_m_u32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq_p (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddvaq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq (uint32x4_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vsriq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq (uint32x4_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vsliq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_r (uint32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_r_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m_n (uint32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_r (uint32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_r_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m_n (uint32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminavq_p (uint32_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminavq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminaq_m (uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminaq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxavq_p (uint32_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxavq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxaq_m (uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxaq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_r (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_r_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m_n (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_r (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_r_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m_n (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqnegq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vqnegq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqabsq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vqabsq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavxq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsdavxq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsdavq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavxq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavxq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmladavq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminvq_p (int32_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminvq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxvq_p (int32_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxvq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (int32x4_t __inactive, int32_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vclsq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddvaq_p (int32_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddvaq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_m (int32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_m_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhxq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrdmlsdhxq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrdmlsdhq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq (int32x4_t __a, int32x4_t __b, int32_t __c)
+{
+ return __arm_vqrdmlashq_n_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq (int32x4_t __a, int32x4_t __b, int32_t __c)
+{
+ return __arm_vqrdmlahq_n_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhxq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrdmladhxq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqrdmladhq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhxq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmlsdhxq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmlsdhq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq (int32x4_t __a, int32x4_t __b, int32_t __c)
+{
+ return __arm_vqdmlahq_n_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhxq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmladhxq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhq (int32x4_t __inactive, int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vqdmladhq_s32 (__inactive, __a, __b);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaxq (int32_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmlsdavaxq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaq (int32_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmlsdavaq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq (int32x4_t __a, int32x4_t __b, int32_t __c)
+{
+ return __arm_vmlasq_n_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq (int32x4_t __a, int32x4_t __b, int32_t __c)
+{
+ return __arm_vmlaq_n_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaxq (int32_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmladavaxq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq (int32_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmladavaq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq (int32x4_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vsriq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq (int32x4_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vsliq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (uint64x2_t __a, uint64x2_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_u64 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (int64x2_t __a, int64x2_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_s64 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhaxq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vrmlaldavhaxq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhaq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vrmlsldavhaq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhaxq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vrmlsldavhaxq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq_p (int64_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddlvaq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev16q_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev16q_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmlaldavhq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhxq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmlaldavhxq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmlsldavhq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhxq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmlsldavhxq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddlvaq_p (uint64_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddlvaq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev16q_m (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev16q_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhq_p (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmlaldavhq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (int16x8_t __inactive, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_n_s16 (__inactive, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m_n (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqrshrntq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqshrnbq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqshrntq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vrshrnbq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vrshrntq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vshrnbq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq (int8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vshrntq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq (int64_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmlaldavaq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaxq (int64_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmlaldavaxq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaq (int64_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmlsldavaq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaxq (int64_t __a, int16x8_t __b, int16x8_t __c)
+{
+ return __arm_vmlsldavaxq_s16 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlaldavq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavxq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlaldavxq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsldavq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavxq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsldavxq_p_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_m (int16x8_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_m (int16x8_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_m (int8x16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovnbq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_m (int8x16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovntq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_m (int8x16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovnbq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_m (int8x16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovntq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_m (int8x16_t __inactive, int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_m_s8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (uint16x8_t __inactive, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_n_u16 (__inactive, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m_n (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshruntq (uint8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqrshruntq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrunbq (uint8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqshrunbq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshruntq (uint8x16_t __a, int16x8_t __b, const int __imm)
+{
+ return __arm_vqshruntq_n_s16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovunbq_m (uint8x16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovunbq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovuntq_m (uint8x16_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovuntq_m_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vqrshrntq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vqshrnbq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vqshrntq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vrshrnbq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vrshrntq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vshrnbq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq (uint8x16_t __a, uint16x8_t __b, const int __imm)
+{
+ return __arm_vshrntq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq (uint64_t __a, uint16x8_t __b, uint16x8_t __c)
+{
+ return __arm_vmlaldavaq_u16 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_p (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlaldavq_p_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_m (uint16x8_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_m (uint16x8_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_m (uint8x16_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovnbq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_m (uint8x16_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovntq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_m (uint8x16_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovnbq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_m (uint8x16_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovntq_m_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_m (uint8x16_t __inactive, uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_m_u8 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (int32x4_t __inactive, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_n_s32 (__inactive, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m_n (int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_n_s32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqrshrntq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqshrnbq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqshrntq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vrshrnbq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vrshrntq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vshrnbq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq (int16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vshrntq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmlaldavaq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaxq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmlaldavaxq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmlsldavaq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaxq (int64_t __a, int32x4_t __b, int32x4_t __c)
+{
+ return __arm_vmlsldavaxq_s32 (__a, __b, __c);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlaldavq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavxq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlaldavxq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsldavq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavxq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlsldavxq_p_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_m (int32x4_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_m (int32x4_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_m (int16x8_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovnbq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_m (int16x8_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovntq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_m (int16x8_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovnbq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_m (int16x8_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovntq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_m (int16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_m_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_m (uint32x4_t __inactive, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vmvnq_m_n_u32 (__inactive, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m_n (uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshruntq (uint16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqrshruntq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrunbq (uint16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqshrunbq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshruntq (uint16x8_t __a, int32x4_t __b, const int __imm)
+{
+ return __arm_vqshruntq_n_s32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovunbq_m (uint16x8_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovunbq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovuntq_m (uint16x8_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovuntq_m_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vqrshrntq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vqshrnbq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vqshrntq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vrshrnbq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vrshrntq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vshrnbq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq (uint16x8_t __a, uint32x4_t __b, const int __imm)
+{
+ return __arm_vshrntq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq (uint64_t __a, uint32x4_t __b, uint32x4_t __c)
+{
+ return __arm_vmlaldavaq_u32 (__a, __b, __c);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavq_p (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmlaldavq_p_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_m (uint32x4_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_m_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_m (uint32x4_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_m_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovnbq_m (uint16x8_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovnbq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovntq_m (uint16x8_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmovntq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovnbq_m (uint16x8_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovnbq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqmovntq_m (uint16x8_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqmovntq_m_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_m (uint16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_m_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq_m (int8x16_t __a, int8x16_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsriq_m_n_s8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshluq_m (uint8x16_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshluq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq_p (uint32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vabavq_p_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq_m (uint8x16_t __a, uint8x16_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsriq_m_n_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m (uint8x16_t __inactive, uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq_p (uint32_t __a, uint8x16_t __b, uint8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vabavq_p_u8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq_m (int16x8_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsriq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshluq_m (uint16x8_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshluq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq_p (uint32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vabavq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq_m (uint16x8_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsriq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m (uint16x8_t __inactive, uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq_p (uint32_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vabavq_p_u16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq_m (int32x4_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsriq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshluq_m (uint32x4_t __inactive, int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshluq_m_n_s32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq_p (uint32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vabavq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsriq_m (uint32x4_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsriq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m (uint32x4_t __inactive, uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabavq_p (uint32_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vabavq_p_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (int8x16_t __inactive, int8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (int16x8_t __inactive, int16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (uint8x16_t __inactive, uint8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (uint32x4_t __inactive, uint32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (uint16x8_t __inactive, uint16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot270_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot270_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot270_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot90_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot90_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot90_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq_p (int32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaq_p_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq_p (int32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq_p (int32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq_p (uint32_t __a, uint8x16_t __b, uint8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaq_p_u8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq_p (uint32_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaq_p_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaq_p (uint32_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaq_p_u16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaxq_p (int32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaxq_p_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaxq_p (int32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaxq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmladavaxq_p (int32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmladavaxq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq_m (int8x16_t __a, int8x16_t __b, int8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaq_m_n_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq_m (int32x4_t __a, int32x4_t __b, int32_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaq_m_n_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq_m (int16x8_t __a, int16x8_t __b, int16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaq_m_n_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq_m (uint8x16_t __a, uint8x16_t __b, uint8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaq_m_n_u8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq_m (uint32x4_t __a, uint32x4_t __b, uint32_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaq_m_n_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaq_m (uint16x8_t __a, uint16x8_t __b, uint16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaq_m_n_u16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq_m (int8x16_t __a, int8x16_t __b, int8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlasq_m_n_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq_m (int32x4_t __a, int32x4_t __b, int32_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlasq_m_n_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq_m (int16x8_t __a, int16x8_t __b, int16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlasq_m_n_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq_m (uint8x16_t __a, uint8x16_t __b, uint8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlasq_m_n_u8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq_m (uint32x4_t __a, uint32x4_t __b, uint32_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlasq_m_n_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlasq_m (uint16x8_t __a, uint16x8_t __b, uint16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlasq_m_n_u16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaq_p (int32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsdavaq_p_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaq_p (int32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsdavaq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaq_p (int32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsdavaq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaxq_p (int32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsdavaxq_p_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaxq_p (int32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsdavaxq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsdavaxq_p (int32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsdavaxq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_m (int16x8_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_m (int64x2_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_m (int32x4_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_m (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_m (uint64x2_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_m (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_m (int16x8_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_m (int64x2_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_m (int32x4_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_m (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_m (uint64x2_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_m (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqaddq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmladhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmladhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmladhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhxq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmladhxq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhxq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmladhxq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmladhxq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmladhxq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq_m (int8x16_t __a, int8x16_t __b, int8_t __c, mve_pred16_t __p)
+{
+ return __arm_vqdmlahq_m_n_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq_m (int32x4_t __a, int32x4_t __b, int32_t __c, mve_pred16_t __p)
+{
+ return __arm_vqdmlahq_m_n_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlahq_m (int16x8_t __a, int16x8_t __b, int16_t __c, mve_pred16_t __p)
+{
+ return __arm_vqdmlahq_m_n_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmlsdhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmlsdhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmlsdhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhxq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmlsdhxq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhxq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmlsdhxq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmlsdhxq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmlsdhxq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulhq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulhq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulhq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmladhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmladhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmladhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhxq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmladhxq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhxq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmladhxq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmladhxq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmladhxq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq_m (int8x16_t __a, int8x16_t __b, int8_t __c, mve_pred16_t __p)
+{
+ return __arm_vqrdmlahq_m_n_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq_m (int32x4_t __a, int32x4_t __b, int32_t __c, mve_pred16_t __p)
+{
+ return __arm_vqrdmlahq_m_n_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlahq_m (int16x8_t __a, int16x8_t __b, int16_t __c, mve_pred16_t __p)
+{
+ return __arm_vqrdmlahq_m_n_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq_m (int8x16_t __a, int8x16_t __b, int8_t __c, mve_pred16_t __p)
+{
+ return __arm_vqrdmlashq_m_n_s8 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq_m (int32x4_t __a, int32x4_t __b, int32_t __c, mve_pred16_t __p)
+{
+ return __arm_vqrdmlashq_m_n_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlashq_m (int16x8_t __a, int16x8_t __b, int16_t __c, mve_pred16_t __p)
+{
+ return __arm_vqrdmlashq_m_n_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmlsdhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmlsdhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmlsdhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhxq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmlsdhxq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhxq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmlsdhxq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmlsdhxq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmlsdhxq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmulhq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmulhq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmulhq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmulhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmulhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrdmulhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrdmulhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m (uint8x16_t __inactive, uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m (uint32x4_t __inactive, uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshlq_m (uint16x8_t __inactive, uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqrshlq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_n (int8x16_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_n (int32x4_t __inactive, int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_n_s32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_n (int16x8_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_n (uint8x16_t __inactive, uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_n (uint32x4_t __inactive, uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_n_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m_n (uint16x8_t __inactive, uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m (uint8x16_t __inactive, uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m (uint32x4_t __inactive, uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshlq_m (uint16x8_t __inactive, uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqshlq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqsubq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqsubq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m (uint8x16_t __inactive, uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m (uint32x4_t __inactive, uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_m (uint16x8_t __inactive, uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_m_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_m (int8x16_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_m (int32x4_t __inactive, int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_m_n_s32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_m (int16x8_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_m (uint8x16_t __inactive, uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_m (uint32x4_t __inactive, uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_m_n_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_m (uint16x8_t __inactive, uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_n (int8x16_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_n (int32x4_t __inactive, int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_n_s32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_n (int16x8_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_n (uint8x16_t __inactive, uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_n (uint32x4_t __inactive, uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_n_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_m_n (uint16x8_t __inactive, uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_m (int8x16_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_m (int32x4_t __inactive, int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_m_n_s32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_m (int16x8_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_m (uint8x16_t __inactive, uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_m (uint32x4_t __inactive, uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_m_n_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_m (uint16x8_t __inactive, uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq_m (int8x16_t __a, int8x16_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsliq_m_n_s8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq_m (int32x4_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsliq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq_m (int16x8_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsliq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq_m (uint8x16_t __a, uint8x16_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsliq_m_n_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq_m (uint32x4_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsliq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsliq_m (uint16x8_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vsliq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_s8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (uint8x16_t __inactive, uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_u8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (uint32x4_t __inactive, uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_u32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (uint16x8_t __inactive, uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_u16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq_p (int64_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq_p (uint64_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaq_p_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaq_p (uint64_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaq_p_u16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaxq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaxq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaxq_p (int64_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaxq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaxq_p (uint64_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaxq_p_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlaldavaxq_p (uint64_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlaldavaxq_p_u16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsldavaq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaq_p (int64_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsldavaq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaxq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsldavaxq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmlsldavaxq_p (int64_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vmlsldavaxq_p_s16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly_m (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_poly_m_p8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly_m (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_poly_m_p16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly_m (uint16x8_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_poly_m_p8 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly_m (uint32x4_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_poly_m_p16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_m (int64x2_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmullbq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_m (int32x4_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmullbq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_m (int64x2_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmullbq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmullbq_m (int32x4_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmullbq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_m (int64x2_t __inactive, int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulltq_m_n_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_m (int32x4_t __inactive, int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulltq_m_n_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_m (int64x2_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulltq_m_s32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqdmulltq_m (int32x4_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vqdmulltq_m_s16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrnbq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrnbq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrnbq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrnbq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrnbq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrntq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrntq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrntq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrntq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrntq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrunbq_m (uint16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrunbq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshrunbq_m (uint8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshrunbq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshruntq_m (uint16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshruntq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqrshruntq_m (uint8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqrshruntq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrnbq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrnbq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrnbq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrnbq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrnbq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrntq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrntq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrntq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrntq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrntq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrunbq_m (uint16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrunbq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshrunbq_m (uint8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshrunbq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshruntq_m (uint16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshruntq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vqshruntq_m (uint8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vqshruntq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhaq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vrmlaldavhaq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhaq_p (uint64_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vrmlaldavhaq_p_u32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlaldavhaxq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vrmlaldavhaxq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhaq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vrmlsldavhaq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmlsldavhaxq_p (int64_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vrmlsldavhaxq_p_s32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrnbq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrnbq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrnbq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrnbq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrnbq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrntq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrntq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrntq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrntq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrntq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_m (int16x8_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_m (int32x4_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_m (uint16x8_t __inactive, uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_m (uint32x4_t __inactive, uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_m (int16x8_t __inactive, int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_m_n_s8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_m (int32x4_t __inactive, int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_m_n_s16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_m (uint16x8_t __inactive, uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_m (uint32x4_t __inactive, uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrnbq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrnbq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrnbq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrnbq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrnbq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq_m (int16x8_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrntq_m_n_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq_m (int8x16_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrntq_m_n_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq_m (uint16x8_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrntq_m_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrntq_m (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrntq_m_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset (int8_t * __base, uint8x16_t __offset, int8x16_t __value)
