diff options
Diffstat (limited to 'lib/gcc')
25 files changed, 0 insertions, 27943 deletions
diff --git a/lib/gcc/aarch64-linux-android/4.8/crtbegin.o b/lib/gcc/aarch64-linux-android/4.8/crtbegin.o Binary files differdeleted file mode 100644 index a884c9b..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/crtbegin.o +++ /dev/null diff --git a/lib/gcc/aarch64-linux-android/4.8/crtbeginS.o b/lib/gcc/aarch64-linux-android/4.8/crtbeginS.o Binary files differdeleted file mode 100644 index c94901e..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/crtbeginS.o +++ /dev/null diff --git a/lib/gcc/aarch64-linux-android/4.8/crtbeginT.o b/lib/gcc/aarch64-linux-android/4.8/crtbeginT.o Binary files differdeleted file mode 100644 index a884c9b..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/crtbeginT.o +++ /dev/null diff --git a/lib/gcc/aarch64-linux-android/4.8/crtend.o b/lib/gcc/aarch64-linux-android/4.8/crtend.o Binary files differdeleted file mode 100644 index 34754f7..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/crtend.o +++ /dev/null diff --git a/lib/gcc/aarch64-linux-android/4.8/crtendS.o b/lib/gcc/aarch64-linux-android/4.8/crtendS.o Binary files differdeleted file mode 100644 index 34754f7..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/crtendS.o +++ /dev/null diff --git a/lib/gcc/aarch64-linux-android/4.8/include-fixed/README b/lib/gcc/aarch64-linux-android/4.8/include-fixed/README deleted file mode 100644 index 7086a77..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include-fixed/README +++ /dev/null @@ -1,14 +0,0 @@ -This README file is copied into the directory for GCC-only header files -when fixincludes is run by the makefile for GCC. - -Many of the files in this directory were automatically edited from the -standard system header files by the fixincludes process. They are -system-specific, and will not work on any other kind of system. They -are also not part of GCC. The reason we have to do this is because -GCC requires ANSI C headers and many vendors supply ANSI-incompatible -headers. - -Because this is an automated process, sometimes headers get "fixed" -that do not, strictly speaking, need a fix. As long as nothing is broken -by the process, it is just an unfortunate collateral inconvenience. -We would like to rectify it, if it is not "too inconvenient". diff --git a/lib/gcc/aarch64-linux-android/4.8/include-fixed/limits.h b/lib/gcc/aarch64-linux-android/4.8/include-fixed/limits.h deleted file mode 100644 index 9640a88..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include-fixed/limits.h +++ /dev/null @@ -1,171 +0,0 @@ -/* Copyright (C) 1992-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify it under -the terms of the GNU General Public License as published by the Free -Software Foundation; either version 3, or (at your option) any later -version. - -GCC is distributed in the hope that it will be useful, but WITHOUT ANY -WARRANTY; without even the implied warranty of MERCHANTABILITY or -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License -for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* This administrivia gets added to the beginning of limits.h - if the system has its own version of limits.h. */ - -/* We use _GCC_LIMITS_H_ because we want this not to match - any macros that the system's limits.h uses for its own purposes. */ -#ifndef _GCC_LIMITS_H_ /* Terminated in limity.h. */ -#define _GCC_LIMITS_H_ - -#ifndef _LIBC_LIMITS_H_ -/* Use "..." so that we find syslimits.h only in this same directory. */ -#include "syslimits.h" -#endif -/* Copyright (C) 1991-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify it under -the terms of the GNU General Public License as published by the Free -Software Foundation; either version 3, or (at your option) any later -version. - -GCC is distributed in the hope that it will be useful, but WITHOUT ANY -WARRANTY; without even the implied warranty of MERCHANTABILITY or -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License -for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -#ifndef _LIMITS_H___ -#define _LIMITS_H___ - -/* Number of bits in a `char'. */ -#undef CHAR_BIT -#define CHAR_BIT __CHAR_BIT__ - -/* Maximum length of a multibyte character. */ -#ifndef MB_LEN_MAX -#define MB_LEN_MAX 1 -#endif - -/* Minimum and maximum values a `signed char' can hold. */ -#undef SCHAR_MIN -#define SCHAR_MIN (-SCHAR_MAX - 1) -#undef SCHAR_MAX -#define SCHAR_MAX __SCHAR_MAX__ - -/* Maximum value an `unsigned char' can hold. (Minimum is 0). */ -#undef UCHAR_MAX -#if __SCHAR_MAX__ == __INT_MAX__ -# define UCHAR_MAX (SCHAR_MAX * 2U + 1U) -#else -# define UCHAR_MAX (SCHAR_MAX * 2 + 1) -#endif - -/* Minimum and maximum values a `char' can hold. */ -#ifdef __CHAR_UNSIGNED__ -# undef CHAR_MIN -# if __SCHAR_MAX__ == __INT_MAX__ -# define CHAR_MIN 0U -# else -# define CHAR_MIN 0 -# endif -# undef CHAR_MAX -# define CHAR_MAX UCHAR_MAX -#else -# undef CHAR_MIN -# define CHAR_MIN SCHAR_MIN -# undef CHAR_MAX -# define CHAR_MAX SCHAR_MAX -#endif - -/* Minimum and maximum values a `signed short int' can hold. */ -#undef SHRT_MIN -#define SHRT_MIN (-SHRT_MAX - 1) -#undef SHRT_MAX -#define SHRT_MAX __SHRT_MAX__ - -/* Maximum value an `unsigned short int' can hold. (Minimum is 0). */ -#undef USHRT_MAX -#if __SHRT_MAX__ == __INT_MAX__ -# define USHRT_MAX (SHRT_MAX * 2U + 1U) -#else -# define USHRT_MAX (SHRT_MAX * 2 + 1) -#endif - -/* Minimum and maximum values a `signed int' can hold. */ -#undef INT_MIN -#define INT_MIN (-INT_MAX - 1) -#undef INT_MAX -#define INT_MAX __INT_MAX__ - -/* Maximum value an `unsigned int' can hold. (Minimum is 0). */ -#undef UINT_MAX -#define UINT_MAX (INT_MAX * 2U + 1U) - -/* Minimum and maximum values a `signed long int' can hold. - (Same as `int'). */ -#undef LONG_MIN -#define LONG_MIN (-LONG_MAX - 1L) -#undef LONG_MAX -#define LONG_MAX __LONG_MAX__ - -/* Maximum value an `unsigned long int' can hold. (Minimum is 0). */ -#undef ULONG_MAX -#define ULONG_MAX (LONG_MAX * 2UL + 1UL) - -#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L -/* Minimum and maximum values a `signed long long int' can hold. */ -# undef LLONG_MIN -# define LLONG_MIN (-LLONG_MAX - 1LL) -# undef LLONG_MAX -# define LLONG_MAX __LONG_LONG_MAX__ - -/* Maximum value an `unsigned long long int' can hold. (Minimum is 0). */ -# undef ULLONG_MAX -# define ULLONG_MAX (LLONG_MAX * 2ULL + 1ULL) -#endif - -#if defined (__GNU_LIBRARY__) ? defined (__USE_GNU) : !defined (__STRICT_ANSI__) -/* Minimum and maximum values a `signed long long int' can hold. */ -# undef LONG_LONG_MIN -# define LONG_LONG_MIN (-LONG_LONG_MAX - 1LL) -# undef LONG_LONG_MAX -# define LONG_LONG_MAX __LONG_LONG_MAX__ - -/* Maximum value an `unsigned long long int' can hold. (Minimum is 0). */ -# undef ULONG_LONG_MAX -# define ULONG_LONG_MAX (LONG_LONG_MAX * 2ULL + 1ULL) -#endif - -#endif /* _LIMITS_H___ */ -/* This administrivia gets added to the end of limits.h - if the system has its own version of limits.h. */ - -#else /* not _GCC_LIMITS_H_ */ - -#ifdef _GCC_NEXT_LIMITS_H -#include_next <limits.h> /* recurse down to the real one */ -#endif - -#endif /* not _GCC_LIMITS_H_ */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include-fixed/stdio.h b/lib/gcc/aarch64-linux-android/4.8/include-fixed/stdio.h deleted file mode 100644 index a5c846e..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include-fixed/stdio.h +++ /dev/null @@ -1,477 +0,0 @@ -/* DO NOT EDIT THIS FILE. - - It has been auto-edited by fixincludes from: - - "/tmp/toolchain-build-aarch64-linux-4.8/prefix/sysroot/usr/include/stdio.h" - - This had to be done to correct non-standard usages in the - original, manufacturer supplied header file. */ - -/* $OpenBSD: stdio.h,v 1.35 2006/01/13 18:10:09 miod Exp $ */ -/* $NetBSD: stdio.h,v 1.18 1996/04/25 18:29:21 jtc Exp $ */ - -/*- - * Copyright (c) 1990 The Regents of the University of California. - * All rights reserved. - * - * This code is derived from software contributed to Berkeley by - * Chris Torek. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the University nor the names of its contributors - * may be used to endorse or promote products derived from this software - * without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND - * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL - * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS - * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - * - * @(#)stdio.h 5.17 (Berkeley) 6/3/91 - */ - -#ifndef _STDIO_H_ -#define _STDIO_H_ - -#include <sys/cdefs.h> -#include <sys/types.h> - -#include <stdarg.h> -#include <stddef.h> - -#define __need_NULL -#include <stddef.h> - -#define _FSTDIO /* Define for new stdio with functions. */ - -typedef off_t fpos_t; /* stdio file position type */ - -/* - * NB: to fit things in six character monocase externals, the stdio - * code uses the prefix `__s' for stdio objects, typically followed - * by a three-character attempt at a mnemonic. - */ - -/* stdio buffers */ -struct __sbuf { - unsigned char *_base; - int _size; -}; - -/* - * stdio state variables. - * - * The following always hold: - * - * if (_flags&(__SLBF|__SWR)) == (__SLBF|__SWR), - * _lbfsize is -_bf._size, else _lbfsize is 0 - * if _flags&__SRD, _w is 0 - * if _flags&__SWR, _r is 0 - * - * This ensures that the getc and putc macros (or inline functions) never - * try to write or read from a file that is in `read' or `write' mode. - * (Moreover, they can, and do, automatically switch from read mode to - * write mode, and back, on "r+" and "w+" files.) - * - * _lbfsize is used only to make the inline line-buffered output stream - * code as compact as possible. - * - * _ub, _up, and _ur are used when ungetc() pushes back more characters - * than fit in the current _bf, or when ungetc() pushes back a character - * that does not match the previous one in _bf. When this happens, - * _ub._base becomes non-nil (i.e., a stream has ungetc() data iff - * _ub._base!=NULL) and _up and _ur save the current values of _p and _r. - * - * NOTE: if you change this structure, you also need to update the - * std() initializer in findfp.c. - */ -typedef struct __sFILE { - unsigned char *_p; /* current position in (some) buffer */ - int _r; /* read space left for getc() */ - int _w; /* write space left for putc() */ - short _flags; /* flags, below; this FILE is free if 0 */ - short _file; /* fileno, if Unix descriptor, else -1 */ - struct __sbuf _bf; /* the buffer (at least 1 byte, if !NULL) */ - int _lbfsize; /* 0 or -_bf._size, for inline putc */ - - /* operations */ - void *_cookie; /* cookie passed to io functions */ - int (*_close)(void *); - int (*_read)(void *, char *, int); - fpos_t (*_seek)(void *, fpos_t, int); - int (*_write)(void *, const char *, int); - - /* extension data, to avoid further ABI breakage */ - struct __sbuf _ext; - /* data for long sequences of ungetc() */ - unsigned char *_up; /* saved _p when _p is doing ungetc data */ - int _ur; /* saved _r when _r is counting ungetc data */ - - /* tricks to meet minimum requirements even when malloc() fails */ - unsigned char _ubuf[3]; /* guarantee an ungetc() buffer */ - unsigned char _nbuf[1]; /* guarantee a getc() buffer */ - - /* separate buffer for fgetln() when line crosses buffer boundary */ - struct __sbuf _lb; /* buffer for fgetln() */ - - /* Unix stdio files get aligned to block boundaries on fseek() */ - int _blksize; /* stat.st_blksize (may be != _bf._size) */ - fpos_t _offset; /* current lseek offset */ -} FILE; - -__BEGIN_DECLS -extern FILE __sF[]; -__END_DECLS - -#define __SLBF 0x0001 /* line buffered */ -#define __SNBF 0x0002 /* unbuffered */ -#define __SRD 0x0004 /* OK to read */ -#define __SWR 0x0008 /* OK to write */ - /* RD and WR are never simultaneously asserted */ -#define __SRW 0x0010 /* open for reading & writing */ -#define __SEOF 0x0020 /* found EOF */ -#define __SERR 0x0040 /* found error */ -#define __SMBF 0x0080 /* _buf is from malloc */ -#define __SAPP 0x0100 /* fdopen()ed in append mode */ -#define __SSTR 0x0200 /* this is an sprintf/snprintf string */ -#define __SOPT 0x0400 /* do fseek() optimization */ -#define __SNPT 0x0800 /* do not do fseek() optimization */ -#define __SOFF 0x1000 /* set iff _offset is in fact correct */ -#define __SMOD 0x2000 /* true => fgetln modified _p text */ -#define __SALC 0x4000 /* allocate string space dynamically */ -#define __SIGN 0x8000 /* ignore this file in _fwalk */ - -/* - * The following three definitions are for ANSI C, which took them - * from System V, which brilliantly took internal interface macros and - * made them official arguments to setvbuf(), without renaming them. - * Hence, these ugly _IOxxx names are *supposed* to appear in user code. - * - * Although numbered as their counterparts above, the implementation - * does not rely on this. - */ -#define _IOFBF 0 /* setvbuf should set fully buffered */ -#define _IOLBF 1 /* setvbuf should set line buffered */ -#define _IONBF 2 /* setvbuf should set unbuffered */ - -#define BUFSIZ 1024 /* size of buffer used by setbuf */ -#define EOF (-1) - -/* - * FOPEN_MAX is a minimum maximum, and is the number of streams that - * stdio can provide without attempting to allocate further resources - * (which could fail). Do not use this for anything. - */ - -#define FOPEN_MAX 20 /* must be <= OPEN_MAX <sys/syslimits.h> */ -#define FILENAME_MAX 1024 /* must be <= PATH_MAX <sys/syslimits.h> */ - -/* System V/ANSI C; this is the wrong way to do this, do *not* use these. */ -#if __BSD_VISIBLE || __XPG_VISIBLE -#define P_tmpdir "/tmp/" -#endif -#define L_tmpnam 1024 /* XXX must be == PATH_MAX */ -#define TMP_MAX 308915776 - -/* Always ensure that these are consistent with <fcntl.h> and <unistd.h>! */ -#ifndef SEEK_SET -#define SEEK_SET 0 /* set file offset to offset */ -#endif -#ifndef SEEK_CUR -#define SEEK_CUR 1 /* set file offset to current plus offset */ -#endif -#ifndef SEEK_END -#define SEEK_END 2 /* set file offset to EOF plus offset */ -#endif - -#define stdin (&__sF[0]) -#define stdout (&__sF[1]) -#define stderr (&__sF[2]) - -/* - * Functions defined in ANSI C standard. - */ -__BEGIN_DECLS -void clearerr(FILE *); -int fclose(FILE *); -int feof(FILE *); -int ferror(FILE *); -int fflush(FILE *); -int fgetc(FILE *); -char *fgets(char * __restrict, int, FILE * __restrict); -FILE *fopen(const char * __restrict , const char * __restrict); -int fprintf(FILE * __restrict , const char * __restrict, ...) - __printflike(2, 3); -int fputc(int, FILE *); -int fputs(const char * __restrict, FILE * __restrict); -size_t fread(void * __restrict, size_t, size_t, FILE * __restrict); -FILE *freopen(const char * __restrict, const char * __restrict, - FILE * __restrict); -int fscanf(FILE * __restrict, const char * __restrict, ...) - __scanflike(2, 3); -int fseek(FILE *, long, int); -long ftell(FILE *); -size_t fwrite(const void * __restrict, size_t, size_t, FILE * __restrict); -int getc(FILE *); -int getchar(void); -ssize_t getdelim(char ** __restrict, size_t * __restrict, int, - FILE * __restrict); -ssize_t getline(char ** __restrict, size_t * __restrict, FILE * __restrict); - -#if __BSD_VISIBLE && !defined(__SYS_ERRLIST) -#define __SYS_ERRLIST -extern int sys_nerr; /* perror(3) external variables */ -extern char *sys_errlist[]; -#endif - -void perror(const char *); -int printf(const char * __restrict, ...) - __printflike(1, 2); -int putc(int, FILE *); -int putchar(int); -int puts(const char *); -int remove(const char *); -void rewind(FILE *); -int scanf(const char * __restrict, ...) - __scanflike(1, 2); -void setbuf(FILE * __restrict, char * __restrict); -int setvbuf(FILE * __restrict, char * __restrict, int, size_t); -int sscanf(const char * __restrict, const char * __restrict, ...) - __scanflike(2, 3); -FILE *tmpfile(void); -int ungetc(int, FILE *); -int vfprintf(FILE * __restrict, const char * __restrict, __gnuc_va_list) - __printflike(2, 0); -int vprintf(const char * __restrict, __gnuc_va_list) - __printflike(1, 0); - -#ifndef __AUDIT__ -char* gets(char*) __warnattr("gets is very unsafe; consider using fgets"); -int sprintf(char* __restrict, const char* __restrict, ...) - __printflike(2, 3); //__warnattr("sprintf is often misused; please use snprintf"); -char* tmpnam(char*) __warnattr("tmpnam possibly used unsafely; consider using mkstemp"); -int vsprintf(char* __restrict, const char* __restrict, __gnuc_va_list) - __printflike(2, 0); //__warnattr("vsprintf is often misused; please use vsnprintf"); -#if __XPG_VISIBLE -char* tempnam(const char*, const char*) - __warnattr("tempnam possibly used unsafely; consider using mkstemp"); -#endif -#endif - -extern int rename(const char*, const char*); -extern int renameat(int, const char*, int, const char*); - -int fgetpos(FILE * __restrict, fpos_t * __restrict); -int fsetpos(FILE *, const fpos_t *); - -int fseeko(FILE *, off_t, int); -off_t ftello(FILE *); - -#if __ISO_C_VISIBLE >= 1999 || __BSD_VISIBLE -int snprintf(char * __restrict, size_t, const char * __restrict, ...) - __printflike(3, 4); -int vfscanf(FILE * __restrict, const char * __restrict, __gnuc_va_list) - __scanflike(2, 0); -int vscanf(const char *, __gnuc_va_list) - __scanflike(1, 0); -int vsnprintf(char * __restrict, size_t, const char * __restrict, __gnuc_va_list) - __printflike(3, 0); -int vsscanf(const char * __restrict, const char * __restrict, __gnuc_va_list) - __scanflike(2, 0); -#endif /* __ISO_C_VISIBLE >= 1999 || __BSD_VISIBLE */ - -__END_DECLS - - -/* - * Functions defined in POSIX 1003.1. - */ -#if __BSD_VISIBLE || __POSIX_VISIBLE || __XPG_VISIBLE -#define L_ctermid 1024 /* size for ctermid(); PATH_MAX */ -#define L_cuserid 9 /* size for cuserid(); UT_NAMESIZE + 1 */ - -__BEGIN_DECLS -#if 0 /* MISSING FROM BIONIC */ -char *ctermid(char *); -char *cuserid(char *); -#endif /* MISSING */ -FILE *fdopen(int, const char *); -int fileno(FILE *); - -#if (__POSIX_VISIBLE >= 199209) -int pclose(FILE *); -FILE *popen(const char *, const char *); -#endif - -#if __POSIX_VISIBLE >= 199506 -void flockfile(FILE *); -int ftrylockfile(FILE *); -void funlockfile(FILE *); - -/* - * These are normally used through macros as defined below, but POSIX - * requires functions as well. - */ -int getc_unlocked(FILE *); -int getchar_unlocked(void); -int putc_unlocked(int, FILE *); -int putchar_unlocked(int); -#endif /* __POSIX_VISIBLE >= 199506 */ - -__END_DECLS - -#endif /* __BSD_VISIBLE || __POSIX_VISIBLE || __XPG_VISIBLE */ - -/* - * Routines that are purely local. - */ -#if __BSD_VISIBLE -__BEGIN_DECLS -int asprintf(char ** __restrict, const char * __restrict, ...) - __printflike(2, 3); -char *fgetln(FILE * __restrict, size_t * __restrict); -int fpurge(FILE *); -int getw(FILE *); -int putw(int, FILE *); -void setbuffer(FILE *, char *, int); -int setlinebuf(FILE *); -int vasprintf(char ** __restrict, const char * __restrict, - __gnuc_va_list) - __printflike(2, 0); -__END_DECLS - -/* - * Stdio function-access interface. - */ -__BEGIN_DECLS -FILE *funopen(const void *, - int (*)(void *, char *, int), - int (*)(void *, const char *, int), - fpos_t (*)(void *, fpos_t, int), - int (*)(void *)); -__END_DECLS -#define fropen(cookie, fn) funopen(cookie, fn, 0, 0, 0) -#define fwopen(cookie, fn) funopen(cookie, 0, fn, 0, 0) -#endif /* __BSD_VISIBLE */ - -#ifdef _GNU_SOURCE -/* - * glibc defines dprintf(int, const char*, ...), which is poorly named - * and likely to conflict with locally defined debugging printfs - * fdprintf is a better name, and some programs that use fdprintf use a - * #define fdprintf dprintf for compatibility - */ -__BEGIN_DECLS -int fdprintf(int, const char*, ...) - __printflike(2, 3); -int vfdprintf(int, const char*, __gnuc_va_list) - __printflike(2, 0); -__END_DECLS -#endif /* _GNU_SOURCE */ - -#if defined(__BIONIC_FORTIFY) - -__BEGIN_DECLS - -__BIONIC_FORTIFY_INLINE -__printflike(3, 0) -int vsnprintf(char *dest, size_t size, const char *format, __va_list ap) -{ - return __builtin___vsnprintf_chk(dest, size, 0, __bos(dest), format, ap); -} - -__BIONIC_FORTIFY_INLINE -__printflike(2, 0) -int vsprintf(char *dest, const char *format, __va_list ap) -{ - return __builtin___vsprintf_chk(dest, 0, __bos(dest), format, ap); -} - -#if defined(__clang__) - #if !defined(snprintf) - #define __wrap_snprintf(dest, size, ...) __builtin___snprintf_chk(dest, size, 0, __bos(dest), __VA_ARGS__) - #define snprintf(...) __wrap_snprintf(__VA_ARGS__) - #endif -#else -__BIONIC_FORTIFY_INLINE -__printflike(3, 4) -int snprintf(char *dest, size_t size, const char *format, ...) -{ - return __builtin___snprintf_chk(dest, size, 0, - __bos(dest), format, __builtin_va_arg_pack()); -} -#endif - -#if defined(__clang__) - #if !defined(sprintf) - #define __wrap_sprintf(dest, ...) __builtin___sprintf_chk(dest, 0, __bos(dest), __VA_ARGS__) - #define sprintf(...) __wrap_sprintf(__VA_ARGS__) - #endif -#else -__BIONIC_FORTIFY_INLINE -__printflike(2, 3) -int sprintf(char *dest, const char *format, ...) -{ - return __builtin___sprintf_chk(dest, 0, - __bos(dest), format, __builtin_va_arg_pack()); -} -#endif - -extern char* __fgets_chk(char*, int, FILE*, size_t); -extern char* __fgets_real(char*, int, FILE*) __asm__(__USER_LABEL_PREFIX__ "fgets"); -__errordecl(__fgets_too_big_error, "fgets called with size bigger than buffer"); -__errordecl(__fgets_too_small_error, "fgets called with size less than zero"); - -#if !defined(__clang__) - -__BIONIC_FORTIFY_INLINE -char *fgets(char* dest, int size, FILE* stream) { - size_t bos = __bos(dest); - - // Compiler can prove, at compile time, that the passed in size - // is always negative. Force a compiler error. - if (__builtin_constant_p(size) && (size < 0)) { - __fgets_too_small_error(); - } - - // Compiler doesn't know destination size. Don't call __fgets_chk - if (bos == __BIONIC_FORTIFY_UNKNOWN_SIZE) { - return __fgets_real(dest, size, stream); - } - - // Compiler can prove, at compile time, that the passed in size - // is always <= the actual object size. Don't call __fgets_chk - if (__builtin_constant_p(size) && (size <= (int) bos)) { - return __fgets_real(dest, size, stream); - } - - // Compiler can prove, at compile time, that the passed in size - // is always > the actual object size. Force a compiler error. - if (__builtin_constant_p(size) && (size > (int) bos)) { - __fgets_too_big_error(); - } - - return __fgets_chk(dest, size, stream, bos); -} - -#endif /* !defined(__clang__) */ - -__END_DECLS - -#endif /* defined(__BIONIC_FORTIFY) */ - -#endif /* _STDIO_H_ */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include-fixed/syslimits.h b/lib/gcc/aarch64-linux-android/4.8/include-fixed/syslimits.h deleted file mode 100644 index a362802..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include-fixed/syslimits.h +++ /dev/null @@ -1,8 +0,0 @@ -/* syslimits.h stands for the system's own limits.h file. - If we can use it ok unmodified, then we install this text. - If fixincludes fixes it, then the fixed version is installed - instead of this text. */ - -#define _GCC_NEXT_LIMITS_H /* tell gcc's limits.h to recurse */ -#include_next <limits.h> -#undef _GCC_NEXT_LIMITS_H diff --git a/lib/gcc/aarch64-linux-android/4.8/include/arm_neon.h b/lib/gcc/aarch64-linux-android/4.8/include/arm_neon.h deleted file mode 100644 index 2bb42af..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/arm_neon.h +++ /dev/null @@ -1,25374 +0,0 @@ -/* ARM NEON intrinsics include file. - - Copyright (C) 2011-2013 Free Software Foundation, Inc. - Contributed by ARM Ltd. - - This file is part of GCC. - - GCC is free software; you can redistribute it and/or modify it - under the terms of the GNU General Public License as published - by the Free Software Foundation; either version 3, or (at your - option) any later version. - - GCC is distributed in the hope that it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public - License for more details. - - Under Section 7 of GPL version 3, you are granted additional - permissions described in the GCC Runtime Library Exception, version - 3.1, as published by the Free Software Foundation. - - You should have received a copy of the GNU General Public License and - a copy of the GCC Runtime Library Exception along with this program; - see the files COPYING3 and COPYING.RUNTIME respectively. If not, see - <http://www.gnu.org/licenses/>. */ - -#ifndef _AARCH64_NEON_H_ -#define _AARCH64_NEON_H_ - -#include <stdint.h> - -typedef __builtin_aarch64_simd_qi int8x8_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_hi int16x4_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_si int32x2_t - __attribute__ ((__vector_size__ (8))); -typedef int64_t int64x1_t; -typedef int32_t int32x1_t; -typedef int16_t int16x1_t; -typedef int8_t int8x1_t; -typedef double float64x1_t; -typedef __builtin_aarch64_simd_sf float32x2_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_poly8 poly8x8_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_poly16 poly16x4_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_uqi uint8x8_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_uhi uint16x4_t - __attribute__ ((__vector_size__ (8))); -typedef __builtin_aarch64_simd_usi uint32x2_t - __attribute__ ((__vector_size__ (8))); -typedef uint64_t uint64x1_t; -typedef uint32_t uint32x1_t; -typedef uint16_t uint16x1_t; -typedef uint8_t uint8x1_t; -typedef __builtin_aarch64_simd_qi int8x16_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_hi int16x8_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_si int32x4_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_di int64x2_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_sf float32x4_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_df float64x2_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_poly8 poly8x16_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_poly16 poly16x8_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_uqi uint8x16_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_uhi uint16x8_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_usi uint32x4_t - __attribute__ ((__vector_size__ (16))); -typedef __builtin_aarch64_simd_udi uint64x2_t - __attribute__ ((__vector_size__ (16))); - -typedef float float32_t; -typedef double float64_t; -typedef __builtin_aarch64_simd_poly8 poly8_t; -typedef __builtin_aarch64_simd_poly16 poly16_t; - -typedef struct int8x8x2_t -{ - int8x8_t val[2]; -} int8x8x2_t; - -typedef struct int8x16x2_t -{ - int8x16_t val[2]; -} int8x16x2_t; - -typedef struct int16x4x2_t -{ - int16x4_t val[2]; -} int16x4x2_t; - -typedef struct int16x8x2_t -{ - int16x8_t val[2]; -} int16x8x2_t; - -typedef struct int32x2x2_t -{ - int32x2_t val[2]; -} int32x2x2_t; - -typedef struct int32x4x2_t -{ - int32x4_t val[2]; -} int32x4x2_t; - -typedef struct int64x1x2_t -{ - int64x1_t val[2]; -} int64x1x2_t; - -typedef struct int64x2x2_t -{ - int64x2_t val[2]; -} int64x2x2_t; - -typedef struct uint8x8x2_t -{ - uint8x8_t val[2]; -} uint8x8x2_t; - -typedef struct uint8x16x2_t -{ - uint8x16_t val[2]; -} uint8x16x2_t; - -typedef struct uint16x4x2_t -{ - uint16x4_t val[2]; -} uint16x4x2_t; - -typedef struct uint16x8x2_t -{ - uint16x8_t val[2]; -} uint16x8x2_t; - -typedef struct uint32x2x2_t -{ - uint32x2_t val[2]; -} uint32x2x2_t; - -typedef struct uint32x4x2_t -{ - uint32x4_t val[2]; -} uint32x4x2_t; - -typedef struct uint64x1x2_t -{ - uint64x1_t val[2]; -} uint64x1x2_t; - -typedef struct uint64x2x2_t -{ - uint64x2_t val[2]; -} uint64x2x2_t; - -typedef struct float32x2x2_t -{ - float32x2_t val[2]; -} float32x2x2_t; - -typedef struct float32x4x2_t -{ - float32x4_t val[2]; -} float32x4x2_t; - -typedef struct float64x2x2_t -{ - float64x2_t val[2]; -} float64x2x2_t; - -typedef struct float64x1x2_t -{ - float64x1_t val[2]; -} float64x1x2_t; - -typedef struct poly8x8x2_t -{ - poly8x8_t val[2]; -} poly8x8x2_t; - -typedef struct poly8x16x2_t -{ - poly8x16_t val[2]; -} poly8x16x2_t; - -typedef struct poly16x4x2_t -{ - poly16x4_t val[2]; -} poly16x4x2_t; - -typedef struct poly16x8x2_t -{ - poly16x8_t val[2]; -} poly16x8x2_t; - -typedef struct int8x8x3_t -{ - int8x8_t val[3]; -} int8x8x3_t; - -typedef struct int8x16x3_t -{ - int8x16_t val[3]; -} int8x16x3_t; - -typedef struct int16x4x3_t -{ - int16x4_t val[3]; -} int16x4x3_t; - -typedef struct int16x8x3_t -{ - int16x8_t val[3]; -} int16x8x3_t; - -typedef struct int32x2x3_t -{ - int32x2_t val[3]; -} int32x2x3_t; - -typedef struct int32x4x3_t -{ - int32x4_t val[3]; -} int32x4x3_t; - -typedef struct int64x1x3_t -{ - int64x1_t val[3]; -} int64x1x3_t; - -typedef struct int64x2x3_t -{ - int64x2_t val[3]; -} int64x2x3_t; - -typedef struct uint8x8x3_t -{ - uint8x8_t val[3]; -} uint8x8x3_t; - -typedef struct uint8x16x3_t -{ - uint8x16_t val[3]; -} uint8x16x3_t; - -typedef struct uint16x4x3_t -{ - uint16x4_t val[3]; -} uint16x4x3_t; - -typedef struct uint16x8x3_t -{ - uint16x8_t val[3]; -} uint16x8x3_t; - -typedef struct uint32x2x3_t -{ - uint32x2_t val[3]; -} uint32x2x3_t; - -typedef struct uint32x4x3_t -{ - uint32x4_t val[3]; -} uint32x4x3_t; - -typedef struct uint64x1x3_t -{ - uint64x1_t val[3]; -} uint64x1x3_t; - -typedef struct uint64x2x3_t -{ - uint64x2_t val[3]; -} uint64x2x3_t; - -typedef struct float32x2x3_t -{ - float32x2_t val[3]; -} float32x2x3_t; - -typedef struct float32x4x3_t -{ - float32x4_t val[3]; -} float32x4x3_t; - -typedef struct float64x2x3_t -{ - float64x2_t val[3]; -} float64x2x3_t; - -typedef struct float64x1x3_t -{ - float64x1_t val[3]; -} float64x1x3_t; - -typedef struct poly8x8x3_t -{ - poly8x8_t val[3]; -} poly8x8x3_t; - -typedef struct poly8x16x3_t -{ - poly8x16_t val[3]; -} poly8x16x3_t; - -typedef struct poly16x4x3_t -{ - poly16x4_t val[3]; -} poly16x4x3_t; - -typedef struct poly16x8x3_t -{ - poly16x8_t val[3]; -} poly16x8x3_t; - -typedef struct int8x8x4_t -{ - int8x8_t val[4]; -} int8x8x4_t; - -typedef struct int8x16x4_t -{ - int8x16_t val[4]; -} int8x16x4_t; - -typedef struct int16x4x4_t -{ - int16x4_t val[4]; -} int16x4x4_t; - -typedef struct int16x8x4_t -{ - int16x8_t val[4]; -} int16x8x4_t; - -typedef struct int32x2x4_t -{ - int32x2_t val[4]; -} int32x2x4_t; - -typedef struct int32x4x4_t -{ - int32x4_t val[4]; -} int32x4x4_t; - -typedef struct int64x1x4_t -{ - int64x1_t val[4]; -} int64x1x4_t; - -typedef struct int64x2x4_t -{ - int64x2_t val[4]; -} int64x2x4_t; - -typedef struct uint8x8x4_t -{ - uint8x8_t val[4]; -} uint8x8x4_t; - -typedef struct uint8x16x4_t -{ - uint8x16_t val[4]; -} uint8x16x4_t; - -typedef struct uint16x4x4_t -{ - uint16x4_t val[4]; -} uint16x4x4_t; - -typedef struct uint16x8x4_t -{ - uint16x8_t val[4]; -} uint16x8x4_t; - -typedef struct uint32x2x4_t -{ - uint32x2_t val[4]; -} uint32x2x4_t; - -typedef struct uint32x4x4_t -{ - uint32x4_t val[4]; -} uint32x4x4_t; - -typedef struct uint64x1x4_t -{ - uint64x1_t val[4]; -} uint64x1x4_t; - -typedef struct uint64x2x4_t -{ - uint64x2_t val[4]; -} uint64x2x4_t; - -typedef struct float32x2x4_t -{ - float32x2_t val[4]; -} float32x2x4_t; - -typedef struct float32x4x4_t -{ - float32x4_t val[4]; -} float32x4x4_t; - -typedef struct float64x2x4_t -{ - float64x2_t val[4]; -} float64x2x4_t; - -typedef struct float64x1x4_t -{ - float64x1_t val[4]; -} float64x1x4_t; - -typedef struct poly8x8x4_t -{ - poly8x8_t val[4]; -} poly8x8x4_t; - -typedef struct poly8x16x4_t -{ - poly8x16_t val[4]; -} poly8x16x4_t; - -typedef struct poly16x4x4_t -{ - poly16x4_t val[4]; -} poly16x4x4_t; - -typedef struct poly16x8x4_t -{ - poly16x8_t val[4]; -} poly16x8x4_t; - - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vadd_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vadd_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vadd_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a + __b; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vadd_f32 (float32x2_t __a, float32x2_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vadd_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vadd_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vadd_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vadd_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vadd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vaddq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vaddq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vaddq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vaddq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a + __b; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vaddq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __a + __b; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vaddq_f64 (float64x2_t __a, float64x2_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vaddq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vaddq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vaddq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vaddq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a + __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vaddl_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_saddlv8qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vaddl_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_saddlv4hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vaddl_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_saddlv2si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vaddl_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uaddlv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vaddl_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uaddlv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vaddl_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uaddlv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vaddl_high_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int16x8_t) __builtin_aarch64_saddl2v16qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vaddl_high_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int32x4_t) __builtin_aarch64_saddl2v8hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vaddl_high_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int64x2_t) __builtin_aarch64_saddl2v4si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vaddl_high_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uaddl2v16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vaddl_high_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uaddl2v8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vaddl_high_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uaddl2v4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vaddw_s8 (int16x8_t __a, int8x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_saddwv8qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vaddw_s16 (int32x4_t __a, int16x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_saddwv4hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vaddw_s32 (int64x2_t __a, int32x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_saddwv2si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vaddw_u8 (uint16x8_t __a, uint8x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uaddwv8qi ((int16x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vaddw_u16 (uint32x4_t __a, uint16x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uaddwv4hi ((int32x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vaddw_u32 (uint64x2_t __a, uint32x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uaddwv2si ((int64x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vaddw_high_s8 (int16x8_t __a, int8x16_t __b) -{ - return (int16x8_t) __builtin_aarch64_saddw2v16qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vaddw_high_s16 (int32x4_t __a, int16x8_t __b) -{ - return (int32x4_t) __builtin_aarch64_saddw2v8hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vaddw_high_s32 (int64x2_t __a, int32x4_t __b) -{ - return (int64x2_t) __builtin_aarch64_saddw2v4si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vaddw_high_u8 (uint16x8_t __a, uint8x16_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uaddw2v16qi ((int16x8_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vaddw_high_u16 (uint32x4_t __a, uint16x8_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uaddw2v8hi ((int32x4_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vaddw_high_u32 (uint64x2_t __a, uint32x4_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uaddw2v4si ((int64x2_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vhadd_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_shaddv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vhadd_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_shaddv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vhadd_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_shaddv2si (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vhadd_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_uhaddv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vhadd_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_uhaddv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vhadd_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_uhaddv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vhaddq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_shaddv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vhaddq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_shaddv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vhaddq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_shaddv4si (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vhaddq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_uhaddv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vhaddq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uhaddv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vhaddq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uhaddv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrhadd_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_srhaddv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrhadd_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_srhaddv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vrhadd_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_srhaddv2si (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrhadd_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_urhaddv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrhadd_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_urhaddv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrhadd_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_urhaddv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrhaddq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_srhaddv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrhaddq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_srhaddv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vrhaddq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_srhaddv4si (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrhaddq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_urhaddv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrhaddq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_urhaddv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrhaddq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_urhaddv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vaddhn_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_addhnv8hi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vaddhn_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_addhnv4si (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vaddhn_s64 (int64x2_t __a, int64x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_addhnv2di (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vaddhn_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_addhnv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vaddhn_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_addhnv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vaddhn_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_addhnv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vraddhn_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_raddhnv8hi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vraddhn_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_raddhnv4si (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vraddhn_s64 (int64x2_t __a, int64x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_raddhnv2di (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vraddhn_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_raddhnv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vraddhn_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_raddhnv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vraddhn_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_raddhnv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vaddhn_high_s16 (int8x8_t __a, int16x8_t __b, int16x8_t __c) -{ - return (int8x16_t) __builtin_aarch64_addhn2v8hi (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vaddhn_high_s32 (int16x4_t __a, int32x4_t __b, int32x4_t __c) -{ - return (int16x8_t) __builtin_aarch64_addhn2v4si (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vaddhn_high_s64 (int32x2_t __a, int64x2_t __b, int64x2_t __c) -{ - return (int32x4_t) __builtin_aarch64_addhn2v2di (__a, __b, __c); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vaddhn_high_u16 (uint8x8_t __a, uint16x8_t __b, uint16x8_t __c) -{ - return (uint8x16_t) __builtin_aarch64_addhn2v8hi ((int8x8_t) __a, - (int16x8_t) __b, - (int16x8_t) __c); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vaddhn_high_u32 (uint16x4_t __a, uint32x4_t __b, uint32x4_t __c) -{ - return (uint16x8_t) __builtin_aarch64_addhn2v4si ((int16x4_t) __a, - (int32x4_t) __b, - (int32x4_t) __c); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vaddhn_high_u64 (uint32x2_t __a, uint64x2_t __b, uint64x2_t __c) -{ - return (uint32x4_t) __builtin_aarch64_addhn2v2di ((int32x2_t) __a, - (int64x2_t) __b, - (int64x2_t) __c); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vraddhn_high_s16 (int8x8_t __a, int16x8_t __b, int16x8_t __c) -{ - return (int8x16_t) __builtin_aarch64_raddhn2v8hi (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vraddhn_high_s32 (int16x4_t __a, int32x4_t __b, int32x4_t __c) -{ - return (int16x8_t) __builtin_aarch64_raddhn2v4si (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vraddhn_high_s64 (int32x2_t __a, int64x2_t __b, int64x2_t __c) -{ - return (int32x4_t) __builtin_aarch64_raddhn2v2di (__a, __b, __c); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vraddhn_high_u16 (uint8x8_t __a, uint16x8_t __b, uint16x8_t __c) -{ - return (uint8x16_t) __builtin_aarch64_raddhn2v8hi ((int8x8_t) __a, - (int16x8_t) __b, - (int16x8_t) __c); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vraddhn_high_u32 (uint16x4_t __a, uint32x4_t __b, uint32x4_t __c) -{ - return (uint16x8_t) __builtin_aarch64_raddhn2v4si ((int16x4_t) __a, - (int32x4_t) __b, - (int32x4_t) __c); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vraddhn_high_u64 (uint32x2_t __a, uint64x2_t __b, uint64x2_t __c) -{ - return (uint32x4_t) __builtin_aarch64_raddhn2v2di ((int32x2_t) __a, - (int64x2_t) __b, - (int64x2_t) __c); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vdiv_f32 (float32x2_t __a, float32x2_t __b) -{ - return __a / __b; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vdivq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __a / __b; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vdivq_f64 (float64x2_t __a, float64x2_t __b) -{ - return __a / __b; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmul_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a * __b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmul_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a * __b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmul_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a * __b; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmul_f32 (float32x2_t __a, float32x2_t __b) -{ - return __a * __b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmul_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a * __b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmul_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a * __b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmul_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a * __b; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vmul_p8 (poly8x8_t __a, poly8x8_t __b) -{ - return (poly8x8_t) __builtin_aarch64_pmulv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmulq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a * __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmulq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a * __b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmulq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a * __b; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmulq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __a * __b; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmulq_f64 (float64x2_t __a, float64x2_t __b) -{ - return __a * __b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmulq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a * __b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmulq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a * __b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmulq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a * __b; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vmulq_p8 (poly8x16_t __a, poly8x16_t __b) -{ - return (poly8x16_t) __builtin_aarch64_pmulv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vand_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vand_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vand_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vand_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vand_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vand_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vand_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vand_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vandq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vandq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vandq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vandq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vandq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vandq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vandq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a & __b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vandq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a & __b; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vorr_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vorr_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vorr_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vorr_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vorr_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vorr_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vorr_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vorr_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vorrq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vorrq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vorrq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vorrq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vorrq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vorrq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vorrq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a | __b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vorrq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a | __b; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -veor_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -veor_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -veor_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -veor_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -veor_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -veor_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -veor_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -veor_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -veorq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -veorq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -veorq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -veorq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -veorq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -veorq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -veorq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -veorq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a ^ __b; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vbic_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vbic_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vbic_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vbic_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vbic_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vbic_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vbic_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vbic_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vbicq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vbicq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vbicq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vbicq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vbicq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vbicq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vbicq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vbicq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a & ~__b; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vorn_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vorn_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vorn_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vorn_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vorn_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vorn_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vorn_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vorn_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vornq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vornq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vornq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vornq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vornq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vornq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vornq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vornq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a | ~__b; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vsub_s8 (int8x8_t __a, int8x8_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vsub_s16 (int16x4_t __a, int16x4_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vsub_s32 (int32x2_t __a, int32x2_t __b) -{ - return __a - __b; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vsub_f32 (float32x2_t __a, float32x2_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vsub_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vsub_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vsub_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsub_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsub_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vsubq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsubq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsubq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsubq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __a - __b; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vsubq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __a - __b; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vsubq_f64 (float64x2_t __a, float64x2_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vsubq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsubq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsubq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsubq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return __a - __b; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsubl_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_ssublv8qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsubl_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_ssublv4hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsubl_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_ssublv2si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsubl_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_usublv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsubl_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_usublv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsubl_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_usublv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsubl_high_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int16x8_t) __builtin_aarch64_ssubl2v16qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsubl_high_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int32x4_t) __builtin_aarch64_ssubl2v8hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsubl_high_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int64x2_t) __builtin_aarch64_ssubl2v4si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsubl_high_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint16x8_t) __builtin_aarch64_usubl2v16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsubl_high_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint32x4_t) __builtin_aarch64_usubl2v8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsubl_high_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint64x2_t) __builtin_aarch64_usubl2v4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsubw_s8 (int16x8_t __a, int8x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_ssubwv8qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsubw_s16 (int32x4_t __a, int16x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_ssubwv4hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsubw_s32 (int64x2_t __a, int32x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_ssubwv2si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsubw_u8 (uint16x8_t __a, uint8x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_usubwv8qi ((int16x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsubw_u16 (uint32x4_t __a, uint16x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_usubwv4hi ((int32x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsubw_u32 (uint64x2_t __a, uint32x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_usubwv2si ((int64x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsubw_high_s8 (int16x8_t __a, int8x16_t __b) -{ - return (int16x8_t) __builtin_aarch64_ssubw2v16qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsubw_high_s16 (int32x4_t __a, int16x8_t __b) -{ - return (int32x4_t) __builtin_aarch64_ssubw2v8hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsubw_high_s32 (int64x2_t __a, int32x4_t __b) -{ - return (int64x2_t) __builtin_aarch64_ssubw2v4si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsubw_high_u8 (uint16x8_t __a, uint8x16_t __b) -{ - return (uint16x8_t) __builtin_aarch64_usubw2v16qi ((int16x8_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsubw_high_u16 (uint32x4_t __a, uint16x8_t __b) -{ - return (uint32x4_t) __builtin_aarch64_usubw2v8hi ((int32x4_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsubw_high_u32 (uint64x2_t __a, uint32x4_t __b) -{ - return (uint64x2_t) __builtin_aarch64_usubw2v4si ((int64x2_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqadd_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_sqaddv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqadd_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_sqaddv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqadd_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_sqaddv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqadd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sqadddi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqadd_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_uqaddv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqadd_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_uqaddv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqadd_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_uqaddv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqadd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqadddi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqaddq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_sqaddv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqaddq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_sqaddv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqaddq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_sqaddv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqaddq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_sqaddv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqaddq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_uqaddv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqaddq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uqaddv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqaddq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uqaddv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vqaddq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uqaddv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqsub_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_sqsubv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqsub_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_sqsubv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqsub_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_sqsubv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqsub_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sqsubdi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqsub_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_uqsubv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqsub_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_uqsubv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqsub_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_uqsubv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqsub_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqsubdi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqsubq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_sqsubv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqsubq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_sqsubv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqsubq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_sqsubv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqsubq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_sqsubv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqsubq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_uqsubv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqsubq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uqsubv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqsubq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uqsubv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vqsubq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uqsubv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqneg_s8 (int8x8_t __a) -{ - return (int8x8_t) __builtin_aarch64_sqnegv8qi (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqneg_s16 (int16x4_t __a) -{ - return (int16x4_t) __builtin_aarch64_sqnegv4hi (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqneg_s32 (int32x2_t __a) -{ - return (int32x2_t) __builtin_aarch64_sqnegv2si (__a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqnegq_s8 (int8x16_t __a) -{ - return (int8x16_t) __builtin_aarch64_sqnegv16qi (__a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqnegq_s16 (int16x8_t __a) -{ - return (int16x8_t) __builtin_aarch64_sqnegv8hi (__a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqnegq_s32 (int32x4_t __a) -{ - return (int32x4_t) __builtin_aarch64_sqnegv4si (__a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqabs_s8 (int8x8_t __a) -{ - return (int8x8_t) __builtin_aarch64_sqabsv8qi (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqabs_s16 (int16x4_t __a) -{ - return (int16x4_t) __builtin_aarch64_sqabsv4hi (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqabs_s32 (int32x2_t __a) -{ - return (int32x2_t) __builtin_aarch64_sqabsv2si (__a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqabsq_s8 (int8x16_t __a) -{ - return (int8x16_t) __builtin_aarch64_sqabsv16qi (__a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqabsq_s16 (int16x8_t __a) -{ - return (int16x8_t) __builtin_aarch64_sqabsv8hi (__a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqabsq_s32 (int32x4_t __a) -{ - return (int32x4_t) __builtin_aarch64_sqabsv4si (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqdmulh_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_sqdmulhv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqdmulh_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_sqdmulhv2si (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqdmulhq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_sqdmulhv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmulhq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_sqdmulhv4si (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqrdmulh_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_sqrdmulhv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqrdmulh_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_sqrdmulhv2si (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqrdmulhq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_sqrdmulhv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqrdmulhq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_sqrdmulhv4si (__a, __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vcreate_s8 (uint64_t __a) -{ - return (int8x8_t) __a; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vcreate_s16 (uint64_t __a) -{ - return (int16x4_t) __a; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcreate_s32 (uint64_t __a) -{ - return (int32x2_t) __a; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vcreate_s64 (uint64_t __a) -{ - return (int64x1_t) __a; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vcreate_f32 (uint64_t __a) -{ - return (float32x2_t) __a; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcreate_u8 (uint64_t __a) -{ - return (uint8x8_t) __a; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcreate_u16 (uint64_t __a) -{ - return (uint16x4_t) __a; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcreate_u32 (uint64_t __a) -{ - return (uint32x2_t) __a; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcreate_u64 (uint64_t __a) -{ - return (uint64x1_t) __a; -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vcreate_f64 (uint64_t __a) -{ - return (float64x1_t) __builtin_aarch64_createdf (__a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vcreate_p8 (uint64_t __a) -{ - return (poly8x8_t) __a; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vcreate_p16 (uint64_t __a) -{ - return (poly16x4_t) __a; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vget_lane_s8 (int8x8_t __a, const int __b) -{ - return (int8_t) __builtin_aarch64_get_lane_signedv8qi (__a, __b); -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vget_lane_s16 (int16x4_t __a, const int __b) -{ - return (int16_t) __builtin_aarch64_get_lane_signedv4hi (__a, __b); -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vget_lane_s32 (int32x2_t __a, const int __b) -{ - return (int32_t) __builtin_aarch64_get_lane_signedv2si (__a, __b); -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vget_lane_f32 (float32x2_t __a, const int __b) -{ - return (float32_t) __builtin_aarch64_get_lanev2sf (__a, __b); -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vget_lane_u8 (uint8x8_t __a, const int __b) -{ - return (uint8_t) __builtin_aarch64_get_lane_unsignedv8qi ((int8x8_t) __a, - __b); -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vget_lane_u16 (uint16x4_t __a, const int __b) -{ - return (uint16_t) __builtin_aarch64_get_lane_unsignedv4hi ((int16x4_t) __a, - __b); -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vget_lane_u32 (uint32x2_t __a, const int __b) -{ - return (uint32_t) __builtin_aarch64_get_lane_unsignedv2si ((int32x2_t) __a, - __b); -} - -__extension__ static __inline poly8_t __attribute__ ((__always_inline__)) -vget_lane_p8 (poly8x8_t __a, const int __b) -{ - return (poly8_t) __builtin_aarch64_get_lane_unsignedv8qi ((int8x8_t) __a, - __b); -} - -__extension__ static __inline poly16_t __attribute__ ((__always_inline__)) -vget_lane_p16 (poly16x4_t __a, const int __b) -{ - return (poly16_t) __builtin_aarch64_get_lane_unsignedv4hi ((int16x4_t) __a, - __b); -} - -__extension__ static __inline int64_t __attribute__ ((__always_inline__)) -vget_lane_s64 (int64x1_t __a, const int __b) -{ - return (int64_t) __builtin_aarch64_get_lanedi (__a, __b); -} - -__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) -vget_lane_u64 (uint64x1_t __a, const int __b) -{ - return (uint64_t) __builtin_aarch64_get_lanedi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vgetq_lane_s8 (int8x16_t __a, const int __b) -{ - return (int8_t) __builtin_aarch64_get_lane_signedv16qi (__a, __b); -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vgetq_lane_s16 (int16x8_t __a, const int __b) -{ - return (int16_t) __builtin_aarch64_get_lane_signedv8hi (__a, __b); -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vgetq_lane_s32 (int32x4_t __a, const int __b) -{ - return (int32_t) __builtin_aarch64_get_lane_signedv4si (__a, __b); -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vgetq_lane_f32 (float32x4_t __a, const int __b) -{ - return (float32_t) __builtin_aarch64_get_lanev4sf (__a, __b); -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vgetq_lane_f64 (float64x2_t __a, const int __b) -{ - return (float64_t) __builtin_aarch64_get_lanev2df (__a, __b); -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vgetq_lane_u8 (uint8x16_t __a, const int __b) -{ - return (uint8_t) __builtin_aarch64_get_lane_unsignedv16qi ((int8x16_t) __a, - __b); -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vgetq_lane_u16 (uint16x8_t __a, const int __b) -{ - return (uint16_t) __builtin_aarch64_get_lane_unsignedv8hi ((int16x8_t) __a, - __b); -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vgetq_lane_u32 (uint32x4_t __a, const int __b) -{ - return (uint32_t) __builtin_aarch64_get_lane_unsignedv4si ((int32x4_t) __a, - __b); -} - -__extension__ static __inline poly8_t __attribute__ ((__always_inline__)) -vgetq_lane_p8 (poly8x16_t __a, const int __b) -{ - return (poly8_t) __builtin_aarch64_get_lane_unsignedv16qi ((int8x16_t) __a, - __b); -} - -__extension__ static __inline poly16_t __attribute__ ((__always_inline__)) -vgetq_lane_p16 (poly16x8_t __a, const int __b) -{ - return (poly16_t) __builtin_aarch64_get_lane_unsignedv8hi ((int16x8_t) __a, - __b); -} - -__extension__ static __inline int64_t __attribute__ ((__always_inline__)) -vgetq_lane_s64 (int64x2_t __a, const int __b) -{ - return __builtin_aarch64_get_lane_unsignedv2di (__a, __b); -} - -__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) -vgetq_lane_u64 (uint64x2_t __a, const int __b) -{ - return (uint64_t) __builtin_aarch64_get_lane_unsignedv2di ((int64x2_t) __a, - __b); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_s8 (int8x8_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv8qi (__a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_s16 (int16x4_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv4hi (__a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_s32 (int32x2_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv2si (__a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_s64 (int64x1_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qidi (__a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_f32 (float32x2_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv2sf (__a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_u8 (uint8x8_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_u16 (uint16x4_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_u32 (uint32x2_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv2si ((int32x2_t) __a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_u64 (uint64x1_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qidi ((int64x1_t) __a); -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vreinterpret_p8_p16 (poly16x4_t __a) -{ - return (poly8x8_t) __builtin_aarch64_reinterpretv8qiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_s8 (int8x16_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv16qi (__a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_s16 (int16x8_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv8hi (__a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_s32 (int32x4_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv4si (__a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_s64 (int64x2_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv2di (__a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_f32 (float32x4_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv4sf (__a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_u8 (uint8x16_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_u16 (uint16x8_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv8hi ((int16x8_t) - __a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_u32 (uint32x4_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv4si ((int32x4_t) - __a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_u64 (uint64x2_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv2di ((int64x2_t) - __a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_p8_p16 (poly16x8_t __a) -{ - return (poly8x16_t) __builtin_aarch64_reinterpretv16qiv8hi ((int16x8_t) - __a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_s8 (int8x8_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv8qi (__a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_s16 (int16x4_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv4hi (__a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_s32 (int32x2_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv2si (__a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_s64 (int64x1_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hidi (__a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_f32 (float32x2_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv2sf (__a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_u8 (uint8x8_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_u16 (uint16x4_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_u32 (uint32x2_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv2si ((int32x2_t) __a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_u64 (uint64x1_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hidi ((int64x1_t) __a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vreinterpret_p16_p8 (poly8x8_t __a) -{ - return (poly16x4_t) __builtin_aarch64_reinterpretv4hiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_s8 (int8x16_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv16qi (__a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_s16 (int16x8_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv8hi (__a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_s32 (int32x4_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv4si (__a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_s64 (int64x2_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv2di (__a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_f32 (float32x4_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv4sf (__a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_u8 (uint8x16_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_u16 (uint16x8_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv8hi ((int16x8_t) __a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_u32 (uint32x4_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv4si ((int32x4_t) __a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_u64 (uint64x2_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv2di ((int64x2_t) __a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_p16_p8 (poly8x16_t __a) -{ - return (poly16x8_t) __builtin_aarch64_reinterpretv8hiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_s8 (int8x8_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv8qi (__a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_s16 (int16x4_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv4hi (__a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_s32 (int32x2_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv2si (__a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_s64 (int64x1_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfdi (__a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_u8 (uint8x8_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv8qi ((int8x8_t) __a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_u16 (uint16x4_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv4hi ((int16x4_t) - __a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_u32 (uint32x2_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv2si ((int32x2_t) - __a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_u64 (uint64x1_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfdi ((int64x1_t) __a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_p8 (poly8x8_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv8qi ((int8x8_t) __a); -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vreinterpret_f32_p16 (poly16x4_t __a) -{ - return (float32x2_t) __builtin_aarch64_reinterpretv2sfv4hi ((int16x4_t) - __a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_s8 (int8x16_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv16qi (__a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_s16 (int16x8_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv8hi (__a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_s32 (int32x4_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv4si (__a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_s64 (int64x2_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv2di (__a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_u8 (uint8x16_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_u16 (uint16x8_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv8hi ((int16x8_t) - __a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_u32 (uint32x4_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv4si ((int32x4_t) - __a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_u64 (uint64x2_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv2di ((int64x2_t) - __a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_p8 (poly8x16_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_f32_p16 (poly16x8_t __a) -{ - return (float32x4_t) __builtin_aarch64_reinterpretv4sfv8hi ((int16x8_t) - __a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_s8 (int8x8_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv8qi (__a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_s16 (int16x4_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv4hi (__a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_s32 (int32x2_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv2si (__a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_f32 (float32x2_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv2sf (__a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_u8 (uint8x8_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_u16 (uint16x4_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_u32 (uint32x2_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv2si ((int32x2_t) __a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_u64 (uint64x1_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdidi ((int64x1_t) __a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_p8 (poly8x8_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vreinterpret_s64_p16 (poly16x4_t __a) -{ - return (int64x1_t) __builtin_aarch64_reinterpretdiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_s8 (int8x16_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div16qi (__a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_s16 (int16x8_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div8hi (__a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_s32 (int32x4_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div4si (__a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_f32 (float32x4_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div4sf (__a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_u8 (uint8x16_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div16qi ((int8x16_t) __a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_u16 (uint16x8_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div8hi ((int16x8_t) __a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_u32 (uint32x4_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div4si ((int32x4_t) __a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_u64 (uint64x2_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div2di ((int64x2_t) __a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_p8 (poly8x16_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div16qi ((int8x16_t) __a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_s64_p16 (poly16x8_t __a) -{ - return (int64x2_t) __builtin_aarch64_reinterpretv2div8hi ((int16x8_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_s8 (int8x8_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv8qi (__a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_s16 (int16x4_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv4hi (__a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_s32 (int32x2_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv2si (__a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_s64 (int64x1_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdidi (__a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_f32 (float32x2_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv2sf (__a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_u8 (uint8x8_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_u16 (uint16x4_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_u32 (uint32x2_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv2si ((int32x2_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_p8 (poly8x8_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vreinterpret_u64_p16 (poly16x4_t __a) -{ - return (uint64x1_t) __builtin_aarch64_reinterpretdiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_s8 (int8x16_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div16qi (__a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_s16 (int16x8_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div8hi (__a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_s32 (int32x4_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div4si (__a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_s64 (int64x2_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div2di (__a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_f32 (float32x4_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div4sf (__a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_u8 (uint8x16_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_u16 (uint16x8_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div8hi ((int16x8_t) __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_u32 (uint32x4_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div4si ((int32x4_t) __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_p8 (poly8x16_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vreinterpretq_u64_p16 (poly16x8_t __a) -{ - return (uint64x2_t) __builtin_aarch64_reinterpretv2div8hi ((int16x8_t) __a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_s16 (int16x4_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv4hi (__a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_s32 (int32x2_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv2si (__a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_s64 (int64x1_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qidi (__a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_f32 (float32x2_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv2sf (__a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_u8 (uint8x8_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_u16 (uint16x4_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_u32 (uint32x2_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv2si ((int32x2_t) __a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_u64 (uint64x1_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qidi ((int64x1_t) __a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_p8 (poly8x8_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vreinterpret_s8_p16 (poly16x4_t __a) -{ - return (int8x8_t) __builtin_aarch64_reinterpretv8qiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_s16 (int16x8_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv8hi (__a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_s32 (int32x4_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv4si (__a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_s64 (int64x2_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv2di (__a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_f32 (float32x4_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv4sf (__a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_u8 (uint8x16_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_u16 (uint16x8_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv8hi ((int16x8_t) __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_u32 (uint32x4_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv4si ((int32x4_t) __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_u64 (uint64x2_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv2di ((int64x2_t) __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_p8 (poly8x16_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_s8_p16 (poly16x8_t __a) -{ - return (int8x16_t) __builtin_aarch64_reinterpretv16qiv8hi ((int16x8_t) __a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_s8 (int8x8_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv8qi (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_s32 (int32x2_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv2si (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_s64 (int64x1_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hidi (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_f32 (float32x2_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv2sf (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_u8 (uint8x8_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_u16 (uint16x4_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_u32 (uint32x2_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv2si ((int32x2_t) __a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_u64 (uint64x1_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hidi ((int64x1_t) __a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_p8 (poly8x8_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vreinterpret_s16_p16 (poly16x4_t __a) -{ - return (int16x4_t) __builtin_aarch64_reinterpretv4hiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_s8 (int8x16_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv16qi (__a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_s32 (int32x4_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv4si (__a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_s64 (int64x2_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv2di (__a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_f32 (float32x4_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv4sf (__a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_u8 (uint8x16_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv16qi ((int8x16_t) __a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_u16 (uint16x8_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv8hi ((int16x8_t) __a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_u32 (uint32x4_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv4si ((int32x4_t) __a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_u64 (uint64x2_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv2di ((int64x2_t) __a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_p8 (poly8x16_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv16qi ((int8x16_t) __a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_s16_p16 (poly16x8_t __a) -{ - return (int16x8_t) __builtin_aarch64_reinterpretv8hiv8hi ((int16x8_t) __a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_s8 (int8x8_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv8qi (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_s16 (int16x4_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv4hi (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_s64 (int64x1_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2sidi (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_f32 (float32x2_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv2sf (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_u8 (uint8x8_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_u16 (uint16x4_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_u32 (uint32x2_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv2si ((int32x2_t) __a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_u64 (uint64x1_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2sidi ((int64x1_t) __a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_p8 (poly8x8_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv8qi ((int8x8_t) __a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vreinterpret_s32_p16 (poly16x4_t __a) -{ - return (int32x2_t) __builtin_aarch64_reinterpretv2siv4hi ((int16x4_t) __a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_s8 (int8x16_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv16qi (__a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_s16 (int16x8_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv8hi (__a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_s64 (int64x2_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv2di (__a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_f32 (float32x4_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv4sf (__a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_u8 (uint8x16_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv16qi ((int8x16_t) __a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_u16 (uint16x8_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv8hi ((int16x8_t) __a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_u32 (uint32x4_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv4si ((int32x4_t) __a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_u64 (uint64x2_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv2di ((int64x2_t) __a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_p8 (poly8x16_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv16qi ((int8x16_t) __a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_s32_p16 (poly16x8_t __a) -{ - return (int32x4_t) __builtin_aarch64_reinterpretv4siv8hi ((int16x8_t) __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_s8 (int8x8_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv8qi (__a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_s16 (int16x4_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv4hi (__a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_s32 (int32x2_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv2si (__a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_s64 (int64x1_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qidi (__a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_f32 (float32x2_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv2sf (__a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_u16 (uint16x4_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_u32 (uint32x2_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv2si ((int32x2_t) __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_u64 (uint64x1_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qidi ((int64x1_t) __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_p8 (poly8x8_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vreinterpret_u8_p16 (poly16x4_t __a) -{ - return (uint8x8_t) __builtin_aarch64_reinterpretv8qiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_s8 (int8x16_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv16qi (__a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_s16 (int16x8_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv8hi (__a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_s32 (int32x4_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv4si (__a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_s64 (int64x2_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv2di (__a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_f32 (float32x4_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv4sf (__a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_u16 (uint16x8_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv8hi ((int16x8_t) - __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_u32 (uint32x4_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv4si ((int32x4_t) - __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_u64 (uint64x2_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv2di ((int64x2_t) - __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_p8 (poly8x16_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vreinterpretq_u8_p16 (poly16x8_t __a) -{ - return (uint8x16_t) __builtin_aarch64_reinterpretv16qiv8hi ((int16x8_t) - __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_s8 (int8x8_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv8qi (__a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_s16 (int16x4_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv4hi (__a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_s32 (int32x2_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv2si (__a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_s64 (int64x1_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hidi (__a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_f32 (float32x2_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv2sf (__a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_u8 (uint8x8_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_u32 (uint32x2_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv2si ((int32x2_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_u64 (uint64x1_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hidi ((int64x1_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_p8 (poly8x8_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vreinterpret_u16_p16 (poly16x4_t __a) -{ - return (uint16x4_t) __builtin_aarch64_reinterpretv4hiv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_s8 (int8x16_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv16qi (__a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_s16 (int16x8_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv8hi (__a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_s32 (int32x4_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv4si (__a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_s64 (int64x2_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv2di (__a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_f32 (float32x4_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv4sf (__a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_u8 (uint8x16_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_u32 (uint32x4_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv4si ((int32x4_t) __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_u64 (uint64x2_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv2di ((int64x2_t) __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_p8 (poly8x16_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vreinterpretq_u16_p16 (poly16x8_t __a) -{ - return (uint16x8_t) __builtin_aarch64_reinterpretv8hiv8hi ((int16x8_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_s8 (int8x8_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv8qi (__a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_s16 (int16x4_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv4hi (__a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_s32 (int32x2_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv2si (__a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_s64 (int64x1_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2sidi (__a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_f32 (float32x2_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv2sf (__a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_u8 (uint8x8_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_u16 (uint16x4_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_u64 (uint64x1_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2sidi ((int64x1_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_p8 (poly8x8_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv8qi ((int8x8_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vreinterpret_u32_p16 (poly16x4_t __a) -{ - return (uint32x2_t) __builtin_aarch64_reinterpretv2siv4hi ((int16x4_t) __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_s8 (int8x16_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv16qi (__a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_s16 (int16x8_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv8hi (__a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_s32 (int32x4_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv4si (__a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_s64 (int64x2_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv2di (__a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_f32 (float32x4_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv4sf (__a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_u8 (uint8x16_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_u16 (uint16x8_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv8hi ((int16x8_t) __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_u64 (uint64x2_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv2di ((int64x2_t) __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_p8 (poly8x16_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv16qi ((int8x16_t) - __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vreinterpretq_u32_p16 (poly16x8_t __a) -{ - return (uint32x4_t) __builtin_aarch64_reinterpretv4siv8hi ((int16x8_t) __a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vcombine_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x16_t) __builtin_aarch64_combinev8qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vcombine_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x8_t) __builtin_aarch64_combinev4hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vcombine_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x4_t) __builtin_aarch64_combinev2si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vcombine_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x2_t) __builtin_aarch64_combinedi (__a, __b); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vcombine_f32 (float32x2_t __a, float32x2_t __b) -{ - return (float32x4_t) __builtin_aarch64_combinev2sf (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcombine_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x16_t) __builtin_aarch64_combinev8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcombine_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x8_t) __builtin_aarch64_combinev4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcombine_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x4_t) __builtin_aarch64_combinev2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcombine_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x2_t) __builtin_aarch64_combinedi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vcombine_f64 (float64x1_t __a, float64x1_t __b) -{ - return (float64x2_t) __builtin_aarch64_combinedf (__a, __b); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vcombine_p8 (poly8x8_t __a, poly8x8_t __b) -{ - return (poly8x16_t) __builtin_aarch64_combinev8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vcombine_p16 (poly16x4_t __a, poly16x4_t __b) -{ - return (poly16x8_t) __builtin_aarch64_combinev4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -/* Start of temporary inline asm implementations. */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vaba_s8 (int8x8_t a, int8x8_t b, int8x8_t c) -{ - int8x8_t result; - __asm__ ("saba %0.8b,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vaba_s16 (int16x4_t a, int16x4_t b, int16x4_t c) -{ - int16x4_t result; - __asm__ ("saba %0.4h,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vaba_s32 (int32x2_t a, int32x2_t b, int32x2_t c) -{ - int32x2_t result; - __asm__ ("saba %0.2s,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vaba_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint8x8_t result; - __asm__ ("uaba %0.8b,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vaba_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint16x4_t result; - __asm__ ("uaba %0.4h,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vaba_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint32x2_t result; - __asm__ ("uaba %0.2s,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabal_high_s8 (int16x8_t a, int8x16_t b, int8x16_t c) -{ - int16x8_t result; - __asm__ ("sabal2 %0.8h,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabal_high_s16 (int32x4_t a, int16x8_t b, int16x8_t c) -{ - int32x4_t result; - __asm__ ("sabal2 %0.4s,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vabal_high_s32 (int64x2_t a, int32x4_t b, int32x4_t c) -{ - int64x2_t result; - __asm__ ("sabal2 %0.2d,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vabal_high_u8 (uint16x8_t a, uint8x16_t b, uint8x16_t c) -{ - uint16x8_t result; - __asm__ ("uabal2 %0.8h,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vabal_high_u16 (uint32x4_t a, uint16x8_t b, uint16x8_t c) -{ - uint32x4_t result; - __asm__ ("uabal2 %0.4s,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vabal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) -{ - uint64x2_t result; - __asm__ ("uabal2 %0.2d,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabal_s8 (int16x8_t a, int8x8_t b, int8x8_t c) -{ - int16x8_t result; - __asm__ ("sabal %0.8h,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabal_s16 (int32x4_t a, int16x4_t b, int16x4_t c) -{ - int32x4_t result; - __asm__ ("sabal %0.4s,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vabal_s32 (int64x2_t a, int32x2_t b, int32x2_t c) -{ - int64x2_t result; - __asm__ ("sabal %0.2d,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vabal_u8 (uint16x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint16x8_t result; - __asm__ ("uabal %0.8h,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vabal_u16 (uint32x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint32x4_t result; - __asm__ ("uabal %0.4s,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vabal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint64x2_t result; - __asm__ ("uabal %0.2d,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vabaq_s8 (int8x16_t a, int8x16_t b, int8x16_t c) -{ - int8x16_t result; - __asm__ ("saba %0.16b,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabaq_s16 (int16x8_t a, int16x8_t b, int16x8_t c) -{ - int16x8_t result; - __asm__ ("saba %0.8h,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabaq_s32 (int32x4_t a, int32x4_t b, int32x4_t c) -{ - int32x4_t result; - __asm__ ("saba %0.4s,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vabaq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c) -{ - uint8x16_t result; - __asm__ ("uaba %0.16b,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vabaq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c) -{ - uint16x8_t result; - __asm__ ("uaba %0.8h,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vabaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c) -{ - uint32x4_t result; - __asm__ ("uaba %0.4s,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vabd_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fabd %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vabd_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("sabd %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vabd_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("sabd %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vabd_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("sabd %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vabd_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("uabd %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vabd_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("uabd %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vabd_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("uabd %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vabdd_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("fabd %d0, %d1, %d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabdl_high_s8 (int8x16_t a, int8x16_t b) -{ - int16x8_t result; - __asm__ ("sabdl2 %0.8h,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabdl_high_s16 (int16x8_t a, int16x8_t b) -{ - int32x4_t result; - __asm__ ("sabdl2 %0.4s,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vabdl_high_s32 (int32x4_t a, int32x4_t b) -{ - int64x2_t result; - __asm__ ("sabdl2 %0.2d,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vabdl_high_u8 (uint8x16_t a, uint8x16_t b) -{ - uint16x8_t result; - __asm__ ("uabdl2 %0.8h,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vabdl_high_u16 (uint16x8_t a, uint16x8_t b) -{ - uint32x4_t result; - __asm__ ("uabdl2 %0.4s,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vabdl_high_u32 (uint32x4_t a, uint32x4_t b) -{ - uint64x2_t result; - __asm__ ("uabdl2 %0.2d,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabdl_s8 (int8x8_t a, int8x8_t b) -{ - int16x8_t result; - __asm__ ("sabdl %0.8h, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabdl_s16 (int16x4_t a, int16x4_t b) -{ - int32x4_t result; - __asm__ ("sabdl %0.4s, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vabdl_s32 (int32x2_t a, int32x2_t b) -{ - int64x2_t result; - __asm__ ("sabdl %0.2d, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vabdl_u8 (uint8x8_t a, uint8x8_t b) -{ - uint16x8_t result; - __asm__ ("uabdl %0.8h, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vabdl_u16 (uint16x4_t a, uint16x4_t b) -{ - uint32x4_t result; - __asm__ ("uabdl %0.4s, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vabdl_u32 (uint32x2_t a, uint32x2_t b) -{ - uint64x2_t result; - __asm__ ("uabdl %0.2d, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vabdq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fabd %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vabdq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fabd %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vabdq_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("sabd %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabdq_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("sabd %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabdq_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("sabd %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vabdq_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("uabd %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vabdq_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("uabd %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vabdq_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("uabd %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vabds_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("fabd %s0, %s1, %s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vabs_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("fabs %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vabs_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("abs %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vabs_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("abs %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vabs_s32 (int32x2_t a) -{ - int32x2_t result; - __asm__ ("abs %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vabsq_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("fabs %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vabsq_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("fabs %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vabsq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("abs %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vabsq_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("abs %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vabsq_s32 (int32x4_t a) -{ - int32x4_t result; - __asm__ ("abs %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vabsq_s64 (int64x2_t a) -{ - int64x2_t result; - __asm__ ("abs %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vacged_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("facge %d0,%d1,%d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vacges_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("facge %s0,%s1,%s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vacgtd_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("facgt %d0,%d1,%d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vacgts_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("facgt %s0,%s1,%s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vaddlv_s8 (int8x8_t a) -{ - int16_t result; - __asm__ ("saddlv %h0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vaddlv_s16 (int16x4_t a) -{ - int32_t result; - __asm__ ("saddlv %s0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vaddlv_u8 (uint8x8_t a) -{ - uint16_t result; - __asm__ ("uaddlv %h0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vaddlv_u16 (uint16x4_t a) -{ - uint32_t result; - __asm__ ("uaddlv %s0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vaddlvq_s8 (int8x16_t a) -{ - int16_t result; - __asm__ ("saddlv %h0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vaddlvq_s16 (int16x8_t a) -{ - int32_t result; - __asm__ ("saddlv %s0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64_t __attribute__ ((__always_inline__)) -vaddlvq_s32 (int32x4_t a) -{ - int64_t result; - __asm__ ("saddlv %d0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vaddlvq_u8 (uint8x16_t a) -{ - uint16_t result; - __asm__ ("uaddlv %h0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vaddlvq_u16 (uint16x8_t a) -{ - uint32_t result; - __asm__ ("uaddlv %s0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) -vaddlvq_u32 (uint32x4_t a) -{ - uint64_t result; - __asm__ ("uaddlv %d0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vaddv_s8 (int8x8_t a) -{ - int8_t result; - __asm__ ("addv %b0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vaddv_s16 (int16x4_t a) -{ - int16_t result; - __asm__ ("addv %h0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vaddv_u8 (uint8x8_t a) -{ - uint8_t result; - __asm__ ("addv %b0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vaddv_u16 (uint16x4_t a) -{ - uint16_t result; - __asm__ ("addv %h0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vaddvq_s8 (int8x16_t a) -{ - int8_t result; - __asm__ ("addv %b0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vaddvq_s16 (int16x8_t a) -{ - int16_t result; - __asm__ ("addv %h0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vaddvq_s32 (int32x4_t a) -{ - int32_t result; - __asm__ ("addv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vaddvq_u8 (uint8x16_t a) -{ - uint8_t result; - __asm__ ("addv %b0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vaddvq_u16 (uint16x8_t a) -{ - uint16_t result; - __asm__ ("addv %h0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vaddvq_u32 (uint32x4_t a) -{ - uint32_t result; - __asm__ ("addv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vbsl_f32 (uint32x2_t a, float32x2_t b, float32x2_t c) -{ - float32x2_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vbsl_p8 (uint8x8_t a, poly8x8_t b, poly8x8_t c) -{ - poly8x8_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vbsl_p16 (uint16x4_t a, poly16x4_t b, poly16x4_t c) -{ - poly16x4_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vbsl_s8 (uint8x8_t a, int8x8_t b, int8x8_t c) -{ - int8x8_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vbsl_s16 (uint16x4_t a, int16x4_t b, int16x4_t c) -{ - int16x4_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vbsl_s32 (uint32x2_t a, int32x2_t b, int32x2_t c) -{ - int32x2_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vbsl_s64 (uint64x1_t a, int64x1_t b, int64x1_t c) -{ - int64x1_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vbsl_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint8x8_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vbsl_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint16x4_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vbsl_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint32x2_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vbsl_u64 (uint64x1_t a, uint64x1_t b, uint64x1_t c) -{ - uint64x1_t result; - __asm__ ("bsl %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vbslq_f32 (uint32x4_t a, float32x4_t b, float32x4_t c) -{ - float32x4_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vbslq_f64 (uint64x2_t a, float64x2_t b, float64x2_t c) -{ - float64x2_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vbslq_p8 (uint8x16_t a, poly8x16_t b, poly8x16_t c) -{ - poly8x16_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vbslq_p16 (uint16x8_t a, poly16x8_t b, poly16x8_t c) -{ - poly16x8_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vbslq_s8 (uint8x16_t a, int8x16_t b, int8x16_t c) -{ - int8x16_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vbslq_s16 (uint16x8_t a, int16x8_t b, int16x8_t c) -{ - int16x8_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vbslq_s32 (uint32x4_t a, int32x4_t b, int32x4_t c) -{ - int32x4_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vbslq_s64 (uint64x2_t a, int64x2_t b, int64x2_t c) -{ - int64x2_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vbslq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c) -{ - uint8x16_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vbslq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c) -{ - uint16x8_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vbslq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c) -{ - uint32x4_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vbslq_u64 (uint64x2_t a, uint64x2_t b, uint64x2_t c) -{ - uint64x2_t result; - __asm__ ("bsl %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcage_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("facge %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcageq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("facge %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcageq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("facge %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcagt_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("facgt %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcagtq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("facgt %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcagtq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("facgt %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcale_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("facge %0.2s, %2.2s, %1.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcaleq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("facge %0.4s, %2.4s, %1.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcaleq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("facge %0.2d, %2.2d, %1.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcalt_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("facgt %0.2s, %2.2s, %1.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcaltq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("facgt %0.4s, %2.4s, %1.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcaltq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("facgt %0.2d, %2.2d, %1.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vceq_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("fcmeq %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vceq_f64 (float64x1_t a, float64x1_t b) -{ - uint64x1_t result; - __asm__ ("fcmeq %d0, %d1, %d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vceqd_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("fcmeq %d0,%d1,%d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vceqq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("fcmeq %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vceqq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("fcmeq %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vceqs_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("fcmeq %s0,%s1,%s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vceqzd_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcmeq %d0,%d1,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vceqzs_f32 (float32_t a) -{ - float32_t result; - __asm__ ("fcmeq %s0,%s1,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcge_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("fcmge %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcge_f64 (float64x1_t a, float64x1_t b) -{ - uint64x1_t result; - __asm__ ("fcmge %d0, %d1, %d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcgeq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("fcmge %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcgeq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("fcmge %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcgt_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("fcmgt %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgt_f64 (float64x1_t a, float64x1_t b) -{ - uint64x1_t result; - __asm__ ("fcmgt %d0, %d1, %d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcgtq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("fcmgt %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcgtq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("fcmgt %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcle_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("fcmge %0.2s, %2.2s, %1.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcle_f64 (float64x1_t a, float64x1_t b) -{ - uint64x1_t result; - __asm__ ("fcmge %d0, %d2, %d1" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcleq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("fcmge %0.4s, %2.4s, %1.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcleq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("fcmge %0.2d, %2.2d, %1.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vcls_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("cls %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vcls_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("cls %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcls_s32 (int32x2_t a) -{ - int32x2_t result; - __asm__ ("cls %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vclsq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("cls %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vclsq_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("cls %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vclsq_s32 (int32x4_t a) -{ - int32x4_t result; - __asm__ ("cls %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vclt_f32 (float32x2_t a, float32x2_t b) -{ - uint32x2_t result; - __asm__ ("fcmgt %0.2s, %2.2s, %1.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vclt_f64 (float64x1_t a, float64x1_t b) -{ - uint64x1_t result; - __asm__ ("fcmgt %d0, %d2, %d1" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcltq_f32 (float32x4_t a, float32x4_t b) -{ - uint32x4_t result; - __asm__ ("fcmgt %0.4s, %2.4s, %1.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcltq_f64 (float64x2_t a, float64x2_t b) -{ - uint64x2_t result; - __asm__ ("fcmgt %0.2d, %2.2d, %1.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vclz_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("clz %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vclz_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("clz %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vclz_s32 (int32x2_t a) -{ - int32x2_t result; - __asm__ ("clz %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vclz_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("clz %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vclz_u16 (uint16x4_t a) -{ - uint16x4_t result; - __asm__ ("clz %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vclz_u32 (uint32x2_t a) -{ - uint32x2_t result; - __asm__ ("clz %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vclzq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("clz %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vclzq_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("clz %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vclzq_s32 (int32x4_t a) -{ - int32x4_t result; - __asm__ ("clz %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vclzq_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("clz %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vclzq_u16 (uint16x8_t a) -{ - uint16x8_t result; - __asm__ ("clz %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vclzq_u32 (uint32x4_t a) -{ - uint32x4_t result; - __asm__ ("clz %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vcnt_p8 (poly8x8_t a) -{ - poly8x8_t result; - __asm__ ("cnt %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vcnt_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("cnt %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcnt_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("cnt %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vcntq_p8 (poly8x16_t a) -{ - poly8x16_t result; - __asm__ ("cnt %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vcntq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("cnt %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcntq_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("cnt %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vcopyq_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x4_t c_ = (c); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("ins %0.s[%2], %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_f64(a, b, c, d) \ - __extension__ \ - ({ \ - float64x2_t c_ = (c); \ - float64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("ins %0.d[%2], %3.d[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_p8(a, b, c, d) \ - __extension__ \ - ({ \ - poly8x16_t c_ = (c); \ - poly8x16_t a_ = (a); \ - poly8x16_t result; \ - __asm__ ("ins %0.b[%2], %3.b[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_p16(a, b, c, d) \ - __extension__ \ - ({ \ - poly16x8_t c_ = (c); \ - poly16x8_t a_ = (a); \ - poly16x8_t result; \ - __asm__ ("ins %0.h[%2], %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_s8(a, b, c, d) \ - __extension__ \ - ({ \ - int8x16_t c_ = (c); \ - int8x16_t a_ = (a); \ - int8x16_t result; \ - __asm__ ("ins %0.b[%2], %3.b[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("ins %0.h[%2], %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("ins %0.s[%2], %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_s64(a, b, c, d) \ - __extension__ \ - ({ \ - int64x2_t c_ = (c); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("ins %0.d[%2], %3.d[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_u8(a, b, c, d) \ - __extension__ \ - ({ \ - uint8x16_t c_ = (c); \ - uint8x16_t a_ = (a); \ - uint8x16_t result; \ - __asm__ ("ins %0.b[%2], %3.b[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("ins %0.h[%2], %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("ins %0.s[%2], %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcopyq_lane_u64(a, b, c, d) \ - __extension__ \ - ({ \ - uint64x2_t c_ = (c); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("ins %0.d[%2], %3.d[%4]" \ - : "=w"(result) \ - : "0"(a_), "i"(b), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -/* vcvt_f16_f32 not supported */ - -/* vcvt_f32_f16 not supported */ - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vcvt_f32_f64 (float64x2_t a) -{ - float32x2_t result; - __asm__ ("fcvtn %0.2s,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vcvt_f32_s32 (int32x2_t a) -{ - float32x2_t result; - __asm__ ("scvtf %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vcvt_f32_u32 (uint32x2_t a) -{ - float32x2_t result; - __asm__ ("ucvtf %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vcvt_f64_f32 (float32x2_t a) -{ - float64x2_t result; - __asm__ ("fcvtl %0.2d,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vcvt_f64_s64 (uint64x1_t a) -{ - float64x1_t result; - __asm__ ("scvtf %d0, %d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vcvt_f64_u64 (uint64x1_t a) -{ - float64x1_t result; - __asm__ ("ucvtf %d0, %d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -/* vcvt_high_f16_f32 not supported */ - -/* vcvt_high_f32_f16 not supported */ - -static float32x2_t vdup_n_f32 (float32_t); - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vcvt_high_f32_f64 (float32x2_t a, float64x2_t b) -{ - float32x4_t result = vcombine_f32 (a, vdup_n_f32 (0.0f)); - __asm__ ("fcvtn2 %0.4s,%2.2d" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vcvt_high_f64_f32 (float32x4_t a) -{ - float64x2_t result; - __asm__ ("fcvtl2 %0.2d,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vcvt_n_f32_s32(a, b) \ - __extension__ \ - ({ \ - int32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("scvtf %0.2s, %1.2s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvt_n_f32_u32(a, b) \ - __extension__ \ - ({ \ - uint32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("ucvtf %0.2s, %1.2s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvt_n_s32_f32(a, b) \ - __extension__ \ - ({ \ - float32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("fcvtzs %0.2s, %1.2s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvt_n_u32_f32(a, b) \ - __extension__ \ - ({ \ - float32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("fcvtzu %0.2s, %1.2s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcvt_s32_f32 (float32x2_t a) -{ - int32x2_t result; - __asm__ ("fcvtzs %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcvt_u32_f32 (float32x2_t a) -{ - uint32x2_t result; - __asm__ ("fcvtzu %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcvta_s32_f32 (float32x2_t a) -{ - int32x2_t result; - __asm__ ("fcvtas %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcvta_u32_f32 (float32x2_t a) -{ - uint32x2_t result; - __asm__ ("fcvtau %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtad_s64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtas %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtad_u64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtau %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vcvtaq_s32_f32 (float32x4_t a) -{ - int32x4_t result; - __asm__ ("fcvtas %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vcvtaq_s64_f64 (float64x2_t a) -{ - int64x2_t result; - __asm__ ("fcvtas %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcvtaq_u32_f32 (float32x4_t a) -{ - uint32x4_t result; - __asm__ ("fcvtau %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcvtaq_u64_f64 (float64x2_t a) -{ - uint64x2_t result; - __asm__ ("fcvtau %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtas_s64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtas %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtas_u64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtau %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64_t __attribute__ ((__always_inline__)) -vcvtd_f64_s64 (int64_t a) -{ - int64_t result; - __asm__ ("scvtf %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) -vcvtd_f64_u64 (uint64_t a) -{ - uint64_t result; - __asm__ ("ucvtf %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vcvtd_n_f64_s64(a, b) \ - __extension__ \ - ({ \ - int64_t a_ = (a); \ - int64_t result; \ - __asm__ ("scvtf %d0,%d1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtd_n_f64_u64(a, b) \ - __extension__ \ - ({ \ - uint64_t a_ = (a); \ - uint64_t result; \ - __asm__ ("ucvtf %d0,%d1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtd_n_s64_f64(a, b) \ - __extension__ \ - ({ \ - float64_t a_ = (a); \ - float64_t result; \ - __asm__ ("fcvtzs %d0,%d1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtd_n_u64_f64(a, b) \ - __extension__ \ - ({ \ - float64_t a_ = (a); \ - float64_t result; \ - __asm__ ("fcvtzu %d0,%d1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtd_s64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtzs %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtd_u64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtzu %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcvtm_s32_f32 (float32x2_t a) -{ - int32x2_t result; - __asm__ ("fcvtms %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcvtm_u32_f32 (float32x2_t a) -{ - uint32x2_t result; - __asm__ ("fcvtmu %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtmd_s64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtms %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtmd_u64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtmu %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vcvtmq_s32_f32 (float32x4_t a) -{ - int32x4_t result; - __asm__ ("fcvtms %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vcvtmq_s64_f64 (float64x2_t a) -{ - int64x2_t result; - __asm__ ("fcvtms %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcvtmq_u32_f32 (float32x4_t a) -{ - uint32x4_t result; - __asm__ ("fcvtmu %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcvtmq_u64_f64 (float64x2_t a) -{ - uint64x2_t result; - __asm__ ("fcvtmu %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtms_s64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtms %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtms_u64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtmu %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcvtn_s32_f32 (float32x2_t a) -{ - int32x2_t result; - __asm__ ("fcvtns %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcvtn_u32_f32 (float32x2_t a) -{ - uint32x2_t result; - __asm__ ("fcvtnu %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtnd_s64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtns %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtnd_u64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtnu %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vcvtnq_s32_f32 (float32x4_t a) -{ - int32x4_t result; - __asm__ ("fcvtns %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vcvtnq_s64_f64 (float64x2_t a) -{ - int64x2_t result; - __asm__ ("fcvtns %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcvtnq_u32_f32 (float32x4_t a) -{ - uint32x4_t result; - __asm__ ("fcvtnu %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcvtnq_u64_f64 (float64x2_t a) -{ - uint64x2_t result; - __asm__ ("fcvtnu %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtns_s64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtns %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtns_u64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtnu %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vcvtp_s32_f32 (float32x2_t a) -{ - int32x2_t result; - __asm__ ("fcvtps %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcvtp_u32_f32 (float32x2_t a) -{ - uint32x2_t result; - __asm__ ("fcvtpu %0.2s, %1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtpd_s64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtps %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vcvtpd_u64_f64 (float64_t a) -{ - float64_t result; - __asm__ ("fcvtpu %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vcvtpq_s32_f32 (float32x4_t a) -{ - int32x4_t result; - __asm__ ("fcvtps %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vcvtpq_s64_f64 (float64x2_t a) -{ - int64x2_t result; - __asm__ ("fcvtps %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcvtpq_u32_f32 (float32x4_t a) -{ - uint32x4_t result; - __asm__ ("fcvtpu %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcvtpq_u64_f64 (float64x2_t a) -{ - uint64x2_t result; - __asm__ ("fcvtpu %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtps_s64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtps %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtps_u64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtpu %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vcvtq_f32_s32 (int32x4_t a) -{ - float32x4_t result; - __asm__ ("scvtf %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vcvtq_f32_u32 (uint32x4_t a) -{ - float32x4_t result; - __asm__ ("ucvtf %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vcvtq_f64_s64 (int64x2_t a) -{ - float64x2_t result; - __asm__ ("scvtf %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vcvtq_f64_u64 (uint64x2_t a) -{ - float64x2_t result; - __asm__ ("ucvtf %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vcvtq_n_f32_s32(a, b) \ - __extension__ \ - ({ \ - int32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("scvtf %0.4s, %1.4s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_f32_u32(a, b) \ - __extension__ \ - ({ \ - uint32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("ucvtf %0.4s, %1.4s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_f64_s64(a, b) \ - __extension__ \ - ({ \ - int64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("scvtf %0.2d, %1.2d, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_f64_u64(a, b) \ - __extension__ \ - ({ \ - uint64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("ucvtf %0.2d, %1.2d, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_s32_f32(a, b) \ - __extension__ \ - ({ \ - float32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("fcvtzs %0.4s, %1.4s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_s64_f64(a, b) \ - __extension__ \ - ({ \ - float64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("fcvtzs %0.2d, %1.2d, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_u32_f32(a, b) \ - __extension__ \ - ({ \ - float32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("fcvtzu %0.4s, %1.4s, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvtq_n_u64_f64(a, b) \ - __extension__ \ - ({ \ - float64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("fcvtzu %0.2d, %1.2d, #%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vcvtq_s32_f32 (float32x4_t a) -{ - int32x4_t result; - __asm__ ("fcvtzs %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vcvtq_s64_f64 (float64x2_t a) -{ - int64x2_t result; - __asm__ ("fcvtzs %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcvtq_u32_f32 (float32x4_t a) -{ - uint32x4_t result; - __asm__ ("fcvtzu %0.4s, %1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcvtq_u64_f64 (float64x2_t a) -{ - uint64x2_t result; - __asm__ ("fcvtzu %0.2d, %1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vcvts_f64_s32 (int32_t a) -{ - int32_t result; - __asm__ ("scvtf %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vcvts_f64_u32 (uint32_t a) -{ - uint32_t result; - __asm__ ("ucvtf %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vcvts_n_f32_s32(a, b) \ - __extension__ \ - ({ \ - int32_t a_ = (a); \ - int32_t result; \ - __asm__ ("scvtf %s0,%s1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvts_n_f32_u32(a, b) \ - __extension__ \ - ({ \ - uint32_t a_ = (a); \ - uint32_t result; \ - __asm__ ("ucvtf %s0,%s1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvts_n_s32_f32(a, b) \ - __extension__ \ - ({ \ - float32_t a_ = (a); \ - float32_t result; \ - __asm__ ("fcvtzs %s0,%s1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vcvts_n_u32_f32(a, b) \ - __extension__ \ - ({ \ - float32_t a_ = (a); \ - float32_t result; \ - __asm__ ("fcvtzu %s0,%s1,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvts_s64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtzs %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvts_u64_f64 (float32_t a) -{ - float32_t result; - __asm__ ("fcvtzu %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vcvtx_f32_f64 (float64x2_t a) -{ - float32x2_t result; - __asm__ ("fcvtxn %0.2s,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vcvtx_high_f32_f64 (float64x2_t a) -{ - float32x4_t result; - __asm__ ("fcvtxn2 %0.4s,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vcvtxd_f32_f64 (float64_t a) -{ - float32_t result; - __asm__ ("fcvtxn %s0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vdup_lane_f32(a, b) \ - __extension__ \ - ({ \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("dup %0.2s,%1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_p8(a, b) \ - __extension__ \ - ({ \ - poly8x8_t a_ = (a); \ - poly8x8_t result; \ - __asm__ ("dup %0.8b,%1.b[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_p16(a, b) \ - __extension__ \ - ({ \ - poly16x4_t a_ = (a); \ - poly16x4_t result; \ - __asm__ ("dup %0.4h,%1.h[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_s8(a, b) \ - __extension__ \ - ({ \ - int8x8_t a_ = (a); \ - int8x8_t result; \ - __asm__ ("dup %0.8b,%1.b[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_s16(a, b) \ - __extension__ \ - ({ \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("dup %0.4h,%1.h[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_s32(a, b) \ - __extension__ \ - ({ \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("dup %0.2s,%1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_s64(a, b) \ - __extension__ \ - ({ \ - int64x1_t a_ = (a); \ - int64x1_t result; \ - __asm__ ("ins %0.d[0],%1.d[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_u8(a, b) \ - __extension__ \ - ({ \ - uint8x8_t a_ = (a); \ - uint8x8_t result; \ - __asm__ ("dup %0.8b,%1.b[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_u16(a, b) \ - __extension__ \ - ({ \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("dup %0.4h,%1.h[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_u32(a, b) \ - __extension__ \ - ({ \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("dup %0.2s,%1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdup_lane_u64(a, b) \ - __extension__ \ - ({ \ - uint64x1_t a_ = (a); \ - uint64x1_t result; \ - __asm__ ("ins %0.d[0],%1.d[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vdup_n_f32 (float32_t a) -{ - float32x2_t result; - __asm__ ("dup %0.2s, %w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vdup_n_p8 (uint32_t a) -{ - poly8x8_t result; - __asm__ ("dup %0.8b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vdup_n_p16 (uint32_t a) -{ - poly16x4_t result; - __asm__ ("dup %0.4h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vdup_n_s8 (int32_t a) -{ - int8x8_t result; - __asm__ ("dup %0.8b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vdup_n_s16 (int32_t a) -{ - int16x4_t result; - __asm__ ("dup %0.4h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vdup_n_s32 (int32_t a) -{ - int32x2_t result; - __asm__ ("dup %0.2s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vdup_n_s64 (int64_t a) -{ - int64x1_t result; - __asm__ ("ins %0.d[0],%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vdup_n_u8 (uint32_t a) -{ - uint8x8_t result; - __asm__ ("dup %0.8b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vdup_n_u16 (uint32_t a) -{ - uint16x4_t result; - __asm__ ("dup %0.4h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vdup_n_u32 (uint32_t a) -{ - uint32x2_t result; - __asm__ ("dup %0.2s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vdup_n_u64 (uint64_t a) -{ - uint64x1_t result; - __asm__ ("ins %0.d[0],%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -#define vdupd_lane_f64(a, b) \ - __extension__ \ - ({ \ - float64x2_t a_ = (a); \ - float64_t result; \ - __asm__ ("dup %d0, %1.d[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_f32(a, b) \ - __extension__ \ - ({ \ - float32x2_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("dup %0.4s,%1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_f64(a, b) \ - __extension__ \ - ({ \ - float64x1_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("dup %0.2d,%1.d[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_p8(a, b) \ - __extension__ \ - ({ \ - poly8x8_t a_ = (a); \ - poly8x16_t result; \ - __asm__ ("dup %0.16b,%1.b[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_p16(a, b) \ - __extension__ \ - ({ \ - poly16x4_t a_ = (a); \ - poly16x8_t result; \ - __asm__ ("dup %0.8h,%1.h[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_s8(a, b) \ - __extension__ \ - ({ \ - int8x8_t a_ = (a); \ - int8x16_t result; \ - __asm__ ("dup %0.16b,%1.b[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_s16(a, b) \ - __extension__ \ - ({ \ - int16x4_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("dup %0.8h,%1.h[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_s32(a, b) \ - __extension__ \ - ({ \ - int32x2_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("dup %0.4s,%1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_s64(a, b) \ - __extension__ \ - ({ \ - int64x1_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("dup %0.2d,%1.d[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_u8(a, b) \ - __extension__ \ - ({ \ - uint8x8_t a_ = (a); \ - uint8x16_t result; \ - __asm__ ("dup %0.16b,%1.b[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_u16(a, b) \ - __extension__ \ - ({ \ - uint16x4_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("dup %0.8h,%1.h[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_u32(a, b) \ - __extension__ \ - ({ \ - uint32x2_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("dup %0.4s,%1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vdupq_lane_u64(a, b) \ - __extension__ \ - ({ \ - uint64x1_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("dup %0.2d,%1.d[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vdupq_n_f32 (float32_t a) -{ - float32x4_t result; - __asm__ ("dup %0.4s, %w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vdupq_n_f64 (float64_t a) -{ - float64x2_t result; - __asm__ ("dup %0.2d, %x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vdupq_n_p8 (uint32_t a) -{ - poly8x16_t result; - __asm__ ("dup %0.16b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vdupq_n_p16 (uint32_t a) -{ - poly16x8_t result; - __asm__ ("dup %0.8h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vdupq_n_s8 (int32_t a) -{ - int8x16_t result; - __asm__ ("dup %0.16b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vdupq_n_s16 (int32_t a) -{ - int16x8_t result; - __asm__ ("dup %0.8h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vdupq_n_s32 (int32_t a) -{ - int32x4_t result; - __asm__ ("dup %0.4s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vdupq_n_s64 (int64_t a) -{ - int64x2_t result; - __asm__ ("dup %0.2d,%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vdupq_n_u8 (uint32_t a) -{ - uint8x16_t result; - __asm__ ("dup %0.16b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vdupq_n_u16 (uint32_t a) -{ - uint16x8_t result; - __asm__ ("dup %0.8h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vdupq_n_u32 (uint32_t a) -{ - uint32x4_t result; - __asm__ ("dup %0.4s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vdupq_n_u64 (uint64_t a) -{ - uint64x2_t result; - __asm__ ("dup %0.2d,%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -#define vdups_lane_f32(a, b) \ - __extension__ \ - ({ \ - float32x4_t a_ = (a); \ - float32_t result; \ - __asm__ ("dup %s0, %1.s[%2]" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x2_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*4" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x1_t b_ = (b); \ - float64x1_t a_ = (a); \ - float64x1_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*8" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x8_t b_ = (b); \ - poly8x8_t a_ = (a); \ - poly8x8_t result; \ - __asm__ ("ext %0.8b,%1.8b,%2.8b,%3" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x4_t b_ = (b); \ - poly16x4_t a_ = (a); \ - poly16x4_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*2" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x8_t b_ = (b); \ - int8x8_t a_ = (a); \ - int8x8_t result; \ - __asm__ ("ext %0.8b,%1.8b,%2.8b,%3" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*2" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*4" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x1_t b_ = (b); \ - int64x1_t a_ = (a); \ - int64x1_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*8" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x8_t result; \ - __asm__ ("ext %0.8b,%1.8b,%2.8b,%3" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*2" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*4" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vext_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x1_t b_ = (b); \ - uint64x1_t a_ = (a); \ - uint64x1_t result; \ - __asm__ ("ext %0.8b, %1.8b, %2.8b, #%3*8" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*4" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*8" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x16_t b_ = (b); \ - poly8x16_t a_ = (a); \ - poly8x16_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x8_t b_ = (b); \ - poly16x8_t a_ = (a); \ - poly16x8_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*2" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x16_t b_ = (b); \ - int8x16_t a_ = (a); \ - int8x16_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*2" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*4" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*8" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x16_t b_ = (b); \ - uint8x16_t a_ = (a); \ - uint8x16_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*2" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*4" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vextq_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("ext %0.16b, %1.16b, %2.16b, #%3*8" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vfma_f32 (float32x2_t a, float32x2_t b, float32x2_t c) -{ - float32x2_t result; - __asm__ ("fmla %0.2s,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vfma_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x2_t c_ = (c); \ - float32x2_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("fmla %0.2s,%2.2s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vfmad_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64_t a_ = (a); \ - float64_t result; \ - __asm__ ("fmla %d0,%d1,%2.d[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vfmaq_f32 (float32x4_t a, float32x4_t b, float32x4_t c) -{ - float32x4_t result; - __asm__ ("fmla %0.4s,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vfmaq_f64 (float64x2_t a, float64x2_t b, float64x2_t c) -{ - float64x2_t result; - __asm__ ("fmla %0.2d,%2.2d,%3.2d" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vfmaq_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x4_t c_ = (c); \ - float32x4_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("fmla %0.4s,%2.4s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vfmaq_lane_f64(a, b, c, d) \ - __extension__ \ - ({ \ - float64x2_t c_ = (c); \ - float64x2_t b_ = (b); \ - float64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("fmla %0.2d,%2.2d,%3.d[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vfmas_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32_t a_ = (a); \ - float32_t result; \ - __asm__ ("fmla %s0,%s1,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vfma_n_f32 (float32x2_t a, float32x2_t b, float32_t c) -{ - float32x2_t result; - __asm__ ("fmla %0.2s, %2.2s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vfmaq_n_f32 (float32x4_t a, float32x4_t b, float32_t c) -{ - float32x4_t result; - __asm__ ("fmla %0.4s, %2.4s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vfmaq_n_f64 (float64x2_t a, float64x2_t b, float64_t c) -{ - float64x2_t result; - __asm__ ("fmla %0.2d, %2.2d, %3.d[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vfms_f32 (float32x2_t a, float32x2_t b, float32x2_t c) -{ - float32x2_t result; - __asm__ ("fmls %0.2s,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vfmsd_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64_t a_ = (a); \ - float64_t result; \ - __asm__ ("fmls %d0,%d1,%2.d[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vfmsq_f32 (float32x4_t a, float32x4_t b, float32x4_t c) -{ - float32x4_t result; - __asm__ ("fmls %0.4s,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vfmsq_f64 (float64x2_t a, float64x2_t b, float64x2_t c) -{ - float64x2_t result; - __asm__ ("fmls %0.2d,%2.2d,%3.2d" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vfmss_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32_t a_ = (a); \ - float32_t result; \ - __asm__ ("fmls %s0,%s1,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vget_high_f32 (float32x4_t a) -{ - float32x2_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vget_high_f64 (float64x2_t a) -{ - float64x1_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vget_high_p8 (poly8x16_t a) -{ - poly8x8_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vget_high_p16 (poly16x8_t a) -{ - poly16x4_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vget_high_s8 (int8x16_t a) -{ - int8x8_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vget_high_s16 (int16x8_t a) -{ - int16x4_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vget_high_s32 (int32x4_t a) -{ - int32x2_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vget_high_s64 (int64x2_t a) -{ - int64x1_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vget_high_u8 (uint8x16_t a) -{ - uint8x8_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vget_high_u16 (uint16x8_t a) -{ - uint16x4_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vget_high_u32 (uint32x4_t a) -{ - uint32x2_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vget_high_u64 (uint64x2_t a) -{ - uint64x1_t result; - __asm__ ("ins %0.d[0], %1.d[1]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vget_lane_f64(a, b) \ - __extension__ \ - ({ \ - float64x1_t a_ = (a); \ - float64_t result; \ - __asm__ ("umov %x0, %1.d[%2]" \ - : "=r"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vget_low_f32 (float32x4_t a) -{ - float32x2_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vget_low_f64 (float64x2_t a) -{ - float64x1_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vget_low_p8 (poly8x16_t a) -{ - poly8x8_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vget_low_p16 (poly16x8_t a) -{ - poly16x4_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vget_low_s8 (int8x16_t a) -{ - int8x8_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vget_low_s16 (int16x8_t a) -{ - int16x4_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vget_low_s32 (int32x4_t a) -{ - int32x2_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vget_low_s64 (int64x2_t a) -{ - int64x1_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vget_low_u8 (uint8x16_t a) -{ - uint8x8_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vget_low_u16 (uint16x8_t a) -{ - uint16x4_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vget_low_u32 (uint32x4_t a) -{ - uint32x2_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vget_low_u64 (uint64x2_t a) -{ - uint64x1_t result; - __asm__ ("ins %0.d[0], %1.d[0]" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vhsub_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("shsub %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vhsub_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("shsub %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vhsub_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("shsub %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vhsub_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("uhsub %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vhsub_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("uhsub %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vhsub_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("uhsub %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vhsubq_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("shsub %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vhsubq_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("shsub %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vhsubq_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("shsub %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vhsubq_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("uhsub %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vhsubq_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("uhsub %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vhsubq_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("uhsub %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vld1_dup_f32 (const float32_t * a) -{ - float32x2_t result; - __asm__ ("ld1r {%0.2s}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vld1_dup_f64 (const float64_t * a) -{ - float64x1_t result; - __asm__ ("ld1r {%0.1d}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vld1_dup_p8 (const poly8_t * a) -{ - poly8x8_t result; - __asm__ ("ld1r {%0.8b}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vld1_dup_p16 (const poly16_t * a) -{ - poly16x4_t result; - __asm__ ("ld1r {%0.4h}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vld1_dup_s8 (const int8_t * a) -{ - int8x8_t result; - __asm__ ("ld1r {%0.8b}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vld1_dup_s16 (const int16_t * a) -{ - int16x4_t result; - __asm__ ("ld1r {%0.4h}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vld1_dup_s32 (const int32_t * a) -{ - int32x2_t result; - __asm__ ("ld1r {%0.2s}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vld1_dup_s64 (const int64_t * a) -{ - int64x1_t result; - __asm__ ("ld1r {%0.1d}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vld1_dup_u8 (const uint8_t * a) -{ - uint8x8_t result; - __asm__ ("ld1r {%0.8b}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vld1_dup_u16 (const uint16_t * a) -{ - uint16x4_t result; - __asm__ ("ld1r {%0.4h}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vld1_dup_u32 (const uint32_t * a) -{ - uint32x2_t result; - __asm__ ("ld1r {%0.2s}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vld1_dup_u64 (const uint64_t * a) -{ - uint64x1_t result; - __asm__ ("ld1r {%0.1d}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -#define vld1_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x2_t b_ = (b); \ - const float32_t * a_ = (a); \ - float32x2_t result; \ - __asm__ ("ld1 {%0.s}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x1_t b_ = (b); \ - const float64_t * a_ = (a); \ - float64x1_t result; \ - __asm__ ("ld1 {%0.d}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x8_t b_ = (b); \ - const poly8_t * a_ = (a); \ - poly8x8_t result; \ - __asm__ ("ld1 {%0.b}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x4_t b_ = (b); \ - const poly16_t * a_ = (a); \ - poly16x4_t result; \ - __asm__ ("ld1 {%0.h}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x8_t b_ = (b); \ - const int8_t * a_ = (a); \ - int8x8_t result; \ - __asm__ ("ld1 {%0.b}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - const int16_t * a_ = (a); \ - int16x4_t result; \ - __asm__ ("ld1 {%0.h}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - const int32_t * a_ = (a); \ - int32x2_t result; \ - __asm__ ("ld1 {%0.s}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x1_t b_ = (b); \ - const int64_t * a_ = (a); \ - int64x1_t result; \ - __asm__ ("ld1 {%0.d}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x8_t b_ = (b); \ - const uint8_t * a_ = (a); \ - uint8x8_t result; \ - __asm__ ("ld1 {%0.b}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - const uint16_t * a_ = (a); \ - uint16x4_t result; \ - __asm__ ("ld1 {%0.h}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - const uint32_t * a_ = (a); \ - uint32x2_t result; \ - __asm__ ("ld1 {%0.s}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1_lane_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x1_t b_ = (b); \ - const uint64_t * a_ = (a); \ - uint64x1_t result; \ - __asm__ ("ld1 {%0.d}[%1], %2" \ - : "=w"(result) \ - : "i" (c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vld1q_dup_f32 (const float32_t * a) -{ - float32x4_t result; - __asm__ ("ld1r {%0.4s}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vld1q_dup_f64 (const float64_t * a) -{ - float64x2_t result; - __asm__ ("ld1r {%0.2d}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vld1q_dup_p8 (const poly8_t * a) -{ - poly8x16_t result; - __asm__ ("ld1r {%0.16b}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vld1q_dup_p16 (const poly16_t * a) -{ - poly16x8_t result; - __asm__ ("ld1r {%0.8h}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vld1q_dup_s8 (const int8_t * a) -{ - int8x16_t result; - __asm__ ("ld1r {%0.16b}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vld1q_dup_s16 (const int16_t * a) -{ - int16x8_t result; - __asm__ ("ld1r {%0.8h}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vld1q_dup_s32 (const int32_t * a) -{ - int32x4_t result; - __asm__ ("ld1r {%0.4s}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vld1q_dup_s64 (const int64_t * a) -{ - int64x2_t result; - __asm__ ("ld1r {%0.2d}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vld1q_dup_u8 (const uint8_t * a) -{ - uint8x16_t result; - __asm__ ("ld1r {%0.16b}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vld1q_dup_u16 (const uint16_t * a) -{ - uint16x8_t result; - __asm__ ("ld1r {%0.8h}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vld1q_dup_u32 (const uint32_t * a) -{ - uint32x4_t result; - __asm__ ("ld1r {%0.4s}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vld1q_dup_u64 (const uint64_t * a) -{ - uint64x2_t result; - __asm__ ("ld1r {%0.2d}, %1" - : "=w"(result) - : "Utv"(*a) - : /* No clobbers */); - return result; -} - -#define vld1q_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - const float32_t * a_ = (a); \ - float32x4_t result; \ - __asm__ ("ld1 {%0.s}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - const float64_t * a_ = (a); \ - float64x2_t result; \ - __asm__ ("ld1 {%0.d}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x16_t b_ = (b); \ - const poly8_t * a_ = (a); \ - poly8x16_t result; \ - __asm__ ("ld1 {%0.b}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x8_t b_ = (b); \ - const poly16_t * a_ = (a); \ - poly16x8_t result; \ - __asm__ ("ld1 {%0.h}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x16_t b_ = (b); \ - const int8_t * a_ = (a); \ - int8x16_t result; \ - __asm__ ("ld1 {%0.b}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - const int16_t * a_ = (a); \ - int16x8_t result; \ - __asm__ ("ld1 {%0.h}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - const int32_t * a_ = (a); \ - int32x4_t result; \ - __asm__ ("ld1 {%0.s}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - const int64_t * a_ = (a); \ - int64x2_t result; \ - __asm__ ("ld1 {%0.d}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x16_t b_ = (b); \ - const uint8_t * a_ = (a); \ - uint8x16_t result; \ - __asm__ ("ld1 {%0.b}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - const uint16_t * a_ = (a); \ - uint16x8_t result; \ - __asm__ ("ld1 {%0.h}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - const uint32_t * a_ = (a); \ - uint32x4_t result; \ - __asm__ ("ld1 {%0.s}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -#define vld1q_lane_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - const uint64_t * a_ = (a); \ - uint64x2_t result; \ - __asm__ ("ld1 {%0.d}[%1], %2" \ - : "=w"(result) \ - : "i"(c), "Utv"(*a_), "0"(b_) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmaxnm_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fmaxnm %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmaxnmq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fmaxnm %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmaxnmq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fmaxnm %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vmaxnmvq_f32 (float32x4_t a) -{ - float32_t result; - __asm__ ("fmaxnmv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vmaxv_s8 (int8x8_t a) -{ - int8_t result; - __asm__ ("smaxv %b0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vmaxv_s16 (int16x4_t a) -{ - int16_t result; - __asm__ ("smaxv %h0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vmaxv_u8 (uint8x8_t a) -{ - uint8_t result; - __asm__ ("umaxv %b0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vmaxv_u16 (uint16x4_t a) -{ - uint16_t result; - __asm__ ("umaxv %h0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vmaxvq_f32 (float32x4_t a) -{ - float32_t result; - __asm__ ("fmaxv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vmaxvq_s8 (int8x16_t a) -{ - int8_t result; - __asm__ ("smaxv %b0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vmaxvq_s16 (int16x8_t a) -{ - int16_t result; - __asm__ ("smaxv %h0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vmaxvq_s32 (int32x4_t a) -{ - int32_t result; - __asm__ ("smaxv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vmaxvq_u8 (uint8x16_t a) -{ - uint8_t result; - __asm__ ("umaxv %b0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vmaxvq_u16 (uint16x8_t a) -{ - uint16_t result; - __asm__ ("umaxv %h0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vmaxvq_u32 (uint32x4_t a) -{ - uint32_t result; - __asm__ ("umaxv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vminnmvq_f32 (float32x4_t a) -{ - float32_t result; - __asm__ ("fminnmv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vminv_s8 (int8x8_t a) -{ - int8_t result; - __asm__ ("sminv %b0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vminv_s16 (int16x4_t a) -{ - int16_t result; - __asm__ ("sminv %h0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vminv_u8 (uint8x8_t a) -{ - uint8_t result; - __asm__ ("uminv %b0,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vminv_u16 (uint16x4_t a) -{ - uint16_t result; - __asm__ ("uminv %h0,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vminvq_f32 (float32x4_t a) -{ - float32_t result; - __asm__ ("fminv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8_t __attribute__ ((__always_inline__)) -vminvq_s8 (int8x16_t a) -{ - int8_t result; - __asm__ ("sminv %b0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16_t __attribute__ ((__always_inline__)) -vminvq_s16 (int16x8_t a) -{ - int16_t result; - __asm__ ("sminv %h0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vminvq_s32 (int32x4_t a) -{ - int32_t result; - __asm__ ("sminv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) -vminvq_u8 (uint8x16_t a) -{ - uint8_t result; - __asm__ ("uminv %b0,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) -vminvq_u16 (uint16x8_t a) -{ - uint16_t result; - __asm__ ("uminv %h0,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vminvq_u32 (uint32x4_t a) -{ - uint32_t result; - __asm__ ("uminv %s0,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vmla_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x2_t c_ = (c); \ - float32x2_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - float32x2_t t1; \ - __asm__ ("fmul %1.2s, %3.2s, %4.s[%5]; fadd %0.2s, %0.2s, %1.2s" \ - : "=w"(result), "=w"(t1) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x4_t c_ = (c); \ - int16x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x2_t c_ = (c); \ - int32x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("mla %0.2s, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x4_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x2_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("mla %0.2s, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_laneq_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_laneq_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("mla %0.2s, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_laneq_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmla_laneq_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("mla %0.2s, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmla_n_f32 (float32x2_t a, float32x2_t b, float32_t c) -{ - float32x2_t result; - float32x2_t t1; - __asm__ ("fmul %1.2s, %3.2s, %4.s[0]; fadd %0.2s, %0.2s, %1.2s" - : "=w"(result), "=w"(t1) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmla_n_s16 (int16x4_t a, int16x4_t b, int16_t c) -{ - int16x4_t result; - __asm__ ("mla %0.4h,%2.4h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmla_n_s32 (int32x2_t a, int32x2_t b, int32_t c) -{ - int32x2_t result; - __asm__ ("mla %0.2s,%2.2s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmla_n_u16 (uint16x4_t a, uint16x4_t b, uint16_t c) -{ - uint16x4_t result; - __asm__ ("mla %0.4h,%2.4h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmla_n_u32 (uint32x2_t a, uint32x2_t b, uint32_t c) -{ - uint32x2_t result; - __asm__ ("mla %0.2s,%2.2s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmla_s8 (int8x8_t a, int8x8_t b, int8x8_t c) -{ - int8x8_t result; - __asm__ ("mla %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmla_s16 (int16x4_t a, int16x4_t b, int16x4_t c) -{ - int16x4_t result; - __asm__ ("mla %0.4h, %2.4h, %3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmla_s32 (int32x2_t a, int32x2_t b, int32x2_t c) -{ - int32x2_t result; - __asm__ ("mla %0.2s, %2.2s, %3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmla_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint8x8_t result; - __asm__ ("mla %0.8b, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmla_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint16x4_t result; - __asm__ ("mla %0.4h, %2.4h, %3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmla_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint32x2_t result; - __asm__ ("mla %0.2s, %2.2s, %3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmlal_high_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlal2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlal2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlal2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlal2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_laneq_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlal2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_laneq_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlal2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_laneq_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlal2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_high_laneq_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlal2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlal_high_n_s16 (int32x4_t a, int16x8_t b, int16_t c) -{ - int32x4_t result; - __asm__ ("smlal2 %0.4s,%2.8h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlal_high_n_s32 (int64x2_t a, int32x4_t b, int32_t c) -{ - int64x2_t result; - __asm__ ("smlal2 %0.2d,%2.4s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlal_high_n_u16 (uint32x4_t a, uint16x8_t b, uint16_t c) -{ - uint32x4_t result; - __asm__ ("umlal2 %0.4s,%2.8h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlal_high_n_u32 (uint64x2_t a, uint32x4_t b, uint32_t c) -{ - uint64x2_t result; - __asm__ ("umlal2 %0.2d,%2.4s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlal_high_s8 (int16x8_t a, int8x16_t b, int8x16_t c) -{ - int16x8_t result; - __asm__ ("smlal2 %0.8h,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlal_high_s16 (int32x4_t a, int16x8_t b, int16x8_t c) -{ - int32x4_t result; - __asm__ ("smlal2 %0.4s,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlal_high_s32 (int64x2_t a, int32x4_t b, int32x4_t c) -{ - int64x2_t result; - __asm__ ("smlal2 %0.2d,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlal_high_u8 (uint16x8_t a, uint8x16_t b, uint8x16_t c) -{ - uint16x8_t result; - __asm__ ("umlal2 %0.8h,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlal_high_u16 (uint32x4_t a, uint16x8_t b, uint16x8_t c) -{ - uint32x4_t result; - __asm__ ("umlal2 %0.4s,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) -{ - uint64x2_t result; - __asm__ ("umlal2 %0.2d,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmlal_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x4_t c_ = (c); \ - int16x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlal %0.4s,%2.4h,%3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x2_t c_ = (c); \ - int32x2_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlal %0.2d,%2.2s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x4_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlal %0.4s,%2.4h,%3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x2_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlal %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_laneq_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlal %0.4s, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_laneq_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x2_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlal %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_laneq_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlal %0.4s, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlal_laneq_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlal %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlal_n_s16 (int32x4_t a, int16x4_t b, int16_t c) -{ - int32x4_t result; - __asm__ ("smlal %0.4s,%2.4h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlal_n_s32 (int64x2_t a, int32x2_t b, int32_t c) -{ - int64x2_t result; - __asm__ ("smlal %0.2d,%2.2s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlal_n_u16 (uint32x4_t a, uint16x4_t b, uint16_t c) -{ - uint32x4_t result; - __asm__ ("umlal %0.4s,%2.4h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlal_n_u32 (uint64x2_t a, uint32x2_t b, uint32_t c) -{ - uint64x2_t result; - __asm__ ("umlal %0.2d,%2.2s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlal_s8 (int16x8_t a, int8x8_t b, int8x8_t c) -{ - int16x8_t result; - __asm__ ("smlal %0.8h,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlal_s16 (int32x4_t a, int16x4_t b, int16x4_t c) -{ - int32x4_t result; - __asm__ ("smlal %0.4s,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlal_s32 (int64x2_t a, int32x2_t b, int32x2_t c) -{ - int64x2_t result; - __asm__ ("smlal %0.2d,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlal_u8 (uint16x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint16x8_t result; - __asm__ ("umlal %0.8h,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlal_u16 (uint32x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint32x4_t result; - __asm__ ("umlal %0.4s,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint64x2_t result; - __asm__ ("umlal %0.2d,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmlaq_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x4_t c_ = (c); \ - float32x4_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - float32x4_t t1; \ - __asm__ ("fmul %1.4s, %3.4s, %4.s[%5]; fadd %0.4s, %0.4s, %1.4s" \ - : "=w"(result), "=w"(t1) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("mla %0.4s, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("mla %0.4s, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_laneq_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_laneq_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("mla %0.4s, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_laneq_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlaq_laneq_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("mla %0.4s, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmlaq_n_f32 (float32x4_t a, float32x4_t b, float32_t c) -{ - float32x4_t result; - float32x4_t t1; - __asm__ ("fmul %1.4s, %3.4s, %4.s[0]; fadd %0.4s, %0.4s, %1.4s" - : "=w"(result), "=w"(t1) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmlaq_n_f64 (float64x2_t a, float64x2_t b, float64_t c) -{ - float64x2_t result; - float64x2_t t1; - __asm__ ("fmul %1.2d, %3.2d, %4.d[0]; fadd %0.2d, %0.2d, %1.2d" - : "=w"(result), "=w"(t1) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlaq_n_s16 (int16x8_t a, int16x8_t b, int16_t c) -{ - int16x8_t result; - __asm__ ("mla %0.8h,%2.8h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlaq_n_s32 (int32x4_t a, int32x4_t b, int32_t c) -{ - int32x4_t result; - __asm__ ("mla %0.4s,%2.4s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlaq_n_u16 (uint16x8_t a, uint16x8_t b, uint16_t c) -{ - uint16x8_t result; - __asm__ ("mla %0.8h,%2.8h,%3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlaq_n_u32 (uint32x4_t a, uint32x4_t b, uint32_t c) -{ - uint32x4_t result; - __asm__ ("mla %0.4s,%2.4s,%3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmlaq_s8 (int8x16_t a, int8x16_t b, int8x16_t c) -{ - int8x16_t result; - __asm__ ("mla %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlaq_s16 (int16x8_t a, int16x8_t b, int16x8_t c) -{ - int16x8_t result; - __asm__ ("mla %0.8h, %2.8h, %3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlaq_s32 (int32x4_t a, int32x4_t b, int32x4_t c) -{ - int32x4_t result; - __asm__ ("mla %0.4s, %2.4s, %3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmlaq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c) -{ - uint8x16_t result; - __asm__ ("mla %0.16b, %2.16b, %3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlaq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c) -{ - uint16x8_t result; - __asm__ ("mla %0.8h, %2.8h, %3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c) -{ - uint32x4_t result; - __asm__ ("mla %0.4s, %2.4s, %3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmls_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x2_t