+{
+ __arm_vstrbq_scatter_offset_s8 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset (int8_t * __base, uint32x4_t __offset, int32x4_t __value)
+{
+ __arm_vstrbq_scatter_offset_s32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset (int8_t * __base, uint16x8_t __offset, int16x8_t __value)
+{
+ __arm_vstrbq_scatter_offset_s16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset (uint8_t * __base, uint8x16_t __offset, uint8x16_t __value)
+{
+ __arm_vstrbq_scatter_offset_u8 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset (uint8_t * __base, uint32x4_t __offset, uint32x4_t __value)
+{
+ __arm_vstrbq_scatter_offset_u32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset (uint8_t * __base, uint16x8_t __offset, uint16x8_t __value)
+{
+ __arm_vstrbq_scatter_offset_u16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq (int8_t * __addr, int8x16_t __value)
+{
+ __arm_vstrbq_s8 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq (int8_t * __addr, int32x4_t __value)
+{
+ __arm_vstrbq_s32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq (int8_t * __addr, int16x8_t __value)
+{
+ __arm_vstrbq_s16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq (uint8_t * __addr, uint8x16_t __value)
+{
+ __arm_vstrbq_u8 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq (uint8_t * __addr, uint32x4_t __value)
+{
+ __arm_vstrbq_u32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq (uint8_t * __addr, uint16x8_t __value)
+{
+ __arm_vstrbq_u16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base (uint32x4_t __addr, const int __offset, int32x4_t __value)
+{
+ __arm_vstrwq_scatter_base_s32 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base (uint32x4_t __addr, const int __offset, uint32x4_t __value)
+{
+ __arm_vstrwq_scatter_base_u32 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset (uint8_t const * __base, uint8x16_t __offset)
+{
+ return __arm_vldrbq_gather_offset_u8 (__base, __offset);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset (int8_t const * __base, uint8x16_t __offset)
+{
+ return __arm_vldrbq_gather_offset_s8 (__base, __offset);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset (uint8_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrbq_gather_offset_u16 (__base, __offset);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset (int8_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrbq_gather_offset_s16 (__base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset (uint8_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrbq_gather_offset_u32 (__base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset (int8_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrbq_gather_offset_s32 (__base, __offset);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_p (int8_t * __addr, int8x16_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_p_s8 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_p (int8_t * __addr, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_p_s32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_p (int8_t * __addr, int16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_p_s16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_p (uint8_t * __addr, uint8x16_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_p_u8 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_p (uint8_t * __addr, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_p_u32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_p (uint8_t * __addr, uint16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_p_u16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_p (int8_t * __base, uint8x16_t __offset, int8x16_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_scatter_offset_p_s8 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_p (int8_t * __base, uint32x4_t __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_scatter_offset_p_s32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_p (int8_t * __base, uint16x8_t __offset, int16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_scatter_offset_p_s16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_p (uint8_t * __base, uint8x16_t __offset, uint8x16_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_scatter_offset_p_u8 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_p (uint8_t * __base, uint32x4_t __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_scatter_offset_p_u32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_p (uint8_t * __base, uint16x8_t __offset, uint16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrbq_scatter_offset_p_u16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_p (uint32x4_t __addr, const int __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_base_p_s32 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_p (uint32x4_t __addr, const int __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_base_p_u32 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z (int8_t const * __base, uint8x16_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrbq_gather_offset_z_s8 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z (int8_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrbq_gather_offset_z_s32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z (int8_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrbq_gather_offset_z_s16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z (uint8_t const * __base, uint8x16_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrbq_gather_offset_z_u8 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z (uint8_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrbq_gather_offset_z_u32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z (uint8_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrbq_gather_offset_z_u16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (int8_t const * __base)
+{
+ return __arm_vld1q_s8 (__base);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (int32_t const * __base)
+{
+ return __arm_vld1q_s32 (__base);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (int16_t const * __base)
+{
+ return __arm_vld1q_s16 (__base);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (uint8_t const * __base)
+{
+ return __arm_vld1q_u8 (__base);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (uint32_t const * __base)
+{
+ return __arm_vld1q_u32 (__base);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (uint16_t const * __base)
+{
+ return __arm_vld1q_u16 (__base);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset (int16_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrhq_gather_offset_s32 (__base, __offset);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset (int16_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrhq_gather_offset_s16 (__base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset (uint16_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrhq_gather_offset_u32 (__base, __offset);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset (uint16_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrhq_gather_offset_u16 (__base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z (int16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_offset_z_s32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z (int16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_offset_z_s16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z (uint16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_offset_z_u32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z (uint16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_offset_z_u16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset (int16_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrhq_gather_shifted_offset_s32 (__base, __offset);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset (int16_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrhq_gather_shifted_offset_s16 (__base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset (uint16_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrhq_gather_shifted_offset_u32 (__base, __offset);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset (uint16_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrhq_gather_shifted_offset_u16 (__base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z (int16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_shifted_offset_z_s32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z (int16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_shifted_offset_z_s16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z (uint16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_shifted_offset_z_u32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z (uint16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_shifted_offset_z_u16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_offset (int64_t const * __base, uint64x2_t __offset)
+{
+ return __arm_vldrdq_gather_offset_s64 (__base, __offset);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_offset (uint64_t const * __base, uint64x2_t __offset)
+{
+ return __arm_vldrdq_gather_offset_u64 (__base, __offset);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_offset_z (int64_t const * __base, uint64x2_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrdq_gather_offset_z_s64 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_offset_z (uint64_t const * __base, uint64x2_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrdq_gather_offset_z_u64 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_shifted_offset (int64_t const * __base, uint64x2_t __offset)
+{
+ return __arm_vldrdq_gather_shifted_offset_s64 (__base, __offset);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_shifted_offset (uint64_t const * __base, uint64x2_t __offset)
+{
+ return __arm_vldrdq_gather_shifted_offset_u64 (__base, __offset);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_shifted_offset_z (int64_t const * __base, uint64x2_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrdq_gather_shifted_offset_z_s64 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrdq_gather_shifted_offset_z (uint64_t const * __base, uint64x2_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrdq_gather_shifted_offset_z_u64 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_offset (int32_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrwq_gather_offset_s32 (__base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_offset (uint32_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrwq_gather_offset_u32 (__base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_offset_z (int32_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrwq_gather_offset_z_s32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_offset_z (uint32_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrwq_gather_offset_z_u32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_shifted_offset (int32_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrwq_gather_shifted_offset_s32 (__base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_shifted_offset (uint32_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrwq_gather_shifted_offset_u32 (__base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_shifted_offset_z (int32_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrwq_gather_shifted_offset_z_s32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_shifted_offset_z (uint32_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrwq_gather_shifted_offset_z_u32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (int8_t * __addr, int8x16_t __value)
+{
+ __arm_vst1q_s8 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (int32_t * __addr, int32x4_t __value)
+{
+ __arm_vst1q_s32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (int16_t * __addr, int16x8_t __value)
+{
+ __arm_vst1q_s16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (uint8_t * __addr, uint8x16_t __value)
+{
+ __arm_vst1q_u8 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (uint32_t * __addr, uint32x4_t __value)
+{
+ __arm_vst1q_u32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (uint16_t * __addr, uint16x8_t __value)
+{
+ __arm_vst1q_u16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset (int16_t * __base, uint32x4_t __offset, int32x4_t __value)
+{
+ __arm_vstrhq_scatter_offset_s32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset (int16_t * __base, uint16x8_t __offset, int16x8_t __value)
+{
+ __arm_vstrhq_scatter_offset_s16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset (uint16_t * __base, uint32x4_t __offset, uint32x4_t __value)
+{
+ __arm_vstrhq_scatter_offset_u32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset (uint16_t * __base, uint16x8_t __offset, uint16x8_t __value)
+{
+ __arm_vstrhq_scatter_offset_u16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset_p (int16_t * __base, uint32x4_t __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_offset_p_s32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset_p (int16_t * __base, uint16x8_t __offset, int16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_offset_p_s16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset_p (uint16_t * __base, uint32x4_t __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_offset_p_u32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset_p (uint16_t * __base, uint16x8_t __offset, uint16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_offset_p_u16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset (int16_t * __base, uint32x4_t __offset, int32x4_t __value)
+{
+ __arm_vstrhq_scatter_shifted_offset_s32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset (int16_t * __base, uint16x8_t __offset, int16x8_t __value)
+{
+ __arm_vstrhq_scatter_shifted_offset_s16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset (uint16_t * __base, uint32x4_t __offset, uint32x4_t __value)
+{
+ __arm_vstrhq_scatter_shifted_offset_u32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset (uint16_t * __base, uint16x8_t __offset, uint16x8_t __value)
+{
+ __arm_vstrhq_scatter_shifted_offset_u16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset_p (int16_t * __base, uint32x4_t __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_shifted_offset_p_s32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset_p (int16_t * __base, uint16x8_t __offset, int16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_shifted_offset_p_s16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset_p (uint16_t * __base, uint32x4_t __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_shifted_offset_p_u32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset_p (uint16_t * __base, uint16x8_t __offset, uint16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_shifted_offset_p_u16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq (int16_t * __addr, int32x4_t __value)
+{
+ __arm_vstrhq_s32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq (int16_t * __addr, int16x8_t __value)
+{
+ __arm_vstrhq_s16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq (uint16_t * __addr, uint32x4_t __value)
+{
+ __arm_vstrhq_u32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq (uint16_t * __addr, uint16x8_t __value)
+{
+ __arm_vstrhq_u16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_p (int16_t * __addr, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_p_s32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_p (int16_t * __addr, int16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_p_s16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_p (uint16_t * __addr, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_p_u32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_p (uint16_t * __addr, uint16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_p_u16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq (int32_t * __addr, int32x4_t __value)
+{
+ __arm_vstrwq_s32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq (uint32_t * __addr, uint32x4_t __value)
+{
+ __arm_vstrwq_u32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_p (int32_t * __addr, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_p_s32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_p (uint32_t * __addr, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_p_u32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base_p (uint64x2_t __addr, const int __offset, int64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_base_p_s64 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base_p (uint64x2_t __addr, const int __offset, uint64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_base_p_u64 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base (uint64x2_t __addr, const int __offset, int64x2_t __value)
+{
+ __arm_vstrdq_scatter_base_s64 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base (uint64x2_t __addr, const int __offset, uint64x2_t __value)
+{
+ __arm_vstrdq_scatter_base_u64 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_offset_p (int64_t * __base, uint64x2_t __offset, int64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_offset_p_s64 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_offset_p (uint64_t * __base, uint64x2_t __offset, uint64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_offset_p_u64 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_offset (int64_t * __base, uint64x2_t __offset, int64x2_t __value)
+{
+ __arm_vstrdq_scatter_offset_s64 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_offset (uint64_t * __base, uint64x2_t __offset, uint64x2_t __value)
+{
+ __arm_vstrdq_scatter_offset_u64 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_shifted_offset_p (int64_t * __base, uint64x2_t __offset, int64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_shifted_offset_p_s64 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_shifted_offset_p (uint64_t * __base, uint64x2_t __offset, uint64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_shifted_offset_p_u64 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_shifted_offset (int64_t * __base, uint64x2_t __offset, int64x2_t __value)
+{
+ __arm_vstrdq_scatter_shifted_offset_s64 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_shifted_offset (uint64_t * __base, uint64x2_t __offset, uint64x2_t __value)
+{
+ __arm_vstrdq_scatter_shifted_offset_u64 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_offset_p (int32_t * __base, uint32x4_t __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_offset_p_s32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_offset_p (uint32_t * __base, uint32x4_t __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_offset_p_u32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_offset (int32_t * __base, uint32x4_t __offset, int32x4_t __value)
+{
+ __arm_vstrwq_scatter_offset_s32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_offset (uint32_t * __base, uint32x4_t __offset, uint32x4_t __value)
+{
+ __arm_vstrwq_scatter_offset_u32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_shifted_offset_p (int32_t * __base, uint32x4_t __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_shifted_offset_p_s32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_shifted_offset_p (uint32_t * __base, uint32x4_t __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_shifted_offset_p_u32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_shifted_offset (int32_t * __base, uint32x4_t __offset, int32x4_t __value)
+{
+ __arm_vstrwq_scatter_shifted_offset_s32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_shifted_offset (uint32_t * __base, uint32x4_t __offset, uint32x4_t __value)
+{
+ __arm_vstrwq_scatter_shifted_offset_u32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (int8x16_t __a, int8x16_t __b)
+{
+ return __arm_vaddq_s8 (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (int16x8_t __a, int16x8_t __b)
+{
+ return __arm_vaddq_s16 (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (int32x4_t __a, int32x4_t __b)
+{
+ return __arm_vaddq_s32 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (uint8x16_t __a, uint8x16_t __b)
+{
+ return __arm_vaddq_u8 (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (uint16x8_t __a, uint16x8_t __b)
+{
+ return __arm_vaddq_u16 (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (uint32x4_t __a, uint32x4_t __b)
+{
+ return __arm_vaddq_u32 (__a, __b);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (uint8x16_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_u8 ();
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (uint16x8_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_u16 ();
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (uint32x4_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_u32 ();
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (uint64x2_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_u64 ();
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (int8x16_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_s8 ();
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (int16x8_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_s16 ();
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (int32x4_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_s32 ();
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (int64x2_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_s64 ();
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_s16_s32 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_s16_s64 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_s16_s8 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_s16_u16 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_s16_u32 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_s16_u64 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_s16_u8 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_s32_s16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_s32_s64 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_s32_s8 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_s32_u16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_s32_u32 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_s32_u64 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_s32_u8 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_s64_s16 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_s64_s32 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_s64_s8 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_s64_u16 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_s64_u32 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_s64_u64 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_s64_u8 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_s8_s16 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_s8_s32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_s8_s64 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_s8_u16 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_s8_u32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_s8_u64 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_s8_u8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_u16_s16 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_u16_s32 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_u16_s64 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_u16_s8 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_u16_u32 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_u16_u64 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_u16_u8 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_u32_s16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_u32_s32 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_u32_s64 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_u32_s8 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_u32_u16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_u32_u64 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_u32_u8 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_u64_s16 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_u64_s32 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_u64_s64 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_u64_s8 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_u64_u16 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_u64_u32 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_u64_u8 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_u8_s16 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_u8_s32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_u8_s64 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_u8_s8 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_u8_u16 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_u8_u32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_u8_u64 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_m (uint8x16_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_m (uint32x4_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_m_n_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_m (uint16x8_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_m (uint8x16_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_m_wb_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_m (uint16x8_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_m_wb_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_m (uint32x4_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_m_wb_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_u8 (uint32_t __a, const int __imm)
+{
+ return __arm_vddupq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_u32 (uint32_t __a, const int __imm)
+{
+ return __arm_vddupq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_u16 (uint32_t __a, const int __imm)
+{
+ return __arm_vddupq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_m (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_m_n_u8 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_m (uint32x4_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_m_n_u32 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_m (uint16x8_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_m_n_u16 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_m (uint8x16_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_m_wb_u8 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_m (uint32x4_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_m_wb_u32 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_m (uint16x8_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_m_wb_u16 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_u8 (uint32_t __a, uint32_t __b, const int __imm)
+{
+ return __arm_vdwdupq_n_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_u32 (uint32_t __a, uint32_t __b, const int __imm)
+{
+ return __arm_vdwdupq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_u16 (uint32_t __a, uint32_t __b, const int __imm)
+{
+ return __arm_vdwdupq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_u8 (uint32_t * __a, uint32_t __b, const int __imm)
+{
+ return __arm_vdwdupq_wb_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_u32 (uint32_t * __a, uint32_t __b, const int __imm)
+{
+ return __arm_vdwdupq_wb_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_u16 (uint32_t * __a, uint32_t __b, const int __imm)
+{
+ return __arm_vdwdupq_wb_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_m (uint8x16_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_m_n_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_m (uint32x4_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_m_n_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_m (uint16x8_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_m_n_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_u8 (uint32_t __a, const int __imm)
+{
+ return __arm_vidupq_n_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_m (uint8x16_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_m_wb_u8 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_m (uint16x8_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_m_wb_u16 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_m (uint32x4_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_m_wb_u32 (__inactive, __a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_u32 (uint32_t __a, const int __imm)
+{
+ return __arm_vidupq_n_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_u16 (uint32_t __a, const int __imm)
+{
+ return __arm_vidupq_n_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_u8 (uint32_t * __a, const int __imm)
+{
+ return __arm_vidupq_wb_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_u16 (uint32_t * __a, const int __imm)
+{
+ return __arm_vidupq_wb_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_u32 (uint32_t * __a, const int __imm)
+{
+ return __arm_vidupq_wb_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_u8 (uint32_t * __a, const int __imm)
+{
+ return __arm_vddupq_wb_u8 (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_u16 (uint32_t * __a, const int __imm)
+{
+ return __arm_vddupq_wb_u16 (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_u32 (uint32_t * __a, const int __imm)
+{
+ return __arm_vddupq_wb_u32 (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_m (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_m_n_u8 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_m (uint32x4_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_m_n_u32 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_m (uint16x8_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_m_n_u16 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_m (uint8x16_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_m_wb_u8 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_m (uint32x4_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_m_wb_u32 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_m (uint16x8_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_m_wb_u16 (__inactive, __a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_u8 (uint32_t __a, uint32_t __b, const int __imm)
+{
+ return __arm_viwdupq_n_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_u32 (uint32_t __a, uint32_t __b, const int __imm)
+{
+ return __arm_viwdupq_n_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_u16 (uint32_t __a, uint32_t __b, const int __imm)
+{
+ return __arm_viwdupq_n_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_u8 (uint32_t * __a, uint32_t __b, const int __imm)
+{
+ return __arm_viwdupq_wb_u8 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_u32 (uint32_t * __a, uint32_t __b, const int __imm)
+{
+ return __arm_viwdupq_wb_u32 (__a, __b, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_u16 (uint32_t * __a, uint32_t __b, const int __imm)
+{