c_ = (c); \ - float32x2_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - float32x2_t t1; \ - __asm__ ("fmul %1.2s, %3.2s, %4.s[%5]; fsub %0.2s, %0.2s, %1.2s" \ - : "=w"(result), "=w"(t1) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmls_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x4_t c_ = (c); \ - int16x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("mls %0.4h,%2.4h,%3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmls_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x2_t c_ = (c); \ - int32x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("mls %0.2s,%2.2s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmls_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x4_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("mls %0.4h,%2.4h,%3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmls_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x2_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("mls %0.2s,%2.2s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmls_n_f32 (float32x2_t a, float32x2_t b, float32_t c) -{ - float32x2_t result; - float32x2_t t1; - __asm__ ("fmul %1.2s, %3.2s, %4.s[0]; fsub %0.2s, %0.2s, %1.2s" - : "=w"(result), "=w"(t1) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmls_n_s16 (int16x4_t a, int16x4_t b, int16_t c) -{ - int16x4_t result; - __asm__ ("mls %0.4h, %2.4h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmls_n_s32 (int32x2_t a, int32x2_t b, int32_t c) -{ - int32x2_t result; - __asm__ ("mls %0.2s, %2.2s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmls_n_u16 (uint16x4_t a, uint16x4_t b, uint16_t c) -{ - uint16x4_t result; - __asm__ ("mls %0.4h, %2.4h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmls_n_u32 (uint32x2_t a, uint32x2_t b, uint32_t c) -{ - uint32x2_t result; - __asm__ ("mls %0.2s, %2.2s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmls_s8 (int8x8_t a, int8x8_t b, int8x8_t c) -{ - int8x8_t result; - __asm__ ("mls %0.8b,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmls_s16 (int16x4_t a, int16x4_t b, int16x4_t c) -{ - int16x4_t result; - __asm__ ("mls %0.4h,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmls_s32 (int32x2_t a, int32x2_t b, int32x2_t c) -{ - int32x2_t result; - __asm__ ("mls %0.2s,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmls_u8 (uint8x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint8x8_t result; - __asm__ ("mls %0.8b,%2.8b,%3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmls_u16 (uint16x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint16x4_t result; - __asm__ ("mls %0.4h,%2.4h,%3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmls_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint32x2_t result; - __asm__ ("mls %0.2s,%2.2s,%3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmlsl_high_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlsl2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlsl2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_laneq_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_laneq_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlsl2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_laneq_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_high_laneq_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlsl2 %0.2d, %2.4s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlsl_high_n_s16 (int32x4_t a, int16x8_t b, int16_t c) -{ - int32x4_t result; - __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlsl_high_n_s32 (int64x2_t a, int32x4_t b, int32_t c) -{ - int64x2_t result; - __asm__ ("smlsl2 %0.2d, %2.4s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlsl_high_n_u16 (uint32x4_t a, uint16x8_t b, uint16_t c) -{ - uint32x4_t result; - __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlsl_high_n_u32 (uint64x2_t a, uint32x4_t b, uint32_t c) -{ - uint64x2_t result; - __asm__ ("umlsl2 %0.2d, %2.4s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlsl_high_s8 (int16x8_t a, int8x16_t b, int8x16_t c) -{ - int16x8_t result; - __asm__ ("smlsl2 %0.8h,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlsl_high_s16 (int32x4_t a, int16x8_t b, int16x8_t c) -{ - int32x4_t result; - __asm__ ("smlsl2 %0.4s,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlsl_high_s32 (int64x2_t a, int32x4_t b, int32x4_t c) -{ - int64x2_t result; - __asm__ ("smlsl2 %0.2d,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlsl_high_u8 (uint16x8_t a, uint8x16_t b, uint8x16_t c) -{ - uint16x8_t result; - __asm__ ("umlsl2 %0.8h,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlsl_high_u16 (uint32x4_t a, uint16x8_t b, uint16x8_t c) -{ - uint32x4_t result; - __asm__ ("umlsl2 %0.4s,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlsl_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) -{ - uint64x2_t result; - __asm__ ("umlsl2 %0.2d,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmlsl_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x4_t c_ = (c); \ - int16x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlsl %0.4s, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x2_t c_ = (c); \ - int32x2_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlsl %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x4_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlsl %0.4s, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x2_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlsl %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_laneq_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smlsl %0.4s, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_laneq_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x2_t b_ = (b); \ - int64x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smlsl %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_laneq_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umlsl %0.4s, %2.4h, %3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsl_laneq_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x2_t b_ = (b); \ - uint64x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umlsl %0.2d, %2.2s, %3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlsl_n_s16 (int32x4_t a, int16x4_t b, int16_t c) -{ - int32x4_t result; - __asm__ ("smlsl %0.4s, %2.4h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlsl_n_s32 (int64x2_t a, int32x2_t b, int32_t c) -{ - int64x2_t result; - __asm__ ("smlsl %0.2d, %2.2s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlsl_n_u16 (uint32x4_t a, uint16x4_t b, uint16_t c) -{ - uint32x4_t result; - __asm__ ("umlsl %0.4s, %2.4h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlsl_n_u32 (uint64x2_t a, uint32x2_t b, uint32_t c) -{ - uint64x2_t result; - __asm__ ("umlsl %0.2d, %2.2s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlsl_s8 (int16x8_t a, int8x8_t b, int8x8_t c) -{ - int16x8_t result; - __asm__ ("smlsl %0.8h, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlsl_s16 (int32x4_t a, int16x4_t b, int16x4_t c) -{ - int32x4_t result; - __asm__ ("smlsl %0.4s, %2.4h, %3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmlsl_s32 (int64x2_t a, int32x2_t b, int32x2_t c) -{ - int64x2_t result; - __asm__ ("smlsl %0.2d, %2.2s, %3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlsl_u8 (uint16x8_t a, uint8x8_t b, uint8x8_t c) -{ - uint16x8_t result; - __asm__ ("umlsl %0.8h, %2.8b, %3.8b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlsl_u16 (uint32x4_t a, uint16x4_t b, uint16x4_t c) -{ - uint32x4_t result; - __asm__ ("umlsl %0.4s, %2.4h, %3.4h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmlsl_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) -{ - uint64x2_t result; - __asm__ ("umlsl %0.2d, %2.2s, %3.2s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -#define vmlsq_lane_f32(a, b, c, d) \ - __extension__ \ - ({ \ - float32x4_t c_ = (c); \ - float32x4_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - float32x4_t t1; \ - __asm__ ("fmul %1.4s, %3.4s, %4.s[%5]; fsub %0.4s, %0.4s, %1.4s" \ - : "=w"(result), "=w"(t1) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsq_lane_s16(a, b, c, d) \ - __extension__ \ - ({ \ - int16x8_t c_ = (c); \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("mls %0.8h,%2.8h,%3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsq_lane_s32(a, b, c, d) \ - __extension__ \ - ({ \ - int32x4_t c_ = (c); \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("mls %0.4s,%2.4s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsq_lane_u16(a, b, c, d) \ - __extension__ \ - ({ \ - uint16x8_t c_ = (c); \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("mls %0.8h,%2.8h,%3.h[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsq_lane_u32(a, b, c, d) \ - __extension__ \ - ({ \ - uint32x4_t c_ = (c); \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("mls %0.4s,%2.4s,%3.s[%4]" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmlsq_laneq_f32(__a, __b, __c, __d) \ - __extension__ \ - ({ \ - float32x4_t __c_ = (__c); \ - float32x4_t __b_ = (__b); \ - float32x4_t __a_ = (__a); \ - float32x4_t __result; \ - float32x4_t __t1; \ - __asm__ ("fmul %1.4s, %3.4s, %4.s[%5]; fsub %0.4s, %0.4s, %1.4s" \ - : "=w"(__result), "=w"(__t1) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ - : /* No clobbers */); \ - __result; \ - }) - -#define vmlsq_laneq_s16(__a, __b, __c, __d) \ - __extension__ \ - ({ \ - int16x8_t __c_ = (__c); \ - int16x8_t __b_ = (__b); \ - int16x8_t __a_ = (__a); \ - int16x8_t __result; \ - __asm__ ("mls %0.8h, %2.8h, %3.h[%4]" \ - : "=w"(__result) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ - : /* No clobbers */); \ - __result; \ - }) - -#define vmlsq_laneq_s32(__a, __b, __c, __d) \ - __extension__ \ - ({ \ - int32x4_t __c_ = (__c); \ - int32x4_t __b_ = (__b); \ - int32x4_t __a_ = (__a); \ - int32x4_t __result; \ - __asm__ ("mls %0.4s, %2.4s, %3.s[%4]" \ - : "=w"(__result) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ - : /* No clobbers */); \ - __result; \ - }) - -#define vmlsq_laneq_u16(__a, __b, __c, __d) \ - __extension__ \ - ({ \ - uint16x8_t __c_ = (__c); \ - uint16x8_t __b_ = (__b); \ - uint16x8_t __a_ = (__a); \ - uint16x8_t __result; \ - __asm__ ("mls %0.8h, %2.8h, %3.h[%4]" \ - : "=w"(__result) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ - : /* No clobbers */); \ - __result; \ - }) - -#define vmlsq_laneq_u32(__a, __b, __c, __d) \ - __extension__ \ - ({ \ - uint32x4_t __c_ = (__c); \ - uint32x4_t __b_ = (__b); \ - uint32x4_t __a_ = (__a); \ - uint32x4_t __result; \ - __asm__ ("mls %0.4s, %2.4s, %3.s[%4]" \ - : "=w"(__result) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ - : /* No clobbers */); \ - __result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmlsq_n_f32 (float32x4_t a, float32x4_t b, float32_t c) -{ - float32x4_t result; - float32x4_t t1; - __asm__ ("fmul %1.4s, %3.4s, %4.s[0]; fsub %0.4s, %0.4s, %1.4s" - : "=w"(result), "=w"(t1) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmlsq_n_f64 (float64x2_t a, float64x2_t b, float64_t c) -{ - float64x2_t result; - float64x2_t t1; - __asm__ ("fmul %1.2d, %3.2d, %4.d[0]; fsub %0.2d, %0.2d, %1.2d" - : "=w"(result), "=w"(t1) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlsq_n_s16 (int16x8_t a, int16x8_t b, int16_t c) -{ - int16x8_t result; - __asm__ ("mls %0.8h, %2.8h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlsq_n_s32 (int32x4_t a, int32x4_t b, int32_t c) -{ - int32x4_t result; - __asm__ ("mls %0.4s, %2.4s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlsq_n_u16 (uint16x8_t a, uint16x8_t b, uint16_t c) -{ - uint16x8_t result; - __asm__ ("mls %0.8h, %2.8h, %3.h[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlsq_n_u32 (uint32x4_t a, uint32x4_t b, uint32_t c) -{ - uint32x4_t result; - __asm__ ("mls %0.4s, %2.4s, %3.s[0]" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmlsq_s8 (int8x16_t a, int8x16_t b, int8x16_t c) -{ - int8x16_t result; - __asm__ ("mls %0.16b,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmlsq_s16 (int16x8_t a, int16x8_t b, int16x8_t c) -{ - int16x8_t result; - __asm__ ("mls %0.8h,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmlsq_s32 (int32x4_t a, int32x4_t b, int32x4_t c) -{ - int32x4_t result; - __asm__ ("mls %0.4s,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmlsq_u8 (uint8x16_t a, uint8x16_t b, uint8x16_t c) -{ - uint8x16_t result; - __asm__ ("mls %0.16b,%2.16b,%3.16b" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmlsq_u16 (uint16x8_t a, uint16x8_t b, uint16x8_t c) -{ - uint16x8_t result; - __asm__ ("mls %0.8h,%2.8h,%3.8h" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmlsq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c) -{ - uint32x4_t result; - __asm__ ("mls %0.4s,%2.4s,%3.4s" - : "=w"(result) - : "0"(a), "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmov_n_f32 (float32_t a) -{ - float32x2_t result; - __asm__ ("dup %0.2s, %w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vmov_n_p8 (uint32_t a) -{ - poly8x8_t result; - __asm__ ("dup %0.8b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vmov_n_p16 (uint32_t a) -{ - poly16x4_t result; - __asm__ ("dup %0.4h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmov_n_s8 (int32_t a) -{ - int8x8_t result; - __asm__ ("dup %0.8b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmov_n_s16 (int32_t a) -{ - int16x4_t result; - __asm__ ("dup %0.4h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmov_n_s32 (int32_t a) -{ - int32x2_t result; - __asm__ ("dup %0.2s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vmov_n_s64 (int64_t a) -{ - int64x1_t result; - __asm__ ("ins %0.d[0],%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmov_n_u8 (uint32_t a) -{ - uint8x8_t result; - __asm__ ("dup %0.8b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmov_n_u16 (uint32_t a) -{ - uint16x4_t result; - __asm__ ("dup %0.4h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmov_n_u32 (uint32_t a) -{ - uint32x2_t result; - __asm__ ("dup %0.2s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vmov_n_u64 (uint64_t a) -{ - uint64x1_t result; - __asm__ ("ins %0.d[0],%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmovl_high_s8 (int8x16_t a) -{ - int16x8_t result; - __asm__ ("sshll2 %0.8h,%1.16b,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmovl_high_s16 (int16x8_t a) -{ - int32x4_t result; - __asm__ ("sshll2 %0.4s,%1.8h,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmovl_high_s32 (int32x4_t a) -{ - int64x2_t result; - __asm__ ("sshll2 %0.2d,%1.4s,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmovl_high_u8 (uint8x16_t a) -{ - uint16x8_t result; - __asm__ ("ushll2 %0.8h,%1.16b,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmovl_high_u16 (uint16x8_t a) -{ - uint32x4_t result; - __asm__ ("ushll2 %0.4s,%1.8h,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmovl_high_u32 (uint32x4_t a) -{ - uint64x2_t result; - __asm__ ("ushll2 %0.2d,%1.4s,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmovl_s8 (int8x8_t a) -{ - int16x8_t result; - __asm__ ("sshll %0.8h,%1.8b,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmovl_s16 (int16x4_t a) -{ - int32x4_t result; - __asm__ ("sshll %0.4s,%1.4h,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmovl_s32 (int32x2_t a) -{ - int64x2_t result; - __asm__ ("sshll %0.2d,%1.2s,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmovl_u8 (uint8x8_t a) -{ - uint16x8_t result; - __asm__ ("ushll %0.8h,%1.8b,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmovl_u16 (uint16x4_t a) -{ - uint32x4_t result; - __asm__ ("ushll %0.4s,%1.4h,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmovl_u32 (uint32x2_t a) -{ - uint64x2_t result; - __asm__ ("ushll %0.2d,%1.2s,#0" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmovn_high_s16 (int8x8_t a, int16x8_t b) -{ - int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0))); - __asm__ ("xtn2 %0.16b,%1.8h" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmovn_high_s32 (int16x4_t a, int32x4_t b) -{ - int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0))); - __asm__ ("xtn2 %0.8h,%1.4s" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmovn_high_s64 (int32x2_t a, int64x2_t b) -{ - int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0))); - __asm__ ("xtn2 %0.4s,%1.2d" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmovn_high_u16 (uint8x8_t a, uint16x8_t b) -{ - uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("xtn2 %0.16b,%1.8h" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmovn_high_u32 (uint16x4_t a, uint32x4_t b) -{ - uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0))); - __asm__ ("xtn2 %0.8h,%1.4s" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmovn_high_u64 (uint32x2_t a, uint64x2_t b) -{ - uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0))); - __asm__ ("xtn2 %0.4s,%1.2d" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmovn_s16 (int16x8_t a) -{ - int8x8_t result; - __asm__ ("xtn %0.8b,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmovn_s32 (int32x4_t a) -{ - int16x4_t result; - __asm__ ("xtn %0.4h,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmovn_s64 (int64x2_t a) -{ - int32x2_t result; - __asm__ ("xtn %0.2s,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmovn_u16 (uint16x8_t a) -{ - uint8x8_t result; - __asm__ ("xtn %0.8b,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmovn_u32 (uint32x4_t a) -{ - uint16x4_t result; - __asm__ ("xtn %0.4h,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmovn_u64 (uint64x2_t a) -{ - uint32x2_t result; - __asm__ ("xtn %0.2s,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmovq_n_f32 (float32_t a) -{ - float32x4_t result; - __asm__ ("dup %0.4s, %w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmovq_n_f64 (float64_t a) -{ - return (float64x2_t) {a, a}; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vmovq_n_p8 (uint32_t a) -{ - poly8x16_t result; - __asm__ ("dup %0.16b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vmovq_n_p16 (uint32_t a) -{ - poly16x8_t result; - __asm__ ("dup %0.8h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmovq_n_s8 (int32_t a) -{ - int8x16_t result; - __asm__ ("dup %0.16b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmovq_n_s16 (int32_t a) -{ - int16x8_t result; - __asm__ ("dup %0.8h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmovq_n_s32 (int32_t a) -{ - int32x4_t result; - __asm__ ("dup %0.4s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmovq_n_s64 (int64_t a) -{ - int64x2_t result; - __asm__ ("dup %0.2d,%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmovq_n_u8 (uint32_t a) -{ - uint8x16_t result; - __asm__ ("dup %0.16b,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmovq_n_u16 (uint32_t a) -{ - uint16x8_t result; - __asm__ ("dup %0.8h,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmovq_n_u32 (uint32_t a) -{ - uint32x4_t result; - __asm__ ("dup %0.4s,%w1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmovq_n_u64 (uint64_t a) -{ - uint64x2_t result; - __asm__ ("dup %0.2d,%x1" - : "=w"(result) - : "r"(a) - : /* No clobbers */); - return result; -} - -#define vmul_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x2_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("fmul %0.2s,%1.2s,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("mul %0.4h,%1.4h,%2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("mul %0.2s,%1.2s,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("mul %0.4h,%1.4h,%2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("mul %0.2s, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_laneq_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("fmul %0.2s, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_laneq_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("mul %0.4h, %1.4h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_laneq_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("mul %0.2s, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_laneq_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("mul %0.4h, %1.4h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmul_laneq_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("mul %0.2s, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmul_n_f32 (float32x2_t a, float32_t b) -{ - float32x2_t result; - __asm__ ("fmul %0.2s,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmul_n_s16 (int16x4_t a, int16_t b) -{ - int16x4_t result; - __asm__ ("mul %0.4h,%1.4h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmul_n_s32 (int32x2_t a, int32_t b) -{ - int32x2_t result; - __asm__ ("mul %0.2s,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmul_n_u16 (uint16x4_t a, uint16_t b) -{ - uint16x4_t result; - __asm__ ("mul %0.4h,%1.4h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmul_n_u32 (uint32x2_t a, uint32_t b) -{ - uint32x2_t result; - __asm__ ("mul %0.2s,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vmuld_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64_t a_ = (a); \ - float64_t result; \ - __asm__ ("fmul %d0,%d1,%2.d[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smull2 %0.4s, %1.8h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smull2 %0.2d, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umull2 %0.4s, %1.8h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umull2 %0.2d, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_laneq_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smull2 %0.4s, %1.8h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_laneq_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smull2 %0.2d, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_laneq_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umull2 %0.4s, %1.8h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_high_laneq_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umull2 %0.2d, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmull_high_n_s16 (int16x8_t a, int16_t b) -{ - int32x4_t result; - __asm__ ("smull2 %0.4s,%1.8h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmull_high_n_s32 (int32x4_t a, int32_t b) -{ - int64x2_t result; - __asm__ ("smull2 %0.2d,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmull_high_n_u16 (uint16x8_t a, uint16_t b) -{ - uint32x4_t result; - __asm__ ("umull2 %0.4s,%1.8h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmull_high_n_u32 (uint32x4_t a, uint32_t b) -{ - uint64x2_t result; - __asm__ ("umull2 %0.2d,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vmull_high_p8 (poly8x16_t a, poly8x16_t b) -{ - poly16x8_t result; - __asm__ ("pmull2 %0.8h,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmull_high_s8 (int8x16_t a, int8x16_t b) -{ - int16x8_t result; - __asm__ ("smull2 %0.8h,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmull_high_s16 (int16x8_t a, int16x8_t b) -{ - int32x4_t result; - __asm__ ("smull2 %0.4s,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmull_high_s32 (int32x4_t a, int32x4_t b) -{ - int64x2_t result; - __asm__ ("smull2 %0.2d,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmull_high_u8 (uint8x16_t a, uint8x16_t b) -{ - uint16x8_t result; - __asm__ ("umull2 %0.8h,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmull_high_u16 (uint16x8_t a, uint16x8_t b) -{ - uint32x4_t result; - __asm__ ("umull2 %0.4s,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmull_high_u32 (uint32x4_t a, uint32x4_t b) -{ - uint64x2_t result; - __asm__ ("umull2 %0.2d,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vmull_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smull %0.4s,%1.4h,%2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smull %0.2d,%1.2s,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umull %0.4s,%1.4h,%2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umull %0.2d, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_laneq_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("smull %0.4s, %1.4h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_laneq_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32x2_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("smull %0.2d, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_laneq_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("umull %0.4s, %1.4h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmull_laneq_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("umull %0.2d, %1.2s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmull_n_s16 (int16x4_t a, int16_t b) -{ - int32x4_t result; - __asm__ ("smull %0.4s,%1.4h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmull_n_s32 (int32x2_t a, int32_t b) -{ - int64x2_t result; - __asm__ ("smull %0.2d,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmull_n_u16 (uint16x4_t a, uint16_t b) -{ - uint32x4_t result; - __asm__ ("umull %0.4s,%1.4h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmull_n_u32 (uint32x2_t a, uint32_t b) -{ - uint64x2_t result; - __asm__ ("umull %0.2d,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vmull_p8 (poly8x8_t a, poly8x8_t b) -{ - poly16x8_t result; - __asm__ ("pmull %0.8h, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmull_s8 (int8x8_t a, int8x8_t b) -{ - int16x8_t result; - __asm__ ("smull %0.8h, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmull_s16 (int16x4_t a, int16x4_t b) -{ - int32x4_t result; - __asm__ ("smull %0.4s, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vmull_s32 (int32x2_t a, int32x2_t b) -{ - int64x2_t result; - __asm__ ("smull %0.2d, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmull_u8 (uint8x8_t a, uint8x8_t b) -{ - uint16x8_t result; - __asm__ ("umull %0.8h, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmull_u16 (uint16x4_t a, uint16x4_t b) -{ - uint32x4_t result; - __asm__ ("umull %0.4s, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vmull_u32 (uint32x2_t a, uint32x2_t b) -{ - uint64x2_t result; - __asm__ ("umull %0.2d, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vmulq_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x2_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("fmul %0.4s, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x1_t b_ = (b); \ - float64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("fmul %0.2d,%1.2d,%2.d[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("mul %0.8h,%1.8h,%2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("mul %0.4s,%1.4s,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("mul %0.8h,%1.8h,%2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("mul %0.4s, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_laneq_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("fmul %0.4s, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_laneq_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("fmul %0.2d,%1.2d,%2.d[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_laneq_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16x8_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("mul %0.8h, %1.8h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_laneq_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32x4_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("mul %0.4s, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_laneq_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16x8_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("mul %0.8h, %1.8h, %2.h[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulq_laneq_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32x4_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("mul %0.4s, %1.4s, %2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmulq_n_f32 (float32x4_t a, float32_t b) -{ - float32x4_t result; - __asm__ ("fmul %0.4s,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmulq_n_f64 (float64x2_t a, float64_t b) -{ - float64x2_t result; - __asm__ ("fmul %0.2d,%1.2d,%2.d[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmulq_n_s16 (int16x8_t a, int16_t b) -{ - int16x8_t result; - __asm__ ("mul %0.8h,%1.8h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmulq_n_s32 (int32x4_t a, int32_t b) -{ - int32x4_t result; - __asm__ ("mul %0.4s,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmulq_n_u16 (uint16x8_t a, uint16_t b) -{ - uint16x8_t result; - __asm__ ("mul %0.8h,%1.8h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmulq_n_u32 (uint32x4_t a, uint32_t b) -{ - uint32x4_t result; - __asm__ ("mul %0.4s,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vmuls_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32_t a_ = (a); \ - float32_t result; \ - __asm__ ("fmul %s0,%s1,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmulx_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fmulx %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vmulx_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32x2_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("fmulx %0.2s,%1.2s,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vmulxd_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("fmulx %d0, %d1, %d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmulxq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fmulx %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmulxq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fmulx %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vmulxq_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32x4_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("fmulx %0.4s,%1.4s,%2.s[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vmulxq_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64x2_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("fmulx %0.2d,%1.2d,%2.d[%3]" \ - : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vmulxs_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("fmulx %s0, %s1, %s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vmvn_p8 (poly8x8_t a) -{ - poly8x8_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmvn_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmvn_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmvn_s32 (int32x2_t a) -{ - int32x2_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmvn_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmvn_u16 (uint16x4_t a) -{ - uint16x4_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmvn_u32 (uint32x2_t a) -{ - uint32x2_t result; - __asm__ ("mvn %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vmvnq_p8 (poly8x16_t a) -{ - poly8x16_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmvnq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmvnq_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmvnq_s32 (int32x4_t a) -{ - int32x4_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmvnq_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmvnq_u16 (uint16x8_t a) -{ - uint16x8_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmvnq_u32 (uint32x4_t a) -{ - uint32x4_t result; - __asm__ ("mvn %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vneg_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("fneg %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vneg_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("neg %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vneg_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("neg %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vneg_s32 (int32x2_t a) -{ - int32x2_t result; - __asm__ ("neg %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vnegq_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("fneg %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vnegq_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("fneg %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vnegq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("neg %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vnegq_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("neg %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vnegq_s32 (int32x4_t a) -{ - int32x4_t result; - __asm__ ("neg %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vnegq_s64 (int64x2_t a) -{ - int64x2_t result; - __asm__ ("neg %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vpadal_s8 (int16x4_t a, int8x8_t b) -{ - int16x4_t result; - __asm__ ("sadalp %0.4h,%2.8b" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vpadal_s16 (int32x2_t a, int16x4_t b) -{ - int32x2_t result; - __asm__ ("sadalp %0.2s,%2.4h" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vpadal_s32 (int64x1_t a, int32x2_t b) -{ - int64x1_t result; - __asm__ ("sadalp %0.1d,%2.2s" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vpadal_u8 (uint16x4_t a, uint8x8_t b) -{ - uint16x4_t result; - __asm__ ("uadalp %0.4h,%2.8b" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vpadal_u16 (uint32x2_t a, uint16x4_t b) -{ - uint32x2_t result; - __asm__ ("uadalp %0.2s,%2.4h" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vpadal_u32 (uint64x1_t a, uint32x2_t b) -{ - uint64x1_t result; - __asm__ ("uadalp %0.1d,%2.2s" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vpadalq_s8 (int16x8_t a, int8x16_t b) -{ - int16x8_t result; - __asm__ ("sadalp %0.8h,%2.16b" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vpadalq_s16 (int32x4_t a, int16x8_t b) -{ - int32x4_t result; - __asm__ ("sadalp %0.4s,%2.8h" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vpadalq_s32 (int64x2_t a, int32x4_t b) -{ - int64x2_t result; - __asm__ ("sadalp %0.2d,%2.4s" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vpadalq_u8 (uint16x8_t a, uint8x16_t b) -{ - uint16x8_t result; - __asm__ ("uadalp %0.8h,%2.16b" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vpadalq_u16 (uint32x4_t a, uint16x8_t b) -{ - uint32x4_t result; - __asm__ ("uadalp %0.4s,%2.8h" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vpadalq_u32 (uint64x2_t a, uint32x4_t b) -{ - uint64x2_t result; - __asm__ ("uadalp %0.2d,%2.4s" - : "=w"(result) - : "0"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vpadd_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("faddp %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vpadd_s8 (int8x8_t __a, int8x8_t __b) -{ - return __builtin_aarch64_addpv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vpadd_s16 (int16x4_t __a, int16x4_t __b) -{ - return __builtin_aarch64_addpv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vpadd_s32 (int32x2_t __a, int32x2_t __b) -{ - return __builtin_aarch64_addpv2si (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vpadd_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_addpv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vpadd_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_addpv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vpadd_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_addpv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vpaddd_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("faddp %d0,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vpaddl_s8 (int8x8_t a) -{ - int16x4_t result; - __asm__ ("saddlp %0.4h,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vpaddl_s16 (int16x4_t a) -{ - int32x2_t result; - __asm__ ("saddlp %0.2s,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vpaddl_s32 (int32x2_t a) -{ - int64x1_t result; - __asm__ ("saddlp %0.1d,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vpaddl_u8 (uint8x8_t a) -{ - uint16x4_t result; - __asm__ ("uaddlp %0.4h,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vpaddl_u16 (uint16x4_t a) -{ - uint32x2_t result; - __asm__ ("uaddlp %0.2s,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vpaddl_u32 (uint32x2_t a) -{ - uint64x1_t result; - __asm__ ("uaddlp %0.1d,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vpaddlq_s8 (int8x16_t a) -{ - int16x8_t result; - __asm__ ("saddlp %0.8h,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vpaddlq_s16 (int16x8_t a) -{ - int32x4_t result; - __asm__ ("saddlp %0.4s,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vpaddlq_s32 (int32x4_t a) -{ - int64x2_t result; - __asm__ ("saddlp %0.2d,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vpaddlq_u8 (uint8x16_t a) -{ - uint16x8_t result; - __asm__ ("uaddlp %0.8h,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vpaddlq_u16 (uint16x8_t a) -{ - uint32x4_t result; - __asm__ ("uaddlp %0.4s,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vpaddlq_u32 (uint32x4_t a) -{ - uint64x2_t result; - __asm__ ("uaddlp %0.2d,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vpaddq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("faddp %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vpaddq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("faddp %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vpaddq_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("addp %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vpaddq_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("addp %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vpaddq_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("addp %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vpaddq_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("addp %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vpaddq_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("addp %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vpaddq_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("addp %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vpaddq_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("addp %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vpaddq_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("addp %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vpadds_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("faddp %s0,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vpmax_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fmaxp %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vpmax_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("smaxp %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vpmax_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("smaxp %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vpmax_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("smaxp %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vpmax_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("umaxp %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vpmax_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("umaxp %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vpmax_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("umaxp %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vpmaxnm_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fmaxnmp %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vpmaxnmq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fmaxnmp %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vpmaxnmq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fmaxnmp %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vpmaxnmqd_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("fmaxnmp %d0,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vpmaxnms_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("fmaxnmp %s0,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vpmaxq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fmaxp %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vpmaxq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fmaxp %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vpmaxq_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("smaxp %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vpmaxq_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("smaxp %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vpmaxq_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("smaxp %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vpmaxq_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("umaxp %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vpmaxq_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("umaxp %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vpmaxq_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("umaxp %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vpmaxqd_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("fmaxp %d0,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vpmaxs_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("fmaxp %s0,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vpmin_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fminp %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vpmin_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("sminp %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vpmin_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("sminp %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vpmin_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("sminp %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vpmin_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("uminp %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vpmin_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("uminp %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vpmin_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("uminp %0.2s, %1.2s, %2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vpminnm_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("fminnmp %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vpminnmq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fminnmp %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vpminnmq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fminnmp %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vpminnmqd_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("fminnmp %d0,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vpminnms_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("fminnmp %s0,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vpminq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("fminp %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vpminq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("fminp %0.2d, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vpminq_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("sminp %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vpminq_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("sminp %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vpminq_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("sminp %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vpminq_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("uminp %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vpminq_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("uminp %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vpminq_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("uminp %0.4s, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vpminqd_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("fminp %d0,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vpmins_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("fminp %s0,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqdmulh_n_s16 (int16x4_t a, int16_t b) -{ - int16x4_t result; - __asm__ ("sqdmulh %0.4h,%1.4h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqdmulh_n_s32 (int32x2_t a, int32_t b) -{ - int32x2_t result; - __asm__ ("sqdmulh %0.2s,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqdmulhq_n_s16 (int16x8_t a, int16_t b) -{ - int16x8_t result; - __asm__ ("sqdmulh %0.8h,%1.8h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmulhq_n_s32 (int32x4_t a, int32_t b) -{ - int32x4_t result; - __asm__ ("sqdmulh %0.4s,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqmovn_high_s16 (int8x8_t a, int16x8_t b) -{ - int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0))); - __asm__ ("sqxtn2 %0.16b, %1.8h" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqmovn_high_s32 (int16x4_t a, int32x4_t b) -{ - int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0))); - __asm__ ("sqxtn2 %0.8h, %1.4s" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqmovn_high_s64 (int32x2_t a, int64x2_t b) -{ - int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0))); - __asm__ ("sqxtn2 %0.4s, %1.2d" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqmovn_high_u16 (uint8x8_t a, uint16x8_t b) -{ - uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("uqxtn2 %0.16b, %1.8h" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqmovn_high_u32 (uint16x4_t a, uint32x4_t b) -{ - uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0))); - __asm__ ("uqxtn2 %0.8h, %1.4s" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqmovn_high_u64 (uint32x2_t a, uint64x2_t b) -{ - uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0))); - __asm__ ("uqxtn2 %0.4s, %1.2d" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqmovun_high_s16 (uint8x8_t a, int16x8_t b) -{ - uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("sqxtun2 %0.16b, %1.8h" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqmovun_high_s32 (uint16x4_t a, int32x4_t b) -{ - uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0))); - __asm__ ("sqxtun2 %0.8h, %1.4s" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqmovun_high_s64 (uint32x2_t a, int64x2_t b) -{ - uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0))); - __asm__ ("sqxtun2 %0.4s, %1.2d" - : "+w"(result) - : "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqrdmulh_n_s16 (int16x4_t a, int16_t b) -{ - int16x4_t result; - __asm__ ("sqrdmulh %0.4h,%1.4h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqrdmulh_n_s32 (int32x2_t a, int32_t b) -{ - int32x2_t result; - __asm__ ("sqrdmulh %0.2s,%1.2s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqrdmulhq_n_s16 (int16x8_t a, int16_t b) -{ - int16x8_t result; - __asm__ ("sqrdmulh %0.8h,%1.8h,%2.h[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqrdmulhq_n_s32 (int32x4_t a, int32_t b) -{ - int32x4_t result; - __asm__ ("sqrdmulh %0.4s,%1.4s,%2.s[0]" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vqrshrn_high_n_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int8x8_t a_ = (a); \ - int8x16_t result = vcombine_s8 \ - (a_, vcreate_s8 (UINT64_C (0x0))); \ - __asm__ ("sqrshrn2 %0.16b, %1.8h, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrn_high_n_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x8_t result = vcombine_s16 \ - (a_, vcreate_s16 (UINT64_C (0x0))); \ - __asm__ ("sqrshrn2 %0.8h, %1.4s, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrn_high_n_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x4_t result = vcombine_s32 \ - (a_, vcreate_s32 (UINT64_C (0x0))); \ - __asm__ ("sqrshrn2 %0.4s, %1.2d, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrn_high_n_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x16_t result = vcombine_u8 \ - (a_, vcreate_u8 (UINT64_C (0x0))); \ - __asm__ ("uqrshrn2 %0.16b, %1.8h, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrn_high_n_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x8_t result = vcombine_u16 \ - (a_, vcreate_u16 (UINT64_C (0x0))); \ - __asm__ ("uqrshrn2 %0.8h, %1.4s, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrn_high_n_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x4_t result = vcombine_u32 \ - (a_, vcreate_u32 (UINT64_C (0x0))); \ - __asm__ ("uqrshrn2 %0.4s, %1.2d, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrun_high_n_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x16_t result = vcombine_u8 \ - (a_, vcreate_u8 (UINT64_C (0x0))); \ - __asm__ ("sqrshrun2 %0.16b, %1.8h, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrun_high_n_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x8_t result = vcombine_u16 \ - (a_, vcreate_u16 (UINT64_C (0x0))); \ - __asm__ ("sqrshrun2 %0.8h, %1.4s, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqrshrun_high_n_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x4_t result = vcombine_u32 \ - (a_, vcreate_u32 (UINT64_C (0x0))); \ - __asm__ ("sqrshrun2 %0.4s, %1.2d, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrn_high_n_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int8x8_t a_ = (a); \ - int8x16_t result = vcombine_s8 \ - (a_, vcreate_s8 (UINT64_C (0x0))); \ - __asm__ ("sqshrn2 %0.16b, %1.8h, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrn_high_n_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x8_t result = vcombine_s16 \ - (a_, vcreate_s16 (UINT64_C (0x0))); \ - __asm__ ("sqshrn2 %0.8h, %1.4s, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrn_high_n_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x4_t result = vcombine_s32 \ - (a_, vcreate_s32 (UINT64_C (0x0))); \ - __asm__ ("sqshrn2 %0.4s, %1.2d, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrn_high_n_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x16_t result = vcombine_u8 \ - (a_, vcreate_u8 (UINT64_C (0x0))); \ - __asm__ ("uqshrn2 %0.16b, %1.8h, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrn_high_n_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x8_t result = vcombine_u16 \ - (a_, vcreate_u16 (UINT64_C (0x0))); \ - __asm__ ("uqshrn2 %0.8h, %1.4s, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrn_high_n_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x4_t result = vcombine_u32 \ - (a_, vcreate_u32 (UINT64_C (0x0))); \ - __asm__ ("uqshrn2 %0.4s, %1.2d, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrun_high_n_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x16_t result = vcombine_u8 \ - (a_, vcreate_u8 (UINT64_C (0x0))); \ - __asm__ ("sqshrun2 %0.16b, %1.8h, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrun_high_n_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x8_t result = vcombine_u16 \ - (a_, vcreate_u16 (UINT64_C (0x0))); \ - __asm__ ("sqshrun2 %0.8h, %1.4s, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vqshrun_high_n_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x4_t result = vcombine_u32 \ - (a_, vcreate_u32 (UINT64_C (0x0))); \ - __asm__ ("sqshrun2 %0.4s, %1.2d, #%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrbit_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("rbit %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrbit_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("rbit %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrbitq_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("rbit %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrbitq_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("rbit %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrecpe_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frecpe %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrecpe_u32 (uint32x2_t a) -{ - uint32x2_t result; - __asm__ ("urecpe %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vrecped_f64 (float64_t a) -{ - float64_t result; - __asm__ ("frecpe %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrecpeq_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frecpe %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrecpeq_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frecpe %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrecpeq_u32 (uint32x4_t a) -{ - uint32x4_t result; - __asm__ ("urecpe %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vrecpes_f32 (float32_t a) -{ - float32_t result; - __asm__ ("frecpe %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrecps_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("frecps %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vrecpsd_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("frecps %d0,%d1,%d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrecpsq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("frecps %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrecpsq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("frecps %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vrecpss_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("frecps %s0,%s1,%s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vrecpxd_f64 (float64_t a) -{ - float64_t result; - __asm__ ("frecpe %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vrecpxs_f32 (float32_t a) -{ - float32_t result; - __asm__ ("frecpe %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vrev16_p8 (poly8x8_t a) -{ - poly8x8_t result; - __asm__ ("rev16 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrev16_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("rev16 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrev16_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("rev16 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vrev16q_p8 (poly8x16_t a) -{ - poly8x16_t result; - __asm__ ("rev16 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrev16q_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("rev16 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrev16q_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("rev16 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vrev32_p8 (poly8x8_t a) -{ - poly8x8_t result; - __asm__ ("rev32 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vrev32_p16 (poly16x4_t a) -{ - poly16x4_t result; - __asm__ ("rev32 %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrev32_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("rev32 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrev32_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("rev32 %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrev32_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("rev32 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrev32_u16 (uint16x4_t a) -{ - uint16x4_t result; - __asm__ ("rev32 %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vrev32q_p8 (poly8x16_t a) -{ - poly8x16_t result; - __asm__ ("rev32 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vrev32q_p16 (poly16x8_t a) -{ - poly16x8_t result; - __asm__ ("rev32 %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrev32q_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("rev32 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrev32q_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("rev32 %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrev32q_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("rev32 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrev32q_u16 (uint16x8_t a) -{ - uint16x8_t result; - __asm__ ("rev32 %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrev64_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("rev64 %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vrev64_p8 (poly8x8_t a) -{ - poly8x8_t result; - __asm__ ("rev64 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vrev64_p16 (poly16x4_t a) -{ - poly16x4_t result; - __asm__ ("rev64 %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrev64_s8 (int8x8_t a) -{ - int8x8_t result; - __asm__ ("rev64 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrev64_s16 (int16x4_t a) -{ - int16x4_t result; - __asm__ ("rev64 %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vrev64_s32 (int32x2_t a) -{ - int32x2_t result; - __asm__ ("rev64 %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrev64_u8 (uint8x8_t a) -{ - uint8x8_t result; - __asm__ ("rev64 %0.8b,%1.8b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrev64_u16 (uint16x4_t a) -{ - uint16x4_t result; - __asm__ ("rev64 %0.4h,%1.4h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrev64_u32 (uint32x2_t a) -{ - uint32x2_t result; - __asm__ ("rev64 %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrev64q_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("rev64 %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vrev64q_p8 (poly8x16_t a) -{ - poly8x16_t result; - __asm__ ("rev64 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vrev64q_p16 (poly16x8_t a) -{ - poly16x8_t result; - __asm__ ("rev64 %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrev64q_s8 (int8x16_t a) -{ - int8x16_t result; - __asm__ ("rev64 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrev64q_s16 (int16x8_t a) -{ - int16x8_t result; - __asm__ ("rev64 %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vrev64q_s32 (int32x4_t a) -{ - int32x4_t result; - __asm__ ("rev64 %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrev64q_u8 (uint8x16_t a) -{ - uint8x16_t result; - __asm__ ("rev64 %0.16b,%1.16b" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrev64q_u16 (uint16x8_t a) -{ - uint16x8_t result; - __asm__ ("rev64 %0.8h,%1.8h" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrev64q_u32 (uint32x4_t a) -{ - uint32x4_t result; - __asm__ ("rev64 %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrnd_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frintz %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrnda_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frinta %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrndm_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frintm %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrndn_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frintn %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrndp_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frintp %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrndq_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frintz %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrndq_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frintz %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrndqa_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frinta %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrndqa_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frinta %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrndqm_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frintm %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrndqm_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frintm %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrndqn_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frintn %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrndqn_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frintn %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrndqp_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frintp %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrndqp_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frintp %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -#define vrshrn_high_n_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int8x8_t a_ = (a); \ - int8x16_t result = vcombine_s8 \ - (a_, vcreate_s8 (UINT64_C (0x0))); \ - __asm__ ("rshrn2 %0.16b,%1.8h,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_high_n_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x8_t result = vcombine_s16 \ - (a_, vcreate_s16 (UINT64_C (0x0))); \ - __asm__ ("rshrn2 %0.8h,%1.4s,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_high_n_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x4_t result = vcombine_s32 \ - (a_, vcreate_s32 (UINT64_C (0x0))); \ - __asm__ ("rshrn2 %0.4s,%1.2d,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_high_n_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x16_t result = vcombine_u8 \ - (a_, vcreate_u8 (UINT64_C (0x0))); \ - __asm__ ("rshrn2 %0.16b,%1.8h,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_high_n_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x8_t result = vcombine_u16 \ - (a_, vcreate_u16 (UINT64_C (0x0))); \ - __asm__ ("rshrn2 %0.8h,%1.4s,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_high_n_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x4_t result = vcombine_u32 \ - (a_, vcreate_u32 (UINT64_C (0x0))); \ - __asm__ ("rshrn2 %0.4s,%1.2d,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_n_s16(a, b) \ - __extension__ \ - ({ \ - int16x8_t a_ = (a); \ - int8x8_t result; \ - __asm__ ("rshrn %0.8b,%1.8h,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_n_s32(a, b) \ - __extension__ \ - ({ \ - int32x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("rshrn %0.4h,%1.4s,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_n_s64(a, b) \ - __extension__ \ - ({ \ - int64x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("rshrn %0.2s,%1.2d,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_n_u16(a, b) \ - __extension__ \ - ({ \ - uint16x8_t a_ = (a); \ - uint8x8_t result; \ - __asm__ ("rshrn %0.8b,%1.8h,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_n_u32(a, b) \ - __extension__ \ - ({ \ - uint32x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("rshrn %0.4h,%1.4s,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vrshrn_n_u64(a, b) \ - __extension__ \ - ({ \ - uint64x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("rshrn %0.2s,%1.2d,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrsqrte_f32 (float32x2_t a) -{ - float32x2_t result; - __asm__ ("frsqrte %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrsqrte_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frsqrte %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrsqrte_u32 (uint32x2_t a) -{ - uint32x2_t result; - __asm__ ("ursqrte %0.2s,%1.2s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vrsqrted_f64 (float64_t a) -{ - float64_t result; - __asm__ ("frsqrte %d0,%d1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrsqrteq_f32 (float32x4_t a) -{ - float32x4_t result; - __asm__ ("frsqrte %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrsqrteq_f64 (float64x2_t a) -{ - float64x2_t result; - __asm__ ("frsqrte %0.2d,%1.2d" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrsqrteq_u32 (uint32x4_t a) -{ - uint32x4_t result; - __asm__ ("ursqrte %0.4s,%1.4s" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vrsqrtes_f32 (float32_t a) -{ - float32_t result; - __asm__ ("frsqrte %s0,%s1" - : "=w"(result) - : "w"(a) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vrsqrts_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("frsqrts %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vrsqrtsd_f64 (float64_t a, float64_t b) -{ - float64_t result; - __asm__ ("frsqrts %d0,%d1,%d2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vrsqrtsq_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("frsqrts %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrsqrtsq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("frsqrts %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vrsqrtss_f32 (float32_t a, float32_t b) -{ - float32_t result; - __asm__ ("frsqrts %s0,%s1,%s2" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vrsrtsq_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("frsqrts %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrsubhn_high_s16 (int8x8_t a, int16x8_t b, int16x8_t c) -{ - int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0))); - __asm__ ("rsubhn2 %0.16b, %1.8h, %2.8h" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrsubhn_high_s32 (int16x4_t a, int32x4_t b, int32x4_t c) -{ - int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0))); - __asm__ ("rsubhn2 %0.8h, %1.4s, %2.4s" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vrsubhn_high_s64 (int32x2_t a, int64x2_t b, int64x2_t c) -{ - int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0))); - __asm__ ("rsubhn2 %0.4s, %1.2d, %2.2d" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrsubhn_high_u16 (uint8x8_t a, uint16x8_t b, uint16x8_t c) -{ - uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("rsubhn2 %0.16b, %1.8h, %2.8h" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrsubhn_high_u32 (uint16x4_t a, uint32x4_t b, uint32x4_t c) -{ - uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0))); - __asm__ ("rsubhn2 %0.8h, %1.4s, %2.4s" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrsubhn_high_u64 (uint32x2_t a, uint64x2_t b, uint64x2_t c) -{ - uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0))); - __asm__ ("rsubhn2 %0.4s, %1.2d, %2.2d" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrsubhn_s16 (int16x8_t a, int16x8_t b) -{ - int8x8_t result; - __asm__ ("rsubhn %0.8b, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrsubhn_s32 (int32x4_t a, int32x4_t b) -{ - int16x4_t result; - __asm__ ("rsubhn %0.4h, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vrsubhn_s64 (int64x2_t a, int64x2_t b) -{ - int32x2_t result; - __asm__ ("rsubhn %0.2s, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrsubhn_u16 (uint16x8_t a, uint16x8_t b) -{ - uint8x8_t result; - __asm__ ("rsubhn %0.8b, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrsubhn_u32 (uint32x4_t a, uint32x4_t b) -{ - uint16x4_t result; - __asm__ ("rsubhn %0.4h, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrsubhn_u64 (uint64x2_t a, uint64x2_t b) -{ - uint32x2_t result; - __asm__ ("rsubhn %0.2s, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -#define vset_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x2_t b_ = (b); \ - float32_t a_ = (a); \ - float32x2_t result; \ - __asm__ ("ins %0.s[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x1_t b_ = (b); \ - float64_t a_ = (a); \ - float64x1_t result; \ - __asm__ ("ins %0.d[%3], %x1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x8_t b_ = (b); \ - poly8_t a_ = (a); \ - poly8x8_t result; \ - __asm__ ("ins %0.b[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x4_t b_ = (b); \ - poly16_t a_ = (a); \ - poly16x4_t result; \ - __asm__ ("ins %0.h[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x8_t b_ = (b); \ - int8_t a_ = (a); \ - int8x8_t result; \ - __asm__ ("ins %0.b[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - int16_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("ins %0.h[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - int32_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("ins %0.s[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x1_t b_ = (b); \ - int64_t a_ = (a); \ - int64x1_t result; \ - __asm__ ("ins %0.d[%3], %x1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x8_t b_ = (b); \ - uint8_t a_ = (a); \ - uint8x8_t result; \ - __asm__ ("ins %0.b[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - uint16_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("ins %0.h[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - uint32_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("ins %0.s[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vset_lane_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x1_t b_ = (b); \ - uint64_t a_ = (a); \ - uint64x1_t result; \ - __asm__ ("ins %0.d[%3], %x1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32_t a_ = (a); \ - float32x4_t result; \ - __asm__ ("ins %0.s[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64_t a_ = (a); \ - float64x2_t result; \ - __asm__ ("ins %0.d[%3], %x1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x16_t b_ = (b); \ - poly8_t a_ = (a); \ - poly8x16_t result; \ - __asm__ ("ins %0.b[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x8_t b_ = (b); \ - poly16_t a_ = (a); \ - poly16x8_t result; \ - __asm__ ("ins %0.h[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x16_t b_ = (b); \ - int8_t a_ = (a); \ - int8x16_t result; \ - __asm__ ("ins %0.b[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16_t a_ = (a); \ - int16x8_t result; \ - __asm__ ("ins %0.h[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32_t a_ = (a); \ - int32x4_t result; \ - __asm__ ("ins %0.s[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int64_t a_ = (a); \ - int64x2_t result; \ - __asm__ ("ins %0.d[%3], %x1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x16_t b_ = (b); \ - uint8_t a_ = (a); \ - uint8x16_t result; \ - __asm__ ("ins %0.b[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16_t a_ = (a); \ - uint16x8_t result; \ - __asm__ ("ins %0.h[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32_t a_ = (a); \ - uint32x4_t result; \ - __asm__ ("ins %0.s[%3], %w1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsetq_lane_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint64_t a_ = (a); \ - uint64x2_t result; \ - __asm__ ("ins %0.d[%3], %x1" \ - : "=w"(result) \ - : "r"(a_), "0"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_high_n_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int8x8_t a_ = (a); \ - int8x16_t result = vcombine_s8 \ - (a_, vcreate_s8 (UINT64_C (0x0))); \ - __asm__ ("shrn2 %0.16b,%1.8h,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_high_n_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int16x4_t a_ = (a); \ - int16x8_t result = vcombine_s16 \ - (a_, vcreate_s16 (UINT64_C (0x0))); \ - __asm__ ("shrn2 %0.8h,%1.4s,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_high_n_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int32x2_t a_ = (a); \ - int32x4_t result = vcombine_s32 \ - (a_, vcreate_s32 (UINT64_C (0x0))); \ - __asm__ ("shrn2 %0.4s,%1.2d,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_high_n_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint8x8_t a_ = (a); \ - uint8x16_t result = vcombine_u8 \ - (a_, vcreate_u8 (UINT64_C (0x0))); \ - __asm__ ("shrn2 %0.16b,%1.8h,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_high_n_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint16x4_t a_ = (a); \ - uint16x8_t result = vcombine_u16 \ - (a_, vcreate_u16 (UINT64_C (0x0))); \ - __asm__ ("shrn2 %0.8h,%1.4s,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_high_n_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint32x2_t a_ = (a); \ - uint32x4_t result = vcombine_u32 \ - (a_, vcreate_u32 (UINT64_C (0x0))); \ - __asm__ ("shrn2 %0.4s,%1.2d,#%2" \ - : "+w"(result) \ - : "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_n_s16(a, b) \ - __extension__ \ - ({ \ - int16x8_t a_ = (a); \ - int8x8_t result; \ - __asm__ ("shrn %0.8b,%1.8h,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_n_s32(a, b) \ - __extension__ \ - ({ \ - int32x4_t a_ = (a); \ - int16x4_t result; \ - __asm__ ("shrn %0.4h,%1.4s,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_n_s64(a, b) \ - __extension__ \ - ({ \ - int64x2_t a_ = (a); \ - int32x2_t result; \ - __asm__ ("shrn %0.2s,%1.2d,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_n_u16(a, b) \ - __extension__ \ - ({ \ - uint16x8_t a_ = (a); \ - uint8x8_t result; \ - __asm__ ("shrn %0.8b,%1.8h,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_n_u32(a, b) \ - __extension__ \ - ({ \ - uint32x4_t a_ = (a); \ - uint16x4_t result; \ - __asm__ ("shrn %0.4h,%1.4s,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vshrn_n_u64(a, b) \ - __extension__ \ - ({ \ - uint64x2_t a_ = (a); \ - uint32x2_t result; \ - __asm__ ("shrn %0.2s,%1.2d,%2" \ - : "=w"(result) \ - : "w"(a_), "i"(b) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsli_n_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x8_t b_ = (b); \ - poly8x8_t a_ = (a); \ - poly8x8_t result; \ - __asm__ ("sli %0.8b,%2.8b,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsli_n_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x4_t b_ = (b); \ - poly16x4_t a_ = (a); \ - poly16x4_t result; \ - __asm__ ("sli %0.4h,%2.4h,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsliq_n_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x16_t b_ = (b); \ - poly8x16_t a_ = (a); \ - poly8x16_t result; \ - __asm__ ("sli %0.16b,%2.16b,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsliq_n_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x8_t b_ = (b); \ - poly16x8_t a_ = (a); \ - poly16x8_t result; \ - __asm__ ("sli %0.8h,%2.8h,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsri_n_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x8_t b_ = (b); \ - poly8x8_t a_ = (a); \ - poly8x8_t result; \ - __asm__ ("sri %0.8b,%2.8b,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsri_n_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x4_t b_ = (b); \ - poly16x4_t a_ = (a); \ - poly16x4_t result; \ - __asm__ ("sri %0.4h,%2.4h,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsriq_n_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x16_t b_ = (b); \ - poly8x16_t a_ = (a); \ - poly8x16_t result; \ - __asm__ ("sri %0.16b,%2.16b,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vsriq_n_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x8_t b_ = (b); \ - poly16x8_t a_ = (a); \ - poly16x8_t result; \ - __asm__ ("sri %0.8h,%2.8h,%3" \ - : "=w"(result) \ - : "0"(a_), "w"(b_), "i"(c) \ - : /* No clobbers */); \ - result; \ - }) - -#define vst1_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x2_t b_ = (b); \ - float32_t * a_ = (a); \ - __asm__ ("st1 {%1.s}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x1_t b_ = (b); \ - float64_t * a_ = (a); \ - __asm__ ("st1 {%1.d}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x8_t b_ = (b); \ - poly8_t * a_ = (a); \ - __asm__ ("st1 {%1.b}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x4_t b_ = (b); \ - poly16_t * a_ = (a); \ - __asm__ ("st1 {%1.h}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x8_t b_ = (b); \ - int8_t * a_ = (a); \ - __asm__ ("st1 {%1.b}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x4_t b_ = (b); \ - int16_t * a_ = (a); \ - __asm__ ("st1 {%1.h}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x2_t b_ = (b); \ - int32_t * a_ = (a); \ - __asm__ ("st1 {%1.s}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x1_t b_ = (b); \ - int64_t * a_ = (a); \ - __asm__ ("st1 {%1.d}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x8_t b_ = (b); \ - uint8_t * a_ = (a); \ - __asm__ ("st1 {%1.b}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x4_t b_ = (b); \ - uint16_t * a_ = (a); \ - __asm__ ("st1 {%1.h}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x2_t b_ = (b); \ - uint32_t * a_ = (a); \ - __asm__ ("st1 {%1.s}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1_lane_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x1_t b_ = (b); \ - uint64_t * a_ = (a); \ - __asm__ ("st1 {%1.d}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - - -#define vst1q_lane_f32(a, b, c) \ - __extension__ \ - ({ \ - float32x4_t b_ = (b); \ - float32_t * a_ = (a); \ - __asm__ ("st1 {%1.s}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_f64(a, b, c) \ - __extension__ \ - ({ \ - float64x2_t b_ = (b); \ - float64_t * a_ = (a); \ - __asm__ ("st1 {%1.d}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_p8(a, b, c) \ - __extension__ \ - ({ \ - poly8x16_t b_ = (b); \ - poly8_t * a_ = (a); \ - __asm__ ("st1 {%1.b}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_p16(a, b, c) \ - __extension__ \ - ({ \ - poly16x8_t b_ = (b); \ - poly16_t * a_ = (a); \ - __asm__ ("st1 {%1.h}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_s8(a, b, c) \ - __extension__ \ - ({ \ - int8x16_t b_ = (b); \ - int8_t * a_ = (a); \ - __asm__ ("st1 {%1.b}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_s16(a, b, c) \ - __extension__ \ - ({ \ - int16x8_t b_ = (b); \ - int16_t * a_ = (a); \ - __asm__ ("st1 {%1.h}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_s32(a, b, c) \ - __extension__ \ - ({ \ - int32x4_t b_ = (b); \ - int32_t * a_ = (a); \ - __asm__ ("st1 {%1.s}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_s64(a, b, c) \ - __extension__ \ - ({ \ - int64x2_t b_ = (b); \ - int64_t * a_ = (a); \ - __asm__ ("st1 {%1.d}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_u8(a, b, c) \ - __extension__ \ - ({ \ - uint8x16_t b_ = (b); \ - uint8_t * a_ = (a); \ - __asm__ ("st1 {%1.b}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_u16(a, b, c) \ - __extension__ \ - ({ \ - uint16x8_t b_ = (b); \ - uint16_t * a_ = (a); \ - __asm__ ("st1 {%1.h}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_u32(a, b, c) \ - __extension__ \ - ({ \ - uint32x4_t b_ = (b); \ - uint32_t * a_ = (a); \ - __asm__ ("st1 {%1.s}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -#define vst1q_lane_u64(a, b, c) \ - __extension__ \ - ({ \ - uint64x2_t b_ = (b); \ - uint64_t * a_ = (a); \ - __asm__ ("st1 {%1.d}[%2],[%0]" \ - : \ - : "r"(a_), "w"(b_), "i"(c) \ - : "memory"); \ - }) - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vsubhn_high_s16 (int8x8_t a, int16x8_t b, int16x8_t c) -{ - int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0))); - __asm__ ("subhn2 %0.16b, %1.8h, %2.8h" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsubhn_high_s32 (int16x4_t a, int32x4_t b, int32x4_t c) -{ - int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0))); - __asm__ ("subhn2 %0.8h, %1.4s, %2.4s" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsubhn_high_s64 (int32x2_t a, int64x2_t b, int64x2_t c) -{ - int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0))); - __asm__ ("subhn2 %0.4s, %1.2d, %2.2d" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vsubhn_high_u16 (uint8x8_t a, uint16x8_t b, uint16x8_t c) -{ - uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("subhn2 %0.16b, %1.8h, %2.8h" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsubhn_high_u32 (uint16x4_t a, uint32x4_t b, uint32x4_t c) -{ - uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0))); - __asm__ ("subhn2 %0.8h, %1.4s, %2.4s" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsubhn_high_u64 (uint32x2_t a, uint64x2_t b, uint64x2_t c) -{ - uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0))); - __asm__ ("subhn2 %0.4s, %1.2d, %2.2d" - : "+w"(result) - : "w"(b), "w"(c) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vsubhn_s16 (int16x8_t a, int16x8_t b) -{ - int8x8_t result; - __asm__ ("subhn %0.8b, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vsubhn_s32 (int32x4_t a, int32x4_t b) -{ - int16x4_t result; - __asm__ ("subhn %0.4h, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vsubhn_s64 (int64x2_t a, int64x2_t b) -{ - int32x2_t result; - __asm__ ("subhn %0.2s, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vsubhn_u16 (uint16x8_t a, uint16x8_t b) -{ - uint8x8_t result; - __asm__ ("subhn %0.8b, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vsubhn_u32 (uint32x4_t a, uint32x4_t b) -{ - uint16x4_t result; - __asm__ ("subhn %0.4h, %1.4s, %2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vsubhn_u64 (uint64x2_t a, uint64x2_t b) -{ - uint32x2_t result; - __asm__ ("subhn %0.2s, %1.2d, %2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vtrn1_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("trn1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtrn1_p8 (poly8x8_t a, poly8x8_t b) -{ - poly8x8_t result; - __asm__ ("trn1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vtrn1_p16 (poly16x4_t a, poly16x4_t b) -{ - poly16x4_t result; - __asm__ ("trn1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtrn1_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("trn1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vtrn1_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("trn1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vtrn1_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("trn1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtrn1_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("trn1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vtrn1_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("trn1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vtrn1_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("trn1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vtrn1q_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("trn1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vtrn1q_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("trn1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vtrn1q_p8 (poly8x16_t a, poly8x16_t b) -{ - poly8x16_t result; - __asm__ ("trn1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vtrn1q_p16 (poly16x8_t a, poly16x8_t b) -{ - poly16x8_t result; - __asm__ ("trn1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vtrn1q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("trn1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vtrn1q_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("trn1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vtrn1q_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("trn1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vtrn1q_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("trn1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vtrn1q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("trn1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vtrn1q_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("trn1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vtrn1q_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("trn1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vtrn1q_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("trn1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vtrn2_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("trn2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtrn2_p8 (poly8x8_t a, poly8x8_t b) -{ - poly8x8_t result; - __asm__ ("trn2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vtrn2_p16 (poly16x4_t a, poly16x4_t b) -{ - poly16x4_t result; - __asm__ ("trn2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtrn2_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("trn2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vtrn2_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("trn2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vtrn2_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("trn2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtrn2_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("trn2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vtrn2_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("trn2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vtrn2_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("trn2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vtrn2q_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("trn2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vtrn2q_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("trn2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vtrn2q_p8 (poly8x16_t a, poly8x16_t b) -{ - poly8x16_t result; - __asm__ ("trn2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vtrn2q_p16 (poly16x8_t a, poly16x8_t b) -{ - poly16x8_t result; - __asm__ ("trn2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vtrn2q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("trn2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vtrn2q_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("trn2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vtrn2q_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("trn2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vtrn2q_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("trn2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vtrn2q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("trn2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vtrn2q_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("trn2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vtrn2q_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("trn2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vtrn2q_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("trn2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtst_p8 (poly8x8_t a, poly8x8_t b) -{ - uint8x8_t result; - __asm__ ("cmtst %0.8b, %1.8b, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vtst_p16 (poly16x4_t a, poly16x4_t b) -{ - uint16x4_t result; - __asm__ ("cmtst %0.4h, %1.4h, %2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vtstq_p8 (poly8x16_t a, poly8x16_t b) -{ - uint8x16_t result; - __asm__ ("cmtst %0.16b, %1.16b, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vtstq_p16 (poly16x8_t a, poly16x8_t b) -{ - uint16x8_t result; - __asm__ ("cmtst %0.8h, %1.8h, %2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vuzp1_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("uzp1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vuzp1_p8 (poly8x8_t a, poly8x8_t b) -{ - poly8x8_t result; - __asm__ ("uzp1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vuzp1_p16 (poly16x4_t a, poly16x4_t b) -{ - poly16x4_t result; - __asm__ ("uzp1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vuzp1_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("uzp1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vuzp1_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("uzp1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vuzp1_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("uzp1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vuzp1_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("uzp1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vuzp1_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("uzp1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vuzp1_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("uzp1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vuzp1q_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("uzp1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vuzp1q_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("uzp1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vuzp1q_p8 (poly8x16_t a, poly8x16_t b) -{ - poly8x16_t result; - __asm__ ("uzp1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vuzp1q_p16 (poly16x8_t a, poly16x8_t b) -{ - poly16x8_t result; - __asm__ ("uzp1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vuzp1q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("uzp1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vuzp1q_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("uzp1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vuzp1q_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("uzp1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vuzp1q_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("uzp1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vuzp1q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("uzp1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vuzp1q_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("uzp1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vuzp1q_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("uzp1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vuzp1q_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("uzp1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vuzp2_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("uzp2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vuzp2_p8 (poly8x8_t a, poly8x8_t b) -{ - poly8x8_t result; - __asm__ ("uzp2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vuzp2_p16 (poly16x4_t a, poly16x4_t b) -{ - poly16x4_t result; - __asm__ ("uzp2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vuzp2_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("uzp2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vuzp2_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("uzp2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vuzp2_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("uzp2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vuzp2_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("uzp2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vuzp2_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("uzp2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vuzp2_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("uzp2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vuzp2q_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("uzp2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vuzp2q_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("uzp2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vuzp2q_p8 (poly8x16_t a, poly8x16_t b) -{ - poly8x16_t result; - __asm__ ("uzp2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vuzp2q_p16 (poly16x8_t a, poly16x8_t b) -{ - poly16x8_t result; - __asm__ ("uzp2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vuzp2q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("uzp2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vuzp2q_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("uzp2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vuzp2q_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("uzp2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vuzp2q_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("uzp2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vuzp2q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("uzp2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vuzp2q_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("uzp2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vuzp2q_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("uzp2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vuzp2q_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("uzp2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vzip1_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("zip1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vzip1_p8 (poly8x8_t a, poly8x8_t b) -{ - poly8x8_t result; - __asm__ ("zip1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vzip1_p16 (poly16x4_t a, poly16x4_t b) -{ - poly16x4_t result; - __asm__ ("zip1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vzip1_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("zip1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vzip1_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("zip1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vzip1_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("zip1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vzip1_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("zip1 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vzip1_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("zip1 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vzip1_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("zip1 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vzip1q_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("zip1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vzip1q_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("zip1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vzip1q_p8 (poly8x16_t a, poly8x16_t b) -{ - poly8x16_t result; - __asm__ ("zip1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vzip1q_p16 (poly16x8_t a, poly16x8_t b) -{ - poly16x8_t result; - __asm__ ("zip1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vzip1q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("zip1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vzip1q_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("zip1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vzip1q_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("zip1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vzip1q_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("zip1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vzip1q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("zip1 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vzip1q_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("zip1 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vzip1q_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("zip1 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vzip1q_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("zip1 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vzip2_f32 (float32x2_t a, float32x2_t b) -{ - float32x2_t result; - __asm__ ("zip2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vzip2_p8 (poly8x8_t a, poly8x8_t b) -{ - poly8x8_t result; - __asm__ ("zip2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vzip2_p16 (poly16x4_t a, poly16x4_t b) -{ - poly16x4_t result; - __asm__ ("zip2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vzip2_s8 (int8x8_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("zip2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vzip2_s16 (int16x4_t a, int16x4_t b) -{ - int16x4_t result; - __asm__ ("zip2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vzip2_s32 (int32x2_t a, int32x2_t b) -{ - int32x2_t result; - __asm__ ("zip2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vzip2_u8 (uint8x8_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("zip2 %0.8b,%1.8b,%2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vzip2_u16 (uint16x4_t a, uint16x4_t b) -{ - uint16x4_t result; - __asm__ ("zip2 %0.4h,%1.4h,%2.4h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vzip2_u32 (uint32x2_t a, uint32x2_t b) -{ - uint32x2_t result; - __asm__ ("zip2 %0.2s,%1.2s,%2.2s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vzip2q_f32 (float32x4_t a, float32x4_t b) -{ - float32x4_t result; - __asm__ ("zip2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vzip2q_f64 (float64x2_t a, float64x2_t b) -{ - float64x2_t result; - __asm__ ("zip2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vzip2q_p8 (poly8x16_t a, poly8x16_t b) -{ - poly8x16_t result; - __asm__ ("zip2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vzip2q_p16 (poly16x8_t a, poly16x8_t b) -{ - poly16x8_t result; - __asm__ ("zip2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vzip2q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("zip2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vzip2q_s16 (int16x8_t a, int16x8_t b) -{ - int16x8_t result; - __asm__ ("zip2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vzip2q_s32 (int32x4_t a, int32x4_t b) -{ - int32x4_t result; - __asm__ ("zip2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vzip2q_s64 (int64x2_t a, int64x2_t b) -{ - int64x2_t result; - __asm__ ("zip2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vzip2q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("zip2 %0.16b,%1.16b,%2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vzip2q_u16 (uint16x8_t a, uint16x8_t b) -{ - uint16x8_t result; - __asm__ ("zip2 %0.8h,%1.8h,%2.8h" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vzip2q_u32 (uint32x4_t a, uint32x4_t b) -{ - uint32x4_t result; - __asm__ ("zip2 %0.4s,%1.4s,%2.4s" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vzip2q_u64 (uint64x2_t a, uint64x2_t b) -{ - uint64x2_t result; - __asm__ ("zip2 %0.2d,%1.2d,%2.2d" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -/* End of temporary inline asm implementations. */ - -/* Start of temporary inline asm for vldn, vstn and friends. */ - -/* Create struct element types for duplicating loads. - - Create 2 element structures of: - - +------+----+----+----+----+ - | | 8 | 16 | 32 | 64 | - +------+----+----+----+----+ - |int | Y | Y | N | N | - +------+----+----+----+----+ - |uint | Y | Y | N | N | - +------+----+----+----+----+ - |float | - | - | N | N | - +------+----+----+----+----+ - |poly | Y | Y | - | - | - +------+----+----+----+----+ - - Create 3 element structures of: - - +------+----+----+----+----+ - | | 8 | 16 | 32 | 64 | - +------+----+----+----+----+ - |int | Y | Y | Y | Y | - +------+----+----+----+----+ - |uint | Y | Y | Y | Y | - +------+----+----+----+----+ - |float | - | - | Y | Y | - +------+----+----+----+----+ - |poly | Y | Y | - | - | - +------+----+----+----+----+ - - Create 4 element structures of: - - +------+----+----+----+----+ - | | 8 | 16 | 32 | 64 | - +------+----+----+----+----+ - |int | Y | N | N | Y | - +------+----+----+----+----+ - |uint | Y | N | N | Y | - +------+----+----+----+----+ - |float | - | - | N | Y | - +------+----+----+----+----+ - |poly | Y | N | - | - | - +------+----+----+----+----+ - - This is required for casting memory reference. */ -#define __STRUCTN(t, sz, nelem) \ - typedef struct t ## sz ## x ## nelem ## _t { \ - t ## sz ## _t val[nelem]; \ - } t ## sz ## x ## nelem ## _t; - -/* 2-element structs. */ -__STRUCTN (int, 8, 2) -__STRUCTN (int, 16, 2) -__STRUCTN (uint, 8, 2) -__STRUCTN (uint, 16, 2) -__STRUCTN (poly, 8, 2) -__STRUCTN (poly, 16, 2) -/* 3-element structs. */ -__STRUCTN (int, 8, 3) -__STRUCTN (int, 16, 3) -__STRUCTN (int, 32, 3) -__STRUCTN (int, 64, 3) -__STRUCTN (uint, 8, 3) -__STRUCTN (uint, 16, 3) -__STRUCTN (uint, 32, 3) -__STRUCTN (uint, 64, 3) -__STRUCTN (float, 32, 3) -__STRUCTN (float, 64, 3) -__STRUCTN (poly, 8, 3) -__STRUCTN (poly, 16, 3) -/* 4-element structs. */ -__STRUCTN (int, 8, 4) -__STRUCTN (int, 64, 4) -__STRUCTN (uint, 8, 4) -__STRUCTN (uint, 64, 4) -__STRUCTN (poly, 8, 4) -__STRUCTN (float, 64, 4) -#undef __STRUCTN - -#define __LD2R_FUNC(rettype, structtype, ptrtype, \ - regsuffix, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - vld2 ## Q ## _dup_ ## funcsuffix (const ptrtype *ptr) \ - { \ - rettype result; \ - __asm__ ("ld2r {v16." #regsuffix ", v17." #regsuffix "}, %1\n\t" \ - "st1 {v16." #regsuffix ", v17." #regsuffix "}, %0\n\t" \ - : "=Q"(result) \ - : "Q"(*(const structtype *)ptr) \ - : "memory", "v16", "v17"); \ - return result; \ - } - -__LD2R_FUNC (float32x2x2_t, float32x2_t, float32_t, 2s, f32,) -__LD2R_FUNC (float64x1x2_t, float64x2_t, float64_t, 1d, f64,) -__LD2R_FUNC (poly8x8x2_t, poly8x2_t, poly8_t, 8b, p8,) -__LD2R_FUNC (poly16x4x2_t, poly16x2_t, poly16_t, 4h, p16,) -__LD2R_FUNC (int8x8x2_t, int8x2_t, int8_t, 8b, s8,) -__LD2R_FUNC (int16x4x2_t, int16x2_t, int16_t, 4h, s16,) -__LD2R_FUNC (int32x2x2_t, int32x2_t, int32_t, 2s, s32,) -__LD2R_FUNC (int64x1x2_t, int64x2_t, int64_t, 1d, s64,) -__LD2R_FUNC (uint8x8x2_t, uint8x2_t, uint8_t, 8b, u8,) -__LD2R_FUNC (uint16x4x2_t, uint16x2_t, uint16_t, 4h, u16,) -__LD2R_FUNC (uint32x2x2_t, uint32x2_t, uint32_t, 2s, u32,) -__LD2R_FUNC (uint64x1x2_t, uint64x2_t, uint64_t, 1d, u64,) -__LD2R_FUNC (float32x4x2_t, float32x2_t, float32_t, 4s, f32, q) -__LD2R_FUNC (float64x2x2_t, float64x2_t, float64_t, 2d, f64, q) -__LD2R_FUNC (poly8x16x2_t, poly8x2_t, poly8_t, 16b, p8, q) -__LD2R_FUNC (poly16x8x2_t, poly16x2_t, poly16_t, 8h, p16, q) -__LD2R_FUNC (int8x16x2_t, int8x2_t, int8_t, 16b, s8, q) -__LD2R_FUNC (int16x8x2_t, int16x2_t, int16_t, 8h, s16, q) -__LD2R_FUNC (int32x4x2_t, int32x2_t, int32_t, 4s, s32, q) -__LD2R_FUNC (int64x2x2_t, int64x2_t, int64_t, 2d, s64, q) -__LD2R_FUNC (uint8x16x2_t, uint8x2_t, uint8_t, 16b, u8, q) -__LD2R_FUNC (uint16x8x2_t, uint16x2_t, uint16_t, 8h, u16, q) -__LD2R_FUNC (uint32x4x2_t, uint32x2_t, uint32_t, 4s, u32, q) -__LD2R_FUNC (uint64x2x2_t, uint64x2_t, uint64_t, 2d, u64, q) - -#define __LD2_LANE_FUNC(rettype, ptrtype, regsuffix, \ - lnsuffix, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - vld2 ## Q ## _lane_ ## funcsuffix (const ptrtype *ptr, \ - rettype b, const int c) \ - { \ - rettype result; \ - __asm__ ("ld1 {v16." #regsuffix ", v17." #regsuffix "}, %1\n\t" \ - "ld2 {v16." #lnsuffix ", v17." #lnsuffix "}[%3], %2\n\t" \ - "st1 {v16." #regsuffix ", v17." #regsuffix "}, %0\n\t" \ - : "=Q"(result) \ - : "Q"(b), "Q"(*(const rettype *)ptr), "i"(c) \ - : "memory", "v16", "v17"); \ - return result; \ - } - -__LD2_LANE_FUNC (int8x8x2_t, uint8_t, 8b, b, s8,) -__LD2_LANE_FUNC (float32x2x2_t, float32_t, 2s, s, f32,) -__LD2_LANE_FUNC (float64x1x2_t, float64_t, 1d, d, f64,) -__LD2_LANE_FUNC (poly8x8x2_t, poly8_t, 8b, b, p8,) -__LD2_LANE_FUNC (poly16x4x2_t, poly16_t, 4h, h, p16,) -__LD2_LANE_FUNC (int16x4x2_t, int16_t, 4h, h, s16,) -__LD2_LANE_FUNC (int32x2x2_t, int32_t, 2s, s, s32,) -__LD2_LANE_FUNC (int64x1x2_t, int64_t, 1d, d, s64,) -__LD2_LANE_FUNC (uint8x8x2_t, uint8_t, 8b, b, u8,) -__LD2_LANE_FUNC (uint16x4x2_t, uint16_t, 4h, h, u16,) -__LD2_LANE_FUNC (uint32x2x2_t, uint32_t, 2s, s, u32,) -__LD2_LANE_FUNC (uint64x1x2_t, uint64_t, 1d, d, u64,) -__LD2_LANE_FUNC (float32x4x2_t, float32_t, 4s, s, f32, q) -__LD2_LANE_FUNC (float64x2x2_t, float64_t, 2d, d, f64, q) -__LD2_LANE_FUNC (poly8x16x2_t, poly8_t, 16b, b, p8, q) -__LD2_LANE_FUNC (poly16x8x2_t, poly16_t, 8h, h, p16, q) -__LD2_LANE_FUNC (int8x16x2_t, int8_t, 16b, b, s8, q) -__LD2_LANE_FUNC (int16x8x2_t, int16_t, 8h, h, s16, q) -__LD2_LANE_FUNC (int32x4x2_t, int32_t, 4s, s, s32, q) -__LD2_LANE_FUNC (int64x2x2_t, int64_t, 2d, d, s64, q) -__LD2_LANE_FUNC (uint8x16x2_t, uint8_t, 16b, b, u8, q) -__LD2_LANE_FUNC (uint16x8x2_t, uint16_t, 8h, h, u16, q) -__LD2_LANE_FUNC (uint32x4x2_t, uint32_t, 4s, s, u32, q) -__LD2_LANE_FUNC (uint64x2x2_t, uint64_t, 2d, d, u64, q) - -#define __LD3R_FUNC(rettype, structtype, ptrtype, \ - regsuffix, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - vld3 ## Q ## _dup_ ## funcsuffix (const ptrtype *ptr) \ - { \ - rettype result; \ - __asm__ ("ld3r {v16." #regsuffix " - v18." #regsuffix "}, %1\n\t" \ - "st1 {v16." #regsuffix " - v18." #regsuffix "}, %0\n\t" \ - : "=Q"(result) \ - : "Q"(*(const structtype *)ptr) \ - : "memory", "v16", "v17", "v18"); \ - return result; \ - } - -__LD3R_FUNC (float32x2x3_t, float32x3_t, float32_t, 2s, f32,) -__LD3R_FUNC (float64x1x3_t, float64x3_t, float64_t, 1d, f64,) -__LD3R_FUNC (poly8x8x3_t, poly8x3_t, poly8_t, 8b, p8,) -__LD3R_FUNC (poly16x4x3_t, poly16x3_t, poly16_t, 4h, p16,) -__LD3R_FUNC (int8x8x3_t, int8x3_t, int8_t, 8b, s8,) -__LD3R_FUNC (int16x4x3_t, int16x3_t, int16_t, 4h, s16,) -__LD3R_FUNC (int32x2x3_t, int32x3_t, int32_t, 2s, s32,) -__LD3R_FUNC (int64x1x3_t, int64x3_t, int64_t, 1d, s64,) -__LD3R_FUNC (uint8x8x3_t, uint8x3_t, uint8_t, 8b, u8,) -__LD3R_FUNC (uint16x4x3_t, uint16x3_t, uint16_t, 4h, u16,) -__LD3R_FUNC (uint32x2x3_t, uint32x3_t, uint32_t, 2s, u32,) -__LD3R_FUNC (uint64x1x3_t, uint64x3_t, uint64_t, 1d, u64,) -__LD3R_FUNC (float32x4x3_t, float32x3_t, float32_t, 4s, f32, q) -__LD3R_FUNC (float64x2x3_t, float64x3_t, float64_t, 2d, f64, q) -__LD3R_FUNC (poly8x16x3_t, poly8x3_t, poly8_t, 16b, p8, q) -__LD3R_FUNC (poly16x8x3_t, poly16x3_t, poly16_t, 8h, p16, q) -__LD3R_FUNC (int8x16x3_t, int8x3_t, int8_t, 16b, s8, q) -__LD3R_FUNC (int16x8x3_t, int16x3_t, int16_t, 8h, s16, q) -__LD3R_FUNC (int32x4x3_t, int32x3_t, int32_t, 4s, s32, q) -__LD3R_FUNC (int64x2x3_t, int64x3_t, int64_t, 2d, s64, q) -__LD3R_FUNC (uint8x16x3_t, uint8x3_t, uint8_t, 16b, u8, q) -__LD3R_FUNC (uint16x8x3_t, uint16x3_t, uint16_t, 8h, u16, q) -__LD3R_FUNC (uint32x4x3_t, uint32x3_t, uint32_t, 4s, u32, q) -__LD3R_FUNC (uint64x2x3_t, uint64x3_t, uint64_t, 2d, u64, q) - -#define __LD3_LANE_FUNC(rettype, ptrtype, regsuffix, \ - lnsuffix, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - vld3 ## Q ## _lane_ ## funcsuffix (const ptrtype *ptr, \ - rettype b, const int c) \ - { \ - rettype result; \ - __asm__ ("ld1 {v16." #regsuffix " - v18." #regsuffix "}, %1\n\t" \ - "ld3 {v16." #lnsuffix " - v18." #lnsuffix "}[%3], %2\n\t" \ - "st1 {v16." #regsuffix " - v18." #regsuffix "}, %0\n\t" \ - : "=Q"(result) \ - : "Q"(b), "Q"(*(const rettype *)ptr), "i"(c) \ - : "memory", "v16", "v17", "v18"); \ - return result; \ - } - -__LD3_LANE_FUNC (int8x8x3_t, uint8_t, 8b, b, s8,) -__LD3_LANE_FUNC (float32x2x3_t, float32_t, 2s, s, f32,) -__LD3_LANE_FUNC (float64x1x3_t, float64_t, 1d, d, f64,) -__LD3_LANE_FUNC (poly8x8x3_t, poly8_t, 8b, b, p8,) -__LD3_LANE_FUNC (poly16x4x3_t, poly16_t, 4h, h, p16,) -__LD3_LANE_FUNC (int16x4x3_t, int16_t, 4h, h, s16,) -__LD3_LANE_FUNC (int32x2x3_t, int32_t, 2s, s, s32,) -__LD3_LANE_FUNC (int64x1x3_t, int64_t, 1d, d, s64,) -__LD3_LANE_FUNC (uint8x8x3_t, uint8_t, 8b, b, u8,) -__LD3_LANE_FUNC (uint16x4x3_t, uint16_t, 4h, h, u16,) -__LD3_LANE_FUNC (uint32x2x3_t, uint32_t, 2s, s, u32,) -__LD3_LANE_FUNC (uint64x1x3_t, uint64_t, 1d, d, u64,) -__LD3_LANE_FUNC (float32x4x3_t, float32_t, 4s, s, f32, q) -__LD3_LANE_FUNC (float64x2x3_t, float64_t, 2d, d, f64, q) -__LD3_LANE_FUNC (poly8x16x3_t, poly8_t, 16b, b, p8, q) -__LD3_LANE_FUNC (poly16x8x3_t, poly16_t, 8h, h, p16, q) -__LD3_LANE_FUNC (int8x16x3_t, int8_t, 16b, b, s8, q) -__LD3_LANE_FUNC (int16x8x3_t, int16_t, 8h, h, s16, q) -__LD3_LANE_FUNC (int32x4x3_t, int32_t, 4s, s, s32, q) -__LD3_LANE_FUNC (int64x2x3_t, int64_t, 2d, d, s64, q) -__LD3_LANE_FUNC (uint8x16x3_t, uint8_t, 16b, b, u8, q) -__LD3_LANE_FUNC (uint16x8x3_t, uint16_t, 8h, h, u16, q) -__LD3_LANE_FUNC (uint32x4x3_t, uint32_t, 4s, s, u32, q) -__LD3_LANE_FUNC (uint64x2x3_t, uint64_t, 2d, d, u64, q) - -#define __LD4R_FUNC(rettype, structtype, ptrtype, \ - regsuffix, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - vld4 ## Q ## _dup_ ## funcsuffix (const ptrtype *ptr) \ - { \ - rettype result; \ - __asm__ ("ld4r {v16." #regsuffix " - v19." #regsuffix "}, %1\n\t" \ - "st1 {v16." #regsuffix " - v19." #regsuffix "}, %0\n\t" \ - : "=Q"(result) \ - : "Q"(*(const structtype *)ptr) \ - : "memory", "v16", "v17", "v18", "v19"); \ - return result; \ - } - -__LD4R_FUNC (float32x2x4_t, float32x4_t, float32_t, 2s, f32,) -__LD4R_FUNC (float64x1x4_t, float64x4_t, float64_t, 1d, f64,) -__LD4R_FUNC (poly8x8x4_t, poly8x4_t, poly8_t, 8b, p8,) -__LD4R_FUNC (poly16x4x4_t, poly16x4_t, poly16_t, 4h, p16,) -__LD4R_FUNC (int8x8x4_t, int8x4_t, int8_t, 8b, s8,) -__LD4R_FUNC (int16x4x4_t, int16x4_t, int16_t, 4h, s16,) -__LD4R_FUNC (int32x2x4_t, int32x4_t, int32_t, 2s, s32,) -__LD4R_FUNC (int64x1x4_t, int64x4_t, int64_t, 1d, s64,) -__LD4R_FUNC (uint8x8x4_t, uint8x4_t, uint8_t, 8b, u8,) -__LD4R_FUNC (uint16x4x4_t, uint16x4_t, uint16_t, 4h, u16,) -__LD4R_FUNC (uint32x2x4_t, uint32x4_t, uint32_t, 2s, u32,) -__LD4R_FUNC (uint64x1x4_t, uint64x4_t, uint64_t, 1d, u64,) -__LD4R_FUNC (float32x4x4_t, float32x4_t, float32_t, 4s, f32, q) -__LD4R_FUNC (float64x2x4_t, float64x4_t, float64_t, 2d, f64, q) -__LD4R_FUNC (poly8x16x4_t, poly8x4_t, poly8_t, 16b, p8, q) -__LD4R_FUNC (poly16x8x4_t, poly16x4_t, poly16_t, 8h, p16, q) -__LD4R_FUNC (int8x16x4_t, int8x4_t, int8_t, 16b, s8, q) -__LD4R_FUNC (int16x8x4_t, int16x4_t, int16_t, 8h, s16, q) -__LD4R_FUNC (int32x4x4_t, int32x4_t, int32_t, 4s, s32, q) -__LD4R_FUNC (int64x2x4_t, int64x4_t, int64_t, 2d, s64, q) -__LD4R_FUNC (uint8x16x4_t, uint8x4_t, uint8_t, 16b, u8, q) -__LD4R_FUNC (uint16x8x4_t, uint16x4_t, uint16_t, 8h, u16, q) -__LD4R_FUNC (uint32x4x4_t, uint32x4_t, uint32_t, 4s, u32, q) -__LD4R_FUNC (uint64x2x4_t, uint64x4_t, uint64_t, 2d, u64, q) - -#define __LD4_LANE_FUNC(rettype, ptrtype, regsuffix, \ - lnsuffix, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - vld4 ## Q ## _lane_ ## funcsuffix (const ptrtype *ptr, \ - rettype b, const int c) \ - { \ - rettype result; \ - __asm__ ("ld1 {v16." #regsuffix " - v19." #regsuffix "}, %1\n\t" \ - "ld4 {v16." #lnsuffix " - v19." #lnsuffix "}[%3], %2\n\t" \ - "st1 {v16." #regsuffix " - v19." #regsuffix "}, %0\n\t" \ - : "=Q"(result) \ - : "Q"(b), "Q"(*(const rettype *)ptr), "i"(c) \ - : "memory", "v16", "v17", "v18", "v19"); \ - return result; \ - } - -__LD4_LANE_FUNC (int8x8x4_t, uint8_t, 8b, b, s8,) -__LD4_LANE_FUNC (float32x2x4_t, float32_t, 2s, s, f32,) -__LD4_LANE_FUNC (float64x1x4_t, float64_t, 1d, d, f64,) -__LD4_LANE_FUNC (poly8x8x4_t, poly8_t, 8b, b, p8,) -__LD4_LANE_FUNC (poly16x4x4_t, poly16_t, 4h, h, p16,) -__LD4_LANE_FUNC (int16x4x4_t, int16_t, 4h, h, s16,) -__LD4_LANE_FUNC (int32x2x4_t, int32_t, 2s, s, s32,) -__LD4_LANE_FUNC (int64x1x4_t, int64_t, 1d, d, s64,) -__LD4_LANE_FUNC (uint8x8x4_t, uint8_t, 8b, b, u8,) -__LD4_LANE_FUNC (uint16x4x4_t, uint16_t, 4h, h, u16,) -__LD4_LANE_FUNC (uint32x2x4_t, uint32_t, 2s, s, u32,) -__LD4_LANE_FUNC (uint64x1x4_t, uint64_t, 1d, d, u64,) -__LD4_LANE_FUNC (float32x4x4_t, float32_t, 4s, s, f32, q) -__LD4_LANE_FUNC (float64x2x4_t, float64_t, 2d, d, f64, q) -__LD4_LANE_FUNC (poly8x16x4_t, poly8_t, 16b, b, p8, q) -__LD4_LANE_FUNC (poly16x8x4_t, poly16_t, 8h, h, p16, q) -__LD4_LANE_FUNC (int8x16x4_t, int8_t, 16b, b, s8, q) -__LD4_LANE_FUNC (int16x8x4_t, int16_t, 8h, h, s16, q) -__LD4_LANE_FUNC (int32x4x4_t, int32_t, 4s, s, s32, q) -__LD4_LANE_FUNC (int64x2x4_t, int64_t, 2d, d, s64, q) -__LD4_LANE_FUNC (uint8x16x4_t, uint8_t, 16b, b, u8, q) -__LD4_LANE_FUNC (uint16x8x4_t, uint16_t, 8h, h, u16, q) -__LD4_LANE_FUNC (uint32x4x4_t, uint32_t, 4s, s, u32, q) -__LD4_LANE_FUNC (uint64x2x4_t, uint64_t, 2d, d, u64, q) - -#define __ST2_LANE_FUNC(intype, ptrtype, regsuffix, \ - lnsuffix, funcsuffix, Q) \ - __extension__ static __inline void \ - __attribute__ ((__always_inline__)) \ - vst2 ## Q ## _lane_ ## funcsuffix (const ptrtype *ptr, \ - intype b, const int c) \ - { \ - __asm__ ("ld1 {v16." #regsuffix ", v17." #regsuffix "}, %1\n\t" \ - "st2 {v16." #lnsuffix ", v17." #lnsuffix "}[%2], %0\n\t" \ - : "=Q"(*(intype *) ptr) \ - : "Q"(b), "i"(c) \ - : "memory", "v16", "v17"); \ - } - -__ST2_LANE_FUNC (int8x8x2_t, int8_t, 8b, b, s8,) -__ST2_LANE_FUNC (float32x2x2_t, float32_t, 2s, s, f32,) -__ST2_LANE_FUNC (float64x1x2_t, float64_t, 1d, d, f64,) -__ST2_LANE_FUNC (poly8x8x2_t, poly8_t, 8b, b, p8,) -__ST2_LANE_FUNC (poly16x4x2_t, poly16_t, 4h, h, p16,) -__ST2_LANE_FUNC (int16x4x2_t, int16_t, 4h, h, s16,) -__ST2_LANE_FUNC (int32x2x2_t, int32_t, 2s, s, s32,) -__ST2_LANE_FUNC (int64x1x2_t, int64_t, 1d, d, s64,) -__ST2_LANE_FUNC (uint8x8x2_t, uint8_t, 8b, b, u8,) -__ST2_LANE_FUNC (uint16x4x2_t, uint16_t, 4h, h, u16,) -__ST2_LANE_FUNC (uint32x2x2_t, uint32_t, 2s, s, u32,) -__ST2_LANE_FUNC (uint64x1x2_t, uint64_t, 1d, d, u64,) -__ST2_LANE_FUNC (float32x4x2_t, float32_t, 4s, s, f32, q) -__ST2_LANE_FUNC (float64x2x2_t, float64_t, 2d, d, f64, q) -__ST2_LANE_FUNC (poly8x16x2_t, poly8_t, 16b, b, p8, q) -__ST2_LANE_FUNC (poly16x8x2_t, poly16_t, 8h, h, p16, q) -__ST2_LANE_FUNC (int8x16x2_t, int8_t, 16b, b, s8, q) -__ST2_LANE_FUNC (int16x8x2_t, int16_t, 8h, h, s16, q) -__ST2_LANE_FUNC (int32x4x2_t, int32_t, 4s, s, s32, q) -__ST2_LANE_FUNC (int64x2x2_t, int64_t, 2d, d, s64, q) -__ST2_LANE_FUNC (uint8x16x2_t, uint8_t, 16b, b, u8, q) -__ST2_LANE_FUNC (uint16x8x2_t, uint16_t, 8h, h, u16, q) -__ST2_LANE_FUNC (uint32x4x2_t, uint32_t, 4s, s, u32, q) -__ST2_LANE_FUNC (uint64x2x2_t, uint64_t, 2d, d, u64, q) - -#define __ST3_LANE_FUNC(intype, ptrtype, regsuffix, \ - lnsuffix, funcsuffix, Q) \ - __extension__ static __inline void \ - __attribute__ ((__always_inline__)) \ - vst3 ## Q ## _lane_ ## funcsuffix (const ptrtype *ptr, \ - intype b, const int c) \ - { \ - __asm__ ("ld1 {v16." #regsuffix " - v18." #regsuffix "}, %1\n\t" \ - "st3 {v16." #lnsuffix " - v18." #lnsuffix "}[%2], %0\n\t" \ - : "=Q"(*(intype *) ptr) \ - : "Q"(b), "i"(c) \ - : "memory", "v16", "v17", "v18"); \ - } - -__ST3_LANE_FUNC (int8x8x3_t, int8_t, 8b, b, s8,) -__ST3_LANE_FUNC (float32x2x3_t, float32_t, 2s, s, f32,) -__ST3_LANE_FUNC (float64x1x3_t, float64_t, 1d, d, f64,) -__ST3_LANE_FUNC (poly8x8x3_t, poly8_t, 8b, b, p8,) -__ST3_LANE_FUNC (poly16x4x3_t, poly16_t, 4h, h, p16,) -__ST3_LANE_FUNC (int16x4x3_t, int16_t, 4h, h, s16,) -__ST3_LANE_FUNC (int32x2x3_t, int32_t, 2s, s, s32,) -__ST3_LANE_FUNC (int64x1x3_t, int64_t, 1d, d, s64,) -__ST3_LANE_FUNC (uint8x8x3_t, uint8_t, 8b, b, u8,) -__ST3_LANE_FUNC (uint16x4x3_t, uint16_t, 4h, h, u16,) -__ST3_LANE_FUNC (uint32x2x3_t, uint32_t, 2s, s, u32,) -__ST3_LANE_FUNC (uint64x1x3_t, uint64_t, 1d, d, u64,) -__ST3_LANE_FUNC (float32x4x3_t, float32_t, 4s, s, f32, q) -__ST3_LANE_FUNC (float64x2x3_t, float64_t, 2d, d, f64, q) -__ST3_LANE_FUNC (poly8x16x3_t, poly8_t, 16b, b, p8, q) -__ST3_LANE_FUNC (poly16x8x3_t, poly16_t, 8h, h, p16, q) -__ST3_LANE_FUNC (int8x16x3_t, int8_t, 16b, b, s8, q) -__ST3_LANE_FUNC (int16x8x3_t, int16_t, 8h, h, s16, q) -__ST3_LANE_FUNC (int32x4x3_t, int32_t, 4s, s, s32, q) -__ST3_LANE_FUNC (int64x2x3_t, int64_t, 2d, d, s64, q) -__ST3_LANE_FUNC (uint8x16x3_t, uint8_t, 16b, b, u8, q) -__ST3_LANE_FUNC (uint16x8x3_t, uint16_t, 8h, h, u16, q) -__ST3_LANE_FUNC (uint32x4x3_t, uint32_t, 4s, s, u32, q) -__ST3_LANE_FUNC (uint64x2x3_t, uint64_t, 2d, d, u64, q) - -#define __ST4_LANE_FUNC(intype, ptrtype, regsuffix, \ - lnsuffix, funcsuffix, Q) \ - __extension__ static __inline void \ - __attribute__ ((__always_inline__)) \ - vst4 ## Q ## _lane_ ## funcsuffix (const ptrtype *ptr, \ - intype b, const int c) \ - { \ - __asm__ ("ld1 {v16." #regsuffix " - v19." #regsuffix "}, %1\n\t" \ - "st4 {v16." #lnsuffix " - v19." #lnsuffix "}[%2], %0\n\t" \ - : "=Q"(*(intype *) ptr) \ - : "Q"(b), "i"(c) \ - : "memory", "v16", "v17", "v18", "v19"); \ - } - -__ST4_LANE_FUNC (int8x8x4_t, int8_t, 8b, b, s8,) -__ST4_LANE_FUNC (float32x2x4_t, float32_t, 2s, s, f32,) -__ST4_LANE_FUNC (float64x1x4_t, float64_t, 1d, d, f64,) -__ST4_LANE_FUNC (poly8x8x4_t, poly8_t, 8b, b, p8,) -__ST4_LANE_FUNC (poly16x4x4_t, poly16_t, 4h, h, p16,) -__ST4_LANE_FUNC (int16x4x4_t, int16_t, 4h, h, s16,) -__ST4_LANE_FUNC (int32x2x4_t, int32_t, 2s, s, s32,) -__ST4_LANE_FUNC (int64x1x4_t, int64_t, 1d, d, s64,) -__ST4_LANE_FUNC (uint8x8x4_t, uint8_t, 8b, b, u8,) -__ST4_LANE_FUNC (uint16x4x4_t, uint16_t, 4h, h, u16,) -__ST4_LANE_FUNC (uint32x2x4_t, uint32_t, 2s, s, u32,) -__ST4_LANE_FUNC (uint64x1x4_t, uint64_t, 1d, d, u64,) -__ST4_LANE_FUNC (float32x4x4_t, float32_t, 4s, s, f32, q) -__ST4_LANE_FUNC (float64x2x4_t, float64_t, 2d, d, f64, q) -__ST4_LANE_FUNC (poly8x16x4_t, poly8_t, 16b, b, p8, q) -__ST4_LANE_FUNC (poly16x8x4_t, poly16_t, 8h, h, p16, q) -__ST4_LANE_FUNC (int8x16x4_t, int8_t, 16b, b, s8, q) -__ST4_LANE_FUNC (int16x8x4_t, int16_t, 8h, h, s16, q) -__ST4_LANE_FUNC (int32x4x4_t, int32_t, 4s, s, s32, q) -__ST4_LANE_FUNC (int64x2x4_t, int64_t, 2d, d, s64, q) -__ST4_LANE_FUNC (uint8x16x4_t, uint8_t, 16b, b, u8, q) -__ST4_LANE_FUNC (uint16x8x4_t, uint16_t, 8h, h, u16, q) -__ST4_LANE_FUNC (uint32x4x4_t, uint32_t, 4s, s, u32, q) -__ST4_LANE_FUNC (uint64x2x4_t, uint64_t, 2d, d, u64, q) - -__extension__ static __inline int64_t __attribute__ ((__always_inline__)) -vaddlv_s32 (int32x2_t a) -{ - int64_t result; - __asm__ ("saddlp %0.1d, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) -vaddlv_u32 (uint32x2_t a) -{ - uint64_t result; - __asm__ ("uaddlp %0.1d, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vaddv_s32 (int32x2_t a) -{ - int32_t result; - __asm__ ("addp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vaddv_u32 (uint32x2_t a) -{ - uint32_t result; - __asm__ ("addp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vmaxnmv_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("fmaxnmp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline float32_t __attribute__ ((__always_inline__)) -vminnmv_f32 (float32x2_t a) -{ - float32_t result; - __asm__ ("fminnmp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vmaxnmvq_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("fmaxnmp %0.2d, %1.2d, %1.2d" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vmaxv_s32 (int32x2_t a) -{ - int32_t result; - __asm__ ("smaxp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vmaxv_u32 (uint32x2_t a) -{ - uint32_t result; - __asm__ ("umaxp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline float64_t __attribute__ ((__always_inline__)) -vminnmvq_f64 (float64x2_t a) -{ - float64_t result; - __asm__ ("fminnmp %0.2d, %1.2d, %1.2d" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline int32_t __attribute__ ((__always_inline__)) -vminv_s32 (int32x2_t a) -{ - int32_t result; - __asm__ ("sminp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) -vminv_u32 (uint32x2_t a) -{ - uint32_t result; - __asm__ ("uminp %0.2s, %1.2s, %1.2s" : "=w"(result) : "w"(a) : ); - return result; -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vpaddd_s64 (int64x2_t __a) -{ - return __builtin_aarch64_addpdi (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqdmulh_laneq_s16 (int16x4_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_laneqv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqdmulh_laneq_s32 (int32x2_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_laneqv2si (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqdmulhq_laneq_s16 (int16x8_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_laneqv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmulhq_laneq_s32 (int32x4_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_laneqv4si (__a, __b, __c); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqrdmulh_laneq_s16 (int16x4_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_laneqv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqrdmulh_laneq_s32 (int32x2_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_laneqv2si (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqrdmulhq_laneq_s16 (int16x8_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_laneqv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqrdmulhq_laneq_s32 (int32x4_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_laneqv4si (__a, __b, __c); -} - -/* Table intrinsics. */ - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbl1_p8 (poly8x16_t a, uint8x8_t b) -{ - poly8x8_t result; - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbl1_s8 (int8x16_t a, int8x8_t b) -{ - int8x8_t result; - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbl1_u8 (uint8x16_t a, uint8x8_t b) -{ - uint8x8_t result; - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbl1q_p8 (poly8x16_t a, uint8x16_t b) -{ - poly8x16_t result; - __asm__ ("tbl %0.16b, {%1.16b}, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbl1q_s8 (int8x16_t a, int8x16_t b) -{ - int8x16_t result; - __asm__ ("tbl %0.16b, {%1.16b}, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbl1q_u8 (uint8x16_t a, uint8x16_t b) -{ - uint8x16_t result; - __asm__ ("tbl %0.16b, {%1.16b}, %2.16b" - : "=w"(result) - : "w"(a), "w"(b) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbl2_s8 (int8x16x2_t tab, int8x8_t idx) -{ - int8x8_t result; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbl %0.8b, {v16.16b, v17.