+ return __arm_viwdupq_wb_u16 (__a, __b, __imm);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base_wb (uint64x2_t * __addr, const int __offset, int64x2_t __value)
+{
+ __arm_vstrdq_scatter_base_wb_s64 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base_wb (uint64x2_t * __addr, const int __offset, uint64x2_t __value)
+{
+ __arm_vstrdq_scatter_base_wb_u64 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base_wb_p (uint64x2_t * __addr, const int __offset, int64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_base_wb_p_s64 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrdq_scatter_base_wb_p (uint64x2_t * __addr, const int __offset, uint64x2_t __value, mve_pred16_t __p)
+{
+ __arm_vstrdq_scatter_base_wb_p_u64 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_wb_p (uint32x4_t * __addr, const int __offset, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_base_wb_p_s32 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_wb_p (uint32x4_t * __addr, const int __offset, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_base_wb_p_u32 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_wb (uint32x4_t * __addr, const int __offset, int32x4_t __value)
+{
+ __arm_vstrwq_scatter_base_wb_s32 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_wb (uint32x4_t * __addr, const int __offset, uint32x4_t __value)
+{
+ __arm_vstrwq_scatter_base_wb_u32 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_x_u8 (uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_x_u16 (uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_x_u32 (uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_x_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_x_u8 (uint32_t *__a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_x_wb_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_x_u16 (uint32_t *__a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_x_wb_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vddupq_x_u32 (uint32_t *__a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vddupq_x_wb_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_x_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_x_n_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_x_u16 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_x_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_x_u32 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_x_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_x_u8 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_x_wb_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_x_u16 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_x_wb_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdwdupq_x_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vdwdupq_x_wb_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_x_u8 (uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_x_u16 (uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_x_u32 (uint32_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_x_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_x_u8 (uint32_t *__a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_x_wb_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_x_u16 (uint32_t *__a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_x_wb_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vidupq_x_u32 (uint32_t *__a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vidupq_x_wb_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_x_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_x_n_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_x_u16 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_x_n_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_x_u32 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_x_n_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_x_u8 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_x_wb_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_x_u16 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_x_wb_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_viwdupq_x_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_viwdupq_x_wb_u32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_x_s32 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vclsq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vclsq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclsq_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vclsq_x_s32 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_x_s32 (__a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_x_u16 (__a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vclzq_x (uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vclzq_x_u32 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_x_s32 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulhq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulhq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_poly_x_p8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_poly_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_poly_x_p16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmullbq_int_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmullbq_int_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_poly_x_p8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_poly_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_poly_x_p16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulltq_int_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulltq_int_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhaddq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhaddq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot90_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot90_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot90_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot90_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot270_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot270_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhcaddq_rot270_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhcaddq_rot270_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (int8x16_t __a, int8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (int16x8_t __a, int16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (uint8x16_t __a, uint8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (uint16x8_t __a, uint16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (uint32x4_t __a, uint32_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vhsubq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vhsubq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrhaddq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrhaddq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrmulhq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrmulhq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (int8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (int16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (int32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (uint8x16_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (uint16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (uint32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovlbq_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovlbq_x_u16 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmovltq_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmovltq_x_u16 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_x_s32 (__a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_x_u16 (__a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmvnq_x (uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vmvnq_x_u32 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev16q_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev16q_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev16q_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev16q_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_x_u16 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (int8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_s8 (__a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_s16 (__a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_s32 (__a, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (uint8x16_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_u8 (__a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_u16 (__a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_u32 (__a, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_x (uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_x (uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshlq_x (uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vrshlq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_x (int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_x_n_s8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_x (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_x_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_x (uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshllbq_x (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshllbq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_x (int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_x_n_s8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_x (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_x_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_x (uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlltq_x (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlltq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_s8 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_s16 (__a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_s32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x (uint8x16_t __a, int8x16_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_u8 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x (uint16x8_t __a, int16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_u16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x (uint32x4_t __a, int32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_u32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x_n (int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_n_s8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x_n (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x_n (int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_n_s32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x_n (uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x_n (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlq_x_n (uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlq_x_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_x (int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_x_n_s8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_x (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_x_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_x (int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_x_n_s32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_x (uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_x (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrshrq_x (uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vrshrq_x_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_x (int8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_x_n_s8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_x (int16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_x_n_s16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_x (int32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_x_n_s32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_x (uint8x16_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_x_n_u8 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_x (uint16x8_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_x_n_u16 (__a, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_x (uint32x4_t __a, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshrq_x_n_u32 (__a, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadciq (int32x4_t __a, int32x4_t __b, unsigned * __carry_out)
+{
+ return __arm_vadciq_s32 (__a, __b, __carry_out);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadciq (uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out)
+{
+ return __arm_vadciq_u32 (__a, __b, __carry_out);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadciq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
+{
+ return __arm_vadciq_m_s32 (__inactive, __a, __b, __carry_out, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadciq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
+{
+ return __arm_vadciq_m_u32 (__inactive, __a, __b, __carry_out, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadcq (int32x4_t __a, int32x4_t __b, unsigned * __carry)
+{
+ return __arm_vadcq_s32 (__a, __b, __carry);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadcq (uint32x4_t __a, uint32x4_t __b, unsigned * __carry)
+{
+ return __arm_vadcq_u32 (__a, __b, __carry);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadcq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry, mve_pred16_t __p)
+{
+ return __arm_vadcq_m_s32 (__inactive, __a, __b, __carry, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vadcq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry, mve_pred16_t __p)
+{
+ return __arm_vadcq_m_u32 (__inactive, __a, __b, __carry, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbciq (int32x4_t __a, int32x4_t __b, unsigned * __carry_out)
+{
+ return __arm_vsbciq_s32 (__a, __b, __carry_out);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbciq (uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out)
+{
+ return __arm_vsbciq_u32 (__a, __b, __carry_out);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbciq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
+{
+ return __arm_vsbciq_m_s32 (__inactive, __a, __b, __carry_out, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbciq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry_out, mve_pred16_t __p)
+{
+ return __arm_vsbciq_m_u32 (__inactive, __a, __b, __carry_out, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbcq (int32x4_t __a, int32x4_t __b, unsigned * __carry)
+{
+ return __arm_vsbcq_s32 (__a, __b, __carry);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbcq (uint32x4_t __a, uint32x4_t __b, unsigned * __carry)
+{
+ return __arm_vsbcq_u32 (__a, __b, __carry);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbcq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry, mve_pred16_t __p)
+{
+ return __arm_vsbcq_m_s32 (__inactive, __a, __b, __carry, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsbcq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry, mve_pred16_t __p)
+{
+ return __arm_vsbcq_m_u32 (__inactive, __a, __b, __carry, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (uint8_t * __addr, uint8x16_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_u8 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (int8_t * __addr, int8x16_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_s8 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (int8_t * __addr, int8x16x2_t __value)
+{
+ __arm_vst2q_s8 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (uint8_t * __addr, uint8x16x2_t __value)
+{
+ __arm_vst2q_u8 (__addr, __value);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (uint8_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_u8 (__base, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (int8_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_s8 (__base, __p);
+}
+
+__extension__ extern __inline int8x16x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (int8_t const * __addr)
+{
+ return __arm_vld2q_s8 (__addr);
+}
+
+__extension__ extern __inline uint8x16x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (uint8_t const * __addr)
+{
+ return __arm_vld2q_u8 (__addr);
+}
+
+__extension__ extern __inline int8x16x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (int8_t const * __addr)
+{
+ return __arm_vld4q_s8 (__addr);
+}
+
+__extension__ extern __inline uint8x16x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (uint8_t const * __addr)
+{
+ return __arm_vld4q_u8 (__addr);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (uint16_t * __addr, uint16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_u16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (int16_t * __addr, int16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_s16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (int16_t * __addr, int16x8x2_t __value)
+{
+ __arm_vst2q_s16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (uint16_t * __addr, uint16x8x2_t __value)
+{
+ __arm_vst2q_u16 (__addr, __value);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (uint16_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_u16 (__base, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (int16_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_s16 (__base, __p);
+}
+
+__extension__ extern __inline int16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (int16_t const * __addr)
+{
+ return __arm_vld2q_s16 (__addr);
+}
+
+__extension__ extern __inline uint16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (uint16_t const * __addr)
+{
+ return __arm_vld2q_u16 (__addr);
+}
+
+__extension__ extern __inline int16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (int16_t const * __addr)
+{
+ return __arm_vld4q_s16 (__addr);
+}
+
+__extension__ extern __inline uint16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (uint16_t const * __addr)
+{
+ return __arm_vld4q_u16 (__addr);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (uint32_t * __addr, uint32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_u32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (int32_t * __addr, int32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_s32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (int32_t * __addr, int32x4x2_t __value)
+{
+ __arm_vst2q_s32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (uint32_t * __addr, uint32x4x2_t __value)
+{
+ __arm_vst2q_u32 (__addr, __value);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (uint32_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_u32 (__base, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (int32_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_s32 (__base, __p);
+}
+
+__extension__ extern __inline int32x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (int32_t const * __addr)
+{
+ return __arm_vld2q_s32 (__addr);
+}
+
+__extension__ extern __inline uint32x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (uint32_t const * __addr)
+{
+ return __arm_vld2q_u32 (__addr);
+}
+
+__extension__ extern __inline int32x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (int32_t const * __addr)
+{
+ return __arm_vld4q_s32 (__addr);
+}
+
+__extension__ extern __inline uint32x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (uint32_t const * __addr)
+{
+ return __arm_vld4q_u32 (__addr);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (int16_t __a, int16x8_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_s16 (__a, __b, __idx);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (int32_t __a, int32x4_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_s32 (__a, __b, __idx);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (int8_t __a, int8x16_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_s8 (__a, __b, __idx);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (int64_t __a, int64x2_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_s64 (__a, __b, __idx);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (uint8_t __a, uint8x16_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_u8 (__a, __b, __idx);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (uint16_t __a, uint16x8_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_u16 (__a, __b, __idx);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (uint32_t __a, uint32x4_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_u32 (__a, __b, __idx);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (uint64_t __a, uint64x2_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_u64 (__a, __b, __idx);
+}
+
+__extension__ extern __inline int16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (int16x8_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_s16 (__a, __idx);
+}
+
+__extension__ extern __inline int32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (int32x4_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_s32 (__a, __idx);
+}
+
+__extension__ extern __inline int8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (int8x16_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_s8 (__a, __idx);
+}
+
+__extension__ extern __inline int64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (int64x2_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_s64 (__a, __idx);
+}
+
+__extension__ extern __inline uint8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (uint8x16_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_u8 (__a, __idx);
+}
+
+__extension__ extern __inline uint16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (uint16x8_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_u16 (__a, __idx);
+}
+
+__extension__ extern __inline uint32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (uint32x4_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_u32 (__a, __idx);
+}
+
+__extension__ extern __inline uint64_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (uint64x2_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_u64 (__a, __idx);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq_m (int8x16_t __a, uint32_t * __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlcq_m_s8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq_m (uint8x16_t __a, uint32_t * __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlcq_m_u8 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq_m (int16x8_t __a, uint32_t * __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlcq_m_s16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq_m (uint16x8_t __a, uint32_t * __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlcq_m_u16 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq_m (int32x4_t __a, uint32_t * __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlcq_m_s32 (__a, __b, __imm, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshlcq_m (uint32x4_t __a, uint32_t * __b, const int __imm, mve_pred16_t __p)
+{
+ return __arm_vshlcq_m_u32 (__a, __b, __imm, __p);
+}
+
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (float16_t * __addr, float16x8x4_t __value)
+{
+ __arm_vst4q_f16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst4q (float32_t * __addr, float32x4x4_t __value)
+{
+ __arm_vst4q_f32 (__addr, __value);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq (float16x8_t __a)
+{
+ return __arm_vrndxq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq (float32x4_t __a)
+{
+ return __arm_vrndxq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq (float16x8_t __a)
+{
+ return __arm_vrndq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq (float32x4_t __a)
+{
+ return __arm_vrndq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq (float16x8_t __a)
+{
+ return __arm_vrndpq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq (float32x4_t __a)
+{
+ return __arm_vrndpq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq (float16x8_t __a)
+{
+ return __arm_vrndnq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq (float32x4_t __a)
+{
+ return __arm_vrndnq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq (float16x8_t __a)
+{
+ return __arm_vrndmq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq (float32x4_t __a)
+{
+ return __arm_vrndmq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq (float16x8_t __a)
+{
+ return __arm_vrndaq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq (float32x4_t __a)
+{
+ return __arm_vrndaq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (float16x8_t __a)
+{
+ return __arm_vrev64q_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q (float32x4_t __a)
+{
+ return __arm_vrev64q_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq (float16x8_t __a)
+{
+ return __arm_vnegq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq (float32x4_t __a)
+{
+ return __arm_vnegq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (float16_t __a)
+{
+ return __arm_vdupq_n_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_n (float32_t __a)
+{
+ return __arm_vdupq_n_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq (float16x8_t __a)
+{
+ return __arm_vabsq_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq (float32x4_t __a)
+{
+ return __arm_vabsq_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q (float16x8_t __a)
+{
+ return __arm_vrev32q_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvttq_f32 (float16x8_t __a)
+{
+ return __arm_vcvttq_f32_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtbq_f32 (float16x8_t __a)
+{
+ return __arm_vcvtbq_f32_f16 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq (int16x8_t __a)
+{
+ return __arm_vcvtq_f16_s16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq (int32x4_t __a)
+{
+ return __arm_vcvtq_f32_s32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq (uint16x8_t __a)
+{
+ return __arm_vcvtq_f16_u16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq (uint32x4_t __a)
+{
+ return __arm_vcvtq_f32_u32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vsubq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vsubq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (float16x8_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq (float32x4_t __a, int32_t __b)
+{
+ return __arm_vbrsrq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n (int16x8_t __a, const int __imm6)
+{
+ return __arm_vcvtq_n_f16_s16 (__a, __imm6);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n (int32x4_t __a, const int __imm6)
+{
+ return __arm_vcvtq_n_f32_s32 (__a, __imm6);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n (uint16x8_t __a, const int __imm6)
+{
+ return __arm_vcvtq_n_f16_u16 (__a, __imm6);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n (uint32x4_t __a, const int __imm6)
+{
+ return __arm_vcvtq_n_f32_u32 (__a, __imm6);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vcmpneq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmpneq_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vcmpltq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmpltq_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vcmpleq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmpleq_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vcmpgtq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmpgtq_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vcmpgeq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmpgeq_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vcmpeqq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmpeqq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vsubq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vorrq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vornq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vmulq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vmulq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq (float16_t __a, float16x8_t __b)
+{
+ return __arm_vminnmvq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vminnmq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq (float16_t __a, float16x8_t __b)
+{
+ return __arm_vminnmavq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vminnmaq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq (float16_t __a, float16x8_t __b)
+{
+ return __arm_vmaxnmvq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vmaxnmq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq (float16_t __a, float16x8_t __b)
+{
+ return __arm_vmaxnmavq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vmaxnmaq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_veorq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90 (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmulq_rot90_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270 (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmulq_rot270_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180 (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmulq_rot180_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcmulq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcaddq_rot90_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vcaddq_rot270_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vbicq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vandq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (float16x8_t __a, float16_t __b)
+{
+ return __arm_vaddq_n_f16 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vabdq_f16 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vcmpneq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmpneq_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vcmpltq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmpltq_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vcmpleq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmpleq_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vcmpgtq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmpgtq_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vcmpgeq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmpgeq_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vcmpeqq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmpeqq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vsubq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vorrq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vornq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vmulq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vmulq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq (float32_t __a, float32x4_t __b)
+{
+ return __arm_vminnmvq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vminnmq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq (float32_t __a, float32x4_t __b)
+{
+ return __arm_vminnmavq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vminnmaq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq (float32_t __a, float32x4_t __b)
+{
+ return __arm_vmaxnmvq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vmaxnmq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq (float32_t __a, float32x4_t __b)
+{
+ return __arm_vmaxnmavq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vmaxnmaq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_veorq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90 (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmulq_rot90_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270 (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmulq_rot270_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180 (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmulq_rot180_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcmulq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90 (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcaddq_rot90_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270 (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vcaddq_rot270_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vbicq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vandq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (float32x4_t __a, float32_t __b)
+{
+ return __arm_vaddq_n_f32 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vabdq_f32 (__a, __b);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtaq_m_s16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtaq_m_u16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtaq_m_s32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtaq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtaq_m_u32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (float16x8_t __inactive, int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_f16_s16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (float16x8_t __inactive, uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_f16_u16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (float32x4_t __inactive, int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_f32_s32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (float32x4_t __inactive, uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_f32_u32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtbq_m (float16x8_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcvtbq_m_f16_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtbq_m (float32x4_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtbq_m_f32_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvttq_m (float16x8_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcvttq_m_f16_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvttq_m (float32x4_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvttq_m_f32_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq (float16x8_t __a, float16x8_t __b, float16x8_t __c)
+{
+ return __arm_vcmlaq_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot180 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
+{
+ return __arm_vcmlaq_rot180_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot270 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
+{
+ return __arm_vcmlaq_rot270_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot90 (float16x8_t __a, float16x8_t __b, float16x8_t __c)
+{
+ return __arm_vcmlaq_rot90_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq (float16x8_t __a, float16x8_t __b, float16x8_t __c)
+{
+ return __arm_vfmaq_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq (float16x8_t __a, float16x8_t __b, float16_t __c)
+{
+ return __arm_vfmaq_n_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmasq (float16x8_t __a, float16x8_t __b, float16_t __c)
+{
+ return __arm_vfmasq_n_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmsq (float16x8_t __a, float16x8_t __b, float16x8_t __c)
+{
+ return __arm_vfmsq_f16 (__a, __b, __c);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtmq_m_s16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtnq_m_s16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtpq_m_s16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_s16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (float16x8_t __inactive, float16_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmaq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq_p (float16_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmavq_p_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq_p (float16_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmvq_p_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmaq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq_p (float16_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmavq_p_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq_p (float16_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmvq_p_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndaq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndmq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndnq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndpq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq_m (float16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndxq_m_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtmq_m_u16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtnq_m_u16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtpq_m_u16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_u16_f16 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq (float32x4_t __a, float32x4_t __b, float32x4_t __c)
+{
+ return __arm_vcmlaq_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot180 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
+{
+ return __arm_vcmlaq_rot180_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot270 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
+{
+ return __arm_vcmlaq_rot270_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot90 (float32x4_t __a, float32x4_t __b, float32x4_t __c)
+{
+ return __arm_vcmlaq_rot90_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq (float32x4_t __a, float32x4_t __b, float32x4_t __c)
+{
+ return __arm_vfmaq_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq (float32x4_t __a, float32x4_t __b, float32_t __c)
+{
+ return __arm_vfmaq_n_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmasq (float32x4_t __a, float32x4_t __b, float32_t __c)
+{
+ return __arm_vfmasq_n_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmsq (float32x4_t __a, float32x4_t __b, float32x4_t __c)
+{
+ return __arm_vfmsq_f32 (__a, __b, __c);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtmq_m_s32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtnq_m_s32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtpq_m_s32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_s32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vdupq_m (float32x4_t __inactive, float32_t __a, mve_pred16_t __p)
+{
+ return __arm_vdupq_m_n_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmaq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmaq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmavq_p (float32_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmavq_p_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmvq_p (float32_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmvq_p_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmaq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmaq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmavq_p (float32_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmavq_p_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmvq_p (float32_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmvq_p_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vpselq (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vpselq_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndaq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndmq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndnq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndpq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq_m (float32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndxq_m_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpeqq_m (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpeqq_m_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgeq_m (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgeq_m_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpgtq_m (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpgtq_m_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpleq_m (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpleq_m_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpltq_m (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpltq_m_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline mve_pred16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmpneq_m (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmpneq_m_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtmq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtmq_m_u32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtnq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtnq_m_u32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtpq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtpq_m_u32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_u32_f32 (__inactive, __a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (float16x8_t __inactive, uint16x8_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_f16_u16 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (float16x8_t __inactive, int16x8_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_f16_s16 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (float32x4_t __inactive, uint32x4_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_f32_u32 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (float32x4_t __inactive, int32x4_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_f32_s32 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (float32x4_t __inactive, float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_m (float16x8_t __inactive, float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_m_n_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (float32x4_t __inactive, float32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_m (float16x8_t __inactive, float16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_m_n_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_m_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_m_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot180_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_rot180_m_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot180_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_rot180_m_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot270_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_rot270_m_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot270_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_rot270_m_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot90_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_rot90_m_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmlaq_rot90_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vcmlaq_rot90_m_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot180_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot180_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot270_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot270_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot90_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot90_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (int32x4_t __inactive, float32x4_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_s32_f32 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (int16x8_t __inactive, float16x8_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_s16_f16 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (uint32x4_t __inactive, float32x4_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_u32_f32 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_m_n (uint16x8_t __inactive, float16x8_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_m_n_u16_f16 (__inactive, __a, __imm6, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmaq_m_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmaq_m_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq_m (float32x4_t __a, float32x4_t __b, float32_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmaq_m_n_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmaq_m (float16x8_t __a, float16x8_t __b, float16_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmaq_m_n_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmasq_m (float32x4_t __a, float32x4_t __b, float32_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmasq_m_n_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmasq_m (float16x8_t __a, float16x8_t __b, float16_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmasq_m_n_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmsq_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmsq_m_f32 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vfmsq_m (float16x8_t __a, float16x8_t __b, float16x8_t __c, mve_pred16_t __p)
+{
+ return __arm_vfmsq_m_f16 (__a, __b, __c, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (float32x4_t __inactive, float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_m (float16x8_t __inactive, float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_m_n_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (float32x4_t __inactive, float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_f32 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_m (float16x8_t __inactive, float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_m_n_f16 (__inactive, __a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (float32_t const * __base)
+{
+ return __arm_vld1q_f32 (__base);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q (float16_t const * __base)
+{
+ return __arm_vld1q_f16 (__base);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset (float16_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrhq_gather_offset_f16 (__base, __offset);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z (float16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_offset_z_f16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset (float16_t const * __base, uint16x8_t __offset)
+{
+ return __arm_vldrhq_gather_shifted_offset_f16 (__base, __offset);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z (float16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrhq_gather_shifted_offset_z_f16 (__base, __offset, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_offset (float32_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrwq_gather_offset_f32 (__base, __offset);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_offset_z (float32_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrwq_gather_offset_z_f32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_shifted_offset (float32_t const * __base, uint32x4_t __offset)
+{
+ return __arm_vldrwq_gather_shifted_offset_f32 (__base, __offset);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_shifted_offset_z (float32_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __arm_vldrwq_gather_shifted_offset_z_f32 (__base, __offset, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_p (float32_t * __addr, float32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_p_f32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq (float32_t * __addr, float32x4_t __value)
+{
+ __arm_vstrwq_f32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (float32_t * __addr, float32x4_t __value)
+{
+ __arm_vst1q_f32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q (float16_t * __addr, float16x8_t __value)
+{
+ __arm_vst1q_f16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq (float16_t * __addr, float16x8_t __value)
+{
+ __arm_vstrhq_f16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_p (float16_t * __addr, float16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_p_f16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset (float16_t * __base, uint16x8_t __offset, float16x8_t __value)
+{
+ __arm_vstrhq_scatter_offset_f16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_offset_p (float16_t * __base, uint16x8_t __offset, float16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_offset_p_f16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset (float16_t * __base, uint16x8_t __offset, float16x8_t __value)
+{
+ __arm_vstrhq_scatter_shifted_offset_f16 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrhq_scatter_shifted_offset_p (float16_t * __base, uint16x8_t __offset, float16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vstrhq_scatter_shifted_offset_p_f16 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base (uint32x4_t __addr, const int __offset, float32x4_t __value)
+{
+ __arm_vstrwq_scatter_base_f32 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_p (uint32x4_t __addr, const int __offset, float32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_base_p_f32 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_offset (float32_t * __base, uint32x4_t __offset, float32x4_t __value)
+{
+ __arm_vstrwq_scatter_offset_f32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_offset_p (float32_t * __base, uint32x4_t __offset, float32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_offset_p_f32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_shifted_offset (float32_t * __base, uint32x4_t __offset, float32x4_t __value)
+{
+ __arm_vstrwq_scatter_shifted_offset_f32 (__base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_shifted_offset_p (float32_t * __base, uint32x4_t __offset, float32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_shifted_offset_p_f32 (__base, __offset, __value, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (float16x8_t __a, float16x8_t __b)
+{
+ return __arm_vaddq_f16 (__a, __b);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq (float32x4_t __a, float32x4_t __b)
+{
+ return __arm_vaddq_f32 (__a, __b);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (float16x8_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_f16 ();
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vuninitializedq (float32x4_t /* __v ATTRIBUTE UNUSED */)
+{
+ return __arm_vuninitializedq_f32 ();
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_s32_f16 (__a);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s32 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_s32_f32 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_s16_f16 (__a);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s16 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_s16_f32 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_s64_f16 (__a);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s64 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_s64_f32 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_s8_f16 (__a);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_s8 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_s8_f32 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_u16_f16 (__a);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u16 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_u16_f32 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_u32_f16 (__a);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u32 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_u32_f32 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_u64_f16 (__a);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u64 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_u64_f32 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_u8_f16 (__a);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_u8 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_u8_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (float32x4_t __a)
+{
+ return __arm_vreinterpretq_f16_f32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_f16_s16 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_f16_s32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_f16_s64 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_f16_s8 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_f16_u16 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_f16_u32 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_f16_u64 (__a);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f16 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_f16_u8 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (float16x8_t __a)
+{
+ return __arm_vreinterpretq_f32_f16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (int16x8_t __a)
+{
+ return __arm_vreinterpretq_f32_s16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (int32x4_t __a)
+{
+ return __arm_vreinterpretq_f32_s32 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (int64x2_t __a)
+{
+ return __arm_vreinterpretq_f32_s64 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (int8x16_t __a)
+{
+ return __arm_vreinterpretq_f32_s8 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (uint16x8_t __a)
+{
+ return __arm_vreinterpretq_f32_u16 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (uint32x4_t __a)
+{
+ return __arm_vreinterpretq_f32_u32 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (uint64x2_t __a)
+{
+ return __arm_vreinterpretq_f32_u64 (__a);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vreinterpretq_f32 (uint8x16_t __a)
+{
+ return __arm_vreinterpretq_f32_u8 (__a);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_wb (uint32x4_t * __addr, const int __offset, float32x4_t __value)
+{
+ __arm_vstrwq_scatter_base_wb_f32 (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_wb_p (uint32x4_t * __addr, const int __offset, float32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vstrwq_scatter_base_wb_p_f32 (__addr, __offset, __value, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vminnmq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vminnmq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmaxnmq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmaxnmq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabdq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vabdq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vabsq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vabsq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vaddq_x (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vaddq_x_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vnegq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vnegq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vmulq_x (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vmulq_x_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (float16x8_t __a, float16_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsubq_x (float32x4_t __a, float32_t __b, mve_pred16_t __p)
+{
+ return __arm_vsubq_x_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot90_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot90_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcaddq_rot270_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcaddq_rot270_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot90_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot90_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot90_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot180_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot180_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot180_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot270_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcmulq_rot270_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vcmulq_rot270_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x (uint16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_f16_u16 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x (int16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_f16_s16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x (int32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_f32_s32 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x (uint32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_f32_u32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x_n (int16x8_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_n_f16_s16 (__a, __imm6, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x_n (uint16x8_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_n_f16_u16 (__a, __imm6, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x_n (int32x4_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_n_f32_s32 (__a, __imm6, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_x_n (uint32x4_t __a, const int __imm6, mve_pred16_t __p)
+{
+ return __arm_vcvtq_x_n_f32_u32 (__a, __imm6, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndnq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndnq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndnq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndmq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndmq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndmq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndpq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndpq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndpq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndaq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndaq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndaq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndxq_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrndxq_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrndxq_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vandq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vandq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbicq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vbicq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (float16x8_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vbrsrq_x (float32x4_t __a, int32_t __b, mve_pred16_t __p)
+{
+ return __arm_vbrsrq_x_n_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_veorq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_veorq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vornq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vornq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_f16 (__a, __b, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vorrq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
+{
+ return __arm_vorrq_x_f32 (__a, __b, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev32q_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev32q_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (float16x8_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_f16 (__a, __p);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vrev64q_x (float32x4_t __a, mve_pred16_t __p)
+{
+ return __arm_vrev64q_x_f32 (__a, __p);
+}
+
+__extension__ extern __inline float16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (float16_t const * __addr)
+{
+ return __arm_vld4q_f16 (__addr);
+}
+
+__extension__ extern __inline float16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (float16_t const * __addr)
+{
+ return __arm_vld2q_f16 (__addr);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (float16_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_f16 (__base, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (float16_t * __addr, float16x8x2_t __value)
+{
+ __arm_vst2q_f16 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (float16_t * __addr, float16x8_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_f16 (__addr, __value, __p);
+}
+
+__extension__ extern __inline float32x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld4q (float32_t const * __addr)
+{
+ return __arm_vld4q_f32 (__addr);
+}
+
+__extension__ extern __inline float32x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld2q (float32_t const * __addr)
+{
+ return __arm_vld2q_f32 (__addr);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_z (float32_t const *__base, mve_pred16_t __p)
+{
+ return __arm_vld1q_z_f32 (__base, __p);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst2q (float32_t * __addr, float32x4x2_t __value)
+{
+ __arm_vst2q_f32 (__addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vst1q_p (float32_t * __addr, float32x4_t __value, mve_pred16_t __p)
+{
+ __arm_vst1q_p_f32 (__addr, __value, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (float16_t __a, float16x8_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_f16 (__a, __b, __idx);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vsetq_lane (float32_t __a, float32x4_t __b, const int __idx)
+{
+ return __arm_vsetq_lane_f32 (__a, __b, __idx);
+}
+
+__extension__ extern __inline float16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (float16x8_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_f16 (__a, __idx);
+}
+
+__extension__ extern __inline float32_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vgetq_lane (float32x4_t __a, const int __idx)
+{
+ return __arm_vgetq_lane_f32 (__a, __idx);
+}
+#endif /* MVE Floating point. */
+
+#else
+enum {
+ __ARM_mve_type_fp_n = 1,
+ __ARM_mve_type_int_n,
+ __ARM_mve_type_float16_t_ptr,
+ __ARM_mve_type_float16x8_t,
+ __ARM_mve_type_float16x8x2_t,
+ __ARM_mve_type_float16x8x4_t,
+ __ARM_mve_type_float32_t_ptr,
+ __ARM_mve_type_float32x4_t,
+ __ARM_mve_type_float32x4x2_t,
+ __ARM_mve_type_float32x4x4_t,
+ __ARM_mve_type_int16_t_ptr,
+ __ARM_mve_type_int16x8_t,
+ __ARM_mve_type_int16x8x2_t,
+ __ARM_mve_type_int16x8x4_t,
+ __ARM_mve_type_int32_t_ptr,
+ __ARM_mve_type_int32x4_t,
+ __ARM_mve_type_int32x4x2_t,
+ __ARM_mve_type_int32x4x4_t,
+ __ARM_mve_type_int64_t_ptr,
+ __ARM_mve_type_int64x2_t,
+ __ARM_mve_type_int8_t_ptr,
+ __ARM_mve_type_int8x16_t,
+ __ARM_mve_type_int8x16x2_t,
+ __ARM_mve_type_int8x16x4_t,
+ __ARM_mve_type_uint16_t_ptr,
+ __ARM_mve_type_uint16x8_t,
+ __ARM_mve_type_uint16x8x2_t,
+ __ARM_mve_type_uint16x8x4_t,
+ __ARM_mve_type_uint32_t_ptr,
+ __ARM_mve_type_uint32x4_t,
+ __ARM_mve_type_uint32x4x2_t,
+ __ARM_mve_type_uint32x4x4_t,
+ __ARM_mve_type_uint64_t_ptr,
+ __ARM_mve_type_uint64x2_t,
+ __ARM_mve_type_uint8_t_ptr,
+ __ARM_mve_type_uint8x16_t,
+ __ARM_mve_type_uint8x16x2_t,
+ __ARM_mve_type_uint8x16x4_t,
+ __ARM_mve_unsupported_type
+};
+
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+#define __ARM_mve_typeid(x) _Generic(x, \
+ float16_t: __ARM_mve_type_fp_n, \
+ float16_t *: __ARM_mve_type_float16_t_ptr, \
+ float16_t const *: __ARM_mve_type_float16_t_ptr, \
+ float16x8_t: __ARM_mve_type_float16x8_t, \
+ float16x8x2_t: __ARM_mve_type_float16x8x2_t, \
+ float16x8x4_t: __ARM_mve_type_float16x8x4_t, \
+ float32_t: __ARM_mve_type_fp_n, \
+ float32_t *: __ARM_mve_type_float32_t_ptr, \
+ float32_t const *: __ARM_mve_type_float32_t_ptr, \
+ float32x4_t: __ARM_mve_type_float32x4_t, \
+ float32x4x2_t: __ARM_mve_type_float32x4x2_t, \
+ float32x4x4_t: __ARM_mve_type_float32x4x4_t, \
+ int16_t: __ARM_mve_type_int_n, \
+ int16_t *: __ARM_mve_type_int16_t_ptr, \
+ int16_t const *: __ARM_mve_type_int16_t_ptr, \
+ int16x8_t: __ARM_mve_type_int16x8_t, \
+ int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
+ int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
+ int32_t: __ARM_mve_type_int_n, \
+ int32_t *: __ARM_mve_type_int32_t_ptr, \
+ int32_t const *: __ARM_mve_type_int32_t_ptr, \
+ int32x4_t: __ARM_mve_type_int32x4_t, \
+ int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
+ int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
+ int64_t: __ARM_mve_type_int_n, \
+ int64_t *: __ARM_mve_type_int64_t_ptr, \
+ int64_t const *: __ARM_mve_type_int64_t_ptr, \
+ int64x2_t: __ARM_mve_type_int64x2_t, \
+ int8_t: __ARM_mve_type_int_n, \
+ int8_t *: __ARM_mve_type_int8_t_ptr, \
+ int8_t const *: __ARM_mve_type_int8_t_ptr, \
+ int8x16_t: __ARM_mve_type_int8x16_t, \
+ int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
+ int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
+ uint16_t: __ARM_mve_type_int_n, \
+ uint16_t *: __ARM_mve_type_uint16_t_ptr, \
+ uint16_t const *: __ARM_mve_type_uint16_t_ptr, \
+ uint16x8_t: __ARM_mve_type_uint16x8_t, \
+ uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
+ uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
+ uint32_t: __ARM_mve_type_int_n, \
+ uint32_t *: __ARM_mve_type_uint32_t_ptr, \
+ uint32_t const *: __ARM_mve_type_uint32_t_ptr, \
+ uint32x4_t: __ARM_mve_type_uint32x4_t, \
+ uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
+ uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
+ uint64_t: __ARM_mve_type_int_n, \
+ uint64_t *: __ARM_mve_type_uint64_t_ptr, \
+ uint64_t const *: __ARM_mve_type_uint64_t_ptr, \
+ uint64x2_t: __ARM_mve_type_uint64x2_t, \
+ uint8_t: __ARM_mve_type_int_n, \
+ uint8_t *: __ARM_mve_type_uint8_t_ptr, \
+ uint8_t const *: __ARM_mve_type_uint8_t_ptr, \
+ uint8x16_t: __ARM_mve_type_uint8x16_t, \
+ uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
+ uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
+ default: _Generic(x, \
+ signed char: __ARM_mve_type_int_n, \
+ short: __ARM_mve_type_int_n, \
+ int: __ARM_mve_type_int_n, \
+ long: __ARM_mve_type_int_n, \
+ long long: __ARM_mve_type_int_n, \
+ unsigned char: __ARM_mve_type_int_n, \
+ unsigned short: __ARM_mve_type_int_n, \
+ unsigned int: __ARM_mve_type_int_n, \
+ unsigned long: __ARM_mve_type_int_n, \
+ unsigned long long: __ARM_mve_type_int_n, \
+ default: __ARM_mve_unsupported_type))
+#else
+#define __ARM_mve_typeid(x) _Generic(x, \
+ int16_t: __ARM_mve_type_int_n, \
+ int16_t *: __ARM_mve_type_int16_t_ptr, \
+ int16_t const *: __ARM_mve_type_int16_t_ptr, \
+ int16x8_t: __ARM_mve_type_int16x8_t, \
+ int16x8x2_t: __ARM_mve_type_int16x8x2_t, \
+ int16x8x4_t: __ARM_mve_type_int16x8x4_t, \
+ int32_t: __ARM_mve_type_int_n, \
+ int32_t *: __ARM_mve_type_int32_t_ptr, \
+ int32_t const *: __ARM_mve_type_int32_t_ptr, \
+ int32x4_t: __ARM_mve_type_int32x4_t, \
+ int32x4x2_t: __ARM_mve_type_int32x4x2_t, \
+ int32x4x4_t: __ARM_mve_type_int32x4x4_t, \
+ int64_t: __ARM_mve_type_int_n, \
+ int64_t *: __ARM_mve_type_int64_t_ptr, \
+ int64_t const *: __ARM_mve_type_int64_t_ptr, \
+ int64x2_t: __ARM_mve_type_int64x2_t, \
+ int8_t: __ARM_mve_type_int_n, \
+ int8_t *: __ARM_mve_type_int8_t_ptr, \
+ int8_t const *: __ARM_mve_type_int8_t_ptr, \
+ int8x16_t: __ARM_mve_type_int8x16_t, \
+ int8x16x2_t: __ARM_mve_type_int8x16x2_t, \
+ int8x16x4_t: __ARM_mve_type_int8x16x4_t, \
+ uint16_t: __ARM_mve_type_int_n, \
+ uint16_t *: __ARM_mve_type_uint16_t_ptr, \
+ uint16_t const *: __ARM_mve_type_uint16_t_ptr, \
+ uint16x8_t: __ARM_mve_type_uint16x8_t, \
+ uint16x8x2_t: __ARM_mve_type_uint16x8x2_t, \
+ uint16x8x4_t: __ARM_mve_type_uint16x8x4_t, \
+ uint32_t: __ARM_mve_type_int_n, \
+ uint32_t *: __ARM_mve_type_uint32_t_ptr, \
+ uint32_t const *: __ARM_mve_type_uint32_t_ptr, \
+ uint32x4_t: __ARM_mve_type_uint32x4_t, \
+ uint32x4x2_t: __ARM_mve_type_uint32x4x2_t, \
+ uint32x4x4_t: __ARM_mve_type_uint32x4x4_t, \
+ uint64_t: __ARM_mve_type_int_n, \
+ uint64_t *: __ARM_mve_type_uint64_t_ptr, \
+ uint64_t const *: __ARM_mve_type_uint64_t_ptr, \
+ uint64x2_t: __ARM_mve_type_uint64x2_t, \
+ uint8_t: __ARM_mve_type_int_n, \
+ uint8_t *: __ARM_mve_type_uint8_t_ptr, \
+ uint8_t const *: __ARM_mve_type_uint8_t_ptr, \
+ uint8x16_t: __ARM_mve_type_uint8x16_t, \
+ uint8x16x2_t: __ARM_mve_type_uint8x16x2_t, \
+ uint8x16x4_t: __ARM_mve_type_uint8x16x4_t, \
+ default: _Generic(x, \
+ signed char: __ARM_mve_type_int_n, \
+ short: __ARM_mve_type_int_n, \
+ int: __ARM_mve_type_int_n, \
+ long: __ARM_mve_type_int_n, \
+ long long: __ARM_mve_type_int_n, \
+ unsigned char: __ARM_mve_type_int_n, \
+ unsigned short: __ARM_mve_type_int_n, \
+ unsigned int: __ARM_mve_type_int_n, \
+ unsigned long: __ARM_mve_type_int_n, \
+ unsigned long long: __ARM_mve_type_int_n, \
+ default: __ARM_mve_unsupported_type))
+#endif /* MVE Floating point. */
+
+extern void *__ARM_undef;
+#define __ARM_mve_coerce(param, type) \
+ _Generic(param, type: param, default: *(type *)__ARM_undef)
+#define __ARM_mve_coerce1(param, type) \
+ _Generic(param, type: param, const type: param, default: *(type *)__ARM_undef)
+
+#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
+
+#define __arm_vst4q(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
+ int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \
+ int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
+ int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \
+ int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \
+ int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
+
+#define __arm_vrndxq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndxq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndxq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define __arm_vrndq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define __arm_vrndpq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndpq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndpq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define __arm_vrndnq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndnq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndnq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define __arm_vrndmq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndmq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
+ int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndmq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
+
+#define __arm_vrndaq(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndaq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndaq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vrev64q(p0) __arm_vrev64q(p0)
#define __arm_vrev64q(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev64q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev64q_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrev64q_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vnegq(p0) __arm_vnegq(p0)
#define __arm_vnegq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
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, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vabsq_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vabsq_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vrev32q(p0) __arm_vrev32q(p0)
#define __arm_vrev32q(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev32q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev32q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev32q_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
-#define vcvtbq_f32(p0) __arm_vcvtbq_f32(p0)
#define __arm_vcvtbq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvtbq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
-#define vcvttq_f32(p0) __arm_vcvttq_f32(p0)
#define __arm_vcvttq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvttq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
-#define vrev16q(p0) __arm_vrev16q(p0)
#define __arm_vrev16q(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev16q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev16q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)));})
-#define vqabsq(p0) __arm_vqabsq(p0)
#define __arm_vqabsq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vqabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vqabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vqnegq(p0) __arm_vqnegq(p0)
#define __arm_vqnegq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vqnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vqnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vmvnq(p0) __arm_vmvnq(p0)
#define __arm_vmvnq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmvnq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmvnq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vmvnq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vmovlbq(p0) __arm_vmovlbq(p0)
#define __arm_vmovlbq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
-#define vmovltq(p0) __arm_vmovltq(p0)
#define __arm_vmovltq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
-#define vclzq(p0) __arm_vclzq(p0)
#define __arm_vclzq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vclzq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vclzq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vclzq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vclsq(p0) __arm_vclsq(p0)
#define __arm_vclsq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vclsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vclsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vclsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vcvtq(p0) __arm_vcvtq(p0)
#define __arm_vcvtq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_f16_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vshlq(p0,p1) __arm_vshlq(p0,p1)
#define __arm_vshlq(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_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vshlq_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_vshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vshrq(p0,p1) __arm_vshrq(p0,p1)
#define __arm_vshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vcvtq_n(p0,p1) __arm_vcvtq_n(p0,p1)
#define __arm_vcvtq_n(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_n_f16_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
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_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_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_float16x8_t][__ARM_mve_type_fp_n]: __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_fp_n]: __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_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_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_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(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_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_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_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_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_int_n]: __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_int_n]: __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_int_n]: __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_fp_n]: __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_fp_n]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
-
-#define vcmpeqq_m(p0,p1,p2) __arm_vcmpeqq_m(p0,p1,p2)
#define __arm_vcmpeqq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpeqq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
-#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_float16x8_t][__ARM_mve_type_fp_n]: __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_fp_n]: __arm_vcmpgtq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_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_float16x8_t][__ARM_mve_type_fp_n]: __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_fp_n]: __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_float16x8_t][__ARM_mve_type_fp_n]: __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_fp_n]: __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_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_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_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
int (*)[__ARM_mve_type_fp_n][__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_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
int (*)[__ARM_mve_type_fp_n][__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_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
int (*)[__ARM_mve_type_fp_n][__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_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
int (*)[__ARM_mve_type_fp_n][__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_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 vsubq(p0,p1) __arm_vsubq(p0,p1)
#define __arm_vsubq(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_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 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_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t)), \
int (*)[__ARM_mve_type_fp_n][__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); \
- _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_int8x16_t][__ARM_mve_type_int_n]: __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_int_n]: __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_int_n]: __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_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)), \
- int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __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_fp_n]: __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_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_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_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_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_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_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_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_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_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_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_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_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_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_uint16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __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_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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 vbicq_m_n(p0,p1,p2) __arm_vbicq_m_n(p0,p1,p2)
#define __arm_vbicq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vbicq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vqrshrnbq(p0,p1,p2) __arm_vqrshrnbq(p0,p1,p2)
#define __arm_vqrshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqrshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqrshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrshrunbq(p0,p1,p2) __arm_vqrshrunbq(p0,p1,p2)
#define __arm_vqrshrunbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshrunbq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshrunbq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vshlcq(p0,p1,p2) __arm_vshlcq(p0,p1,p2)
#define __arm_vshlcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlcq_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vclsq_m(p0,p1,p2) __arm_vclsq_m(p0,p1,p2)
#define __arm_vclsq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vclsq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vclsq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vclzq_m(p0,p1,p2) __arm_vclzq_m(p0,p1,p2)
#define __arm_vclzq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vclzq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vclzq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmaxaq_m(p0,p1,p2) __arm_vmaxaq_m(p0,p1,p2)
#define __arm_vmaxaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxaq_m_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxaq_m_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vminaq_m(p0,p1,p2) __arm_vminaq_m(p0,p1,p2)
#define __arm_vminaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminaq_m_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminaq_m_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlaq(p0,p1,p2) __arm_vmlaq(p0,p1,p2)
#define __arm_vmlaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmlaq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmlaq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vsriq(p0,p1,p2) __arm_vsriq(p0,p1,p2)
#define __arm_vsriq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsriq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsriq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vsliq(p0,p1,p2) __arm_vsliq(p0,p1,p2)
#define __arm_vsliq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsliq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsliq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vshlq_m_r(p0,p1,p2) __arm_vshlq_m_r(p0,p1,p2)
#define __arm_vshlq_m_r(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_m_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_m_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_m_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vrshlq_m_n(p0,p1,p2) __arm_vrshlq_m_n(p0,p1,p2)
#define __arm_vrshlq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshlq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshlq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __p1, p2));})
-#define vqshlq_m_r(p0,p1,p2) __arm_vqshlq_m_r(p0,p1,p2)
#define __arm_vqshlq_m_r(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshlq_m_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_m_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_m_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vqrshlq_m_n(p0,p1,p2) __arm_vqrshlq_m_n(p0,p1,p2)
#define __arm_vqrshlq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqrshlq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqrshlq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqrshlq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vqrdmlsdhxq(p0,p1,p2) __arm_vqrdmlsdhxq(p0,p1,p2)
#define __arm_vqrdmlsdhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmlsdhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmlsdhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqrdmlsdhq(p0,p1,p2) __arm_vqrdmlsdhq(p0,p1,p2)
#define __arm_vqrdmlsdhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmlsdhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmlsdhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqrdmlashq(p0,p1,p2) __arm_vqrdmlashq(p0,p1,p2)
#define __arm_vqrdmlashq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vqrdmlahq(p0,p1,p2) __arm_vqrdmlahq(p0,p1,p2)
#define __arm_vqrdmlahq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vmlasq(p0,p1,p2) __arm_vmlasq(p0,p1,p2)
#define __arm_vmlasq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmlasq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmlasq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vqdmlahq(p0,p1,p2) __arm_vqdmlahq(p0,p1,p2)
#define __arm_vqdmlahq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vqrdmladhxq(p0,p1,p2) __arm_vqrdmladhxq(p0,p1,p2)
#define __arm_vqrdmladhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmladhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmladhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqrdmladhq(p0,p1,p2) __arm_vqrdmladhq(p0,p1,p2)
#define __arm_vqrdmladhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmladhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmladhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqnegq_m(p0,p1,p2) __arm_vqnegq_m(p0,p1,p2)
#define __arm_vqnegq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqnegq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqnegq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqdmlsdhxq(p0,p1,p2) __arm_vqdmlsdhxq(p0,p1,p2)
#define __arm_vqdmlsdhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqdmlsdhq(p0,p1,p2) __arm_vqdmlsdhq(p0,p1,p2)
#define __arm_vqdmlsdhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqdmladhxq(p0,p1,p2) __arm_vqdmladhxq(p0,p1,p2)
#define __arm_vqdmladhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqdmladhq(p0,p1,p2) __arm_vqdmladhq(p0,p1,p2)
#define __arm_vqdmladhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vmovlbq_m(p0,p1,p2) __arm_vmovlbq_m(p0,p1,p2)
#define __arm_vmovlbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_m_u8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_m_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vmovnbq_m(p0,p1,p2) __arm_vmovnbq_m(p0,p1,p2)
#define __arm_vmovnbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovnbq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovnbq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmovntq_m(p0,p1,p2) __arm_vmovntq_m(p0,p1,p2)
#define __arm_vmovntq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovntq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovntq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmovltq_m(p0,p1,p2) __arm_vmovltq_m(p0,p1,p2)
#define __arm_vmovltq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t]: __arm_vmovltq_m_u8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t]: __arm_vmovltq_m_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vshrntq(p0,p1,p2) __arm_vshrntq(p0,p1,p2)
-#define __arm_vshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
- __typeof(p1) __p1 = (p1); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vshrntq_n_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vshrntq_n_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vshrnbq(p0,p1,p2) __arm_vshrnbq(p0,p1,p2)
#define __arm_vshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrshrntq(p0,p1,p2) __arm_vrshrntq(p0,p1,p2)
-#define __arm_vrshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
- __typeof(p1) __p1 = (p1); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vrshrntq_n_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vrshrntq_n_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-
-#define vcvtaq_m(p0,p1,p2) __arm_vcvtaq_m(p0,p1,p2)
#define __arm_vcvtaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtaq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtaq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcvtq_m(p0,p1,p2) __arm_vcvtq_m(p0,p1,p2)
#define __arm_vcvtq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcvtq_m_n(p0,p1,p2,p3) __arm_vcvtq_m_n(p0,p1,p2,p3)
#define __arm_vcvtq_m_n(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcvtq_m_n_f16_u16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcvtq_m_n_f32_u32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vabsq_m(p0,p1,p2) __arm_vabsq_m(p0,p1,p2)
#define __arm_vabsq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabsq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabsq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcmlaq(p0,p1,p2) __arm_vcmlaq(p0,p1,p2)
#define __arm_vcmlaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vcmlaq_rot180(p0,p1,p2) __arm_vcmlaq_rot180(p0,p1,p2)
#define __arm_vcmlaq_rot180(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_rot180_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_rot180_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vcmlaq_rot270(p0,p1,p2) __arm_vcmlaq_rot270(p0,p1,p2)
#define __arm_vcmlaq_rot270(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_rot270_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_rot270_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vcmlaq_rot90(p0,p1,p2) __arm_vcmlaq_rot90(p0,p1,p2)
#define __arm_vcmlaq_rot90(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_rot90_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_rot90_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vrndxq_m(p0,p1,p2) __arm_vrndxq_m(p0,p1,p2)
#define __arm_vrndxq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrndxq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrndxq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndq_m(p0,p1,p2) __arm_vrndq_m(p0,p1,p2)
#define __arm_vrndq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrndq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrndq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndpq_m(p0,p1,p2) __arm_vrndpq_m(p0,p1,p2)
#define __arm_vrndpq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrndpq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrndpq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcmpgtq_m(p0,p1,p2) __arm_vcmpgtq_m(p0,p1,p2)
#define __arm_vcmpgtq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgtq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgtq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcmpleq_m(p0,p1,p2) __arm_vcmpleq_m(p0,p1,p2)
#define __arm_vcmpleq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpleq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
-#define vcmpltq_m(p0,p1,p2) __arm_vcmpltq_m(p0,p1,p2)
#define __arm_vcmpltq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpltq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
-#define vcmpneq_m(p0,p1,p2) __arm_vcmpneq_m(p0,p1,p2)
#define __arm_vcmpneq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vcmpneq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
-#define vcvtbq_m(p0,p1,p2) __arm_vcvtbq_m(p0,p1,p2)
#define __arm_vcvtbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float16x8_t]: __arm_vcvtbq_m_f32_f16 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float32x4_t]: __arm_vcvtbq_m_f16_f32 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcvttq_m(p0,p1,p2) __arm_vcvttq_m(p0,p1,p2)
#define __arm_vcvttq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float16x8_t]: __arm_vcvttq_m_f32_f16 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float32x4_t]: __arm_vcvttq_m_f16_f32 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcvtmq_m(p0,p1,p2) __arm_vcvtmq_m(p0,p1,p2)
#define __arm_vcvtmq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtmq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtmq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcvtnq_m(p0,p1,p2) __arm_vcvtnq_m(p0,p1,p2)
#define __arm_vcvtnq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtnq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtnq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcvtpq_m(p0,p1,p2) __arm_vcvtpq_m(p0,p1,p2)
#define __arm_vcvtpq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtpq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtpq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vdupq_m(p0,p1,p2) __arm_vdupq_m(p0,p1,p2)
#define __arm_vdupq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t), p2));})
-#define vfmaq(p0,p1,p2) __arm_vfmaq(p0,p1,p2)
#define __arm_vfmaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmaq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmaq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vfmsq(p0,p1,p2) __arm_vfmsq(p0,p1,p2)
#define __arm_vfmsq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmsq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmsq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vfmasq(p0,p1,p2) __arm_vfmasq(p0,p1,p2)
#define __arm_vfmasq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t)), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t)));})
-#define vmaxnmaq_m(p0,p1,p2) __arm_vmaxnmaq_m(p0,p1,p2)
#define __arm_vmaxnmaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmaq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmaq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vmaxnmavq_m(p0,p1,p2) __arm_vmaxnmavq_m(p0,p1,p2)
#define __arm_vmaxnmavq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vmaxnmvq_m(p0,p1,p2) __arm_vmaxnmvq_m(p0,p1,p2)
#define __arm_vmaxnmvq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vmaxnmavq_p(p0,p1,p2) __arm_vmaxnmavq_p(p0,p1,p2)
#define __arm_vmaxnmavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmavq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmavq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vmaxnmvq_p(p0,p1,p2) __arm_vmaxnmvq_p(p0,p1,p2)
#define __arm_vmaxnmvq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vmaxnmvq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vmaxnmvq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vminnmaq_m(p0,p1,p2) __arm_vminnmaq_m(p0,p1,p2)
#define __arm_vminnmaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmaq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmaq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vminnmavq_p(p0,p1,p2) __arm_vminnmavq_p(p0,p1,p2)
#define __arm_vminnmavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmavq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmavq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vminnmvq_p(p0,p1,p2) __arm_vminnmvq_p(p0,p1,p2)
#define __arm_vminnmvq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vminnmvq_p_f16 (__ARM_mve_coerce(__p0, float16_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vminnmvq_p_f32 (__ARM_mve_coerce(__p0, float32_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndnq_m(p0,p1,p2) __arm_vrndnq_m(p0,p1,p2)
#define __arm_vrndnq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrndnq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrndnq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __p2));})
-#define vrndaq_m(p0,p1,p2) __arm_vrndaq_m(p0,p1,p2)
#define __arm_vrndaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrndaq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrndaq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndmq_m(p0,p1,p2) __arm_vrndmq_m(p0,p1,p2)
#define __arm_vrndmq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrndmq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrndmq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrev64q_m(p0,p1,p2) __arm_vrev64q_m(p0,p1,p2)
#define __arm_vrev64q_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrev64q_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vrev64q_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrev32q_m(p0,p1,p2) __arm_vrev32q_m(p0,p1,p2)
#define __arm_vrev32q_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrev32q_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vrev32q_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2));})
-#define vpselq(p0,p1,p2) __arm_vpselq(p0,p1,p2)
#define __arm_vpselq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vpselq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vpselq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#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_float16x8_t][__ARM_mve_type_fp_n]: __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_fp_n]: __arm_vcmpgeq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32_t)));})
-#define vrshrnbq(p0,p1,p2) __arm_vrshrnbq(p0,p1,p2)
#define __arm_vrshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrev16q_m(p0,p1,p2) __arm_vrev16q_m(p0,p1,p2)
#define __arm_vrev16q_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrev16q_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vrev16q_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2));})
-#define vqshruntq(p0,p1,p2) __arm_vqshruntq(p0,p1,p2)
#define __arm_vqshruntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqshruntq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqshruntq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqshrunbq_n(p0,p1,p2) __arm_vqshrunbq_n(p0,p1,p2)
-#define __arm_vqshrunbq_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
- __typeof(p1) __p1 = (p1); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqshrunbq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqshrunbq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-
-#define vqshrnbq(p0,p1,p2) __arm_vqshrnbq(p0,p1,p2)
#define __arm_vqshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqshrntq(p0,p1,p2) __arm_vqshrntq(p0,p1,p2)
#define __arm_vqshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrshruntq(p0,p1,p2) __arm_vqrshruntq(p0,p1,p2)
#define __arm_vqrshruntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshruntq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshruntq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqmovnbq_m(p0,p1,p2) __arm_vqmovnbq_m(p0,p1,p2)
#define __arm_vqmovnbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovnbq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovnbq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqmovntq_m(p0,p1,p2) __arm_vqmovntq_m(p0,p1,p2)
#define __arm_vqmovntq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovntq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovntq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqmovunbq_m(p0,p1,p2) __arm_vqmovunbq_m(p0,p1,p2)
#define __arm_vqmovunbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovunbq_m_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_m_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqmovuntq_m(p0,p1,p2) __arm_vqmovuntq_m(p0,p1,p2)
#define __arm_vqmovuntq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovuntq_m_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovuntq_m_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqrshrntq(p0,p1,p2) __arm_vqrshrntq(p0,p1,p2)
#define __arm_vqrshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqrshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqrshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrshruntq(p0,p1,p2) __arm_vqrshruntq(p0,p1,p2)
#define __arm_vqrshruntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshruntq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshruntq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vnegq_m(p0,p1,p2) __arm_vnegq_m(p0,p1,p2)
#define __arm_vnegq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vnegq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vnegq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vcmpgeq_m(p0,p1,p2) __arm_vcmpgeq_m(p0,p1,p2)
#define __arm_vcmpgeq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vabdq_m(p0,p1,p2,p3) __arm_vabdq_m(p0,p1,p2,p3)
#define __arm_vabdq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vaddq_m(p0,p1,p2,p3) __arm_vaddq_m(p0,p1,p2,p3)
#define __arm_vaddq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vandq_m(p0,p1,p2,p3) __arm_vandq_m(p0,p1,p2,p3)
#define __arm_vandq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vandq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vandq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vbicq_m(p0,p1,p2,p3) __arm_vbicq_m(p0,p1,p2,p3)
#define __arm_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbicq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbicq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vbrsrq_m(p0,p1,p2,p3) __arm_vbrsrq_m(p0,p1,p2,p3)
#define __arm_vbrsrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbrsrq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2, p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbrsrq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2, p3));})
-#define vcaddq_rot270_m(p0,p1,p2,p3) __arm_vcaddq_rot270_m(p0,p1,p2,p3)
#define __arm_vcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot270_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot270_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcaddq_rot90_m(p0,p1,p2,p3) __arm_vcaddq_rot90_m(p0,p1,p2,p3)
#define __arm_vcaddq_rot90_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot90_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot90_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmlaq_m(p0,p1,p2,p3) __arm_vcmlaq_m(p0,p1,p2,p3)
#define __arm_vcmlaq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmlaq_rot180_m(p0,p1,p2,p3) __arm_vcmlaq_rot180_m(p0,p1,p2,p3)
#define __arm_vcmlaq_rot180_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_rot180_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_rot180_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmlaq_rot270_m(p0,p1,p2,p3) __arm_vcmlaq_rot270_m(p0,p1,p2,p3)
#define __arm_vcmlaq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_rot270_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_rot270_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmlaq_rot90_m(p0,p1,p2,p3) __arm_vcmlaq_rot90_m(p0,p1,p2,p3)
#define __arm_vcmlaq_rot90_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmlaq_rot90_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmlaq_rot90_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_m(p0,p1,p2,p3) __arm_vcmulq_m(p0,p1,p2,p3)
#define __arm_vcmulq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_rot180_m(p0,p1,p2,p3) __arm_vcmulq_rot180_m(p0,p1,p2,p3)
#define __arm_vcmulq_rot180_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot180_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot180_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_rot270_m(p0,p1,p2,p3) __arm_vcmulq_rot270_m(p0,p1,p2,p3)
#define __arm_vcmulq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot270_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot270_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_rot90_m(p0,p1,p2,p3) __arm_vcmulq_rot90_m(p0,p1,p2,p3)
#define __arm_vcmulq_rot90_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_m_f16(__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot90_m_f32(__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define veorq_m(p0,p1,p2,p3) __arm_veorq_m(p0,p1,p2,p3)
#define __arm_veorq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_veorq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_veorq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vfmaq_m(p0,p1,p2,p3) __arm_vfmaq_m(p0,p1,p2,p3)
#define __arm_vfmaq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmaq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vfmasq_m(p0,p1,p2,p3) __arm_vfmasq_m(p0,p1,p2,p3)
#define __arm_vfmasq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vfmasq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vfmsq_m(p0,p1,p2,p3) __arm_vfmsq_m(p0,p1,p2,p3)
#define __arm_vfmsq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vfmsq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vfmsq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vmaxnmq_m(p0,p1,p2,p3) __arm_vmaxnmq_m(p0,p1,p2,p3)
#define __arm_vmaxnmq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vminnmq_m(p0,p1,p2,p3) __arm_vminnmq_m(p0,p1,p2,p3)
#define __arm_vminnmq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vmulq_m(p0,p1,p2,p3) __arm_vmulq_m(p0,p1,p2,p3)
#define __arm_vmulq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vornq_m(p0,p1,p2,p3) __arm_vornq_m(p0,p1,p2,p3)
#define __arm_vornq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vornq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vornq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vsubq_m(p0,p1,p2,p3) __arm_vsubq_m(p0,p1,p2,p3)
#define __arm_vsubq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vorrq_m(p0,p1,p2,p3) __arm_vorrq_m(p0,p1,p2,p3)
#define __arm_vorrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vorrq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vorrq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vld1q(p0) __arm_vld1q(p0)
#define __arm_vld1q(p0) (\
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce(p0, int8_t const *)), \
int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_f16 (__ARM_mve_coerce(p0, float16_t const *)), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_f32 (__ARM_mve_coerce(p0, float32_t const *))))
-#define vld1q_z(p0,p1) __arm_vld1q_z(p0, p1)
#define __arm_vld1q_z(p0,p1) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce(p0, int8_t const *), p1), \
int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_z_f16 (__ARM_mve_coerce(p0, float16_t const *), p1), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_z_f32 (__ARM_mve_coerce(p0, float32_t const *), p1)))
-#define vld2q(p0) __arm_vld2q(p0)
#define __arm_vld2q(p0) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce(p0, int8_t const *)), \
int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld2q_f16 (__ARM_mve_coerce(p0, float16_t const *)), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld2q_f32 (__ARM_mve_coerce(p0, float32_t const *))))
-#define vld4q(p0) __arm_vld4q(p0)
#define __arm_vld4q(p0) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce(p0, int8_t const *)), \
int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld4q_f16 (__ARM_mve_coerce(p0, float16_t const *)), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld4q_f32 (__ARM_mve_coerce(p0, float32_t const *))))
-#define vldrhq_gather_offset(p0,p1) __arm_vldrhq_gather_offset(p0,p1)
#define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)));})
-#define vldrhq_gather_offset_z(p0,p1,p2) __arm_vldrhq_gather_offset_z(p0,p1,p2)
#define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vldrhq_gather_shifted_offset(p0,p1) __arm_vldrhq_gather_shifted_offset(p0,p1)
#define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)));})
-#define vldrhq_gather_shifted_offset_z(p0,p1,p2) __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2)
#define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce(p0, float16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vldrwq_gather_offset(p0,p1) __arm_vldrwq_gather_offset(p0,p1)
#define __arm_vldrwq_gather_offset(p0,p1) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce(p0, int32_t const *), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce(p0, float32_t const *), p1)))
-#define vldrwq_gather_offset_z(p0,p1,p2) __arm_vldrwq_gather_offset_z(p0,p1,p2)
#define __arm_vldrwq_gather_offset_z(p0,p1,p2) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce(p0, int32_t const *), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1, p2), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce(p0, float32_t const *), p1, p2)))
-#define vldrwq_gather_shifted_offset(p0,p1) __arm_vldrwq_gather_shifted_offset(p0,p1)
#define __arm_vldrwq_gather_shifted_offset(p0,p1) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t const *), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t const *), p1)))
-#define vldrwq_gather_shifted_offset_z(p0,p1,p2) __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2)
#define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ( \
_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(p0, int32_t const *), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1, p2), \
int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce(p0, float32_t const *), p1, p2)))
-#define vst1q_p(p0,p1,p2) __arm_vst1q_p(p0,p1,p2)
#define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_p_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vst2q(p0,p1) __arm_vst2q(p0,p1)
#define __arm_vst2q(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x2_t]: __arm_vst2q_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x2_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x2_t]: __arm_vst2q_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x2_t)));})
-#define vst1q(p0,p1) __arm_vst1q(p0,p1)
#define __arm_vst1q(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));})
-#define vstrhq(p0,p1) __arm_vstrhq(p0,p1)
#define __arm_vstrhq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)));})
-#define vstrhq_p(p0,p1,p2) __arm_vstrhq_p(p0,p1,p2)
#define __arm_vstrhq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2));})
-#define vstrhq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
-#define vstrhq_scatter_offset(p0,p1,p2) __arm_vstrhq_scatter_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
-#define vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
-#define vstrhq_scatter_shifted_offset(p0,p1,p2) __arm_vstrhq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
-#define vstrwq_p(p0,p1,p2) __arm_vstrwq_p(p0,p1,p2)
#define __arm_vstrwq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_p_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vstrwq(p0,p1) __arm_vstrwq(p0,p1)
#define __arm_vstrwq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));})
-#define vstrhq_scatter_offset(p0,p1,p2) __arm_vstrhq_scatter_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
-#define vstrhq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
-#define vstrhq_scatter_shifted_offset(p0,p1,p2) __arm_vstrhq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));})
-#define vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));})
-#define vstrwq_scatter_base(p0,p1,p2) __arm_vstrwq_scatter_base(p0,p1,p2)
#define __arm_vstrwq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_base_f32 (p0, p1, __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vstrwq_scatter_base_p(p0,p1,p2,p3) __arm_vstrwq_scatter_base_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_p_s32(p0, p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_p_u32(p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_base_p_f32(p0, p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vstrwq_scatter_offset(p0,p1,p2) __arm_vstrwq_scatter_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vstrwq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vstrwq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vstrwq_scatter_offset(p0,p1,p2) __arm_vstrwq_scatter_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vstrwq_scatter_shifted_offset(p0,p1,p2) __arm_vstrwq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vstrwq_scatter_shifted_offset(p0,p1,p2) __arm_vstrwq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vuninitializedq(p0) __arm_vuninitializedq(p0)
#define __arm_vuninitializedq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vuninitializedq_s8 (), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vuninitializedq_f16 (), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vuninitializedq_f32 ());})
-#define vreinterpretq_f16(p0) __arm_vreinterpretq_f16(p0)
#define __arm_vreinterpretq_f16(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vreinterpretq_f16_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_f16_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_f16_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_f32(p0) __arm_vreinterpretq_f32(p0)
#define __arm_vreinterpretq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vreinterpretq_f32_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_f32_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
-#define vreinterpretq_s16(p0) __arm_vreinterpretq_s16(p0)
#define __arm_vreinterpretq_s16(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_s16_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s16_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_s16_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_s32(p0) __arm_vreinterpretq_s32(p0)
#define __arm_vreinterpretq_s32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_s32_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s32_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_s32_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_s64(p0) __arm_vreinterpretq_s64(p0)
#define __arm_vreinterpretq_s64(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_s64_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s64_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_s64_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_s8(p0) __arm_vreinterpretq_s8(p0)
#define __arm_vreinterpretq_s8(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_s8_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s8_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_s8_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_u16(p0) __arm_vreinterpretq_u16(p0)
#define __arm_vreinterpretq_u16(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_u16_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_u16_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_u16_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_u32(p0) __arm_vreinterpretq_u32(p0)
#define __arm_vreinterpretq_u32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_u32_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_u32_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_u32_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_u64(p0) __arm_vreinterpretq_u64(p0)
#define __arm_vreinterpretq_u64(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_u64_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_int64x2_t]: __arm_vreinterpretq_u64_s64 (__ARM_mve_coerce(__p0, int64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_u64_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vreinterpretq_u8(p0) __arm_vreinterpretq_u8(p0)
#define __arm_vreinterpretq_u8(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vreinterpretq_u8_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_u8_u64 (__ARM_mve_coerce(__p0, uint64x2_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vreinterpretq_u8_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-#define vstrwq_scatter_base_wb(p0,p1,p2) __arm_vstrwq_scatter_base_wb(p0,p1,p2)
#define __arm_vstrwq_scatter_base_wb(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_wb_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_wb_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_base_wb_f32 (p0, p1, __ARM_mve_coerce(__p2, float32x4_t)));})
-#define vstrwq_scatter_base_wb_p(p0,p1,p2,p3) __arm_vstrwq_scatter_base_wb_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_base_wb_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_wb_p_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_wb_p_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_base_wb_p_f32 (p0, p1, __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vabdq_x(p1,p2,p3) __arm_vabdq_x(p1,p2,p3)
#define __arm_vabdq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vabsq_x(p1,p2) __arm_vabsq_x(p1,p2)
#define __arm_vabsq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vabsq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vabsq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vaddq_x(p1,p2,p3) __arm_vaddq_x(p1,p2,p3)
#define __arm_vaddq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vaddq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vaddq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vandq_x(p1,p2,p3) __arm_vandq_x(p1,p2,p3)
#define __arm_vandq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vandq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vandq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vbicq_x(p1,p2,p3) __arm_vbicq_x(p1,p2,p3)
#define __arm_vbicq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vbicq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vbicq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vbrsrq_x(p1,p2,p3) __arm_vbrsrq_x(p1,p2,p3)
#define __arm_vbrsrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vbrsrq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vbrsrq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2, p3), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vbrsrq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2, p3));})
-#define vcaddq_rot270_x(p1,p2,p3) __arm_vcaddq_rot270_x(p1,p2,p3)
#define __arm_vcaddq_rot270_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot270_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot270_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcaddq_rot90_x(p1,p2,p3) __arm_vcaddq_rot90_x(p1,p2,p3)
#define __arm_vcaddq_rot90_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcaddq_rot90_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcaddq_rot90_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_rot180_x(p1,p2,p3) __arm_vcmulq_rot180_x(p1,p2,p3)
#define __arm_vcmulq_rot180_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot180_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot180_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_rot270_x(p1,p2,p3) __arm_vcmulq_rot270_x(p1,p2,p3)
#define __arm_vcmulq_rot270_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot270_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot270_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcmulq_x(p1,p2,p3) __arm_vcmulq_x(p1,p2,p3)
#define __arm_vcmulq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vcvtq_x(p1,p2) __arm_vcvtq_x(p1,p2)
#define __arm_vcvtq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_x_f16_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_x_f16_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_x_f32_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vcvtq_x_n(p1,p2,p3) __arm_vcvtq_x_n(p1,p2,p3)
#define __arm_vcvtq_x_n(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vcvtq_x_n_f16_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_x_n_f16_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_x_n_f32_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define veorq_x(p1,p2,p3) __arm_veorq_x(p1,p2,p3)
#define __arm_veorq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_veorq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_veorq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vmaxnmq_x(p1,p2,p3) __arm_vmaxnmq_x(p1,p2,p3)
#define __arm_vmaxnmq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vmaxnmq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vmaxnmq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vminnmq_x(p1,p2,p3) __arm_vminnmq_x(p1,p2,p3)
#define __arm_vminnmq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vminnmq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vminnmq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vmulq_x(p1,p2,p3) __arm_vmulq_x(p1,p2,p3)
#define __arm_vmulq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vmulq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vmulq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vnegq_x(p1,p2) __arm_vnegq_x(p1,p2)
#define __arm_vnegq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vnegq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vnegq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vornq_x(p1,p2,p3) __arm_vornq_x(p1,p2,p3)
#define __arm_vornq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vornq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vornq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vorrq_x(p1,p2,p3) __arm_vorrq_x(p1,p2,p3)
#define __arm_vorrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vorrq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vorrq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vrev32q_x(p1,p2) __arm_vrev32q_x(p1,p2)
#define __arm_vrev32q_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev32q_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev32q_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev32q_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2));})
-#define vrev64q_x(p1,p2) __arm_vrev64q_x(p1,p2)
#define __arm_vrev64q_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev64q_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrev64q_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrev64q_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndaq_x(p1,p2) __arm_vrndaq_x(p1,p2)
#define __arm_vrndaq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndaq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndaq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndmq_x(p1,p2) __arm_vrndmq_x(p1,p2)
#define __arm_vrndmq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndmq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndmq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndnq_x(p1,p2) __arm_vrndnq_x(p1,p2)
#define __arm_vrndnq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndnq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndnq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndpq_x(p1,p2) __arm_vrndpq_x(p1,p2)
#define __arm_vrndpq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndpq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndpq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndq_x(p1,p2) __arm_vrndq_x(p1,p2)
#define __arm_vrndq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vrndxq_x(p1,p2) __arm_vrndxq_x(p1,p2)
#define __arm_vrndxq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vrndxq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vrndxq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define vsubq_x(p1,p2,p3) __arm_vsubq_x(p1,p2,p3)
#define __arm_vsubq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vsubq_x_n_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vsubq_x_n_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32_t), p3));})
-#define vcmulq_rot90_x(p1,p2,p3) __arm_vcmulq_rot90_x(p1,p2,p3)
#define __arm_vcmulq_rot90_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmulq_rot90_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
-#define vgetq_lane(p0,p1) __arm_vgetq_lane(p0,p1)
#define __arm_vgetq_lane(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vgetq_lane_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vgetq_lane_f16 (__ARM_mve_coerce(__p0, float16x8_t), p1), \
int (*)[__ARM_mve_type_float32x4_t]: __arm_vgetq_lane_f32 (__ARM_mve_coerce(__p0, float32x4_t), p1));})
-#define vsetq_lane(p0,p1,p2) __arm_vsetq_lane(p0,p1,p2)
#define __arm_vsetq_lane(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
#else /* MVE Integer. */
-#define vstrwq_scatter_base_wb(p0,p1,p2) __arm_vstrwq_scatter_base_wb(p0,p1,p2)
#define __arm_vstrwq_scatter_base_wb(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_wb_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_wb_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrwq_scatter_base_wb_p(p0,p1,p2,p3) __arm_vstrwq_scatter_base_wb_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_base_wb_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_wb_p_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_wb_p_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vst4q(p0,p1) __arm_vst4q(p0,p1)
#define __arm_vst4q(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)));})
-#define vabsq(p0) __arm_vabsq(p0)
#define __arm_vabsq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vclsq(p0) __arm_vclsq(p0)
#define __arm_vclsq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vclsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vclsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vclsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vclzq(p0) __arm_vclzq(p0)
#define __arm_vclzq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vclzq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vclzq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vclzq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vnegq(p0) __arm_vnegq(p0)
#define __arm_vnegq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vmovlbq(p0) __arm_vmovlbq(p0)
#define __arm_vmovlbq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
-#define vmovltq(p0) __arm_vmovltq(p0)
#define __arm_vmovltq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
-#define vmvnq(p0) __arm_vmvnq(p0)
#define __arm_vmvnq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmvnq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmvnq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vmvnq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vrev16q(p0) __arm_vrev16q(p0)
#define __arm_vrev16q(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev16q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev16q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)));})
-#define vrev32q(p0) __arm_vrev32q(p0)
#define __arm_vrev32q(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev32q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev32q_u8 (__ARM_mve_coerce(__p0, uint8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev32q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)));})
-#define vrev64q(p0) __arm_vrev64q(p0)
#define __arm_vrev64q(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev64q_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev64q_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrev64q_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vqabsq(p0) __arm_vqabsq(p0)
#define __arm_vqabsq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqabsq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vqabsq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vqabsq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vqnegq(p0) __arm_vqnegq(p0)
#define __arm_vqnegq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqnegq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vqnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vqnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
-#define vshrq(p0,p1) __arm_vshrq(p0,p1)
#define __arm_vshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define 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_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)));})
-#define vshlq(p0,p1) __arm_vshlq(p0,p1)
#define __arm_vshlq(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_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vshlq_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_vshlq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vsubq(p0,p1) __arm_vsubq(p0,p1)
#define __arm_vsubq(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_uint16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vsubq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_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_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(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_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_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_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_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 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_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_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 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 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_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 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_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 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_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_uint16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __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_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __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_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_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(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_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)));})
-#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_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)));})
-#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_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)));})
-#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_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 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_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 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_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 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_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_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_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_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(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_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 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_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 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_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(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_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 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_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)));})
-#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_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)));})
-#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_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)));})
-#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_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));})
-#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_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define 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_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vaddq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_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_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)));})
-#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_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define 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_uint16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vcmpeqq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_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_uint32x4_t][__ARM_mve_type_int_n]: __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_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_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_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_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_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_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 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_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_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_int_n]: __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_int_n]: __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_int_n]: __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); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vcmpgeq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_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_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vcmpgtq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_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_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vcmpleq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_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_int16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vcmpltq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t)));})
-#define vcmpneq_m(p0,p1,p2) __arm_vcmpneq_m(p0,p1,p2)
#define __arm_vcmpneq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmpneq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmpneq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#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_uint16x8_t][__ARM_mve_type_int_n]: __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_int_n]: __arm_vcmpneq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-#define vshlcq(p0,p1,p2) __arm_vshlcq(p0,p1,p2)
#define __arm_vshlcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlcq_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vcmpeqq_m(p0,p1,p2) __arm_vcmpeqq_m(p0,p1,p2)
#define __arm_vcmpeqq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmpeqq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpeqq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2));})
-#define vbicq_m_n(p0,p1,p2) __arm_vbicq_m_n(p0,p1,p2)
#define __arm_vbicq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vbicq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vqrshrnbq(p0,p1,p2) __arm_vqrshrnbq(p0,p1,p2)
#define __arm_vqrshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqrshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqrshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrshrunbq(p0,p1,p2) __arm_vqrshrunbq(p0,p1,p2)
#define __arm_vqrshrunbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshrunbq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshrunbq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqrdmlsdhq(p0,p1,p2) __arm_vqrdmlsdhq(p0,p1,p2)
#define __arm_vqrdmlsdhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmlsdhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmlsdhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqrdmlsdhxq(p0,p1,p2) __arm_vqrdmlsdhxq(p0,p1,p2)
#define __arm_vqrdmlsdhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmlsdhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmlsdhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqrshlq_m_n(p0,p1,p2) __arm_vqrshlq_m_n(p0,p1,p2)
#define __arm_vqrshlq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqrshlq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqrshlq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqrshlq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vqshlq_m_r(p0,p1,p2) __arm_vqshlq_m_r(p0,p1,p2)
#define __arm_vqshlq_m_r(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vqshlq_m_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_m_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_m_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vrev64q_m(p0,p1,p2) __arm_vrev64q_m(p0,p1,p2)
#define __arm_vrev64q_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrev64q_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrev64q_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrshlq_m_n(p0,p1,p2) __arm_vrshlq_m_n(p0,p1,p2)
#define __arm_vrshlq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshlq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshlq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __p1, p2));})
-#define vshlq_m_r(p0,p1,p2) __arm_vshlq_m_r(p0,p1,p2)
#define __arm_vshlq_m_r(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_m_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_m_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_m_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vsliq(p0,p1,p2) __arm_vsliq(p0,p1,p2)
#define __arm_vsliq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsliq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsliq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vsriq(p0,p1,p2) __arm_vsriq(p0,p1,p2)
#define __arm_vsriq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsriq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsriq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrdmlashq(p0,p1,p2) __arm_vqrdmlashq(p0,p1,p2)
#define __arm_vqrdmlashq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vqrdmlahq(p0,p1,p2) __arm_vqrdmlahq(p0,p1,p2)
#define __arm_vqrdmlahq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vqrdmladhxq(p0,p1,p2) __arm_vqrdmladhxq(p0,p1,p2)
#define __arm_vqrdmladhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmladhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmladhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqrdmladhq(p0,p1,p2) __arm_vqrdmladhq(p0,p1,p2)
#define __arm_vqrdmladhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmladhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmladhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqnegq_m(p0,p1,p2) __arm_vqnegq_m(p0,p1,p2)
#define __arm_vqnegq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqnegq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqnegq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqdmlsdhxq(p0,p1,p2) __arm_vqdmlsdhxq(p0,p1,p2)
#define __arm_vqdmlsdhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vabsq_m(p0,p1,p2) __arm_vabsq_m(p0,p1,p2)
#define __arm_vabsq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabsq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabsq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vclsq_m(p0,p1,p2) __arm_vclsq_m(p0,p1,p2)
#define __arm_vclsq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vclsq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vclsq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vclzq_m(p0,p1,p2) __arm_vclzq_m(p0,p1,p2)
#define __arm_vclzq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vclzq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vclzq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vcmpgeq_m(p0,p1,p2) __arm_vcmpgeq_m(p0,p1,p2)
#define __arm_vcmpgeq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpgeq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpgeq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
-#define vdupq_m(p0,p1,p2) __arm_vdupq_m(p0,p1,p2)
#define __arm_vdupq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2));})
-#define vmaxaq_m(p0,p1,p2) __arm_vmaxaq_m(p0,p1,p2)
#define __arm_vmaxaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmaxaq_m_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmaxaq_m_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlaq(p0,p1,p2) __arm_vmlaq(p0,p1,p2)
#define __arm_vmlaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmlaq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmlaq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vmlasq(p0,p1,p2) __arm_vmlasq(p0,p1,p2)
#define __arm_vmlasq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmlasq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmlasq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vnegq_m(p0,p1,p2) __arm_vnegq_m(p0,p1,p2)
#define __arm_vnegq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vnegq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vnegq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vpselq(p0,p1,p2) __arm_vpselq(p0,p1,p2)
#define __arm_vpselq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vpselq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
int (*)[__ARM_mve_type_uint64x2_t][__ARM_mve_type_uint64x2_t]: __arm_vpselq_u64 (__ARM_mve_coerce(__p0, uint64x2_t), __ARM_mve_coerce(__p1, uint64x2_t), p2));})
-#define vqdmlahq(p0,p1,p2) __arm_vqdmlahq(p0,p1,p2)
#define __arm_vqdmlahq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t)));})
-#define vqdmlsdhq(p0,p1,p2) __arm_vqdmlsdhq(p0,p1,p2)
#define __arm_vqdmlsdhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqdmladhxq(p0,p1,p2) __arm_vqdmladhxq(p0,p1,p2)
#define __arm_vqdmladhxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vqdmladhq(p0,p1,p2) __arm_vqdmladhq(p0,p1,p2)
#define __arm_vqdmladhq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vminaq_m(p0,p1,p2) __arm_vminaq_m(p0,p1,p2)
#define __arm_vminaq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminaq_m_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminaq_m_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vcmpltq_m(p0,p1,p2) __arm_vcmpltq_m(p0,p1,p2)
-#define __arm_vcmpltq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define __arm_vrmlaldavhaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpltq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpltq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpltq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
-#define vcmpleq_m(p0,p1,p2) __arm_vcmpleq_m(p0,p1,p2)
-#define __arm_vcmpleq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define __arm_vmlsdavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpleq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpleq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpleq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
-#define vcmpgtq_m(p0,p1,p2) __arm_vcmpgtq_m(p0,p1,p2)
-#define __arm_vcmpgtq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define __arm_vmlsdavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vcmpgtq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vcmpgtq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vcmpgtq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32_t), p2));})
-#define vshrntq(p0,p1,p2) __arm_vshrntq(p0,p1,p2)
-#define __arm_vshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define __arm_vmlsdavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vshrntq_n_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrshrntq(p0,p1,p2) __arm_vrshrntq(p0,p1,p2)
-#define __arm_vrshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+#define __arm_vmlsdavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vrshrntq_n_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmovlbq_m(p0,p1,p2) __arm_vmovlbq_m(p0,p1,p2)
#define __arm_vmovlbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_m_u8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_m_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vmovnbq_m(p0,p1,p2) __arm_vmovnbq_m(p0,p1,p2)
#define __arm_vmovnbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovnbq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovnbq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmovntq_m(p0,p1,p2) __arm_vmovntq_m(p0,p1,p2)
#define __arm_vmovntq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vmovntq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vmovntq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vshrnbq(p0,p1,p2) __arm_vshrnbq(p0,p1,p2)
#define __arm_vshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrshrnbq(p0,p1,p2) __arm_vrshrnbq(p0,p1,p2)
#define __arm_vrshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrev32q_m(p0,p1,p2) __arm_vrev32q_m(p0,p1,p2)
#define __arm_vrev32q_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vrev32q_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrev32q_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vqshruntq(p0,p1,p2) __arm_vqshruntq(p0,p1,p2)
#define __arm_vqshruntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqshruntq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqshruntq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vrev16q_m(p0,p1,p2) __arm_vrev16q_m(p0,p1,p2)
#define __arm_vrev16q_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vrev16q_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vrev16q_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), p2));})
-#define vqshrntq(p0,p1,p2) __arm_vqshrntq(p0,p1,p2)
#define __arm_vqshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrshruntq(p0,p1,p2) __arm_vqrshruntq(p0,p1,p2)
#define __arm_vqrshruntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshruntq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshruntq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqrshrntq(p0,p1,p2) __arm_vqrshrntq(p0,p1,p2)
#define __arm_vqrshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqrshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqrshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqshrnbq(p0,p1,p2) __arm_vqshrnbq(p0,p1,p2)
#define __arm_vqshrnbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqshrnbq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqshrnbq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqmovuntq_m(p0,p1,p2) __arm_vqmovuntq_m(p0,p1,p2)
#define __arm_vqmovuntq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovuntq_m_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovuntq_m_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqmovntq_m(p0,p1,p2) __arm_vqmovntq_m(p0,p1,p2)
#define __arm_vqmovntq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovntq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovntq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqmovnbq_m(p0,p1,p2) __arm_vqmovnbq_m(p0,p1,p2)
#define __arm_vqmovnbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqmovnbq_m_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqmovnbq_m_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmovltq_m(p0,p1,p2) __arm_vmovltq_m(p0,p1,p2)
#define __arm_vmovltq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t]: __arm_vmovltq_m_u8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t]: __arm_vmovltq_m_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vqmovunbq_m(p0,p1,p2) __arm_vqmovunbq_m(p0,p1,p2)
#define __arm_vqmovunbq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqmovunbq_m_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqmovunbq_m_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vsubq_m(p0,p1,p2,p3) __arm_vsubq_m(p0,p1,p2,p3)
#define __arm_vsubq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsubq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsubq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vabdq_m(p0,p1,p2,p3) __arm_vabdq_m(p0,p1,p2,p3)
+#define __arm_vabavq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabavq_p_s8(__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabavq_p_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabavq_p_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabavq_p_u8(__p0, __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_p_u16(__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_p_u32(__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
#define __arm_vabdq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vandq_m(p0,p1,p2,p3) __arm_vandq_m(p0,p1,p2,p3)
#define __arm_vandq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vandq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vandq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vbicq_m(p0,p1,p2,p3) __arm_vbicq_m(p0,p1,p2,p3)
#define __arm_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vbrsrq_m(p0,p1,p2,p3) __arm_vbrsrq_m(p0,p1,p2,p3)
#define __arm_vbrsrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbrsrq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbrsrq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __p2, p3));})
-#define vcaddq_rot270_m(p0,p1,p2,p3) __arm_vcaddq_rot270_m(p0,p1,p2,p3)
#define __arm_vcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot270_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcaddq_rot270_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vcaddq_rot90_m(p0,p1,p2,p3) __arm_vcaddq_rot90_m(p0,p1,p2,p3)
#define __arm_vcaddq_rot90_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot90_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcaddq_rot90_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define veorq_m(p0,p1,p2,p3) __arm_veorq_m(p0,p1,p2,p3)
#define __arm_veorq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_veorq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_veorq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vornq_m(p0,p1,p2,p3) __arm_vornq_m(p0,p1,p2,p3)
+#define __arm_vmladavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmladavaq_p_s8 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaq_p_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmladavaq_p_u8 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
#define __arm_vornq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vornq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vornq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vorrq_m(p0,p1,p2,p3) __arm_vorrq_m(p0,p1,p2,p3)
#define __arm_vorrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vorrq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vorrq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vaddq_m(p0,p1,p2,p3) __arm_vaddq_m(p0,p1,p2,p3)
#define __arm_vaddq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vaddq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vaddq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmulq_m(p0,p1,p2,p3) __arm_vmulq_m(p0,p1,p2,p3)
#define __arm_vmulq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrbq(p0,p1) __arm_vstrbq(p0,p1)
#define __arm_vstrbq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vstrwq_scatter_base(p0,p1,p2) __arm_vstrwq_scatter_base(p0,p1,p2)
+#define __arm_vstrbq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
#define __arm_vstrwq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_s32(p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_u32(p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vldrbq_gather_offset(p0,p1) __arm_vldrbq_gather_offset(p0,p1)
#define __arm_vldrbq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8 (__ARM_mve_coerce(p0, int8_t const *), __ARM_mve_coerce(__p1, uint8x16_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce(p0, uint8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce(p0, uint8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vstrwq_scatter_base_p(p0,p1,p2,p3) __arm_vstrwq_scatter_base_p(p0,p1,p2,p3)
+#define __arm_vstrbq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_p_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_p_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_p_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_p_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_p_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_p_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define __arm_vstrbq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_p_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_p_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_p_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_p_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
#define __arm_vstrwq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_p_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_p_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vld1q(p0) __arm_vld1q(p0)
#define __arm_vld1q(p0) (_Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce(p0, int8_t const *)), \
int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce(p0, int16_t const *)), \
int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce(p0, uint16_t const *)), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce(p0, uint32_t const *))))
-#define vldrhq_gather_offset(p0,p1) __arm_vldrhq_gather_offset(p0,p1)
#define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vldrhq_gather_offset_z(p0,p1,p2) __arm_vldrhq_gather_offset_z(p0,p1,p2)
#define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vldrhq_gather_shifted_offset(p0,p1) __arm_vldrhq_gather_shifted_offset(p0,p1)
#define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vldrhq_gather_shifted_offset_z(p0,p1,p2) __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2)
#define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce(p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vldrwq_gather_offset(p0,p1) __arm_vldrwq_gather_offset(p0,p1)
#define __arm_vldrwq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1));})
-#define vldrwq_gather_offset_z(p0,p1,p2) __arm_vldrwq_gather_offset_z(p0,p1,p2)
#define __arm_vldrwq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1, p2));})
-#define vldrwq_gather_shifted_offset(p0,p1) __arm_vldrwq_gather_shifted_offset(p0,p1)
#define __arm_vldrwq_gather_shifted_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1));})
-#define vldrwq_gather_shifted_offset_z(p0,p1,p2) __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2)
#define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(__p0, int32_t const *), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(__p0, uint32_t const *), p1, p2));})
-#define vst1q(p0,p1) __arm_vst1q(p0,p1)
#define __arm_vst1q(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vst1q_p(p0,p1,p2) __arm_vst1q_p(p0,p1,p2)
#define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vst2q(p0,p1) __arm_vst2q(p0,p1)
#define __arm_vst2q(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)));})
-#define vstrhq(p0,p1) __arm_vstrhq(p0,p1)
#define __arm_vstrhq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vstrhq_p(p0,p1,p2) __arm_vstrhq_p(p0,p1,p2)
#define __arm_vstrhq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vstrhq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrhq_scatter_offset(p0,p1,p2) __arm_vstrhq_scatter_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrhq_scatter_shifted_offset(p0,p1,p2) __arm_vstrhq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrwq(p0,p1) __arm_vstrwq(p0,p1)
#define __arm_vstrwq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vstrwq_p(p0,p1,p2) __arm_vstrwq_p(p0,p1,p2)
#define __arm_vstrwq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vstrhq_scatter_offset(p0,p1,p2) __arm_vstrhq_scatter_offset(p0,p1,p2)
+#define __arm_vstrdq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_p_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
+ int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_p_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
+
+#define __arm_vstrdq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t)), \
+ int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
+
+#define __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_p_s64 (__ARM_mve_coerce(__p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
+ int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_p_u64 (__ARM_mve_coerce(__p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
+
+#define __arm_vstrdq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_s64 (__ARM_mve_coerce(__p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t)), \
+ int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_u64 (__ARM_mve_coerce(__p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
+
+#define __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_s64 (__ARM_mve_coerce(__p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
+ int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_u64 (__ARM_mve_coerce(__p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
+
+#define __arm_vstrdq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_s64 (__ARM_mve_coerce(__p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t)), \
+ int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_u64 (__ARM_mve_coerce(__p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
+
#define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrhq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrhq_scatter_shifted_offset(p0,p1,p2) __arm_vstrhq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrwq_scatter_offset(p0,p1,p2) __arm_vstrwq_scatter_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrwq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrwq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrwq_scatter_offset(p0,p1,p2) __arm_vstrwq_scatter_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrwq_scatter_shifted_offset(p0,p1,p2) __arm_vstrwq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vuninitializedq(p0) __arm_vuninitializedq(p0)
#define __arm_vuninitializedq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vuninitializedq_s8 (), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vuninitializedq_u32 (), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vuninitializedq_u64 ());})
-#define vreinterpretq_s16(p0) __arm_vreinterpretq_s16(p0)
#define __arm_vreinterpretq_s16(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vreinterpretq_s16_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_s16_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s16_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vreinterpretq_s32(p0) __arm_vreinterpretq_s32(p0)
#define __arm_vreinterpretq_s32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vreinterpretq_s32_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_s32_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s32_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vreinterpretq_s64(p0) __arm_vreinterpretq_s64(p0)
#define __arm_vreinterpretq_s64(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vreinterpretq_s64_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_s64_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s64_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vreinterpretq_s8(p0) __arm_vreinterpretq_s8(p0)
#define __arm_vreinterpretq_s8(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vreinterpretq_s8_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_s8_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_s8_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vreinterpretq_u16(p0) __arm_vreinterpretq_u16(p0)
#define __arm_vreinterpretq_u16(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vreinterpretq_u16_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_u16_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_u16_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vreinterpretq_u32(p0) __arm_vreinterpretq_u32(p0)
#define __arm_vreinterpretq_u32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vreinterpretq_u32_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vreinterpretq_u32_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_u32_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vreinterpretq_u64(p0) __arm_vreinterpretq_u64(p0)
#define __arm_vreinterpretq_u64(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vreinterpretq_u64_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_u64_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_int64x2_t]: __arm_vreinterpretq_u64_s64 (__ARM_mve_coerce(__p0, int64x2_t)));})
-#define vreinterpretq_u8(p0) __arm_vreinterpretq_u8(p0)
#define __arm_vreinterpretq_u8(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vreinterpretq_u8_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vreinterpretq_u8_u32 (__ARM_mve_coerce(__p0, uint32x4_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vreinterpretq_u8_u64 (__ARM_mve_coerce(__p0, uint64x2_t)));})
-#define vabsq_x(p1,p2) __arm_vabsq_x(p1,p2)
#define __arm_vabsq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vabsq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vabsq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vaddq_x(p1,p2,p3) __arm_vaddq_x(p1,p2,p3)
#define __arm_vaddq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vaddq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vaddq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
-#define vcaddq_rot270_x(p1,p2,p3) __arm_vcaddq_rot270_x(p1,p2,p3)
#define __arm_vcaddq_rot270_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot270_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcaddq_rot270_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vcaddq_rot90_x(p1,p2,p3) __arm_vcaddq_rot90_x(p1,p2,p3)
#define __arm_vcaddq_rot90_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot90_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcaddq_rot90_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define veorq_x(p1,p2,p3) __arm_veorq_x(p1,p2,p3)
#define __arm_veorq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_veorq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_veorq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmulq_x(p1,p2,p3) __arm_vmulq_x(p1,p2,p3)
+#define __arm_vmaxq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
+
+#define __arm_vminq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vminq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vminq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vminq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vminq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vminq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vminq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define __arm_vmovlbq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovlbq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
+
+#define __arm_vmovltq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vmovltq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
+
+#define __arm_vmulhq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulhq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulhq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulhq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulhq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulhq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulhq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define __arm_vmullbq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmullbq_int_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmullbq_int_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmullbq_int_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_int_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmullbq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define __arm_vmullbq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
+
+#define __arm_vmulltq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vmulltq_int_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmulltq_int_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
+ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmulltq_int_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_int_x_u8( __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
+ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulltq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+
+#define __arm_vmulltq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
+
#define __arm_vmulq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmulq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
-#define vnegq_x(p1,p2) __arm_vnegq_x(p1,p2)
#define __arm_vnegq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vnegq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vnegq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vnegq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vornq_x(p1,p2,p3) __arm_vornq_x(p1,p2,p3)
#define __arm_vornq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vornq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vornq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vorrq_x(p1,p2,p3) __arm_vorrq_x(p1,p2,p3)
#define __arm_vorrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vorrq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vorrq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vrev32q_x(p1,p2) __arm_vrev32q_x(p1,p2)
#define __arm_vrev32q_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev32q_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev32q_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev32q_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vrev64q_x(p1,p2) __arm_vrev64q_x(p1,p2)
#define __arm_vrev64q_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev64q_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev64q_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrev64q_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vabdq_x(p1,p2,p3) __arm_vabdq_x(p1,p2,p3)
#define __arm_vabdq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vandq_x(p1,p2,p3) __arm_vandq_x(p1,p2,p3)
#define __arm_vandq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vandq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vandq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vbicq_x(p1,p2,p3) __arm_vbicq_x(p1,p2,p3)
#define __arm_vbicq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vbrsrq_x(p1,p2,p3) __arm_vbrsrq_x(p1,p2,p3)
#define __arm_vbrsrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vbrsrq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vbrsrq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vbrsrq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vld1q_z(p0,p1) __arm_vld1q_z(p0, p1)
#define __arm_vld1q_z(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce(p0, int8_t const *), p1), \
int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce(p0, int16_t const *), p1), \
int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce(p0, uint16_t const *), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce(p0, uint32_t const *), p1)))
-#define vld2q(p0) __arm_vld2q(p0)
#define __arm_vld2q(p0) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce(p0, int8_t const *)), \
int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce(p0, int16_t const *)), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce(p0, uint32_t const *))))
-#define vld4q(p0) __arm_vld4q(p0)
#define __arm_vld4q(p0) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce(p0, int8_t const *)), \
int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce(p0, int16_t const *)), \
int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce(p0, uint16_t const *)), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce(p0, uint32_t const *))))
-#define vgetq_lane(p0,p1) __arm_vgetq_lane(p0,p1)
#define __arm_vgetq_lane(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vgetq_lane_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vgetq_lane_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vgetq_lane_u64 (__ARM_mve_coerce(__p0, uint64x2_t), p1));})
-#define vsetq_lane(p0,p1,p2) __arm_vsetq_lane(p0,p1,p2)
#define __arm_vsetq_lane(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
#endif /* MVE Integer. */
-#define vmvnq_x(p1,p2) __arm_vmvnq_x(p1,p2)
+#define __arm_vshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vshrntq_n_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vshrntq_n_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+
+#define __arm_vrshrntq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int16x8_t]: __arm_vrshrntq_n_s16 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int32x4_t]: __arm_vrshrntq_n_s32 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrntq_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrntq_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+
#define __arm_vmvnq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmvnq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmvnq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vmvnq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrev16q_x(p1,p2) __arm_vrev16q_x(p1,p2)
#define __arm_vrev16q_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrev16q_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vrev16q_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2));})
-#define vrhaddq_x(p1,p2,p3) __arm_vrhaddq_x(p1,p2,p3)
#define __arm_vrhaddq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrhaddq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrhaddq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vshlq_x(p0,p1,p2,p3) __arm_vshlq_x(p0,p1,p2,p3)
#define __arm_vshlq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vshlq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vshlq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vrmulhq_x(p1,p2,p3) __arm_vrmulhq_x(p1,p2,p3)
#define __arm_vrmulhq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrmulhq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmulhq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vrshlq_x(p1,p2,p3) __arm_vrshlq_x(p1,p2,p3)
#define __arm_vrshlq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vrshlq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrshlq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vrshrq_x(p1,p2,p3) __arm_vrshrq_x(p1,p2,p3)
#define __arm_vrshrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vrshrq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrshrq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrshrq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vshllbq_x(p1,p2,p3) __arm_vshllbq_x(p1,p2,p3)
#define __arm_vshllbq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshllbq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshllbq_x_n_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshllbq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3));})
-#define vshlltq_x(p1,p2,p3) __arm_vshlltq_x(p1,p2,p3)
#define __arm_vshlltq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlltq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshlltq_x_n_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlltq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3));})
-#define vshlq_x_n(p1,p2,p3) __arm_vshlq_x_n(p1,p2,p3)
#define __arm_vshlq_x_n(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_x_n_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_x_n_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vdwdupq_x_u8(p1,p2,p3,p4) __arm_vdwdupq_x_u8(p1,p2,p3,p4)
#define __arm_vdwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define vdwdupq_x_u16(p1,p2,p3,p4) __arm_vdwdupq_x_u16(p1,p2,p3,p4)
#define __arm_vdwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define vdwdupq_x_u32(p1,p2,p3,p4) __arm_vdwdupq_x_u32(p1,p2,p3,p4)
#define __arm_vdwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define viwdupq_x_u8(p1,p2,p3,p4) __arm_viwdupq_x_u8(p1,p2,p3,p4)
#define __arm_viwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define viwdupq_x_u16(p1,p2,p3,p4) __arm_viwdupq_x_u16(p1,p2,p3,p4)
#define __arm_viwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define viwdupq_x_u32(p1,p2,p3,p4) __arm_viwdupq_x_u32(p1,p2,p3,p4)
#define __arm_viwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define vidupq_x_u8(p1,p2,p3) __arm_vidupq_x_u8(p1,p2,p3)
#define __arm_vidupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vddupq_x_u8(p1,p2,p3) __arm_vddupq_x_u8(p1,p2,p3)
#define __arm_vddupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u8 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vidupq_x_u16(p1,p2,p3) __arm_vidupq_x_u16(p1,p2,p3)
#define __arm_vidupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vddupq_x_u16(p1,p2,p3) __arm_vddupq_x_u16(p1,p2,p3)
#define __arm_vddupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u16 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vidupq_x_u32(p1,p2,p3) __arm_vidupq_x_u32(p1,p2,p3)
#define __arm_vidupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vddupq_x_u32(p1,p2,p3) __arm_vddupq_x_u32(p1,p2,p3)
#define __arm_vddupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u32 (__ARM_mve_coerce(__p1, uint32_t), p2, p3), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vhaddq_x(p1,p2,p3) __arm_vhaddq_x(p1,p2,p3)
-#define vshrq_x(p1,p2,p3) __arm_vshrq_x(p1,p2,p3)
#define __arm_vshrq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshrq_x_n_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vhaddq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vhaddq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vhcaddq_rot270_x(p1,p2,p3) __arm_vhcaddq_rot270_x(p1,p2,p3)
#define __arm_vhcaddq_rot270_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vhcaddq_rot270_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vhcaddq_rot270_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vhcaddq_rot90_x(p1,p2,p3) __arm_vhcaddq_rot90_x(p1,p2,p3)
#define __arm_vhcaddq_rot90_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vhcaddq_rot90_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vhcaddq_rot90_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vhsubq_x(p1,p2,p3) __arm_vhsubq_x(p1,p2,p3)
#define __arm_vhsubq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vhsubq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vhsubq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vclsq_x(p1,p2) __arm_vclsq_x(p1,p2)
#define __arm_vclsq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vclsq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vclsq_x_s16 (__ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vclsq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vclzq_x(p1,p2) __arm_vclzq_x(p1,p2)
#define __arm_vclzq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vclzq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vclzq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vclzq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vadciq(p0,p1,p2) __arm_vadciq(p0,p1,p2)
#define __arm_vadciq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vadciq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vadciq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vstrdq_scatter_base_wb_p(p0,p1,p2,p3) __arm_vstrdq_scatter_base_wb_p(p0,p1,p2,p3)
#define __arm_vstrdq_scatter_base_wb_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_wb_p_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_wb_p_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
-#define vstrdq_scatter_base_wb(p0,p1,p2) __arm_vstrdq_scatter_base_wb(p0,p1,p2)
#define __arm_vstrdq_scatter_base_wb(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_wb_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_wb_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
-#define vldrdq_gather_offset(p0,p1) __arm_vldrdq_gather_offset(p0,p1)
#define __arm_vldrdq_gather_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce(p0, int64_t const *), p1), \
int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1)))
-#define vldrdq_gather_offset_z(p0,p1,p2) __arm_vldrdq_gather_offset_z(p0,p1,p2)
#define __arm_vldrdq_gather_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce(p0, int64_t const *), p1, p2), \
int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1, p2)))
-#define vldrdq_gather_shifted_offset(p0,p1) __arm_vldrdq_gather_shifted_offset(p0,p1)
#define __arm_vldrdq_gather_shifted_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce(p0, int64_t const *), p1), \
int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1)))
-#define vldrdq_gather_shifted_offset_z(p0,p1,p2) __arm_vldrdq_gather_shifted_offset_z(p0,p1,p2)
#define __arm_vldrdq_gather_shifted_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \
int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce(p0, int64_t const *), p1, p2), \
int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce(p0, uint64_t const *), p1, p2)))
-#define vadciq_m(p0,p1,p2,p3,p4) __arm_vadciq_m(p0,p1,p2,p3,p4)
#define __arm_vadciq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vadciq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3, p4), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vadciq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3, p4));})
-#define vadciq(p0,p1,p2) __arm_vadciq(p0,p1,p2)
#define __arm_vadciq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vadciq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vadciq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vadcq_m(p0,p1,p2,p3,p4) __arm_vadcq_m(p0,p1,p2,p3,p4)
#define __arm_vadcq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vadcq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3, p4), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vadcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3, p4));})
-#define vadcq(p0,p1,p2) __arm_vadcq(p0,p1,p2)
#define __arm_vadcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vadcq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vadcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vsbciq_m(p0,p1,p2,p3,p4) __arm_vsbciq_m(p0,p1,p2,p3,p4)
#define __arm_vsbciq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbciq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3, p4), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbciq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3, p4));})
-#define vsbciq(p0,p1,p2) __arm_vsbciq(p0,p1,p2)
#define __arm_vsbciq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbciq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbciq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vsbcq_m(p0,p1,p2,p3,p4) __arm_vsbcq_m(p0,p1,p2,p3,p4)
#define __arm_vsbcq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbcq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3, p4), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3, p4));})
-#define vsbcq(p0,p1,p2) __arm_vsbcq(p0,p1,p2)
#define __arm_vsbcq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vsbcq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsbcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vldrbq_gather_offset_z(p0,p1,p2) __arm_vldrbq_gather_offset_z(p0,p1,p2)
#define __arm_vldrbq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce(p0, int8_t const *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce(p0, uint8_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_u32 (__ARM_mve_coerce(p0, uint8_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vqrdmlahq_m(p0,p1,p2,p3) __arm_vqrdmlahq_m(p0,p1,p2,p3)
#define __arm_vqrdmlahq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlahq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3));})
-#define vqrdmlashq_m(p0,p1,p2,p3) __arm_vqrdmlashq_m(p0,p1,p2,p3)
#define __arm_vqrdmlashq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmlashq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3));})
-#define vqrshlq_m(p0,p1,p2,p3) __arm_vqrshlq_m(p0,p1,p2,p3)
#define __arm_vqrshlq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrshlq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrshlq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqshlq_m_n(p0,p1,p2,p3) __arm_vqshlq_m_n(p0,p1,p2,p3)
#define __arm_vqshlq_m_n(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqshlq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vqshlq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vqshlq_m(p0,p1,p2,p3) __arm_vqshlq_m(p0,p1,p2,p3)
#define __arm_vqshlq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqshlq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqshlq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vrhaddq_m(p0,p1,p2,p3) __arm_vrhaddq_m(p0,p1,p2,p3)
#define __arm_vrhaddq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrhaddq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrhaddq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vrmulhq_m(p0,p1,p2,p3) __arm_vrmulhq_m(p0,p1,p2,p3)
#define __arm_vrmulhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrmulhq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmulhq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vrshlq_m(p0,p1,p2,p3) __arm_vrshlq_m(p0,p1,p2,p3)
#define __arm_vrshlq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vrshlq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrshlq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vrshrq_m(p0,p1,p2,p3) __arm_vrshrq_m(p0,p1,p2,p3)
#define __arm_vrshrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vshrq_m(p0,p1,p2,p3) __arm_vshrq_m(p0,p1,p2,p3)
#define __arm_vshrq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vshrq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vshrq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vsliq_m(p0,p1,p2,p3) __arm_vsliq_m(p0,p1,p2,p3)
#define __arm_vsliq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsliq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsliq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vqsubq_m(p0,p1,p2,p3) __arm_vqsubq_m(p0,p1,p2,p3)
#define __arm_vqsubq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqsubq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vqsubq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vqrdmulhq_m(p0,p1,p2,p3) __arm_vqrdmulhq_m(p0,p1,p2,p3)
#define __arm_vqrdmulhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqrdmulhq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqrdmulhq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3));})
-#define vqrdmlsdhxq_m(p0,p1,p2,p3) __arm_vqrdmlsdhxq_m(p0,p1,p2,p3)
#define __arm_vqrdmlsdhxq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmlsdhxq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmlsdhxq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqrdmlsdhq_m(p0,p1,p2,p3) __arm_vqrdmlsdhq_m(p0,p1,p2,p3)
#define __arm_vqrdmlsdhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmlsdhq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmlsdhq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vshllbq_m(p0,p1,p2,p3) __arm_vshllbq_m(p0,p1,p2,p3)
#define __arm_vshllbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t]: __arm_vshllbq_m_n_u8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t]: __arm_vshllbq_m_n_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3));})
-#define vshrntq_m(p0,p1,p2,p3) __arm_vshrntq_m(p0,p1,p2,p3)
#define __arm_vshrntq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrntq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrntq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vshrnbq_m(p0,p1,p2,p3) __arm_vshrnbq_m(p0,p1,p2,p3)
#define __arm_vshrnbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vshrnbq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vshrnbq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vshlltq_m(p0,p1,p2,p3) __arm_vshlltq_m(p0,p1,p2,p3)
#define __arm_vshlltq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t]: __arm_vshlltq_m_n_u8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t]: __arm_vshlltq_m_n_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3));})
-#define vrshrntq_m(p0,p1,p2,p3) __arm_vrshrntq_m(p0,p1,p2,p3)
#define __arm_vrshrntq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrntq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrntq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vqshruntq_m(p0,p1,p2,p3) __arm_vqshruntq_m(p0,p1,p2,p3)
#define __arm_vqshruntq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqshruntq_m_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqshruntq_m_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2, p3));})
-#define vqshrunbq_m(p0,p1,p2,p3) __arm_vqshrunbq_m(p0,p1,p2,p3)
#define __arm_vqshrunbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqshrunbq_m_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqshrunbq_m_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2, p3));})
-#define vqrshrnbq_m(p0,p1,p2,p3) __arm_vqrshrnbq_m(p0,p1,p2,p3)
#define __arm_vqrshrnbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqrshrnbq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqrshrnbq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vqrshrntq_m(p0,p1,p2,p3) __arm_vqrshrntq_m(p0,p1,p2,p3)
#define __arm_vqrshrntq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqrshrntq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqrshrntq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vqrshrunbq_m(p0,p1,p2,p3) __arm_vqrshrunbq_m(p0,p1,p2,p3)
#define __arm_vqrshrunbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshrunbq_m_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshrunbq_m_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2, p3));})
-#define vqrshruntq_m(p0,p1,p2,p3) __arm_vqrshruntq_m(p0,p1,p2,p3)
#define __arm_vqrshruntq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqrshruntq_m_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqrshruntq_m_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2, p3));})
-#define vqshrnbq_m(p0,p1,p2,p3) __arm_vqshrnbq_m(p0,p1,p2,p3)
#define __arm_vqshrnbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqshrnbq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqshrnbq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vqshrntq_m(p0,p1,p2,p3) __arm_vqshrntq_m(p0,p1,p2,p3)
#define __arm_vqshrntq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vqshrntq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vqshrntq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vrshrnbq_m(p0,p1,p2,p3) __arm_vrshrnbq_m(p0,p1,p2,p3)
#define __arm_vrshrnbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint16x8_t]: __arm_vrshrnbq_m_n_u16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32x4_t]: __arm_vrshrnbq_m_n_u32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vmlaldavaq_p(p0,p1,p2,p3) __arm_vmlaldavaq_p(p0,p1,p2,p3)
#define __arm_vmlaldavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavaq_p_u16 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavaq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmlaldavaxq_p(p0,p1,p2,p3) __arm_vmlaldavaxq_p(p0,p1,p2,p3)
#define __arm_vmlaldavaxq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavaxq_p_u16 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavaxq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmlsldavaq_p(p0,p1,p2,p3) __arm_vmlsldavaq_p(p0,p1,p2,p3)
#define __arm_vmlsldavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaq_p_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaq_p_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vmlsldavaxq_p(p0,p1,p2,p3) __arm_vmlsldavaxq_p(p0,p1,p2,p3)
#define __arm_vmlsldavaxq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaxq_p_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaxq_p_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vrmlaldavhaq_p(p0,p1,p2,p3) __arm_vrmlaldavhaq_p(p0,p1,p2,p3)
#define __arm_vrmlaldavhaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhaq_p_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhaq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vrmlaldavhaxq_p(p0,p1,p2,p3) __arm_vrmlaldavhaxq_p(p0,p1,p2,p3)
#define __arm_vrmlaldavhaxq_p(p0,p1,p2,p3) __arm_vrmlaldavhaxq_p_s32(p0,p1,p2,p3)
-#define vrmlsldavhaq_p(p0,p1,p2,p3) __arm_vrmlsldavhaq_p(p0,p1,p2,p3)
#define __arm_vrmlsldavhaq_p(p0,p1,p2,p3) __arm_vrmlsldavhaq_p_s32(p0,p1,p2,p3)
-#define vrmlsldavhaxq_p(p0,p1,p2,p3) __arm_vrmlsldavhaxq_p(p0,p1,p2,p3)
#define __arm_vrmlsldavhaxq_p(p0,p1,p2,p3) __arm_vrmlsldavhaxq_p_s32(p0,p1,p2,p3)
-#define vqdmladhq_m(p0,p1,p2,p3) __arm_vqdmladhq_m(p0,p1,p2,p3)
#define __arm_vqdmladhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqdmladhxq_m(p0,p1,p2,p3) __arm_vqdmladhxq_m(p0,p1,p2,p3)
#define __arm_vqdmladhxq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhxq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhxq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqdmlsdhq_m(p0,p1,p2,p3) __arm_vqdmlsdhq_m(p0,p1,p2,p3)
#define __arm_vqdmlsdhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqdmlsdhxq_m(p0,p1,p2,p3) __arm_vqdmlsdhxq_m(p0,p1,p2,p3)
#define __arm_vqdmlsdhxq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhxq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhxq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqabsq_m(p0,p1,p2) __arm_vqabsq_m(p0,p1,p2)
#define __arm_vqabsq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqabsq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqabsq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmvnq_m(p0,p1,p2) __arm_vmvnq_m(p0,p1,p2)
#define __arm_vmvnq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmvnq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce1(__p1, int) , p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmvnq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce1(__p1, int) , p2));})
-#define vorrq_m_n(p0,p1,p2) __arm_vorrq_m_n(p0,p1,p2)
#define __arm_vorrq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int16x8_t]: __arm_vorrq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vorrq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vorrq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vqshrunbq(p0,p1,p2) __arm_vqshrunbq(p0,p1,p2)
#define __arm_vqshrunbq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int16x8_t]: __arm_vqshrunbq_n_s16 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int32x4_t]: __arm_vqshrunbq_n_s32 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vqshluq_m(p0,p1,p2,p3) __arm_vqshluq_m(p0,p1,p2,p3)
#define __arm_vqshluq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqshluq_m_n_s16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqshluq_m_n_s32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2, p3));})
-#define vshlq_m(p0,p1,p2,p3) __arm_vshlq_m(p0,p1,p2,p3)
#define __arm_vshlq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vshlq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vshlq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vshlq_m_n(p0,p1,p2,p3) __arm_vshlq_m_n(p0,p1,p2,p3)
#define __arm_vshlq_m_n(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vshlq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vshlq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vshlq_m_r(p0,p1,p2) __arm_vshlq_m_r(p0,p1,p2)
#define __arm_vshlq_m_r(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlq_m_r_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlq_m_r_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlq_m_r_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));})
-#define vsriq_m(p0,p1,p2,p3) __arm_vsriq_m(p0,p1,p2,p3)
#define __arm_vsriq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vsriq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vsriq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));})
-#define vhaddq_m(p0,p1,p2,p3) __arm_vhaddq_m(p0,p1,p2,p3)
#define __arm_vhaddq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vhaddq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vhaddq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vhcaddq_rot270_m(p0,p1,p2,p3) __arm_vhcaddq_rot270_m(p0,p1,p2,p3)
#define __arm_vhcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vhcaddq_rot270_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vhcaddq_rot270_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vhcaddq_rot90_m(p0,p1,p2,p3) __arm_vhcaddq_rot90_m(p0,p1,p2,p3)
#define __arm_vhcaddq_rot90_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vhcaddq_rot90_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vhcaddq_rot90_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vhsubq_m(p0,p1,p2,p3) __arm_vhsubq_m(p0,p1,p2,p3)
#define __arm_vhsubq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vhsubq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vhsubq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
-#define vmaxq_m(p0,p1,p2,p3) __arm_vmaxq_m(p0,p1,p2,p3)
#define __arm_vmaxq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vminq_m(p0,p1,p2,p3) __arm_vminq_m(p0,p1,p2,p3)
#define __arm_vminq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vminq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vminq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmlaq_m(p0,p1,p2,p3) __arm_vmlaq_m(p0,p1,p2,p3)
#define __arm_vmlaq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmlaq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmlaq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
-#define vmlasq_m(p0,p1,p2,p3) __arm_vmlasq_m(p0,p1,p2,p3)
#define __arm_vmlasq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vmlasq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vmlasq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32_t), p3));})
-#define vmulhq_m(p0,p1,p2,p3) __arm_vmulhq_m(p0,p1,p2,p3)
#define __arm_vmulhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulhq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulhq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmullbq_int_m(p0,p1,p2,p3) __arm_vmullbq_int_m(p0,p1,p2,p3)
#define __arm_vmullbq_int_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_int_m_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint64x2_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmullbq_int_m_u32 (__ARM_mve_coerce(__p0, uint64x2_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmulltq_int_m(p0,p1,p2,p3) __arm_vmulltq_int_m(p0,p1,p2,p3)
#define __arm_vmulltq_int_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_int_m_u16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint64x2_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulltq_int_m_u32 (__ARM_mve_coerce(__p0, uint64x2_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmulltq_poly_m(p0,p1,p2,p3) __arm_vmulltq_poly_m(p0,p1,p2,p3)
#define __arm_vmulltq_poly_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_m_p8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_m_p16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-#define vqaddq_m(p0,p1,p2,p3) __arm_vqaddq_m(p0,p1,p2,p3)
#define __arm_vqaddq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vqaddq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vqaddq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vqdmlahq_m(p0,p1,p2,p3) __arm_vqdmlahq_m(p0,p1,p2,p3)
#define __arm_vqdmlahq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqdmlahq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3));})
-#define vqdmulhq_m(p0,p1,p2,p3) __arm_vqdmulhq_m(p0,p1,p2,p3)
#define __arm_vqdmulhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmulhq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmulhq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqdmullbq_m(p0,p1,p2,p3) __arm_vqdmullbq_m(p0,p1,p2,p3)
#define __arm_vqdmullbq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vqdmullbq_m_n_s16 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16_t), p3), \
int (*)[__ARM_mve_type_int64x2_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vqdmullbq_m_n_s32 (__ARM_mve_coerce(__p0, int64x2_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32_t), p3));})
-#define vqdmulltq_m(p0,p1,p2,p3) __arm_vqdmulltq_m(p0,p1,p2,p3)
#define __arm_vqdmulltq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmulltq_m_s16 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int64x2_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmulltq_m_s32 (__ARM_mve_coerce(__p0, int64x2_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqrdmladhq_m(p0,p1,p2,p3) __arm_vqrdmladhq_m(p0,p1,p2,p3)
#define __arm_vqrdmladhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmladhq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmladhq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vqrdmladhxq_m(p0,p1,p2,p3) __arm_vqrdmladhxq_m(p0,p1,p2,p3)
#define __arm_vqrdmladhxq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqrdmladhxq_m_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqrdmladhxq_m_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vmlsdavaxq_p(p0,p1,p2,p3) __arm_vmlsdavaxq_p(p0,p1,p2,p3)
#define __arm_vmlsdavaxq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaxq_p_s16 (__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaxq_p_s32 (__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vmlsdavaq_p(p0,p1,p2,p3) __arm_vmlsdavaq_p(p0,p1,p2,p3)
#define __arm_vmlsdavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaq_p_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaq_p_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vmladavaxq_p(p0,p1,p2,p3) __arm_vmladavaxq_p(p0,p1,p2,p3)
#define __arm_vmladavaxq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavaxq_p_s16 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavaxq_p_s32 (__ARM_mve_coerce(__p0, int32_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3));})
-#define vmullbq_poly_m(p0,p1,p2,p3) __arm_vmullbq_poly_m(p0,p1,p2,p3)
#define __arm_vmullbq_poly_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_m_p8 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_m_p16 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-#define vldrbq_gather_offset(p0,p1) __arm_vldrbq_gather_offset(p0,p1)
#define __arm_vldrbq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8 (__ARM_mve_coerce(p0, int8_t const *), __ARM_mve_coerce(__p1, uint8x16_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce(p0, uint8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce(p0, uint8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vidupq_m(p0,p1,p2,p3) __arm_vidupq_m(p0,p1,p2,p3)
#define __arm_vidupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vddupq_m(p0,p1,p2,p3) __arm_vddupq_m(p0,p1,p2,p3)
#define __arm_vddupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));})
-#define vidupq_u16(p0,p1) __arm_vidupq_u16(p0,p1)
#define __arm_vidupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u16 (__ARM_mve_coerce(__p0, uint32_t), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
-#define vidupq_u32(p0,p1) __arm_vidupq_u32(p0,p1)
#define __arm_vidupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u32 (__ARM_mve_coerce(__p0, uint32_t), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
-#define vidupq_u8(p0,p1) __arm_vidupq_u8(p0,p1)
#define __arm_vidupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u8 (__ARM_mve_coerce(__p0, uint32_t), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
-#define vddupq_u16(p0,p1) __arm_vddupq_u16(p0,p1)
#define __arm_vddupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u16 (__ARM_mve_coerce(__p0, uint32_t), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
-#define vddupq_u32(p0,p1) __arm_vddupq_u32(p0,p1)
#define __arm_vddupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u32 (__ARM_mve_coerce(__p0, uint32_t), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
-#define vddupq_u8(p0,p1) __arm_vddupq_u8(p0,p1)
#define __arm_vddupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u8 (__ARM_mve_coerce(__p0, uint32_t), p1), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));})
-#define viwdupq_m(p0,p1,p2,p3,p4) __arm_viwdupq_m(p0,p1,p2,p3,p4)
#define __arm_viwdupq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define viwdupq_u16(p0,p1,p2) __arm_viwdupq_u16(p0,p1,p2)
#define __arm_viwdupq_u16(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u16 (__ARM_mve_coerce(__p0, uint32_t), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
-#define viwdupq_u32(p0,p1,p2) __arm_viwdupq_u32(p0,p1,p2)
#define __arm_viwdupq_u32(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u32 (__ARM_mve_coerce(__p0, uint32_t), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
-#define viwdupq_u8(p0,p1,p2) __arm_viwdupq_u8(p0,p1,p2)
#define __arm_viwdupq_u8(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u8 (__ARM_mve_coerce(__p0, uint32_t), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
-#define vdwdupq_m(p0,p1,p2,p3,p4) __arm_vdwdupq_m(p0,p1,p2,p3,p4)
#define __arm_vdwdupq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));})
-#define vdwdupq_u16(p0,p1,p2) __arm_vdwdupq_u16(p0,p1,p2)
#define __arm_vdwdupq_u16(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u16 (__ARM_mve_coerce(__p0, uint32_t), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
-#define vdwdupq_u32(p0,p1,p2) __arm_vdwdupq_u32(p0,p1,p2)
#define __arm_vdwdupq_u32(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u32 (__ARM_mve_coerce(__p0, uint32_t), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
-#define vdwdupq_u8(p0,p1,p2) __arm_vdwdupq_u8(p0,p1,p2)
#define __arm_vdwdupq_u8(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u8 (__ARM_mve_coerce(__p0, uint32_t), p1, p2), \
int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));})
-#define vshlcq_m(p0,p1,p2,p3) __arm_vshlcq_m(p0,p1,p2,p3)
#define __arm_vshlcq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vshlcq_m_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1, p2, p3), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2, p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2, p3));})
-#define vabavq(p0,p1,p2) __arm_vabavq(p0,p1,p2)
#define __arm_vabavq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_u16 (__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_u32 (__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vabavq_p(p0,p1,p2,p3) __arm_vabavq_p(p0,p1,p2,p3)
#define __arm_vabavq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_p_u16(__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_p_u32(__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vaddlvaq(p0,p1) __arm_vaddlvaq(p0,p1)
#define __arm_vaddlvaq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vaddlvaq_p(p0,p1,p2) __arm_vaddlvaq_p(p0,p1,p2)
#define __arm_vaddlvaq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vaddlvaq_p_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vaddlvaq_p_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vaddlvq(p0) __arm_vaddlvq(p0)
#define __arm_vaddlvq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_s32 (__ARM_mve_coerce(__p0, int32x4_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vaddlvq_p(p0,p1) __arm_vaddlvq_p(p0,p1)
#define __arm_vaddlvq_p(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vaddlvq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddlvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vaddvaq(p0,p1) __arm_vaddvaq(p0,p1)
#define __arm_vaddvaq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vaddvaq_p(p0,p1,p2) __arm_vaddvaq_p(p0,p1,p2)
#define __arm_vaddvaq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vaddvaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vaddvaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vaddvq(p0) __arm_vaddvq(p0)
#define __arm_vaddvq(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vaddvq_s8 (__ARM_mve_coerce(__p0, int8x16_t)), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vaddvq_u16 (__ARM_mve_coerce(__p0, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddvq_u32 (__ARM_mve_coerce(__p0, uint32x4_t)));})
-#define vaddvq_p(p0,p1) __arm_vaddvq_p(p0,p1)
#define __arm_vaddvq_p(p0,p1) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vaddvq_p_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vaddvq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vaddvq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
-#define vcmpcsq(p0,p1) __arm_vcmpcsq(p0,p1)
#define __arm_vcmpcsq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmpcsq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpcsq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-#define vcmpcsq_m(p0,p1,p2) __arm_vcmpcsq_m(p0,p1,p2)
#define __arm_vcmpcsq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmpcsq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmpcsq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t), p2));})
-#define vcmphiq(p0,p1) __arm_vcmphiq(p0,p1)
#define __arm_vcmphiq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vcmphiq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vcmphiq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t)));})
-#define vcmphiq_m(p0,p1,p2) __arm_vcmphiq_m(p0,p1,p2)
#define __arm_vcmphiq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcmphiq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vcmphiq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmaxavq(p0,p1) __arm_vmaxavq(p0,p1)
#define __arm_vmaxavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vmaxavq_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vmaxavq_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vmaxavq_p(p0,p1,p2) __arm_vmaxavq_p(p0,p1,p2)
#define __arm_vmaxavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vmaxavq_p_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vmaxavq_p_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmaxq_x(p1,p2,p3) __arm_vmaxq_x(p1,p2,p3)
#define __arm_vmaxq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmaxq_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmaxq_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmaxvq(p0,p1) __arm_vmaxvq(p0,p1)
#define __arm_vmaxvq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vmaxvq_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vmaxvq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vmaxvq_p(p0,p1,p2) __arm_vmaxvq_p(p0,p1,p2)
#define __arm_vmaxvq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vmaxvq_p_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vmaxvq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vminavq(p0,p1) __arm_vminavq(p0,p1)
#define __arm_vminavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vminavq_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vminavq_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vminavq_p(p0,p1,p2) __arm_vminavq_p(p0,p1,p2)
#define __arm_vminavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vminavq_p_s16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vminavq_p_s32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vminq_x(p1,p2,p3) __arm_vminq_x(p1,p2,p3)
#define __arm_vminq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vminq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vminq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vminvq(p0,p1) __arm_vminvq(p0,p1)
#define __arm_vminvq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vminvq_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vminvq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vminvq_p(p0,p1,p2) __arm_vminvq_p(p0,p1,p2)
#define __arm_vminvq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vminvq_p_u16 (__ARM_mve_coerce(__p0, uint16_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vminvq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmladavaq(p0,p1,p2) __arm_vmladavaq(p0,p1,p2)
#define __arm_vmladavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vmladavaq_p(p0,p1,p2,p3) __arm_vmladavaq_p(p0,p1,p2,p3)
#define __arm_vmladavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaq_p_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaq_p_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmladavaxq(p0,p1,p2) __arm_vmladavaxq(p0,p1,p2)
#define __arm_vmladavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavaxq_u16 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavaxq_u32 (__ARM_mve_coerce(__p0, uint32_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vmladavq(p0,p1) __arm_vmladavq(p0,p1)
#define __arm_vmladavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vmladavq_p(p0,p1,p2) __arm_vmladavq_p(p0,p1,p2)
#define __arm_vmladavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmladavxq(p0,p1) __arm_vmladavxq(p0,p1)
#define __arm_vmladavxq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmladavxq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmladavxq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vmladavxq_p(p0,p1,p2) __arm_vmladavxq_p(p0,p1,p2)
#define __arm_vmladavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmladavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmladavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlaldavaq(p0,p1,p2) __arm_vmlaldavaq(p0,p1,p2)
#define __arm_vmlaldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavaq_u16 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vmlaldavaxq(p0,p1,p2) __arm_vmlaldavaxq(p0,p1,p2)
#define __arm_vmlaldavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavaxq_s16 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavaxq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vmlaldavq(p0,p1) __arm_vmlaldavq(p0,p1)
#define __arm_vmlaldavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vmlaldavq_p(p0,p1,p2) __arm_vmlaldavq_p(p0,p1,p2)
#define __arm_vmlaldavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmlaldavq_p_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmlaldavq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vmlaldavxq_p(p0,p1,p2) __arm_vmlaldavxq_p(p0,p1,p2)
#define __arm_vmlaldavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlaldavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlaldavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlsdavaq(p0,p1,p2) __arm_vmlsdavaq(p0,p1,p2)
#define __arm_vmlsdavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vmlsdavaxq(p0,p1,p2) __arm_vmlsdavaxq(p0,p1,p2)
#define __arm_vmlsdavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavaxq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavaxq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vmlsdavq(p0,p1) __arm_vmlsdavq(p0,p1)
#define __arm_vmlsdavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vmlsdavq_p(p0,p1,p2) __arm_vmlsdavq_p(p0,p1,p2)
#define __arm_vmlsdavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlsdavxq(p0,p1) __arm_vmlsdavxq(p0,p1)
#define __arm_vmlsdavxq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vmlsdavxq_p(p0,p1,p2) __arm_vmlsdavxq_p(p0,p1,p2)
#define __arm_vmlsdavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsdavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsdavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlsldavaq(p0,p1,p2) __arm_vmlsldavaq(p0,p1,p2)
#define __arm_vmlsldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vmlsldavaxq(p0,p1,p2) __arm_vmlsldavaxq(p0,p1,p2)
#define __arm_vmlsldavaxq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavaxq_s16(__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavaxq_s32(__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define vmlsldavq(p0,p1) __arm_vmlsldavq(p0,p1)
#define __arm_vmlsldavq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vmlsldavq_p(p0,p1,p2) __arm_vmlsldavq_p(p0,p1,p2)
#define __arm_vmlsldavq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmlsldavxq(p0,p1) __arm_vmlsldavxq(p0,p1)
#define __arm_vmlsldavxq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)));})
-#define vmlsldavxq_p(p0,p1,p2) __arm_vmlsldavxq_p(p0,p1,p2)
#define __arm_vmlsldavxq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vmlsldavxq_p_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), p2), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vmlsldavxq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2));})
-#define vmovlbq_x(p1,p2) __arm_vmovlbq_x(p1,p2)
#define __arm_vmovlbq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovlbq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovlbq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vmovltq_x(p1,p2) __arm_vmovltq_x(p1,p2)
#define __arm_vmovltq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovltq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8x16_t]: __arm_vmovltq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), p2), \
int (*)[__ARM_mve_type_uint16x8_t]: __arm_vmovltq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2));})
-#define vmulhq_x(p1,p2,p3) __arm_vmulhq_x(p1,p2,p3)
#define __arm_vmulhq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulhq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulhq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmullbq_int_x(p1,p2,p3) __arm_vmullbq_int_x(p1,p2,p3)
#define __arm_vmullbq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmullbq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmullbq_poly_x(p1,p2,p3) __arm_vmullbq_poly_x(p1,p2,p3)
#define __arm_vmullbq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmullbq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmullbq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-#define vmulltq_int_x(p1,p2,p3) __arm_vmulltq_int_x(p1,p2,p3)
#define __arm_vmulltq_int_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_int_x_u16( __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulltq_int_x_u32( __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vmulltq_poly_x(p1,p2,p3) __arm_vmulltq_poly_x(p1,p2,p3)
#define __arm_vmulltq_poly_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vmulltq_poly_x_p8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulltq_poly_x_p16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3));})
-#define vrmlaldavhaq(p0,p1,p2) __arm_vrmlaldavhaq(p0,p1,p2)
#define __arm_vrmlaldavhaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhaq_s32 (__ARM_mve_coerce(__p0, int64_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhaq_u32 (__ARM_mve_coerce(__p0, uint64_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vrmlaldavhaxq(p0,p1,p2) __arm_vrmlaldavhaxq(p0,p1,p2)
#define __arm_vrmlaldavhaxq(p0,p1,p2) __arm_vrmlaldavhaxq_s32(p0,p1,p2)
-#define vrmlaldavhq(p0,p1) __arm_vrmlaldavhq(p0,p1)
#define __arm_vrmlaldavhq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vrmlaldavhq_p(p0,p1,p2) __arm_vrmlaldavhq_p(p0,p1,p2)
#define __arm_vrmlaldavhq_p(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vrmlaldavhq_p_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vrmlaldavhq_p_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq(p0,p1)
#define __arm_vrmlaldavhxq(p0,p1) __arm_vrmlaldavhxq_s32(p0,p1)
-#define vrmlaldavhxq_p(p0,p1,p2) __arm_vrmlaldavhxq_p(p0,p1,p2)
#define __arm_vrmlaldavhxq_p(p0,p1,p2) __arm_vrmlaldavhxq_p_s32(p0,p1,p2)
-#define vrmlsldavhaq(p0,p1,p2) __arm_vrmlsldavhaq(p0,p1,p2)
#define __arm_vrmlsldavhaq(p0,p1,p2) __arm_vrmlsldavhaq_s32(p0,p1,p2)
-#define vrmlsldavhaxq(p0,p1,p2) __arm_vrmlsldavhaxq(p0,p1,p2)
#define __arm_vrmlsldavhaxq(p0,p1,p2) __arm_vrmlsldavhaxq_s32(p0,p1,p2)
-#define vrmlsldavhq(p0,p1) __arm_vrmlsldavhq(p0,p1)
#define __arm_vrmlsldavhq(p0,p1) __arm_vrmlsldavhq_s32(p0,p1)
-#define vrmlsldavhq_p(p0,p1,p2) __arm_vrmlsldavhq_p(p0,p1,p2)
#define __arm_vrmlsldavhq_p(p0,p1,p2) __arm_vrmlsldavhq_p_s32(p0,p1,p2)
-#define vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq(p0,p1)
#define __arm_vrmlsldavhxq(p0,p1) __arm_vrmlsldavhxq_s32(p0,p1)
-#define vrmlsldavhxq_p(p0,p1,p2) __arm_vrmlsldavhxq_p(p0,p1,p2)
#define __arm_vrmlsldavhxq_p(p0,p1,p2) __arm_vrmlsldavhxq_p_s32(p0,p1,p2)
-#define vstrbq(p0,p1) __arm_vstrbq(p0,p1)
#define __arm_vstrbq(p0,p1) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
-#define vstrbq_p(p0,p1,p2) __arm_vstrbq_p(p0,p1,p2)
#define __arm_vstrbq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \
int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_p_u16 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_p_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
-#define vstrbq_scatter_offset(p0,p1,p2) __arm_vstrbq_scatter_offset(p0,p1,p2)
#define __arm_vstrbq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
-#define vstrbq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrbq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrbq_scatter_offset_p(p0,p1,p2,p3) ({__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));})
-#define vstrdq_scatter_base(p0,p1,p2) __arm_vstrdq_scatter_base(p0,p1,p2)
#define __arm_vstrdq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t)), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
-#define vstrdq_scatter_base_p(p0,p1,p2,p3) __arm_vstrdq_scatter_base_p(p0,p1,p2,p3)
#define __arm_vstrdq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_base_p_s64 (p0, p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_p_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
-#define vstrdq_scatter_offset(p0,p1,p2) __arm_vstrdq_scatter_offset(p0,p1,p2)
#define __arm_vstrdq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_s64 (__ARM_mve_coerce(p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t)), \
int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_u64 (__ARM_mve_coerce(p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
-#define vstrdq_scatter_offset_p(p0,p1,p2,p3) __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3)
#define __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_p_s64 (__ARM_mve_coerce(p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_p_u64 (__ARM_mve_coerce(p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
-#define vstrdq_scatter_shifted_offset(p0,p1,p2) __arm_vstrdq_scatter_shifted_offset(p0,p1,p2)
#define __arm_vstrdq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_s64 (__ARM_mve_coerce(p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t)), \
int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_u64 (__ARM_mve_coerce(p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t)));})
-#define vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3)
#define __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
_Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \
int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_s64 (__ARM_mve_coerce(p0, int64_t *), __p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \
int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_u64 (__ARM_mve_coerce(p0, uint64_t *), __p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));})
-#ifdef __cplusplus
-}
-#endif
-
+#endif /* __cplusplus */
#endif /* __ARM_FEATURE_MVE */
#endif /* _GCC_ARM_MVE_H. */
projects / gcc.git / commitdiff