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbl2_u8 (uint8x16x2_t tab, uint8x8_t idx) -{ - uint8x8_t result; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbl %0.8b, {v16.16b, v17.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbl2_p8 (poly8x16x2_t tab, uint8x8_t idx) -{ - poly8x8_t result; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbl %0.8b, {v16.16b, v17.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbl2q_s8 (int8x16x2_t tab, int8x16_t idx) -{ - int8x16_t result; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbl %0.16b, {v16.16b, v17.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbl2q_u8 (uint8x16x2_t tab, uint8x16_t idx) -{ - uint8x16_t result; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbl %0.16b, {v16.16b, v17.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbl2q_p8 (poly8x16x2_t tab, uint8x16_t idx) -{ - poly8x16_t result; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbl %0.16b, {v16.16b, v17.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbl3_s8 (int8x16x3_t tab, int8x8_t idx) -{ - int8x8_t result; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbl %0.8b, {v16.16b - v18.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbl3_u8 (uint8x16x3_t tab, uint8x8_t idx) -{ - uint8x8_t result; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbl %0.8b, {v16.16b - v18.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbl3_p8 (poly8x16x3_t tab, uint8x8_t idx) -{ - poly8x8_t result; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbl %0.8b, {v16.16b - v18.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbl3q_s8 (int8x16x3_t tab, int8x16_t idx) -{ - int8x16_t result; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbl %0.16b, {v16.16b - v18.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbl3q_u8 (uint8x16x3_t tab, uint8x16_t idx) -{ - uint8x16_t result; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbl %0.16b, {v16.16b - v18.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbl3q_p8 (poly8x16x3_t tab, uint8x16_t idx) -{ - poly8x16_t result; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbl %0.16b, {v16.16b - v18.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbl4_s8 (int8x16x4_t tab, int8x8_t idx) -{ - int8x8_t result; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbl %0.8b, {v16.16b - v19.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbl4_u8 (uint8x16x4_t tab, uint8x8_t idx) -{ - uint8x8_t result; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbl %0.8b, {v16.16b - v19.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbl4_p8 (poly8x16x4_t tab, uint8x8_t idx) -{ - poly8x8_t result; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbl %0.8b, {v16.16b - v19.16b}, %2.8b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbl4q_s8 (int8x16x4_t tab, int8x16_t idx) -{ - int8x16_t result; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbl %0.16b, {v16.16b - v19.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbl4q_u8 (uint8x16x4_t tab, uint8x16_t idx) -{ - uint8x16_t result; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbl %0.16b, {v16.16b - v19.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbl4q_p8 (poly8x16x4_t tab, uint8x16_t idx) -{ - poly8x16_t result; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbl %0.16b, {v16.16b - v19.16b}, %2.16b\n\t" - :"=w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbx1_s8 (int8x8_t r, int8x16_t tab, int8x8_t idx) -{ - int8x8_t result = r; - __asm__ ("tbx %0.8b,{%1.16b},%2.8b" - : "+w"(result) - : "w"(tab), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbx1_u8 (uint8x8_t r, uint8x16_t tab, uint8x8_t idx) -{ - uint8x8_t result = r; - __asm__ ("tbx %0.8b,{%1.16b},%2.8b" - : "+w"(result) - : "w"(tab), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbx1_p8 (poly8x8_t r, poly8x16_t tab, uint8x8_t idx) -{ - poly8x8_t result = r; - __asm__ ("tbx %0.8b,{%1.16b},%2.8b" - : "+w"(result) - : "w"(tab), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbx1q_s8 (int8x16_t r, int8x16_t tab, int8x16_t idx) -{ - int8x16_t result = r; - __asm__ ("tbx %0.16b,{%1.16b},%2.16b" - : "+w"(result) - : "w"(tab), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbx1q_u8 (uint8x16_t r, uint8x16_t tab, uint8x16_t idx) -{ - uint8x16_t result = r; - __asm__ ("tbx %0.16b,{%1.16b},%2.16b" - : "+w"(result) - : "w"(tab), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbx1q_p8 (poly8x16_t r, poly8x16_t tab, uint8x16_t idx) -{ - poly8x16_t result = r; - __asm__ ("tbx %0.16b,{%1.16b},%2.16b" - : "+w"(result) - : "w"(tab), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbx2_s8 (int8x8_t r, int8x16x2_t tab, int8x8_t idx) -{ - int8x8_t result = r; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbx %0.8b, {v16.16b, v17.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbx2_u8 (uint8x8_t r, uint8x16x2_t tab, uint8x8_t idx) -{ - uint8x8_t result = r; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbx %0.8b, {v16.16b, v17.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbx2_p8 (poly8x8_t r, poly8x16x2_t tab, uint8x8_t idx) -{ - poly8x8_t result = r; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbx %0.8b, {v16.16b, v17.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbx2q_s8 (int8x16_t r, int8x16x2_t tab, int8x16_t idx) -{ - int8x16_t result = r; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbx %0.16b, {v16.16b, v17.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbx2q_u8 (uint8x16_t r, uint8x16x2_t tab, uint8x16_t idx) -{ - uint8x16_t result = r; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbx %0.16b, {v16.16b, v17.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbx2q_p8 (poly8x16_t r, poly8x16x2_t tab, uint8x16_t idx) -{ - poly8x16_t result = r; - __asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t" - "tbx %0.16b, {v16.16b, v17.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17"); - return result; -} - - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbx3_s8 (int8x8_t r, int8x16x3_t tab, int8x8_t idx) -{ - int8x8_t result = r; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbx %0.8b, {v16.16b - v18.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbx3_u8 (uint8x8_t r, uint8x16x3_t tab, uint8x8_t idx) -{ - uint8x8_t result = r; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbx %0.8b, {v16.16b - v18.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbx3_p8 (poly8x8_t r, poly8x16x3_t tab, uint8x8_t idx) -{ - poly8x8_t result = r; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbx %0.8b, {v16.16b - v18.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbx3q_s8 (int8x16_t r, int8x16x3_t tab, int8x16_t idx) -{ - int8x16_t result = r; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbx %0.16b, {v16.16b - v18.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbx3q_u8 (uint8x16_t r, uint8x16x3_t tab, uint8x16_t idx) -{ - uint8x16_t result = r; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbx %0.16b, {v16.16b - v18.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbx3q_p8 (poly8x16_t r, poly8x16x3_t tab, uint8x16_t idx) -{ - poly8x16_t result = r; - __asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t" - "tbx %0.16b, {v16.16b - v18.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18"); - return result; -} - - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqtbx4_s8 (int8x8_t r, int8x16x4_t tab, int8x8_t idx) -{ - int8x8_t result = r; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbx %0.8b, {v16.16b - v19.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqtbx4_u8 (uint8x8_t r, uint8x16x4_t tab, uint8x8_t idx) -{ - uint8x8_t result = r; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbx %0.8b, {v16.16b - v19.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vqtbx4_p8 (poly8x8_t r, poly8x16x4_t tab, uint8x8_t idx) -{ - poly8x8_t result = r; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbx %0.8b, {v16.16b - v19.16b}, %2.8b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqtbx4q_s8 (int8x16_t r, int8x16x4_t tab, int8x16_t idx) -{ - int8x16_t result = r; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbx %0.16b, {v16.16b - v19.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqtbx4q_u8 (uint8x16_t r, uint8x16x4_t tab, uint8x16_t idx) -{ - uint8x16_t result = r; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbx %0.16b, {v16.16b - v19.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vqtbx4q_p8 (poly8x16_t r, poly8x16x4_t tab, uint8x16_t idx) -{ - poly8x16_t result = r; - __asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t" - "tbx %0.16b, {v16.16b - v19.16b}, %2.16b\n\t" - :"+w"(result) - :"Q"(tab),"w"(idx) - :"memory", "v16", "v17", "v18", "v19"); - return result; -} - -/* V7 legacy table intrinsics. */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbl1_s8 (int8x8_t tab, int8x8_t idx) -{ - int8x8_t result; - int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (UINT64_C (0x0))); - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbl1_u8 (uint8x8_t tab, uint8x8_t idx) -{ - uint8x8_t result; - uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbl1_p8 (poly8x8_t tab, uint8x8_t idx) -{ - poly8x8_t result; - poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (UINT64_C (0x0))); - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbl2_s8 (int8x8x2_t tab, int8x8_t idx) -{ - int8x8_t result; - int8x16_t temp = vcombine_s8 (tab.val[0], tab.val[1]); - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbl2_u8 (uint8x8x2_t tab, uint8x8_t idx) -{ - uint8x8_t result; - uint8x16_t temp = vcombine_u8 (tab.val[0], tab.val[1]); - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbl2_p8 (poly8x8x2_t tab, uint8x8_t idx) -{ - poly8x8_t result; - poly8x16_t temp = vcombine_p8 (tab.val[0], tab.val[1]); - __asm__ ("tbl %0.8b, {%1.16b}, %2.8b" - : "=w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbl3_s8 (int8x8x3_t tab, int8x8_t idx) -{ - int8x8_t result; - int8x16x2_t temp; - temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (UINT64_C (0x0))); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "=w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbl3_u8 (uint8x8x3_t tab, uint8x8_t idx) -{ - uint8x8_t result; - uint8x16x2_t temp; - temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (UINT64_C (0x0))); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "=w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbl3_p8 (poly8x8x3_t tab, uint8x8_t idx) -{ - poly8x8_t result; - poly8x16x2_t temp; - temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (UINT64_C (0x0))); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "=w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbl4_s8 (int8x8x4_t tab, int8x8_t idx) -{ - int8x8_t result; - int8x16x2_t temp; - temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_s8 (tab.val[2], tab.val[3]); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "=w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbl4_u8 (uint8x8x4_t tab, uint8x8_t idx) -{ - uint8x8_t result; - uint8x16x2_t temp; - temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_u8 (tab.val[2], tab.val[3]); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "=w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbl4_p8 (poly8x8x4_t tab, uint8x8_t idx) -{ - poly8x8_t result; - poly8x16x2_t temp; - temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_p8 (tab.val[2], tab.val[3]); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "=w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbx1_s8 (int8x8_t r, int8x8_t tab, int8x8_t idx) -{ - int8x8_t result; - int8x8_t tmp1; - int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (UINT64_C (0x0))); - __asm__ ("movi %0.8b, 8\n\t" - "cmhs %0.8b, %3.8b, %0.8b\n\t" - "tbl %1.8b, {%2.16b}, %3.8b\n\t" - "bsl %0.8b, %4.8b, %1.8b\n\t" - : "+w"(result), "=&w"(tmp1) - : "w"(temp), "w"(idx), "w"(r) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbx1_u8 (uint8x8_t r, uint8x8_t tab, uint8x8_t idx) -{ - uint8x8_t result; - uint8x8_t tmp1; - uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (UINT64_C (0x0))); - __asm__ ("movi %0.8b, 8\n\t" - "cmhs %0.8b, %3.8b, %0.8b\n\t" - "tbl %1.8b, {%2.16b}, %3.8b\n\t" - "bsl %0.8b, %4.8b, %1.8b\n\t" - : "+w"(result), "=&w"(tmp1) - : "w"(temp), "w"(idx), "w"(r) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbx1_p8 (poly8x8_t r, poly8x8_t tab, uint8x8_t idx) -{ - poly8x8_t result; - poly8x8_t tmp1; - poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (UINT64_C (0x0))); - __asm__ ("movi %0.8b, 8\n\t" - "cmhs %0.8b, %3.8b, %0.8b\n\t" - "tbl %1.8b, {%2.16b}, %3.8b\n\t" - "bsl %0.8b, %4.8b, %1.8b\n\t" - : "+w"(result), "=&w"(tmp1) - : "w"(temp), "w"(idx), "w"(r) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbx2_s8 (int8x8_t r, int8x8x2_t tab, int8x8_t idx) -{ - int8x8_t result = r; - int8x16_t temp = vcombine_s8 (tab.val[0], tab.val[1]); - __asm__ ("tbx %0.8b, {%1.16b}, %2.8b" - : "+w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbx2_u8 (uint8x8_t r, uint8x8x2_t tab, uint8x8_t idx) -{ - uint8x8_t result = r; - uint8x16_t temp = vcombine_u8 (tab.val[0], tab.val[1]); - __asm__ ("tbx %0.8b, {%1.16b}, %2.8b" - : "+w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbx2_p8 (poly8x8_t r, poly8x8x2_t tab, uint8x8_t idx) -{ - poly8x8_t result = r; - poly8x16_t temp = vcombine_p8 (tab.val[0], tab.val[1]); - __asm__ ("tbx %0.8b, {%1.16b}, %2.8b" - : "+w"(result) - : "w"(temp), "w"(idx) - : /* No clobbers */); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbx3_s8 (int8x8_t r, int8x8x3_t tab, int8x8_t idx) -{ - int8x8_t result; - int8x8_t tmp1; - int8x16x2_t temp; - temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (UINT64_C (0x0))); - __asm__ ("ld1 {v16.16b - v17.16b}, %2\n\t" - "movi %0.8b, 24\n\t" - "cmhs %0.8b, %3.8b, %0.8b\n\t" - "tbl %1.8b, {v16.16b - v17.16b}, %3.8b\n\t" - "bsl %0.8b, %4.8b, %1.8b\n\t" - : "+w"(result), "=&w"(tmp1) - : "Q"(temp), "w"(idx), "w"(r) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbx3_u8 (uint8x8_t r, uint8x8x3_t tab, uint8x8_t idx) -{ - uint8x8_t result; - uint8x8_t tmp1; - uint8x16x2_t temp; - temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (UINT64_C (0x0))); - __asm__ ("ld1 {v16.16b - v17.16b}, %2\n\t" - "movi %0.8b, 24\n\t" - "cmhs %0.8b, %3.8b, %0.8b\n\t" - "tbl %1.8b, {v16.16b - v17.16b}, %3.8b\n\t" - "bsl %0.8b, %4.8b, %1.8b\n\t" - : "+w"(result), "=&w"(tmp1) - : "Q"(temp), "w"(idx), "w"(r) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbx3_p8 (poly8x8_t r, poly8x8x3_t tab, uint8x8_t idx) -{ - poly8x8_t result; - poly8x8_t tmp1; - poly8x16x2_t temp; - temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (UINT64_C (0x0))); - __asm__ ("ld1 {v16.16b - v17.16b}, %2\n\t" - "movi %0.8b, 24\n\t" - "cmhs %0.8b, %3.8b, %0.8b\n\t" - "tbl %1.8b, {v16.16b - v17.16b}, %3.8b\n\t" - "bsl %0.8b, %4.8b, %1.8b\n\t" - : "+w"(result), "=&w"(tmp1) - : "Q"(temp), "w"(idx), "w"(r) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vtbx4_s8 (int8x8_t r, int8x8x4_t tab, int8x8_t idx) -{ - int8x8_t result = r; - int8x16x2_t temp; - temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_s8 (tab.val[2], tab.val[3]); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbx %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "+w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtbx4_u8 (uint8x8_t r, uint8x8x4_t tab, uint8x8_t idx) -{ - uint8x8_t result = r; - uint8x16x2_t temp; - temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_u8 (tab.val[2], tab.val[3]); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbx %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "+w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vtbx4_p8 (poly8x8_t r, poly8x8x4_t tab, uint8x8_t idx) -{ - poly8x8_t result = r; - poly8x16x2_t temp; - temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]); - temp.val[1] = vcombine_p8 (tab.val[2], tab.val[3]); - __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t" - "tbx %0.8b, {v16.16b - v17.16b}, %2.8b\n\t" - : "+w"(result) - : "Q"(temp), "w"(idx) - : "v16", "v17", "memory"); - return result; -} - -/* End of temporary inline asm. */ - -/* Start of optimal implementations in approved order. */ - -/* vadd */ - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vaddd_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a + __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vaddd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a + __b; -} - -/* vceq */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vceq_p8 (poly8x8_t __a, poly8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmeqv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vceq_s8 (int8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmeqv8qi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vceq_s16 (int16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmeqv4hi (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vceq_s32 (int32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmeqv2si (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vceq_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmeqdi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vceq_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmeqv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vceq_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmeqv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vceq_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmeqv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vceq_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmeqdi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vceqq_p8 (poly8x16_t __a, poly8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmeqv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vceqq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmeqv16qi (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vceqq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmeqv8hi (__a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vceqq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmeqv4si (__a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vceqq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmeqv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vceqq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmeqv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vceqq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmeqv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vceqq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmeqv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vceqq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmeqv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vceqd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmeqdi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vceqd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmeqdi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vceqzd_s64 (int64x1_t __a) -{ - return (uint64x1_t) __builtin_aarch64_cmeqdi (__a, 0); -} - -/* vcge */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcge_s8 (int8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmgev8qi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcge_s16 (int16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmgev4hi (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcge_s32 (int32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmgev2si (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcge_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgedi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcge_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmhsv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcge_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmhsv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcge_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmhsv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcge_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmhsdi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcgeq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmgev16qi (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcgeq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmgev8hi (__a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcgeq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmgev4si (__a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcgeq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmgev2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcgeq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmhsv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcgeq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmhsv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcgeq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmhsv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcgeq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmhsv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcged_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgedi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcged_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmhsdi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgezd_s64 (int64x1_t __a) -{ - return (uint64x1_t) __builtin_aarch64_cmgedi (__a, 0); -} - -/* vcgt */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcgt_s8 (int8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmgtv8qi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcgt_s16 (int16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmgtv4hi (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcgt_s32 (int32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmgtv2si (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgt_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgtdi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcgt_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmhiv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcgt_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmhiv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcgt_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmhiv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgt_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmhidi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcgtq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmgtv16qi (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcgtq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmgtv8hi (__a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcgtq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmgtv4si (__a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcgtq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmgtv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcgtq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmhiv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcgtq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmhiv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcgtq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmhiv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcgtq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmhiv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgtd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgtdi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgtd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmhidi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcgtzd_s64 (int64x1_t __a) -{ - return (uint64x1_t) __builtin_aarch64_cmgtdi (__a, 0); -} - -/* vcle */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcle_s8 (int8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmgev8qi (__b, __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcle_s16 (int16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmgev4hi (__b, __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcle_s32 (int32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmgev2si (__b, __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcle_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgedi (__b, __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vcle_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmhsv8qi ((int8x8_t) __b, - (int8x8_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vcle_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmhsv4hi ((int16x4_t) __b, - (int16x4_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vcle_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmhsv2si ((int32x2_t) __b, - (int32x2_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcle_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmhsdi ((int64x1_t) __b, - (int64x1_t) __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcleq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmgev16qi (__b, __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcleq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmgev8hi (__b, __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcleq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmgev4si (__b, __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcleq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmgev2di (__b, __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcleq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmhsv16qi ((int8x16_t) __b, - (int8x16_t) __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcleq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmhsv8hi ((int16x8_t) __b, - (int16x8_t) __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcleq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmhsv4si ((int32x4_t) __b, - (int32x4_t) __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcleq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmhsv2di ((int64x2_t) __b, - (int64x2_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcled_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgedi (__b, __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vclezd_s64 (int64x1_t __a) -{ - return (uint64x1_t) __builtin_aarch64_cmledi (__a, 0); -} - -/* vclt */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vclt_s8 (int8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmgtv8qi (__b, __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vclt_s16 (int16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmgtv4hi (__b, __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vclt_s32 (int32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmgtv2si (__b, __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vclt_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgtdi (__b, __a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vclt_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmhiv8qi ((int8x8_t) __b, - (int8x8_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vclt_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmhiv4hi ((int16x4_t) __b, - (int16x4_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vclt_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmhiv2si ((int32x2_t) __b, - (int32x2_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vclt_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmhidi ((int64x1_t) __b, - (int64x1_t) __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcltq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmgtv16qi (__b, __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcltq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmgtv8hi (__b, __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcltq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmgtv4si (__b, __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcltq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmgtv2di (__b, __a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vcltq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmhiv16qi ((int8x16_t) __b, - (int8x16_t) __a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vcltq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmhiv8hi ((int16x8_t) __b, - (int16x8_t) __a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vcltq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmhiv4si ((int32x4_t) __b, - (int32x4_t) __a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vcltq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmhiv2di ((int64x2_t) __b, - (int64x2_t) __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcltd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmgtdi (__b, __a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vcltzd_s64 (int64x1_t __a) -{ - return (uint64x1_t) __builtin_aarch64_cmltdi (__a, 0); -} - -/* vdup */ - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vdupb_lane_s8 (int8x16_t a, int const b) -{ - return __builtin_aarch64_dup_laneqi (a, b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vdupb_lane_u8 (uint8x16_t a, int const b) -{ - return (uint8x1_t) __builtin_aarch64_dup_laneqi ((int8x16_t) a, b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vduph_lane_s16 (int16x8_t a, int const b) -{ - return __builtin_aarch64_dup_lanehi (a, b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vduph_lane_u16 (uint16x8_t a, int const b) -{ - return (uint16x1_t) __builtin_aarch64_dup_lanehi ((int16x8_t) a, b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vdups_lane_s32 (int32x4_t a, int const b) -{ - return __builtin_aarch64_dup_lanesi (a, b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vdups_lane_u32 (uint32x4_t a, int const b) -{ - return (uint32x1_t) __builtin_aarch64_dup_lanesi ((int32x4_t) a, b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vdupd_lane_s64 (int64x2_t a, int const b) -{ - return __builtin_aarch64_dup_lanedi (a, b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vdupd_lane_u64 (uint64x2_t a, int const b) -{ - return (uint64x1_t) __builtin_aarch64_dup_lanedi ((int64x2_t) a, b); -} - -/* vld1 */ - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vld1_f32 (const float32_t *a) -{ - return __builtin_aarch64_ld1v2sf ((const __builtin_aarch64_simd_sf *) a); -} - -__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) -vld1_f64 (const float64_t *a) -{ - return *a; -} - -__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) -vld1_p8 (const poly8_t *a) -{ - return (poly8x8_t) - __builtin_aarch64_ld1v8qi ((const __builtin_aarch64_simd_qi *) a); -} - -__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) -vld1_p16 (const poly16_t *a) -{ - return (poly16x4_t) - __builtin_aarch64_ld1v4hi ((const __builtin_aarch64_simd_hi *) a); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vld1_s8 (const int8_t *a) -{ - return __builtin_aarch64_ld1v8qi ((const __builtin_aarch64_simd_qi *) a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vld1_s16 (const int16_t *a) -{ - return __builtin_aarch64_ld1v4hi ((const __builtin_aarch64_simd_hi *) a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vld1_s32 (const int32_t *a) -{ - return __builtin_aarch64_ld1v2si ((const __builtin_aarch64_simd_si *) a); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vld1_s64 (const int64_t *a) -{ - return *a; -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vld1_u8 (const uint8_t *a) -{ - return (uint8x8_t) - __builtin_aarch64_ld1v8qi ((const __builtin_aarch64_simd_qi *) a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vld1_u16 (const uint16_t *a) -{ - return (uint16x4_t) - __builtin_aarch64_ld1v4hi ((const __builtin_aarch64_simd_hi *) a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vld1_u32 (const uint32_t *a) -{ - return (uint32x2_t) - __builtin_aarch64_ld1v2si ((const __builtin_aarch64_simd_si *) a); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vld1_u64 (const uint64_t *a) -{ - return *a; -} - -/* vld1q */ - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vld1q_f32 (const float32_t *a) -{ - return __builtin_aarch64_ld1v4sf ((const __builtin_aarch64_simd_sf *) a); -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vld1q_f64 (const float64_t *a) -{ - return __builtin_aarch64_ld1v2df ((const __builtin_aarch64_simd_df *) a); -} - -__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) -vld1q_p8 (const poly8_t *a) -{ - return (poly8x16_t) - __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a); -} - -__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) -vld1q_p16 (const poly16_t *a) -{ - return (poly16x8_t) - __builtin_aarch64_ld1v8hi ((const __builtin_aarch64_simd_hi *) a); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vld1q_s8 (const int8_t *a) -{ - return __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vld1q_s16 (const int16_t *a) -{ - return __builtin_aarch64_ld1v8hi ((const __builtin_aarch64_simd_hi *) a); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vld1q_s32 (const int32_t *a) -{ - return __builtin_aarch64_ld1v4si ((const __builtin_aarch64_simd_si *) a); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vld1q_s64 (const int64_t *a) -{ - return __builtin_aarch64_ld1v2di ((const __builtin_aarch64_simd_di *) a); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vld1q_u8 (const uint8_t *a) -{ - return (uint8x16_t) - __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vld1q_u16 (const uint16_t *a) -{ - return (uint16x8_t) - __builtin_aarch64_ld1v8hi ((const __builtin_aarch64_simd_hi *) a); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vld1q_u32 (const uint32_t *a) -{ - return (uint32x4_t) - __builtin_aarch64_ld1v4si ((const __builtin_aarch64_simd_si *) a); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vld1q_u64 (const uint64_t *a) -{ - return (uint64x2_t) - __builtin_aarch64_ld1v2di ((const __builtin_aarch64_simd_di *) a); -} - -/* vldn */ - -__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__)) -vld2_s64 (const int64_t * __a) -{ - int64x1x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 0); - ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 1); - return ret; -} - -__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__)) -vld2_u64 (const uint64_t * __a) -{ - uint64x1x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 0); - ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 1); - return ret; -} - -__extension__ static __inline float64x1x2_t __attribute__ ((__always_inline__)) -vld2_f64 (const float64_t * __a) -{ - float64x1x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2df ((const __builtin_aarch64_simd_df *) __a); - ret.val[0] = (float64x1_t) __builtin_aarch64_get_dregoidf (__o, 0); - ret.val[1] = (float64x1_t) __builtin_aarch64_get_dregoidf (__o, 1); - return ret; -} - -__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) -vld2_s8 (const int8_t * __a) -{ - int8x8x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0); - ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1); - return ret; -} - -__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) -vld2_p8 (const poly8_t * __a) -{ - poly8x8x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0); - ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1); - return ret; -} - -__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) -vld2_s16 (const int16_t * __a) -{ - int16x4x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0); - ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1); - return ret; -} - -__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) -vld2_p16 (const poly16_t * __a) -{ - poly16x4x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0); - ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1); - return ret; -} - -__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) -vld2_s32 (const int32_t * __a) -{ - int32x2x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v2si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0); - ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1); - return ret; -} - -__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) -vld2_u8 (const uint8_t * __a) -{ - uint8x8x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0); - ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1); - return ret; -} - -__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) -vld2_u16 (const uint16_t * __a) -{ - uint16x4x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0); - ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1); - return ret; -} - -__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) -vld2_u32 (const uint32_t * __a) -{ - uint32x2x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v2si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0); - ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1); - return ret; -} - -__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) -vld2_f32 (const float32_t * __a) -{ - float32x2x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v2sf ((const __builtin_aarch64_simd_sf *) __a); - ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 0); - ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 1); - return ret; -} - -__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) -vld2q_s8 (const int8_t * __a) -{ - int8x16x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0); - ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1); - return ret; -} - -__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) -vld2q_p8 (const poly8_t * __a) -{ - poly8x16x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0); - ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1); - return ret; -} - -__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) -vld2q_s16 (const int16_t * __a) -{ - int16x8x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0); - ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1); - return ret; -} - -__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) -vld2q_p16 (const poly16_t * __a) -{ - poly16x8x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0); - ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1); - return ret; -} - -__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) -vld2q_s32 (const int32_t * __a) -{ - int32x4x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v4si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0); - ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1); - return ret; -} - -__extension__ static __inline int64x2x2_t __attribute__ ((__always_inline__)) -vld2q_s64 (const int64_t * __a) -{ - int64x2x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0); - ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1); - return ret; -} - -__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) -vld2q_u8 (const uint8_t * __a) -{ - uint8x16x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0); - ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1); - return ret; -} - -__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) -vld2q_u16 (const uint16_t * __a) -{ - uint16x8x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0); - ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1); - return ret; -} - -__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) -vld2q_u32 (const uint32_t * __a) -{ - uint32x4x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v4si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0); - ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1); - return ret; -} - -__extension__ static __inline uint64x2x2_t __attribute__ ((__always_inline__)) -vld2q_u64 (const uint64_t * __a) -{ - uint64x2x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0); - ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1); - return ret; -} - -__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) -vld2q_f32 (const float32_t * __a) -{ - float32x4x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v4sf ((const __builtin_aarch64_simd_sf *) __a); - ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 0); - ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 1); - return ret; -} - -__extension__ static __inline float64x2x2_t __attribute__ ((__always_inline__)) -vld2q_f64 (const float64_t * __a) -{ - float64x2x2_t ret; - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_ld2v2df ((const __builtin_aarch64_simd_df *) __a); - ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 0); - ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 1); - return ret; -} - -__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__)) -vld3_s64 (const int64_t * __a) -{ - int64x1x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 0); - ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 1); - ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 2); - return ret; -} - -__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__)) -vld3_u64 (const uint64_t * __a) -{ - uint64x1x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 0); - ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 1); - ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 2); - return ret; -} - -__extension__ static __inline float64x1x3_t __attribute__ ((__always_inline__)) -vld3_f64 (const float64_t * __a) -{ - float64x1x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3df ((const __builtin_aarch64_simd_df *) __a); - ret.val[0] = (float64x1_t) __builtin_aarch64_get_dregcidf (__o, 0); - ret.val[1] = (float64x1_t) __builtin_aarch64_get_dregcidf (__o, 1); - ret.val[2] = (float64x1_t) __builtin_aarch64_get_dregcidf (__o, 2); - return ret; -} - -__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__)) -vld3_s8 (const int8_t * __a) -{ - int8x8x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0); - ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1); - ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2); - return ret; -} - -__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__)) -vld3_p8 (const poly8_t * __a) -{ - poly8x8x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0); - ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1); - ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2); - return ret; -} - -__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__)) -vld3_s16 (const int16_t * __a) -{ - int16x4x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0); - ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1); - ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2); - return ret; -} - -__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__)) -vld3_p16 (const poly16_t * __a) -{ - poly16x4x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0); - ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1); - ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2); - return ret; -} - -__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__)) -vld3_s32 (const int32_t * __a) -{ - int32x2x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v2si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0); - ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1); - ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2); - return ret; -} - -__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__)) -vld3_u8 (const uint8_t * __a) -{ - uint8x8x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0); - ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1); - ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2); - return ret; -} - -__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__)) -vld3_u16 (const uint16_t * __a) -{ - uint16x4x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0); - ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1); - ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2); - return ret; -} - -__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__)) -vld3_u32 (const uint32_t * __a) -{ - uint32x2x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v2si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0); - ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1); - ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2); - return ret; -} - -__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__)) -vld3_f32 (const float32_t * __a) -{ - float32x2x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v2sf ((const __builtin_aarch64_simd_sf *) __a); - ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 0); - ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 1); - ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 2); - return ret; -} - -__extension__ static __inline int8x16x3_t __attribute__ ((__always_inline__)) -vld3q_s8 (const int8_t * __a) -{ - int8x16x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0); - ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1); - ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2); - return ret; -} - -__extension__ static __inline poly8x16x3_t __attribute__ ((__always_inline__)) -vld3q_p8 (const poly8_t * __a) -{ - poly8x16x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0); - ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1); - ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2); - return ret; -} - -__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__)) -vld3q_s16 (const int16_t * __a) -{ - int16x8x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0); - ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1); - ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2); - return ret; -} - -__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__)) -vld3q_p16 (const poly16_t * __a) -{ - poly16x8x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0); - ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1); - ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2); - return ret; -} - -__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__)) -vld3q_s32 (const int32_t * __a) -{ - int32x4x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v4si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0); - ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1); - ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2); - return ret; -} - -__extension__ static __inline int64x2x3_t __attribute__ ((__always_inline__)) -vld3q_s64 (const int64_t * __a) -{ - int64x2x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0); - ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1); - ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2); - return ret; -} - -__extension__ static __inline uint8x16x3_t __attribute__ ((__always_inline__)) -vld3q_u8 (const uint8_t * __a) -{ - uint8x16x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0); - ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1); - ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2); - return ret; -} - -__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__)) -vld3q_u16 (const uint16_t * __a) -{ - uint16x8x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0); - ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1); - ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2); - return ret; -} - -__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__)) -vld3q_u32 (const uint32_t * __a) -{ - uint32x4x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v4si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0); - ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1); - ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2); - return ret; -} - -__extension__ static __inline uint64x2x3_t __attribute__ ((__always_inline__)) -vld3q_u64 (const uint64_t * __a) -{ - uint64x2x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0); - ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1); - ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2); - return ret; -} - -__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__)) -vld3q_f32 (const float32_t * __a) -{ - float32x4x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v4sf ((const __builtin_aarch64_simd_sf *) __a); - ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 0); - ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 1); - ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 2); - return ret; -} - -__extension__ static __inline float64x2x3_t __attribute__ ((__always_inline__)) -vld3q_f64 (const float64_t * __a) -{ - float64x2x3_t ret; - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_ld3v2df ((const __builtin_aarch64_simd_df *) __a); - ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 0); - ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 1); - ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 2); - return ret; -} - -__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__)) -vld4_s64 (const int64_t * __a) -{ - int64x1x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 0); - ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 1); - ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 2); - ret.val[3] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 3); - return ret; -} - -__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__)) -vld4_u64 (const uint64_t * __a) -{ - uint64x1x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 0); - ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 1); - ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 2); - ret.val[3] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 3); - return ret; -} - -__extension__ static __inline float64x1x4_t __attribute__ ((__always_inline__)) -vld4_f64 (const float64_t * __a) -{ - float64x1x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4df ((const __builtin_aarch64_simd_df *) __a); - ret.val[0] = (float64x1_t) __builtin_aarch64_get_dregxidf (__o, 0); - ret.val[1] = (float64x1_t) __builtin_aarch64_get_dregxidf (__o, 1); - ret.val[2] = (float64x1_t) __builtin_aarch64_get_dregxidf (__o, 2); - ret.val[3] = (float64x1_t) __builtin_aarch64_get_dregxidf (__o, 3); - return ret; -} - -__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__)) -vld4_s8 (const int8_t * __a) -{ - int8x8x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0); - ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1); - ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2); - ret.val[3] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3); - return ret; -} - -__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__)) -vld4_p8 (const poly8_t * __a) -{ - poly8x8x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0); - ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1); - ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2); - ret.val[3] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3); - return ret; -} - -__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__)) -vld4_s16 (const int16_t * __a) -{ - int16x4x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0); - ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1); - ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2); - ret.val[3] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3); - return ret; -} - -__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__)) -vld4_p16 (const poly16_t * __a) -{ - poly16x4x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0); - ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1); - ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2); - ret.val[3] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3); - return ret; -} - -__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__)) -vld4_s32 (const int32_t * __a) -{ - int32x2x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v2si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0); - ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1); - ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2); - ret.val[3] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3); - return ret; -} - -__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__)) -vld4_u8 (const uint8_t * __a) -{ - uint8x8x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v8qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0); - ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1); - ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2); - ret.val[3] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3); - return ret; -} - -__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__)) -vld4_u16 (const uint16_t * __a) -{ - uint16x4x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v4hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0); - ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1); - ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2); - ret.val[3] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3); - return ret; -} - -__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__)) -vld4_u32 (const uint32_t * __a) -{ - uint32x2x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v2si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0); - ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1); - ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2); - ret.val[3] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3); - return ret; -} - -__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__)) -vld4_f32 (const float32_t * __a) -{ - float32x2x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v2sf ((const __builtin_aarch64_simd_sf *) __a); - ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 0); - ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 1); - ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 2); - ret.val[3] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 3); - return ret; -} - -__extension__ static __inline int8x16x4_t __attribute__ ((__always_inline__)) -vld4q_s8 (const int8_t * __a) -{ - int8x16x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0); - ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1); - ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2); - ret.val[3] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3); - return ret; -} - -__extension__ static __inline poly8x16x4_t __attribute__ ((__always_inline__)) -vld4q_p8 (const poly8_t * __a) -{ - poly8x16x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0); - ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1); - ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2); - ret.val[3] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3); - return ret; -} - -__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__)) -vld4q_s16 (const int16_t * __a) -{ - int16x8x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0); - ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1); - ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2); - ret.val[3] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3); - return ret; -} - -__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__)) -vld4q_p16 (const poly16_t * __a) -{ - poly16x8x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0); - ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1); - ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2); - ret.val[3] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3); - return ret; -} - -__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__)) -vld4q_s32 (const int32_t * __a) -{ - int32x4x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v4si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0); - ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1); - ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2); - ret.val[3] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3); - return ret; -} - -__extension__ static __inline int64x2x4_t __attribute__ ((__always_inline__)) -vld4q_s64 (const int64_t * __a) -{ - int64x2x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0); - ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1); - ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2); - ret.val[3] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3); - return ret; -} - -__extension__ static __inline uint8x16x4_t __attribute__ ((__always_inline__)) -vld4q_u8 (const uint8_t * __a) -{ - uint8x16x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v16qi ((const __builtin_aarch64_simd_qi *) __a); - ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0); - ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1); - ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2); - ret.val[3] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3); - return ret; -} - -__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__)) -vld4q_u16 (const uint16_t * __a) -{ - uint16x8x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v8hi ((const __builtin_aarch64_simd_hi *) __a); - ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0); - ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1); - ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2); - ret.val[3] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3); - return ret; -} - -__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__)) -vld4q_u32 (const uint32_t * __a) -{ - uint32x4x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v4si ((const __builtin_aarch64_simd_si *) __a); - ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0); - ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1); - ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2); - ret.val[3] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3); - return ret; -} - -__extension__ static __inline uint64x2x4_t __attribute__ ((__always_inline__)) -vld4q_u64 (const uint64_t * __a) -{ - uint64x2x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v2di ((const __builtin_aarch64_simd_di *) __a); - ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0); - ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1); - ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2); - ret.val[3] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3); - return ret; -} - -__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__)) -vld4q_f32 (const float32_t * __a) -{ - float32x4x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v4sf ((const __builtin_aarch64_simd_sf *) __a); - ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 0); - ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 1); - ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 2); - ret.val[3] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 3); - return ret; -} - -__extension__ static __inline float64x2x4_t __attribute__ ((__always_inline__)) -vld4q_f64 (const float64_t * __a) -{ - float64x2x4_t ret; - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_ld4v2df ((const __builtin_aarch64_simd_df *) __a); - ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 0); - ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 1); - ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 2); - ret.val[3] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 3); - return ret; -} - -/* vmax */ - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmax_f32 (float32x2_t __a, float32x2_t __b) -{ - return __builtin_aarch64_fmaxv2sf (__a, __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmax_s8 (int8x8_t __a, int8x8_t __b) -{ - return __builtin_aarch64_smaxv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmax_s16 (int16x4_t __a, int16x4_t __b) -{ - return __builtin_aarch64_smaxv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmax_s32 (int32x2_t __a, int32x2_t __b) -{ - return __builtin_aarch64_smaxv2si (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmax_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_umaxv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmax_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_umaxv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmax_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_umaxv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmaxq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __builtin_aarch64_fmaxv4sf (__a, __b); -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmaxq_f64 (float64x2_t __a, float64x2_t __b) -{ - return __builtin_aarch64_fmaxv2df (__a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vmaxq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_aarch64_smaxv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vmaxq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_aarch64_smaxv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vmaxq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_aarch64_smaxv4si (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vmaxq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_umaxv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vmaxq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_umaxv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vmaxq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_umaxv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -/* vmin */ - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmin_f32 (float32x2_t __a, float32x2_t __b) -{ - return __builtin_aarch64_fminv2sf (__a, __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vmin_s8 (int8x8_t __a, int8x8_t __b) -{ - return __builtin_aarch64_sminv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vmin_s16 (int16x4_t __a, int16x4_t __b) -{ - return __builtin_aarch64_sminv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vmin_s32 (int32x2_t __a, int32x2_t __b) -{ - return __builtin_aarch64_sminv2si (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vmin_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_uminv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vmin_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_uminv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vmin_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_uminv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vminq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __builtin_aarch64_fminv4sf (__a, __b); -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vminq_f64 (float64x2_t __a, float64x2_t __b) -{ - return __builtin_aarch64_fminv2df (__a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vminq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_aarch64_sminv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vminq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_aarch64_sminv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vminq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_aarch64_sminv4si (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vminq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_uminv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vminq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uminv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vminq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uminv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -/* vmla */ - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmla_f32 (float32x2_t a, float32x2_t b, float32x2_t c) -{ - return a + b * c; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmlaq_f32 (float32x4_t a, float32x4_t b, float32x4_t c) -{ - return a + b * c; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmlaq_f64 (float64x2_t a, float64x2_t b, float64x2_t c) -{ - return a + b * c; -} - -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vmls_f32 (float32x2_t a, float32x2_t b, float32x2_t c) -{ - return a - b * c; -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vmlsq_f32 (float32x4_t a, float32x4_t b, float32x4_t c) -{ - return a - b * c; -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vmlsq_f64 (float64x2_t a, float64x2_t b, float64x2_t c) -{ - return a - b * c; -} - -/* vqabs */ - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqabsq_s64 (int64x2_t __a) -{ - return (int64x2_t) __builtin_aarch64_sqabsv2di (__a); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqabsb_s8 (int8x1_t __a) -{ - return (int8x1_t) __builtin_aarch64_sqabsqi (__a); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqabsh_s16 (int16x1_t __a) -{ - return (int16x1_t) __builtin_aarch64_sqabshi (__a); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqabss_s32 (int32x1_t __a) -{ - return (int32x1_t) __builtin_aarch64_sqabssi (__a); -} - -/* vqadd */ - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqaddb_s8 (int8x1_t __a, int8x1_t __b) -{ - return (int8x1_t) __builtin_aarch64_sqaddqi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqaddh_s16 (int16x1_t __a, int16x1_t __b) -{ - return (int16x1_t) __builtin_aarch64_sqaddhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqadds_s32 (int32x1_t __a, int32x1_t __b) -{ - return (int32x1_t) __builtin_aarch64_sqaddsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqaddd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sqadddi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqaddb_u8 (uint8x1_t __a, uint8x1_t __b) -{ - return (uint8x1_t) __builtin_aarch64_uqaddqi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqaddh_u16 (uint16x1_t __a, uint16x1_t __b) -{ - return (uint16x1_t) __builtin_aarch64_uqaddhi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqadds_u32 (uint32x1_t __a, uint32x1_t __b) -{ - return (uint32x1_t) __builtin_aarch64_uqaddsi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqaddd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqadddi (__a, __b); -} - -/* vqdmlal */ - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) -{ - return __builtin_aarch64_sqdmlalv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_high_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c) -{ - return __builtin_aarch64_sqdmlal2v8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_high_lane_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlal2_lanev8hi (__a, __b, __c, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_high_laneq_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlal2_laneqv8hi (__a, __b, __c, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_high_n_s16 (int32x4_t __a, int16x8_t __b, int16_t __c) -{ - return __builtin_aarch64_sqdmlal2_nv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, int const __d) -{ - int16x8_t __tmp = vcombine_s16 (__c, vcreate_s16 (INT64_C (0))); - return __builtin_aarch64_sqdmlal_lanev4hi (__a, __b, __tmp, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_laneq_s16 (int32x4_t __a, int16x4_t __b, int16x8_t __c, int const __d) -{ - return __builtin_aarch64_sqdmlal_laneqv4hi (__a, __b, __c, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlal_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c) -{ - return __builtin_aarch64_sqdmlal_nv4hi (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) -{ - return __builtin_aarch64_sqdmlalv2si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_high_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c) -{ - return __builtin_aarch64_sqdmlal2v4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_high_lane_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlal2_lanev4si (__a, __b, __c, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_high_laneq_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlal2_laneqv4si (__a, __b, __c, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_high_n_s32 (int64x2_t __a, int32x4_t __b, int32_t __c) -{ - return __builtin_aarch64_sqdmlal2_nv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, int const __d) -{ - int32x4_t __tmp = vcombine_s32 (__c, vcreate_s32 (INT64_C (0))); - return __builtin_aarch64_sqdmlal_lanev2si (__a, __b, __tmp, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_laneq_s32 (int64x2_t __a, int32x2_t __b, int32x4_t __c, int const __d) -{ - return __builtin_aarch64_sqdmlal_laneqv2si (__a, __b, __c, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlal_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c) -{ - return __builtin_aarch64_sqdmlal_nv2si (__a, __b, __c); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmlalh_s16 (int32x1_t __a, int16x1_t __b, int16x1_t __c) -{ - return __builtin_aarch64_sqdmlalhi (__a, __b, __c); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmlalh_lane_s16 (int32x1_t __a, int16x1_t __b, int16x8_t __c, const int __d) -{ - return __builtin_aarch64_sqdmlal_lanehi (__a, __b, __c, __d); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqdmlals_s32 (int64x1_t __a, int32x1_t __b, int32x1_t __c) -{ - return __builtin_aarch64_sqdmlalsi (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqdmlals_lane_s32 (int64x1_t __a, int32x1_t __b, int32x4_t __c, const int __d) -{ - return __builtin_aarch64_sqdmlal_lanesi (__a, __b, __c, __d); -} - -/* vqdmlsl */ - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) -{ - return __builtin_aarch64_sqdmlslv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_high_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c) -{ - return __builtin_aarch64_sqdmlsl2v8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_high_lane_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlsl2_lanev8hi (__a, __b, __c, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_high_laneq_s16 (int32x4_t __a, int16x8_t __b, int16x8_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlsl2_laneqv8hi (__a, __b, __c, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_high_n_s16 (int32x4_t __a, int16x8_t __b, int16_t __c) -{ - return __builtin_aarch64_sqdmlsl2_nv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, int const __d) -{ - int16x8_t __tmp = vcombine_s16 (__c, vcreate_s16 (INT64_C (0))); - return __builtin_aarch64_sqdmlsl_lanev4hi (__a, __b, __tmp, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_laneq_s16 (int32x4_t __a, int16x4_t __b, int16x8_t __c, int const __d) -{ - return __builtin_aarch64_sqdmlsl_laneqv4hi (__a, __b, __c, __d); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmlsl_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c) -{ - return __builtin_aarch64_sqdmlsl_nv4hi (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) -{ - return __builtin_aarch64_sqdmlslv2si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_high_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c) -{ - return __builtin_aarch64_sqdmlsl2v4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_high_lane_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlsl2_lanev4si (__a, __b, __c, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_high_laneq_s32 (int64x2_t __a, int32x4_t __b, int32x4_t __c, - int const __d) -{ - return __builtin_aarch64_sqdmlsl2_laneqv4si (__a, __b, __c, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_high_n_s32 (int64x2_t __a, int32x4_t __b, int32_t __c) -{ - return __builtin_aarch64_sqdmlsl2_nv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, int const __d) -{ - int32x4_t __tmp = vcombine_s32 (__c, vcreate_s32 (INT64_C (0))); - return __builtin_aarch64_sqdmlsl_lanev2si (__a, __b, __tmp, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_laneq_s32 (int64x2_t __a, int32x2_t __b, int32x4_t __c, int const __d) -{ - return __builtin_aarch64_sqdmlsl_laneqv2si (__a, __b, __c, __d); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmlsl_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c) -{ - return __builtin_aarch64_sqdmlsl_nv2si (__a, __b, __c); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmlslh_s16 (int32x1_t __a, int16x1_t __b, int16x1_t __c) -{ - return __builtin_aarch64_sqdmlslhi (__a, __b, __c); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmlslh_lane_s16 (int32x1_t __a, int16x1_t __b, int16x8_t __c, const int __d) -{ - return __builtin_aarch64_sqdmlsl_lanehi (__a, __b, __c, __d); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqdmlsls_s32 (int64x1_t __a, int32x1_t __b, int32x1_t __c) -{ - return __builtin_aarch64_sqdmlslsi (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqdmlsls_lane_s32 (int64x1_t __a, int32x1_t __b, int32x4_t __c, const int __d) -{ - return __builtin_aarch64_sqdmlsl_lanesi (__a, __b, __c, __d); -} - -/* vqdmulh */ - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqdmulh_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_lanev4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_lanev2si (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqdmulhq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_lanev8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmulhq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_lanev4si (__a, __b, __c); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqdmulhh_s16 (int16x1_t __a, int16x1_t __b) -{ - return (int16x1_t) __builtin_aarch64_sqdmulhhi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqdmulhh_lane_s16 (int16x1_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_lanehi (__a, __b, __c); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmulhs_s32 (int32x1_t __a, int32x1_t __b) -{ - return (int32x1_t) __builtin_aarch64_sqdmulhsi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmulhs_lane_s32 (int32x1_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqdmulh_lanesi (__a, __b, __c); -} - -/* vqdmull */ - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_s16 (int16x4_t __a, int16x4_t __b) -{ - return __builtin_aarch64_sqdmullv4hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_high_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_aarch64_sqdmull2v8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_high_lane_s16 (int16x8_t __a, int16x8_t __b, int const __c) -{ - return __builtin_aarch64_sqdmull2_lanev8hi (__a, __b,__c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_high_laneq_s16 (int16x8_t __a, int16x8_t __b, int const __c) -{ - return __builtin_aarch64_sqdmull2_laneqv8hi (__a, __b,__c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_high_n_s16 (int16x8_t __a, int16_t __b) -{ - return __builtin_aarch64_sqdmull2_nv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_lane_s16 (int16x4_t __a, int16x4_t __b, int const __c) -{ - int16x8_t __tmp = vcombine_s16 (__b, vcreate_s16 (INT64_C (0))); - return __builtin_aarch64_sqdmull_lanev4hi (__a, __tmp, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_laneq_s16 (int16x4_t __a, int16x8_t __b, int const __c) -{ - return __builtin_aarch64_sqdmull_laneqv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqdmull_n_s16 (int16x4_t __a, int16_t __b) -{ - return __builtin_aarch64_sqdmull_nv4hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_s32 (int32x2_t __a, int32x2_t __b) -{ - return __builtin_aarch64_sqdmullv2si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_high_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_aarch64_sqdmull2v4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_high_lane_s32 (int32x4_t __a, int32x4_t __b, int const __c) -{ - return __builtin_aarch64_sqdmull2_lanev4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_high_laneq_s32 (int32x4_t __a, int32x4_t __b, int const __c) -{ - return __builtin_aarch64_sqdmull2_laneqv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_high_n_s32 (int32x4_t __a, int32_t __b) -{ - return __builtin_aarch64_sqdmull2_nv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_lane_s32 (int32x2_t __a, int32x2_t __b, int const __c) -{ - int32x4_t __tmp = vcombine_s32 (__b, vcreate_s32 (INT64_C (0))); - return __builtin_aarch64_sqdmull_lanev2si (__a, __tmp, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_laneq_s32 (int32x2_t __a, int32x4_t __b, int const __c) -{ - return __builtin_aarch64_sqdmull_laneqv2si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqdmull_n_s32 (int32x2_t __a, int32_t __b) -{ - return __builtin_aarch64_sqdmull_nv2si (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmullh_s16 (int16x1_t __a, int16x1_t __b) -{ - return (int32x1_t) __builtin_aarch64_sqdmullhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqdmullh_lane_s16 (int16x1_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqdmull_lanehi (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqdmulls_s32 (int32x1_t __a, int32x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sqdmullsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqdmulls_lane_s32 (int32x1_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqdmull_lanesi (__a, __b, __c); -} - -/* vqmovn */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqmovn_s16 (int16x8_t __a) -{ - return (int8x8_t) __builtin_aarch64_sqmovnv8hi (__a); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqmovn_s32 (int32x4_t __a) -{ - return (int16x4_t) __builtin_aarch64_sqmovnv4si (__a); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqmovn_s64 (int64x2_t __a) -{ - return (int32x2_t) __builtin_aarch64_sqmovnv2di (__a); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqmovn_u16 (uint16x8_t __a) -{ - return (uint8x8_t) __builtin_aarch64_uqmovnv8hi ((int16x8_t) __a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqmovn_u32 (uint32x4_t __a) -{ - return (uint16x4_t) __builtin_aarch64_uqmovnv4si ((int32x4_t) __a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqmovn_u64 (uint64x2_t __a) -{ - return (uint32x2_t) __builtin_aarch64_uqmovnv2di ((int64x2_t) __a); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqmovnh_s16 (int16x1_t __a) -{ - return (int8x1_t) __builtin_aarch64_sqmovnhi (__a); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqmovns_s32 (int32x1_t __a) -{ - return (int16x1_t) __builtin_aarch64_sqmovnsi (__a); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqmovnd_s64 (int64x1_t __a) -{ - return (int32x1_t) __builtin_aarch64_sqmovndi (__a); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqmovnh_u16 (uint16x1_t __a) -{ - return (uint8x1_t) __builtin_aarch64_uqmovnhi (__a); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqmovns_u32 (uint32x1_t __a) -{ - return (uint16x1_t) __builtin_aarch64_uqmovnsi (__a); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqmovnd_u64 (uint64x1_t __a) -{ - return (uint32x1_t) __builtin_aarch64_uqmovndi (__a); -} - -/* vqmovun */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqmovun_s16 (int16x8_t __a) -{ - return (uint8x8_t) __builtin_aarch64_sqmovunv8hi (__a); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqmovun_s32 (int32x4_t __a) -{ - return (uint16x4_t) __builtin_aarch64_sqmovunv4si (__a); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqmovun_s64 (int64x2_t __a) -{ - return (uint32x2_t) __builtin_aarch64_sqmovunv2di (__a); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqmovunh_s16 (int16x1_t __a) -{ - return (int8x1_t) __builtin_aarch64_sqmovunhi (__a); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqmovuns_s32 (int32x1_t __a) -{ - return (int16x1_t) __builtin_aarch64_sqmovunsi (__a); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqmovund_s64 (int64x1_t __a) -{ - return (int32x1_t) __builtin_aarch64_sqmovundi (__a); -} - -/* vqneg */ - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqnegq_s64 (int64x2_t __a) -{ - return (int64x2_t) __builtin_aarch64_sqnegv2di (__a); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqnegb_s8 (int8x1_t __a) -{ - return (int8x1_t) __builtin_aarch64_sqnegqi (__a); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqnegh_s16 (int16x1_t __a) -{ - return (int16x1_t) __builtin_aarch64_sqneghi (__a); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqnegs_s32 (int32x1_t __a) -{ - return (int32x1_t) __builtin_aarch64_sqnegsi (__a); -} - -/* vqrdmulh */ - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqrdmulh_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_lanev4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqrdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_lanev2si (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqrdmulhq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_lanev8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqrdmulhq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_lanev4si (__a, __b, __c); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqrdmulhh_s16 (int16x1_t __a, int16x1_t __b) -{ - return (int16x1_t) __builtin_aarch64_sqrdmulhhi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqrdmulhh_lane_s16 (int16x1_t __a, int16x8_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_lanehi (__a, __b, __c); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqrdmulhs_s32 (int32x1_t __a, int32x1_t __b) -{ - return (int32x1_t) __builtin_aarch64_sqrdmulhsi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqrdmulhs_lane_s32 (int32x1_t __a, int32x4_t __b, const int __c) -{ - return __builtin_aarch64_sqrdmulh_lanesi (__a, __b, __c); -} - -/* vqrshl */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqrshl_s8 (int8x8_t __a, int8x8_t __b) -{ - return __builtin_aarch64_sqrshlv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqrshl_s16 (int16x4_t __a, int16x4_t __b) -{ - return __builtin_aarch64_sqrshlv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqrshl_s32 (int32x2_t __a, int32x2_t __b) -{ - return __builtin_aarch64_sqrshlv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqrshl_s64 (int64x1_t __a, int64x1_t __b) -{ - return __builtin_aarch64_sqrshldi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqrshl_u8 (uint8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_uqrshlv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqrshl_u16 (uint16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_uqrshlv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqrshl_u32 (uint32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_uqrshlv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqrshl_u64 (uint64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqrshldi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqrshlq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_aarch64_sqrshlv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqrshlq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_aarch64_sqrshlv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqrshlq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_aarch64_sqrshlv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqrshlq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __builtin_aarch64_sqrshlv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqrshlq_u8 (uint8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_uqrshlv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqrshlq_u16 (uint16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uqrshlv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqrshlq_u32 (uint32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uqrshlv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vqrshlq_u64 (uint64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uqrshlv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqrshlb_s8 (int8x1_t __a, int8x1_t __b) -{ - return __builtin_aarch64_sqrshlqi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqrshlh_s16 (int16x1_t __a, int16x1_t __b) -{ - return __builtin_aarch64_sqrshlhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqrshls_s32 (int32x1_t __a, int32x1_t __b) -{ - return __builtin_aarch64_sqrshlsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqrshld_s64 (int64x1_t __a, int64x1_t __b) -{ - return __builtin_aarch64_sqrshldi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqrshlb_u8 (uint8x1_t __a, uint8x1_t __b) -{ - return (uint8x1_t) __builtin_aarch64_uqrshlqi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqrshlh_u16 (uint16x1_t __a, uint16x1_t __b) -{ - return (uint16x1_t) __builtin_aarch64_uqrshlhi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqrshls_u32 (uint32x1_t __a, uint32x1_t __b) -{ - return (uint32x1_t) __builtin_aarch64_uqrshlsi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqrshld_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqrshldi (__a, __b); -} - -/* vqrshrn */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqrshrn_n_s16 (int16x8_t __a, const int __b) -{ - return (int8x8_t) __builtin_aarch64_sqrshrn_nv8hi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqrshrn_n_s32 (int32x4_t __a, const int __b) -{ - return (int16x4_t) __builtin_aarch64_sqrshrn_nv4si (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqrshrn_n_s64 (int64x2_t __a, const int __b) -{ - return (int32x2_t) __builtin_aarch64_sqrshrn_nv2di (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqrshrn_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_uqrshrn_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqrshrn_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_uqrshrn_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqrshrn_n_u64 (uint64x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_uqrshrn_nv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqrshrnh_n_s16 (int16x1_t __a, const int __b) -{ - return (int8x1_t) __builtin_aarch64_sqrshrn_nhi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqrshrns_n_s32 (int32x1_t __a, const int __b) -{ - return (int16x1_t) __builtin_aarch64_sqrshrn_nsi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqrshrnd_n_s64 (int64x1_t __a, const int __b) -{ - return (int32x1_t) __builtin_aarch64_sqrshrn_ndi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqrshrnh_n_u16 (uint16x1_t __a, const int __b) -{ - return (uint8x1_t) __builtin_aarch64_uqrshrn_nhi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqrshrns_n_u32 (uint32x1_t __a, const int __b) -{ - return (uint16x1_t) __builtin_aarch64_uqrshrn_nsi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqrshrnd_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint32x1_t) __builtin_aarch64_uqrshrn_ndi (__a, __b); -} - -/* vqrshrun */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqrshrun_n_s16 (int16x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_sqrshrun_nv8hi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqrshrun_n_s32 (int32x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_sqrshrun_nv4si (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqrshrun_n_s64 (int64x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_sqrshrun_nv2di (__a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqrshrunh_n_s16 (int16x1_t __a, const int __b) -{ - return (int8x1_t) __builtin_aarch64_sqrshrun_nhi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqrshruns_n_s32 (int32x1_t __a, const int __b) -{ - return (int16x1_t) __builtin_aarch64_sqrshrun_nsi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqrshrund_n_s64 (int64x1_t __a, const int __b) -{ - return (int32x1_t) __builtin_aarch64_sqrshrun_ndi (__a, __b); -} - -/* vqshl */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqshl_s8 (int8x8_t __a, int8x8_t __b) -{ - return __builtin_aarch64_sqshlv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqshl_s16 (int16x4_t __a, int16x4_t __b) -{ - return __builtin_aarch64_sqshlv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqshl_s32 (int32x2_t __a, int32x2_t __b) -{ - return __builtin_aarch64_sqshlv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqshl_s64 (int64x1_t __a, int64x1_t __b) -{ - return __builtin_aarch64_sqshldi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqshl_u8 (uint8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_uqshlv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqshl_u16 (uint16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_uqshlv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqshl_u32 (uint32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_uqshlv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqshl_u64 (uint64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqshldi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqshlq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_aarch64_sqshlv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqshlq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_aarch64_sqshlv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqshlq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_aarch64_sqshlv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqshlq_s64 (int64x2_t __a, int64x2_t __b) -{ - return __builtin_aarch64_sqshlv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqshlq_u8 (uint8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_uqshlv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqshlq_u16 (uint16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_uqshlv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqshlq_u32 (uint32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_uqshlv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vqshlq_u64 (uint64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_uqshlv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqshlb_s8 (int8x1_t __a, int8x1_t __b) -{ - return __builtin_aarch64_sqshlqi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqshlh_s16 (int16x1_t __a, int16x1_t __b) -{ - return __builtin_aarch64_sqshlhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqshls_s32 (int32x1_t __a, int32x1_t __b) -{ - return __builtin_aarch64_sqshlsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqshld_s64 (int64x1_t __a, int64x1_t __b) -{ - return __builtin_aarch64_sqshldi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqshlb_u8 (uint8x1_t __a, uint8x1_t __b) -{ - return (uint8x1_t) __builtin_aarch64_uqshlqi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqshlh_u16 (uint16x1_t __a, uint16x1_t __b) -{ - return (uint16x1_t) __builtin_aarch64_uqshlhi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqshls_u32 (uint32x1_t __a, uint32x1_t __b) -{ - return (uint32x1_t) __builtin_aarch64_uqshlsi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqshld_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqshldi (__a, __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqshl_n_s8 (int8x8_t __a, const int __b) -{ - return (int8x8_t) __builtin_aarch64_sqshl_nv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqshl_n_s16 (int16x4_t __a, const int __b) -{ - return (int16x4_t) __builtin_aarch64_sqshl_nv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqshl_n_s32 (int32x2_t __a, const int __b) -{ - return (int32x2_t) __builtin_aarch64_sqshl_nv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqshl_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sqshl_ndi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqshl_n_u8 (uint8x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_uqshl_nv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqshl_n_u16 (uint16x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_uqshl_nv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqshl_n_u32 (uint32x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_uqshl_nv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqshl_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_uqshl_ndi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vqshlq_n_s8 (int8x16_t __a, const int __b) -{ - return (int8x16_t) __builtin_aarch64_sqshl_nv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vqshlq_n_s16 (int16x8_t __a, const int __b) -{ - return (int16x8_t) __builtin_aarch64_sqshl_nv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vqshlq_n_s32 (int32x4_t __a, const int __b) -{ - return (int32x4_t) __builtin_aarch64_sqshl_nv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vqshlq_n_s64 (int64x2_t __a, const int __b) -{ - return (int64x2_t) __builtin_aarch64_sqshl_nv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqshlq_n_u8 (uint8x16_t __a, const int __b) -{ - return (uint8x16_t) __builtin_aarch64_uqshl_nv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqshlq_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_uqshl_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqshlq_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_uqshl_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vqshlq_n_u64 (uint64x2_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_uqshl_nv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqshlb_n_s8 (int8x1_t __a, const int __b) -{ - return (int8x1_t) __builtin_aarch64_sqshl_nqi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqshlh_n_s16 (int16x1_t __a, const int __b) -{ - return (int16x1_t) __builtin_aarch64_sqshl_nhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqshls_n_s32 (int32x1_t __a, const int __b) -{ - return (int32x1_t) __builtin_aarch64_sqshl_nsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqshld_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sqshl_ndi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqshlb_n_u8 (uint8x1_t __a, const int __b) -{ - return (uint8x1_t) __builtin_aarch64_uqshl_nqi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqshlh_n_u16 (uint16x1_t __a, const int __b) -{ - return (uint16x1_t) __builtin_aarch64_uqshl_nhi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqshls_n_u32 (uint32x1_t __a, const int __b) -{ - return (uint32x1_t) __builtin_aarch64_uqshl_nsi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqshld_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_uqshl_ndi (__a, __b); -} - -/* vqshlu */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqshlu_n_s8 (int8x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_sqshlu_nv8qi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqshlu_n_s16 (int16x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_sqshlu_nv4hi (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqshlu_n_s32 (int32x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_sqshlu_nv2si (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqshlu_n_s64 (int64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_sqshlu_ndi (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vqshluq_n_s8 (int8x16_t __a, const int __b) -{ - return (uint8x16_t) __builtin_aarch64_sqshlu_nv16qi (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vqshluq_n_s16 (int16x8_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_sqshlu_nv8hi (__a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vqshluq_n_s32 (int32x4_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_sqshlu_nv4si (__a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vqshluq_n_s64 (int64x2_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_sqshlu_nv2di (__a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqshlub_n_s8 (int8x1_t __a, const int __b) -{ - return (int8x1_t) __builtin_aarch64_sqshlu_nqi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqshluh_n_s16 (int16x1_t __a, const int __b) -{ - return (int16x1_t) __builtin_aarch64_sqshlu_nhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqshlus_n_s32 (int32x1_t __a, const int __b) -{ - return (int32x1_t) __builtin_aarch64_sqshlu_nsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqshlud_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sqshlu_ndi (__a, __b); -} - -/* vqshrn */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vqshrn_n_s16 (int16x8_t __a, const int __b) -{ - return (int8x8_t) __builtin_aarch64_sqshrn_nv8hi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vqshrn_n_s32 (int32x4_t __a, const int __b) -{ - return (int16x4_t) __builtin_aarch64_sqshrn_nv4si (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vqshrn_n_s64 (int64x2_t __a, const int __b) -{ - return (int32x2_t) __builtin_aarch64_sqshrn_nv2di (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqshrn_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_uqshrn_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqshrn_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_uqshrn_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqshrn_n_u64 (uint64x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_uqshrn_nv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqshrnh_n_s16 (int16x1_t __a, const int __b) -{ - return (int8x1_t) __builtin_aarch64_sqshrn_nhi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqshrns_n_s32 (int32x1_t __a, const int __b) -{ - return (int16x1_t) __builtin_aarch64_sqshrn_nsi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqshrnd_n_s64 (int64x1_t __a, const int __b) -{ - return (int32x1_t) __builtin_aarch64_sqshrn_ndi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqshrnh_n_u16 (uint16x1_t __a, const int __b) -{ - return (uint8x1_t) __builtin_aarch64_uqshrn_nhi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqshrns_n_u32 (uint32x1_t __a, const int __b) -{ - return (uint16x1_t) __builtin_aarch64_uqshrn_nsi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqshrnd_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint32x1_t) __builtin_aarch64_uqshrn_ndi (__a, __b); -} - -/* vqshrun */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vqshrun_n_s16 (int16x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_sqshrun_nv8hi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vqshrun_n_s32 (int32x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_sqshrun_nv4si (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vqshrun_n_s64 (int64x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_sqshrun_nv2di (__a, __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqshrunh_n_s16 (int16x1_t __a, const int __b) -{ - return (int8x1_t) __builtin_aarch64_sqshrun_nhi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqshruns_n_s32 (int32x1_t __a, const int __b) -{ - return (int16x1_t) __builtin_aarch64_sqshrun_nsi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqshrund_n_s64 (int64x1_t __a, const int __b) -{ - return (int32x1_t) __builtin_aarch64_sqshrun_ndi (__a, __b); -} - -/* vqsub */ - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vqsubb_s8 (int8x1_t __a, int8x1_t __b) -{ - return (int8x1_t) __builtin_aarch64_sqsubqi (__a, __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vqsubh_s16 (int16x1_t __a, int16x1_t __b) -{ - return (int16x1_t) __builtin_aarch64_sqsubhi (__a, __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vqsubs_s32 (int32x1_t __a, int32x1_t __b) -{ - return (int32x1_t) __builtin_aarch64_sqsubsi (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vqsubd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sqsubdi (__a, __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vqsubb_u8 (uint8x1_t __a, uint8x1_t __b) -{ - return (uint8x1_t) __builtin_aarch64_uqsubqi (__a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vqsubh_u16 (uint16x1_t __a, uint16x1_t __b) -{ - return (uint16x1_t) __builtin_aarch64_uqsubhi (__a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vqsubs_u32 (uint32x1_t __a, uint32x1_t __b) -{ - return (uint32x1_t) __builtin_aarch64_uqsubsi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vqsubd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_uqsubdi (__a, __b); -} - -/* vrshl */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrshl_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_srshlv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrshl_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_srshlv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vrshl_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_srshlv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vrshl_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_srshldi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrshl_u8 (uint8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_urshlv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrshl_u16 (uint16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_urshlv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrshl_u32 (uint32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_urshlv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vrshl_u64 (uint64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_urshldi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrshlq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_srshlv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrshlq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_srshlv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vrshlq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_srshlv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vrshlq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_srshlv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrshlq_u8 (uint8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_urshlv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrshlq_u16 (uint16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_urshlv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrshlq_u32 (uint32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_urshlv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vrshlq_u64 (uint64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_urshlv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vrshld_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_srshldi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vrshld_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_urshldi (__a, __b); -} - -/* vrshr */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrshr_n_s8 (int8x8_t __a, const int __b) -{ - return (int8x8_t) __builtin_aarch64_srshr_nv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrshr_n_s16 (int16x4_t __a, const int __b) -{ - return (int16x4_t) __builtin_aarch64_srshr_nv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vrshr_n_s32 (int32x2_t __a, const int __b) -{ - return (int32x2_t) __builtin_aarch64_srshr_nv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vrshr_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_srshr_ndi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrshr_n_u8 (uint8x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_urshr_nv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrshr_n_u16 (uint16x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_urshr_nv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrshr_n_u32 (uint32x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_urshr_nv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vrshr_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_urshr_ndi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrshrq_n_s8 (int8x16_t __a, const int __b) -{ - return (int8x16_t) __builtin_aarch64_srshr_nv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrshrq_n_s16 (int16x8_t __a, const int __b) -{ - return (int16x8_t) __builtin_aarch64_srshr_nv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vrshrq_n_s32 (int32x4_t __a, const int __b) -{ - return (int32x4_t) __builtin_aarch64_srshr_nv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vrshrq_n_s64 (int64x2_t __a, const int __b) -{ - return (int64x2_t) __builtin_aarch64_srshr_nv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrshrq_n_u8 (uint8x16_t __a, const int __b) -{ - return (uint8x16_t) __builtin_aarch64_urshr_nv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrshrq_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_urshr_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrshrq_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_urshr_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vrshrq_n_u64 (uint64x2_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_urshr_nv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vrshrd_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_srshr_ndi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vrshrd_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_urshr_ndi (__a, __b); -} - -/* vrsra */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vrsra_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) -{ - return (int8x8_t) __builtin_aarch64_srsra_nv8qi (__a, __b, __c); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vrsra_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) -{ - return (int16x4_t) __builtin_aarch64_srsra_nv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vrsra_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) -{ - return (int32x2_t) __builtin_aarch64_srsra_nv2si (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vrsra_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_srsra_ndi (__a, __b, __c); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vrsra_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) -{ - return (uint8x8_t) __builtin_aarch64_ursra_nv8qi ((int8x8_t) __a, - (int8x8_t) __b, __c); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vrsra_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) -{ - return (uint16x4_t) __builtin_aarch64_ursra_nv4hi ((int16x4_t) __a, - (int16x4_t) __b, __c); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vrsra_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) -{ - return (uint32x2_t) __builtin_aarch64_ursra_nv2si ((int32x2_t) __a, - (int32x2_t) __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vrsra_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_ursra_ndi ((int64x1_t) __a, - (int64x1_t) __b, __c); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vrsraq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) -{ - return (int8x16_t) __builtin_aarch64_srsra_nv16qi (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vrsraq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) -{ - return (int16x8_t) __builtin_aarch64_srsra_nv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vrsraq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) -{ - return (int32x4_t) __builtin_aarch64_srsra_nv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vrsraq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) -{ - return (int64x2_t) __builtin_aarch64_srsra_nv2di (__a, __b, __c); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vrsraq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) -{ - return (uint8x16_t) __builtin_aarch64_ursra_nv16qi ((int8x16_t) __a, - (int8x16_t) __b, __c); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vrsraq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) -{ - return (uint16x8_t) __builtin_aarch64_ursra_nv8hi ((int16x8_t) __a, - (int16x8_t) __b, __c); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vrsraq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) -{ - return (uint32x4_t) __builtin_aarch64_ursra_nv4si ((int32x4_t) __a, - (int32x4_t) __b, __c); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vrsraq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) -{ - return (uint64x2_t) __builtin_aarch64_ursra_nv2di ((int64x2_t) __a, - (int64x2_t) __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vrsrad_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_srsra_ndi (__a, __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vrsrad_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_ursra_ndi (__a, __b, __c); -} - -/* vshl */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vshl_n_s8 (int8x8_t __a, const int __b) -{ - return (int8x8_t) __builtin_aarch64_sshl_nv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vshl_n_s16 (int16x4_t __a, const int __b) -{ - return (int16x4_t) __builtin_aarch64_sshl_nv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vshl_n_s32 (int32x2_t __a, const int __b) -{ - return (int32x2_t) __builtin_aarch64_sshl_nv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vshl_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sshl_ndi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vshl_n_u8 (uint8x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_ushl_nv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vshl_n_u16 (uint16x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_ushl_nv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vshl_n_u32 (uint32x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_ushl_nv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vshl_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_ushl_ndi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vshlq_n_s8 (int8x16_t __a, const int __b) -{ - return (int8x16_t) __builtin_aarch64_sshl_nv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vshlq_n_s16 (int16x8_t __a, const int __b) -{ - return (int16x8_t) __builtin_aarch64_sshl_nv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vshlq_n_s32 (int32x4_t __a, const int __b) -{ - return (int32x4_t) __builtin_aarch64_sshl_nv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vshlq_n_s64 (int64x2_t __a, const int __b) -{ - return (int64x2_t) __builtin_aarch64_sshl_nv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vshlq_n_u8 (uint8x16_t __a, const int __b) -{ - return (uint8x16_t) __builtin_aarch64_ushl_nv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vshlq_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_ushl_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vshlq_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_ushl_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vshlq_n_u64 (uint64x2_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_ushl_nv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vshld_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sshl_ndi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vshld_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_ushl_ndi (__a, __b); -} - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vshl_s8 (int8x8_t __a, int8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_sshlv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vshl_s16 (int16x4_t __a, int16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_sshlv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vshl_s32 (int32x2_t __a, int32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_sshlv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vshl_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sshldi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vshl_u8 (uint8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_ushlv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vshl_u16 (uint16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_ushlv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vshl_u32 (uint32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_ushlv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vshl_u64 (uint64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_ushldi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vshlq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_sshlv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vshlq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_sshlv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vshlq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_sshlv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vshlq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_sshlv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vshlq_u8 (uint8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_ushlv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vshlq_u16 (uint16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_ushlv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vshlq_u32 (uint32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_ushlv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vshlq_u64 (uint64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_ushlv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vshld_s64 (int64x1_t __a, int64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_sshldi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vshld_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_ushldi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vshll_high_n_s8 (int8x16_t __a, const int __b) -{ - return __builtin_aarch64_sshll2_nv16qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vshll_high_n_s16 (int16x8_t __a, const int __b) -{ - return __builtin_aarch64_sshll2_nv8hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vshll_high_n_s32 (int32x4_t __a, const int __b) -{ - return __builtin_aarch64_sshll2_nv4si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vshll_high_n_u8 (uint8x16_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_ushll2_nv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vshll_high_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_ushll2_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vshll_high_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_ushll2_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vshll_n_s8 (int8x8_t __a, const int __b) -{ - return __builtin_aarch64_sshll_nv8qi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vshll_n_s16 (int16x4_t __a, const int __b) -{ - return __builtin_aarch64_sshll_nv4hi (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vshll_n_s32 (int32x2_t __a, const int __b) -{ - return __builtin_aarch64_sshll_nv2si (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vshll_n_u8 (uint8x8_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_ushll_nv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vshll_n_u16 (uint16x4_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_ushll_nv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vshll_n_u32 (uint32x2_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_ushll_nv2si ((int32x2_t) __a, __b); -} - -/* vshr */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vshr_n_s8 (int8x8_t __a, const int __b) -{ - return (int8x8_t) __builtin_aarch64_sshr_nv8qi (__a, __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vshr_n_s16 (int16x4_t __a, const int __b) -{ - return (int16x4_t) __builtin_aarch64_sshr_nv4hi (__a, __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vshr_n_s32 (int32x2_t __a, const int __b) -{ - return (int32x2_t) __builtin_aarch64_sshr_nv2si (__a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vshr_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sshr_ndi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vshr_n_u8 (uint8x8_t __a, const int __b) -{ - return (uint8x8_t) __builtin_aarch64_ushr_nv8qi ((int8x8_t) __a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vshr_n_u16 (uint16x4_t __a, const int __b) -{ - return (uint16x4_t) __builtin_aarch64_ushr_nv4hi ((int16x4_t) __a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vshr_n_u32 (uint32x2_t __a, const int __b) -{ - return (uint32x2_t) __builtin_aarch64_ushr_nv2si ((int32x2_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vshr_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_ushr_ndi ((int64x1_t) __a, __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vshrq_n_s8 (int8x16_t __a, const int __b) -{ - return (int8x16_t) __builtin_aarch64_sshr_nv16qi (__a, __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vshrq_n_s16 (int16x8_t __a, const int __b) -{ - return (int16x8_t) __builtin_aarch64_sshr_nv8hi (__a, __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vshrq_n_s32 (int32x4_t __a, const int __b) -{ - return (int32x4_t) __builtin_aarch64_sshr_nv4si (__a, __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vshrq_n_s64 (int64x2_t __a, const int __b) -{ - return (int64x2_t) __builtin_aarch64_sshr_nv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vshrq_n_u8 (uint8x16_t __a, const int __b) -{ - return (uint8x16_t) __builtin_aarch64_ushr_nv16qi ((int8x16_t) __a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vshrq_n_u16 (uint16x8_t __a, const int __b) -{ - return (uint16x8_t) __builtin_aarch64_ushr_nv8hi ((int16x8_t) __a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vshrq_n_u32 (uint32x4_t __a, const int __b) -{ - return (uint32x4_t) __builtin_aarch64_ushr_nv4si ((int32x4_t) __a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vshrq_n_u64 (uint64x2_t __a, const int __b) -{ - return (uint64x2_t) __builtin_aarch64_ushr_nv2di ((int64x2_t) __a, __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vshrd_n_s64 (int64x1_t __a, const int __b) -{ - return (int64x1_t) __builtin_aarch64_sshr_ndi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vshrd_n_u64 (uint64x1_t __a, const int __b) -{ - return (uint64x1_t) __builtin_aarch64_ushr_ndi (__a, __b); -} - -/* vsli */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vsli_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) -{ - return (int8x8_t) __builtin_aarch64_ssli_nv8qi (__a, __b, __c); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vsli_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) -{ - return (int16x4_t) __builtin_aarch64_ssli_nv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vsli_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) -{ - return (int32x2_t) __builtin_aarch64_ssli_nv2si (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsli_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_ssli_ndi (__a, __b, __c); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vsli_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) -{ - return (uint8x8_t) __builtin_aarch64_usli_nv8qi ((int8x8_t) __a, - (int8x8_t) __b, __c); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vsli_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) -{ - return (uint16x4_t) __builtin_aarch64_usli_nv4hi ((int16x4_t) __a, - (int16x4_t) __b, __c); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vsli_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) -{ - return (uint32x2_t) __builtin_aarch64_usli_nv2si ((int32x2_t) __a, - (int32x2_t) __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsli_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_usli_ndi ((int64x1_t) __a, - (int64x1_t) __b, __c); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vsliq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) -{ - return (int8x16_t) __builtin_aarch64_ssli_nv16qi (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsliq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) -{ - return (int16x8_t) __builtin_aarch64_ssli_nv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsliq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) -{ - return (int32x4_t) __builtin_aarch64_ssli_nv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsliq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) -{ - return (int64x2_t) __builtin_aarch64_ssli_nv2di (__a, __b, __c); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vsliq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) -{ - return (uint8x16_t) __builtin_aarch64_usli_nv16qi ((int8x16_t) __a, - (int8x16_t) __b, __c); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsliq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) -{ - return (uint16x8_t) __builtin_aarch64_usli_nv8hi ((int16x8_t) __a, - (int16x8_t) __b, __c); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsliq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) -{ - return (uint32x4_t) __builtin_aarch64_usli_nv4si ((int32x4_t) __a, - (int32x4_t) __b, __c); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsliq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) -{ - return (uint64x2_t) __builtin_aarch64_usli_nv2di ((int64x2_t) __a, - (int64x2_t) __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vslid_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_ssli_ndi (__a, __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vslid_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_usli_ndi (__a, __b, __c); -} - -/* vsqadd */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vsqadd_u8 (uint8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_usqaddv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vsqadd_u16 (uint16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_usqaddv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vsqadd_u32 (uint32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_usqaddv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsqadd_u64 (uint64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_usqadddi ((int64x1_t) __a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vsqaddq_u8 (uint8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_usqaddv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsqaddq_u16 (uint16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_usqaddv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsqaddq_u32 (uint32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_usqaddv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsqaddq_u64 (uint64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_usqaddv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline uint8x1_t __attribute__ ((__always_inline__)) -vsqaddb_u8 (uint8x1_t __a, int8x1_t __b) -{ - return (uint8x1_t) __builtin_aarch64_usqaddqi ((int8x1_t) __a, __b); -} - -__extension__ static __inline uint16x1_t __attribute__ ((__always_inline__)) -vsqaddh_u16 (uint16x1_t __a, int16x1_t __b) -{ - return (uint16x1_t) __builtin_aarch64_usqaddhi ((int16x1_t) __a, __b); -} - -__extension__ static __inline uint32x1_t __attribute__ ((__always_inline__)) -vsqadds_u32 (uint32x1_t __a, int32x1_t __b) -{ - return (uint32x1_t) __builtin_aarch64_usqaddsi ((int32x1_t) __a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsqaddd_u64 (uint64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_usqadddi ((int64x1_t) __a, __b); -} - -/* vsqrt */ -__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) -vsqrt_f32 (float32x2_t a) -{ - return __builtin_aarch64_sqrtv2sf (a); -} - -__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) -vsqrtq_f32 (float32x4_t a) -{ - return __builtin_aarch64_sqrtv4sf (a); -} - -__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) -vsqrtq_f64 (float64x2_t a) -{ - return __builtin_aarch64_sqrtv2df (a); -} - -/* vsra */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vsra_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) -{ - return (int8x8_t) __builtin_aarch64_ssra_nv8qi (__a, __b, __c); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vsra_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) -{ - return (int16x4_t) __builtin_aarch64_ssra_nv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vsra_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) -{ - return (int32x2_t) __builtin_aarch64_ssra_nv2si (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsra_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_ssra_ndi (__a, __b, __c); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vsra_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) -{ - return (uint8x8_t) __builtin_aarch64_usra_nv8qi ((int8x8_t) __a, - (int8x8_t) __b, __c); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vsra_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) -{ - return (uint16x4_t) __builtin_aarch64_usra_nv4hi ((int16x4_t) __a, - (int16x4_t) __b, __c); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vsra_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) -{ - return (uint32x2_t) __builtin_aarch64_usra_nv2si ((int32x2_t) __a, - (int32x2_t) __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsra_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_usra_ndi ((int64x1_t) __a, - (int64x1_t) __b, __c); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vsraq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) -{ - return (int8x16_t) __builtin_aarch64_ssra_nv16qi (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsraq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) -{ - return (int16x8_t) __builtin_aarch64_ssra_nv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsraq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) -{ - return (int32x4_t) __builtin_aarch64_ssra_nv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsraq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) -{ - return (int64x2_t) __builtin_aarch64_ssra_nv2di (__a, __b, __c); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vsraq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) -{ - return (uint8x16_t) __builtin_aarch64_usra_nv16qi ((int8x16_t) __a, - (int8x16_t) __b, __c); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsraq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) -{ - return (uint16x8_t) __builtin_aarch64_usra_nv8hi ((int16x8_t) __a, - (int16x8_t) __b, __c); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsraq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) -{ - return (uint32x4_t) __builtin_aarch64_usra_nv4si ((int32x4_t) __a, - (int32x4_t) __b, __c); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsraq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) -{ - return (uint64x2_t) __builtin_aarch64_usra_nv2di ((int64x2_t) __a, - (int64x2_t) __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsrad_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_ssra_ndi (__a, __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsrad_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_usra_ndi (__a, __b, __c); -} - -/* vsri */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vsri_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) -{ - return (int8x8_t) __builtin_aarch64_ssri_nv8qi (__a, __b, __c); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vsri_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) -{ - return (int16x4_t) __builtin_aarch64_ssri_nv4hi (__a, __b, __c); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vsri_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) -{ - return (int32x2_t) __builtin_aarch64_ssri_nv2si (__a, __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsri_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_ssri_ndi (__a, __b, __c); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vsri_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) -{ - return (uint8x8_t) __builtin_aarch64_usri_nv8qi ((int8x8_t) __a, - (int8x8_t) __b, __c); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vsri_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) -{ - return (uint16x4_t) __builtin_aarch64_usri_nv4hi ((int16x4_t) __a, - (int16x4_t) __b, __c); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vsri_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) -{ - return (uint32x2_t) __builtin_aarch64_usri_nv2si ((int32x2_t) __a, - (int32x2_t) __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsri_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_usri_ndi ((int64x1_t) __a, - (int64x1_t) __b, __c); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vsriq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) -{ - return (int8x16_t) __builtin_aarch64_ssri_nv16qi (__a, __b, __c); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vsriq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) -{ - return (int16x8_t) __builtin_aarch64_ssri_nv8hi (__a, __b, __c); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vsriq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) -{ - return (int32x4_t) __builtin_aarch64_ssri_nv4si (__a, __b, __c); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vsriq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) -{ - return (int64x2_t) __builtin_aarch64_ssri_nv2di (__a, __b, __c); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vsriq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) -{ - return (uint8x16_t) __builtin_aarch64_usri_nv16qi ((int8x16_t) __a, - (int8x16_t) __b, __c); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vsriq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) -{ - return (uint16x8_t) __builtin_aarch64_usri_nv8hi ((int16x8_t) __a, - (int16x8_t) __b, __c); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vsriq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) -{ - return (uint32x4_t) __builtin_aarch64_usri_nv4si ((int32x4_t) __a, - (int32x4_t) __b, __c); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vsriq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) -{ - return (uint64x2_t) __builtin_aarch64_usri_nv2di ((int64x2_t) __a, - (int64x2_t) __b, __c); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsrid_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) -{ - return (int64x1_t) __builtin_aarch64_ssri_ndi (__a, __b, __c); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsrid_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) -{ - return (uint64x1_t) __builtin_aarch64_usri_ndi (__a, __b, __c); -} - -/* vst1 */ - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_f32 (float32_t *a, float32x2_t b) -{ - __builtin_aarch64_st1v2sf ((__builtin_aarch64_simd_sf *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_f64 (float64_t *a, float64x1_t b) -{ - *a = b; -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_p8 (poly8_t *a, poly8x8_t b) -{ - __builtin_aarch64_st1v8qi ((__builtin_aarch64_simd_qi *) a, - (int8x8_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_p16 (poly16_t *a, poly16x4_t b) -{ - __builtin_aarch64_st1v4hi ((__builtin_aarch64_simd_hi *) a, - (int16x4_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_s8 (int8_t *a, int8x8_t b) -{ - __builtin_aarch64_st1v8qi ((__builtin_aarch64_simd_qi *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_s16 (int16_t *a, int16x4_t b) -{ - __builtin_aarch64_st1v4hi ((__builtin_aarch64_simd_hi *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_s32 (int32_t *a, int32x2_t b) -{ - __builtin_aarch64_st1v2si ((__builtin_aarch64_simd_si *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_s64 (int64_t *a, int64x1_t b) -{ - *a = b; -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_u8 (uint8_t *a, uint8x8_t b) -{ - __builtin_aarch64_st1v8qi ((__builtin_aarch64_simd_qi *) a, - (int8x8_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_u16 (uint16_t *a, uint16x4_t b) -{ - __builtin_aarch64_st1v4hi ((__builtin_aarch64_simd_hi *) a, - (int16x4_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_u32 (uint32_t *a, uint32x2_t b) -{ - __builtin_aarch64_st1v2si ((__builtin_aarch64_simd_si *) a, - (int32x2_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1_u64 (uint64_t *a, uint64x1_t b) -{ - *a = b; -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_f32 (float32_t *a, float32x4_t b) -{ - __builtin_aarch64_st1v4sf ((__builtin_aarch64_simd_sf *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_f64 (float64_t *a, float64x2_t b) -{ - __builtin_aarch64_st1v2df ((__builtin_aarch64_simd_df *) a, b); -} - -/* vst1q */ - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_p8 (poly8_t *a, poly8x16_t b) -{ - __builtin_aarch64_st1v16qi ((__builtin_aarch64_simd_qi *) a, - (int8x16_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_p16 (poly16_t *a, poly16x8_t b) -{ - __builtin_aarch64_st1v8hi ((__builtin_aarch64_simd_hi *) a, - (int16x8_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_s8 (int8_t *a, int8x16_t b) -{ - __builtin_aarch64_st1v16qi ((__builtin_aarch64_simd_qi *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_s16 (int16_t *a, int16x8_t b) -{ - __builtin_aarch64_st1v8hi ((__builtin_aarch64_simd_hi *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_s32 (int32_t *a, int32x4_t b) -{ - __builtin_aarch64_st1v4si ((__builtin_aarch64_simd_si *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_s64 (int64_t *a, int64x2_t b) -{ - __builtin_aarch64_st1v2di ((__builtin_aarch64_simd_di *) a, b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_u8 (uint8_t *a, uint8x16_t b) -{ - __builtin_aarch64_st1v16qi ((__builtin_aarch64_simd_qi *) a, - (int8x16_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_u16 (uint16_t *a, uint16x8_t b) -{ - __builtin_aarch64_st1v8hi ((__builtin_aarch64_simd_hi *) a, - (int16x8_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_u32 (uint32_t *a, uint32x4_t b) -{ - __builtin_aarch64_st1v4si ((__builtin_aarch64_simd_si *) a, - (int32x4_t) b); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst1q_u64 (uint64_t *a, uint64x2_t b) -{ - __builtin_aarch64_st1v2di ((__builtin_aarch64_simd_di *) a, - (int64x2_t) b); -} - -/* vstn */ - -__extension__ static __inline void -vst2_s64 (int64_t * __a, int64x1x2_t val) -{ - __builtin_aarch64_simd_oi __o; - int64x2x2_t temp; - temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (INT64_C (0))); - temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (INT64_C (0))); - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[1], 1); - __builtin_aarch64_st2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void -vst2_u64 (uint64_t * __a, uint64x1x2_t val) -{ - __builtin_aarch64_simd_oi __o; - uint64x2x2_t temp; - temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (UINT64_C (0))); - temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[1], 1); - __builtin_aarch64_st2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void -vst2_f64 (float64_t * __a, float64x1x2_t val) -{ - __builtin_aarch64_simd_oi __o; - float64x2x2_t temp; - temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (UINT64_C (0))); - temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) temp.val[1], 1); - __builtin_aarch64_st2df ((__builtin_aarch64_simd_df *) __a, __o); -} - -__extension__ static __inline void -vst2_s8 (int8_t * __a, int8x8x2_t val) -{ - __builtin_aarch64_simd_oi __o; - int8x16x2_t temp; - temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (INT64_C (0))); - temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (INT64_C (0))); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1); - __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_p8 (poly8_t * __a, poly8x8x2_t val) -{ - __builtin_aarch64_simd_oi __o; - poly8x16x2_t temp; - temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (UINT64_C (0))); - temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1); - __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_s16 (int16_t * __a, int16x4x2_t val) -{ - __builtin_aarch64_simd_oi __o; - int16x8x2_t temp; - temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (INT64_C (0))); - temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (INT64_C (0))); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1); - __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_p16 (poly16_t * __a, poly16x4x2_t val) -{ - __builtin_aarch64_simd_oi __o; - poly16x8x2_t temp; - temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (UINT64_C (0))); - temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1); - __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_s32 (int32_t * __a, int32x2x2_t val) -{ - __builtin_aarch64_simd_oi __o; - int32x4x2_t temp; - temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (INT64_C (0))); - temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (INT64_C (0))); - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[1], 1); - __builtin_aarch64_st2v2si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_u8 (uint8_t * __a, uint8x8x2_t val) -{ - __builtin_aarch64_simd_oi __o; - uint8x16x2_t temp; - temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (UINT64_C (0))); - temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1); - __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_u16 (uint16_t * __a, uint16x4x2_t val) -{ - __builtin_aarch64_simd_oi __o; - uint16x8x2_t temp; - temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (UINT64_C (0))); - temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1); - __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_u32 (uint32_t * __a, uint32x2x2_t val) -{ - __builtin_aarch64_simd_oi __o; - uint32x4x2_t temp; - temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (UINT64_C (0))); - temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[1], 1); - __builtin_aarch64_st2v2si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2_f32 (float32_t * __a, float32x2x2_t val) -{ - __builtin_aarch64_simd_oi __o; - float32x4x2_t temp; - temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (UINT64_C (0))); - temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) temp.val[1], 1); - __builtin_aarch64_st2v2sf ((__builtin_aarch64_simd_sf *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_s8 (int8_t * __a, int8x16x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[1], 1); - __builtin_aarch64_st2v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_p8 (poly8_t * __a, poly8x16x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[1], 1); - __builtin_aarch64_st2v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_s16 (int16_t * __a, int16x8x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[1], 1); - __builtin_aarch64_st2v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_p16 (poly16_t * __a, poly16x8x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[1], 1); - __builtin_aarch64_st2v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_s32 (int32_t * __a, int32x4x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[1], 1); - __builtin_aarch64_st2v4si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_s64 (int64_t * __a, int64x2x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[1], 1); - __builtin_aarch64_st2v2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_u8 (uint8_t * __a, uint8x16x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) val.val[1], 1); - __builtin_aarch64_st2v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_u16 (uint16_t * __a, uint16x8x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) val.val[1], 1); - __builtin_aarch64_st2v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_u32 (uint32_t * __a, uint32x4x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) val.val[1], 1); - __builtin_aarch64_st2v4si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_u64 (uint64_t * __a, uint64x2x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) val.val[1], 1); - __builtin_aarch64_st2v2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_f32 (float32_t * __a, float32x4x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) val.val[1], 1); - __builtin_aarch64_st2v4sf ((__builtin_aarch64_simd_sf *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst2q_f64 (float64_t * __a, float64x2x2_t val) -{ - __builtin_aarch64_simd_oi __o; - __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) val.val[1], 1); - __builtin_aarch64_st2v2df ((__builtin_aarch64_simd_df *) __a, __o); -} - -__extension__ static __inline void -vst3_s64 (int64_t * __a, int64x1x3_t val) -{ - __builtin_aarch64_simd_ci __o; - int64x2x3_t temp; - temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (INT64_C (0))); - temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (INT64_C (0))); - temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (INT64_C (0))); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[2], 2); - __builtin_aarch64_st3di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void -vst3_u64 (uint64_t * __a, uint64x1x3_t val) -{ - __builtin_aarch64_simd_ci __o; - uint64x2x3_t temp; - temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (UINT64_C (0))); - temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (UINT64_C (0))); - temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[2], 2); - __builtin_aarch64_st3di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void -vst3_f64 (float64_t * __a, float64x1x3_t val) -{ - __builtin_aarch64_simd_ci __o; - float64x2x3_t temp; - temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (UINT64_C (0))); - temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (UINT64_C (0))); - temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[2], 2); - __builtin_aarch64_st3df ((__builtin_aarch64_simd_df *) __a, __o); -} - -__extension__ static __inline void -vst3_s8 (int8_t * __a, int8x8x3_t val) -{ - __builtin_aarch64_simd_ci __o; - int8x16x3_t temp; - temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (INT64_C (0))); - temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (INT64_C (0))); - temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (INT64_C (0))); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2); - __builtin_aarch64_st3v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_p8 (poly8_t * __a, poly8x8x3_t val) -{ - __builtin_aarch64_simd_ci __o; - poly8x16x3_t temp; - temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (UINT64_C (0))); - temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (UINT64_C (0))); - temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2); - __builtin_aarch64_st3v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_s16 (int16_t * __a, int16x4x3_t val) -{ - __builtin_aarch64_simd_ci __o; - int16x8x3_t temp; - temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (INT64_C (0))); - temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (INT64_C (0))); - temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (INT64_C (0))); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2); - __builtin_aarch64_st3v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_p16 (poly16_t * __a, poly16x4x3_t val) -{ - __builtin_aarch64_simd_ci __o; - poly16x8x3_t temp; - temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (UINT64_C (0))); - temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (UINT64_C (0))); - temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2); - __builtin_aarch64_st3v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_s32 (int32_t * __a, int32x2x3_t val) -{ - __builtin_aarch64_simd_ci __o; - int32x4x3_t temp; - temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (INT64_C (0))); - temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (INT64_C (0))); - temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (INT64_C (0))); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[2], 2); - __builtin_aarch64_st3v2si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_u8 (uint8_t * __a, uint8x8x3_t val) -{ - __builtin_aarch64_simd_ci __o; - uint8x16x3_t temp; - temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (UINT64_C (0))); - temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (UINT64_C (0))); - temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2); - __builtin_aarch64_st3v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_u16 (uint16_t * __a, uint16x4x3_t val) -{ - __builtin_aarch64_simd_ci __o; - uint16x8x3_t temp; - temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (UINT64_C (0))); - temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (UINT64_C (0))); - temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2); - __builtin_aarch64_st3v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_u32 (uint32_t * __a, uint32x2x3_t val) -{ - __builtin_aarch64_simd_ci __o; - uint32x4x3_t temp; - temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (UINT64_C (0))); - temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (UINT64_C (0))); - temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[2], 2); - __builtin_aarch64_st3v2si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3_f32 (float32_t * __a, float32x2x3_t val) -{ - __builtin_aarch64_simd_ci __o; - float32x4x3_t temp; - temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (UINT64_C (0))); - temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (UINT64_C (0))); - temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[2], 2); - __builtin_aarch64_st3v2sf ((__builtin_aarch64_simd_sf *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_s8 (int8_t * __a, int8x16x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[2], 2); - __builtin_aarch64_st3v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_p8 (poly8_t * __a, poly8x16x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[2], 2); - __builtin_aarch64_st3v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_s16 (int16_t * __a, int16x8x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[2], 2); - __builtin_aarch64_st3v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_p16 (poly16_t * __a, poly16x8x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[2], 2); - __builtin_aarch64_st3v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_s32 (int32_t * __a, int32x4x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[2], 2); - __builtin_aarch64_st3v4si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_s64 (int64_t * __a, int64x2x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[2], 2); - __builtin_aarch64_st3v2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_u8 (uint8_t * __a, uint8x16x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) val.val[2], 2); - __builtin_aarch64_st3v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_u16 (uint16_t * __a, uint16x8x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) val.val[2], 2); - __builtin_aarch64_st3v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_u32 (uint32_t * __a, uint32x4x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) val.val[2], 2); - __builtin_aarch64_st3v4si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_u64 (uint64_t * __a, uint64x2x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) val.val[2], 2); - __builtin_aarch64_st3v2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_f32 (float32_t * __a, float32x4x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) val.val[2], 2); - __builtin_aarch64_st3v4sf ((__builtin_aarch64_simd_sf *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst3q_f64 (float64_t * __a, float64x2x3_t val) -{ - __builtin_aarch64_simd_ci __o; - __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) val.val[2], 2); - __builtin_aarch64_st3v2df ((__builtin_aarch64_simd_df *) __a, __o); -} - -__extension__ static __inline void -vst4_s64 (int64_t * __a, int64x1x4_t val) -{ - __builtin_aarch64_simd_xi __o; - int64x2x4_t temp; - temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (INT64_C (0))); - temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (INT64_C (0))); - temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (INT64_C (0))); - temp.val[3] = vcombine_s64 (val.val[3], vcreate_s64 (INT64_C (0))); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[3], 3); - __builtin_aarch64_st4di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void -vst4_u64 (uint64_t * __a, uint64x1x4_t val) -{ - __builtin_aarch64_simd_xi __o; - uint64x2x4_t temp; - temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (UINT64_C (0))); - temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (UINT64_C (0))); - temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (UINT64_C (0))); - temp.val[3] = vcombine_u64 (val.val[3], vcreate_u64 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[3], 3); - __builtin_aarch64_st4di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void -vst4_f64 (float64_t * __a, float64x1x4_t val) -{ - __builtin_aarch64_simd_xi __o; - float64x2x4_t temp; - temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (UINT64_C (0))); - temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (UINT64_C (0))); - temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (UINT64_C (0))); - temp.val[3] = vcombine_f64 (val.val[3], vcreate_f64 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[3], 3); - __builtin_aarch64_st4df ((__builtin_aarch64_simd_df *) __a, __o); -} - -__extension__ static __inline void -vst4_s8 (int8_t * __a, int8x8x4_t val) -{ - __builtin_aarch64_simd_xi __o; - int8x16x4_t temp; - temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (INT64_C (0))); - temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (INT64_C (0))); - temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (INT64_C (0))); - temp.val[3] = vcombine_s8 (val.val[3], vcreate_s8 (INT64_C (0))); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[3], 3); - __builtin_aarch64_st4v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_p8 (poly8_t * __a, poly8x8x4_t val) -{ - __builtin_aarch64_simd_xi __o; - poly8x16x4_t temp; - temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (UINT64_C (0))); - temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (UINT64_C (0))); - temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (UINT64_C (0))); - temp.val[3] = vcombine_p8 (val.val[3], vcreate_p8 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[3], 3); - __builtin_aarch64_st4v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_s16 (int16_t * __a, int16x4x4_t val) -{ - __builtin_aarch64_simd_xi __o; - int16x8x4_t temp; - temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (INT64_C (0))); - temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (INT64_C (0))); - temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (INT64_C (0))); - temp.val[3] = vcombine_s16 (val.val[3], vcreate_s16 (INT64_C (0))); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[3], 3); - __builtin_aarch64_st4v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_p16 (poly16_t * __a, poly16x4x4_t val) -{ - __builtin_aarch64_simd_xi __o; - poly16x8x4_t temp; - temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (UINT64_C (0))); - temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (UINT64_C (0))); - temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (UINT64_C (0))); - temp.val[3] = vcombine_p16 (val.val[3], vcreate_p16 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[3], 3); - __builtin_aarch64_st4v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_s32 (int32_t * __a, int32x2x4_t val) -{ - __builtin_aarch64_simd_xi __o; - int32x4x4_t temp; - temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (INT64_C (0))); - temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (INT64_C (0))); - temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (INT64_C (0))); - temp.val[3] = vcombine_s32 (val.val[3], vcreate_s32 (INT64_C (0))); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[3], 3); - __builtin_aarch64_st4v2si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_u8 (uint8_t * __a, uint8x8x4_t val) -{ - __builtin_aarch64_simd_xi __o; - uint8x16x4_t temp; - temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (UINT64_C (0))); - temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (UINT64_C (0))); - temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (UINT64_C (0))); - temp.val[3] = vcombine_u8 (val.val[3], vcreate_u8 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[3], 3); - __builtin_aarch64_st4v8qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_u16 (uint16_t * __a, uint16x4x4_t val) -{ - __builtin_aarch64_simd_xi __o; - uint16x8x4_t temp; - temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (UINT64_C (0))); - temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (UINT64_C (0))); - temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (UINT64_C (0))); - temp.val[3] = vcombine_u16 (val.val[3], vcreate_u16 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[3], 3); - __builtin_aarch64_st4v4hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_u32 (uint32_t * __a, uint32x2x4_t val) -{ - __builtin_aarch64_simd_xi __o; - uint32x4x4_t temp; - temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (UINT64_C (0))); - temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (UINT64_C (0))); - temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (UINT64_C (0))); - temp.val[3] = vcombine_u32 (val.val[3], vcreate_u32 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[3], 3); - __builtin_aarch64_st4v2si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4_f32 (float32_t * __a, float32x2x4_t val) -{ - __builtin_aarch64_simd_xi __o; - float32x4x4_t temp; - temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (UINT64_C (0))); - temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (UINT64_C (0))); - temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (UINT64_C (0))); - temp.val[3] = vcombine_f32 (val.val[3], vcreate_f32 (UINT64_C (0))); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[0], 0); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[1], 1); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[2], 2); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[3], 3); - __builtin_aarch64_st4v2sf ((__builtin_aarch64_simd_sf *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_s8 (int8_t * __a, int8x16x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[3], 3); - __builtin_aarch64_st4v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_p8 (poly8_t * __a, poly8x16x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[3], 3); - __builtin_aarch64_st4v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_s16 (int16_t * __a, int16x8x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[3], 3); - __builtin_aarch64_st4v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_p16 (poly16_t * __a, poly16x8x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[3], 3); - __builtin_aarch64_st4v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_s32 (int32_t * __a, int32x4x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[3], 3); - __builtin_aarch64_st4v4si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_s64 (int64_t * __a, int64x2x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[3], 3); - __builtin_aarch64_st4v2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_u8 (uint8_t * __a, uint8x16x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) val.val[3], 3); - __builtin_aarch64_st4v16qi ((__builtin_aarch64_simd_qi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_u16 (uint16_t * __a, uint16x8x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) val.val[3], 3); - __builtin_aarch64_st4v8hi ((__builtin_aarch64_simd_hi *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_u32 (uint32_t * __a, uint32x4x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) val.val[3], 3); - __builtin_aarch64_st4v4si ((__builtin_aarch64_simd_si *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_u64 (uint64_t * __a, uint64x2x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) val.val[3], 3); - __builtin_aarch64_st4v2di ((__builtin_aarch64_simd_di *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_f32 (float32_t * __a, float32x4x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) val.val[3], 3); - __builtin_aarch64_st4v4sf ((__builtin_aarch64_simd_sf *) __a, __o); -} - -__extension__ static __inline void __attribute__ ((__always_inline__)) -vst4q_f64 (float64_t * __a, float64x2x4_t val) -{ - __builtin_aarch64_simd_xi __o; - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[0], 0); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[1], 1); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[2], 2); - __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) val.val[3], 3); - __builtin_aarch64_st4v2df ((__builtin_aarch64_simd_df *) __a, __o); -} - -/* vsub */ - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vsubd_s64 (int64x1_t __a, int64x1_t __b) -{ - return __a - __b; -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vsubd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return __a - __b; -} - -/* vtrn */ - -__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) -vtrn_f32 (float32x2_t a, float32x2_t b) -{ - return (float32x2x2_t) {vtrn1_f32 (a, b), vtrn2_f32 (a, b)}; -} - -__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) -vtrn_p8 (poly8x8_t a, poly8x8_t b) -{ - return (poly8x8x2_t) {vtrn1_p8 (a, b), vtrn2_p8 (a, b)}; -} - -__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) -vtrn_p16 (poly16x4_t a, poly16x4_t b) -{ - return (poly16x4x2_t) {vtrn1_p16 (a, b), vtrn2_p16 (a, b)}; -} - -__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) -vtrn_s8 (int8x8_t a, int8x8_t b) -{ - return (int8x8x2_t) {vtrn1_s8 (a, b), vtrn2_s8 (a, b)}; -} - -__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) -vtrn_s16 (int16x4_t a, int16x4_t b) -{ - return (int16x4x2_t) {vtrn1_s16 (a, b), vtrn2_s16 (a, b)}; -} - -__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) -vtrn_s32 (int32x2_t a, int32x2_t b) -{ - return (int32x2x2_t) {vtrn1_s32 (a, b), vtrn2_s32 (a, b)}; -} - -__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) -vtrn_u8 (uint8x8_t a, uint8x8_t b) -{ - return (uint8x8x2_t) {vtrn1_u8 (a, b), vtrn2_u8 (a, b)}; -} - -__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) -vtrn_u16 (uint16x4_t a, uint16x4_t b) -{ - return (uint16x4x2_t) {vtrn1_u16 (a, b), vtrn2_u16 (a, b)}; -} - -__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) -vtrn_u32 (uint32x2_t a, uint32x2_t b) -{ - return (uint32x2x2_t) {vtrn1_u32 (a, b), vtrn2_u32 (a, b)}; -} - -__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) -vtrnq_f32 (float32x4_t a, float32x4_t b) -{ - return (float32x4x2_t) {vtrn1q_f32 (a, b), vtrn2q_f32 (a, b)}; -} - -__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) -vtrnq_p8 (poly8x16_t a, poly8x16_t b) -{ - return (poly8x16x2_t) {vtrn1q_p8 (a, b), vtrn2q_p8 (a, b)}; -} - -__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) -vtrnq_p16 (poly16x8_t a, poly16x8_t b) -{ - return (poly16x8x2_t) {vtrn1q_p16 (a, b), vtrn2q_p16 (a, b)}; -} - -__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) -vtrnq_s8 (int8x16_t a, int8x16_t b) -{ - return (int8x16x2_t) {vtrn1q_s8 (a, b), vtrn2q_s8 (a, b)}; -} - -__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) -vtrnq_s16 (int16x8_t a, int16x8_t b) -{ - return (int16x8x2_t) {vtrn1q_s16 (a, b), vtrn2q_s16 (a, b)}; -} - -__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) -vtrnq_s32 (int32x4_t a, int32x4_t b) -{ - return (int32x4x2_t) {vtrn1q_s32 (a, b), vtrn2q_s32 (a, b)}; -} - -__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) -vtrnq_u8 (uint8x16_t a, uint8x16_t b) -{ - return (uint8x16x2_t) {vtrn1q_u8 (a, b), vtrn2q_u8 (a, b)}; -} - -__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) -vtrnq_u16 (uint16x8_t a, uint16x8_t b) -{ - return (uint16x8x2_t) {vtrn1q_u16 (a, b), vtrn2q_u16 (a, b)}; -} - -__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) -vtrnq_u32 (uint32x4_t a, uint32x4_t b) -{ - return (uint32x4x2_t) {vtrn1q_u32 (a, b), vtrn2q_u32 (a, b)}; -} - -/* vtst */ - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtst_s8 (int8x8_t __a, int8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmtstv8qi (__a, __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vtst_s16 (int16x4_t __a, int16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmtstv4hi (__a, __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vtst_s32 (int32x2_t __a, int32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmtstv2si (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vtst_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmtstdi (__a, __b); -} - -__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) -vtst_u8 (uint8x8_t __a, uint8x8_t __b) -{ - return (uint8x8_t) __builtin_aarch64_cmtstv8qi ((int8x8_t) __a, - (int8x8_t) __b); -} - -__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) -vtst_u16 (uint16x4_t __a, uint16x4_t __b) -{ - return (uint16x4_t) __builtin_aarch64_cmtstv4hi ((int16x4_t) __a, - (int16x4_t) __b); -} - -__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) -vtst_u32 (uint32x2_t __a, uint32x2_t __b) -{ - return (uint32x2_t) __builtin_aarch64_cmtstv2si ((int32x2_t) __a, - (int32x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vtst_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmtstdi ((int64x1_t) __a, - (int64x1_t) __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vtstq_s8 (int8x16_t __a, int8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmtstv16qi (__a, __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vtstq_s16 (int16x8_t __a, int16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmtstv8hi (__a, __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vtstq_s32 (int32x4_t __a, int32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmtstv4si (__a, __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vtstq_s64 (int64x2_t __a, int64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmtstv2di (__a, __b); -} - -__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) -vtstq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return (uint8x16_t) __builtin_aarch64_cmtstv16qi ((int8x16_t) __a, - (int8x16_t) __b); -} - -__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) -vtstq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return (uint16x8_t) __builtin_aarch64_cmtstv8hi ((int16x8_t) __a, - (int16x8_t) __b); -} - -__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) -vtstq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return (uint32x4_t) __builtin_aarch64_cmtstv4si ((int32x4_t) __a, - (int32x4_t) __b); -} - -__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) -vtstq_u64 (uint64x2_t __a, uint64x2_t __b) -{ - return (uint64x2_t) __builtin_aarch64_cmtstv2di ((int64x2_t) __a, - (int64x2_t) __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vtstd_s64 (int64x1_t __a, int64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmtstdi (__a, __b); -} - -__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) -vtstd_u64 (uint64x1_t __a, uint64x1_t __b) -{ - return (uint64x1_t) __builtin_aarch64_cmtstdi ((int64x1_t) __a, - (int64x1_t) __b); -} - -/* vuqadd */ - -__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) -vuqadd_s8 (int8x8_t __a, uint8x8_t __b) -{ - return (int8x8_t) __builtin_aarch64_suqaddv8qi (__a, (int8x8_t) __b); -} - -__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) -vuqadd_s16 (int16x4_t __a, uint16x4_t __b) -{ - return (int16x4_t) __builtin_aarch64_suqaddv4hi (__a, (int16x4_t) __b); -} - -__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) -vuqadd_s32 (int32x2_t __a, uint32x2_t __b) -{ - return (int32x2_t) __builtin_aarch64_suqaddv2si (__a, (int32x2_t) __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vuqadd_s64 (int64x1_t __a, uint64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_suqadddi (__a, (int64x1_t) __b); -} - -__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) -vuqaddq_s8 (int8x16_t __a, uint8x16_t __b) -{ - return (int8x16_t) __builtin_aarch64_suqaddv16qi (__a, (int8x16_t) __b); -} - -__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) -vuqaddq_s16 (int16x8_t __a, uint16x8_t __b) -{ - return (int16x8_t) __builtin_aarch64_suqaddv8hi (__a, (int16x8_t) __b); -} - -__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) -vuqaddq_s32 (int32x4_t __a, uint32x4_t __b) -{ - return (int32x4_t) __builtin_aarch64_suqaddv4si (__a, (int32x4_t) __b); -} - -__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) -vuqaddq_s64 (int64x2_t __a, uint64x2_t __b) -{ - return (int64x2_t) __builtin_aarch64_suqaddv2di (__a, (int64x2_t) __b); -} - -__extension__ static __inline int8x1_t __attribute__ ((__always_inline__)) -vuqaddb_s8 (int8x1_t __a, uint8x1_t __b) -{ - return (int8x1_t) __builtin_aarch64_suqaddqi (__a, (int8x1_t) __b); -} - -__extension__ static __inline int16x1_t __attribute__ ((__always_inline__)) -vuqaddh_s16 (int16x1_t __a, uint16x1_t __b) -{ - return (int16x1_t) __builtin_aarch64_suqaddhi (__a, (int16x1_t) __b); -} - -__extension__ static __inline int32x1_t __attribute__ ((__always_inline__)) -vuqadds_s32 (int32x1_t __a, uint32x1_t __b) -{ - return (int32x1_t) __builtin_aarch64_suqaddsi (__a, (int32x1_t) __b); -} - -__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) -vuqaddd_s64 (int64x1_t __a, uint64x1_t __b) -{ - return (int64x1_t) __builtin_aarch64_suqadddi (__a, (int64x1_t) __b); -} - -#define __DEFINTERLEAVE(op, rettype, intype, funcsuffix, Q) \ - __extension__ static __inline rettype \ - __attribute__ ((__always_inline__)) \ - v ## op ## Q ## _ ## funcsuffix (intype a, intype b) \ - { \ - return (rettype) {v ## op ## 1 ## Q ## _ ## funcsuffix (a, b), \ - v ## op ## 2 ## Q ## _ ## funcsuffix (a, b)}; \ - } - -#define __INTERLEAVE_LIST(op) \ - __DEFINTERLEAVE (op, float32x2x2_t, float32x2_t, f32,) \ - __DEFINTERLEAVE (op, poly8x8x2_t, poly8x8_t, p8,) \ - __DEFINTERLEAVE (op, poly16x4x2_t, poly16x4_t, p16,) \ - __DEFINTERLEAVE (op, int8x8x2_t, int8x8_t, s8,) \ - __DEFINTERLEAVE (op, int16x4x2_t, int16x4_t, s16,) \ - __DEFINTERLEAVE (op, int32x2x2_t, int32x2_t, s32,) \ - __DEFINTERLEAVE (op, uint8x8x2_t, uint8x8_t, u8,) \ - __DEFINTERLEAVE (op, uint16x4x2_t, uint16x4_t, u16,) \ - __DEFINTERLEAVE (op, uint32x2x2_t, uint32x2_t, u32,) \ - __DEFINTERLEAVE (op, float32x4x2_t, float32x4_t, f32, q) \ - __DEFINTERLEAVE (op, poly8x16x2_t, poly8x16_t, p8, q) \ - __DEFINTERLEAVE (op, poly16x8x2_t, poly16x8_t, p16, q) \ - __DEFINTERLEAVE (op, int8x16x2_t, int8x16_t, s8, q) \ - __DEFINTERLEAVE (op, int16x8x2_t, int16x8_t, s16, q) \ - __DEFINTERLEAVE (op, int32x4x2_t, int32x4_t, s32, q) \ - __DEFINTERLEAVE (op, uint8x16x2_t, uint8x16_t, u8, q) \ - __DEFINTERLEAVE (op, uint16x8x2_t, uint16x8_t, u16, q) \ - __DEFINTERLEAVE (op, uint32x4x2_t, uint32x4_t, u32, q) - -/* vuzp */ - -__INTERLEAVE_LIST (uzp) - -/* vzip */ - -__INTERLEAVE_LIST (zip) - -#undef __INTERLEAVE_LIST -#undef __DEFINTERLEAVE - -/* End of optimal implementations in approved order. */ - -#endif diff --git a/lib/gcc/aarch64-linux-android/4.8/include/float.h b/lib/gcc/aarch64-linux-android/4.8/include/float.h deleted file mode 100644 index dd461d7..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/float.h +++ /dev/null @@ -1,277 +0,0 @@ -/* Copyright (C) 2002-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* - * ISO C Standard: 5.2.4.2.2 Characteristics of floating types <float.h> - */ - -#ifndef _FLOAT_H___ -#define _FLOAT_H___ - -/* Radix of exponent representation, b. */ -#undef FLT_RADIX -#define FLT_RADIX __FLT_RADIX__ - -/* Number of base-FLT_RADIX digits in the significand, p. */ -#undef FLT_MANT_DIG -#undef DBL_MANT_DIG -#undef LDBL_MANT_DIG -#define FLT_MANT_DIG __FLT_MANT_DIG__ -#define DBL_MANT_DIG __DBL_MANT_DIG__ -#define LDBL_MANT_DIG __LDBL_MANT_DIG__ - -/* Number of decimal digits, q, such that any floating-point number with q - decimal digits can be rounded into a floating-point number with p radix b - digits and back again without change to the q decimal digits, - - p * log10(b) if b is a power of 10 - floor((p - 1) * log10(b)) otherwise -*/ -#undef FLT_DIG -#undef DBL_DIG -#undef LDBL_DIG -#define FLT_DIG __FLT_DIG__ -#define DBL_DIG __DBL_DIG__ -#define LDBL_DIG __LDBL_DIG__ - -/* Minimum int x such that FLT_RADIX**(x-1) is a normalized float, emin */ -#undef FLT_MIN_EXP -#undef DBL_MIN_EXP -#undef LDBL_MIN_EXP -#define FLT_MIN_EXP __FLT_MIN_EXP__ -#define DBL_MIN_EXP __DBL_MIN_EXP__ -#define LDBL_MIN_EXP __LDBL_MIN_EXP__ - -/* Minimum negative integer such that 10 raised to that power is in the - range of normalized floating-point numbers, - - ceil(log10(b) * (emin - 1)) -*/ -#undef FLT_MIN_10_EXP -#undef DBL_MIN_10_EXP -#undef LDBL_MIN_10_EXP -#define FLT_MIN_10_EXP __FLT_MIN_10_EXP__ -#define DBL_MIN_10_EXP __DBL_MIN_10_EXP__ -#define LDBL_MIN_10_EXP __LDBL_MIN_10_EXP__ - -/* Maximum int x such that FLT_RADIX**(x-1) is a representable float, emax. */ -#undef FLT_MAX_EXP -#undef DBL_MAX_EXP -#undef LDBL_MAX_EXP -#define FLT_MAX_EXP __FLT_MAX_EXP__ -#define DBL_MAX_EXP __DBL_MAX_EXP__ -#define LDBL_MAX_EXP __LDBL_MAX_EXP__ - -/* Maximum integer such that 10 raised to that power is in the range of - representable finite floating-point numbers, - - floor(log10((1 - b**-p) * b**emax)) -*/ -#undef FLT_MAX_10_EXP -#undef DBL_MAX_10_EXP -#undef LDBL_MAX_10_EXP -#define FLT_MAX_10_EXP __FLT_MAX_10_EXP__ -#define DBL_MAX_10_EXP __DBL_MAX_10_EXP__ -#define LDBL_MAX_10_EXP __LDBL_MAX_10_EXP__ - -/* Maximum representable finite floating-point number, - - (1 - b**-p) * b**emax -*/ -#undef FLT_MAX -#undef DBL_MAX -#undef LDBL_MAX -#define FLT_MAX __FLT_MAX__ -#define DBL_MAX __DBL_MAX__ -#define LDBL_MAX __LDBL_MAX__ - -/* The difference between 1 and the least value greater than 1 that is - representable in the given floating point type, b**1-p. */ -#undef FLT_EPSILON -#undef DBL_EPSILON -#undef LDBL_EPSILON -#define FLT_EPSILON __FLT_EPSILON__ -#define DBL_EPSILON __DBL_EPSILON__ -#define LDBL_EPSILON __LDBL_EPSILON__ - -/* Minimum normalized positive floating-point number, b**(emin - 1). */ -#undef FLT_MIN -#undef DBL_MIN -#undef LDBL_MIN -#define FLT_MIN __FLT_MIN__ -#define DBL_MIN __DBL_MIN__ -#define LDBL_MIN __LDBL_MIN__ - -/* Addition rounds to 0: zero, 1: nearest, 2: +inf, 3: -inf, -1: unknown. */ -/* ??? This is supposed to change with calls to fesetround in <fenv.h>. */ -#undef FLT_ROUNDS -#define FLT_ROUNDS 1 - -#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L -/* The floating-point expression evaluation method. - -1 indeterminate - 0 evaluate all operations and constants just to the range and - precision of the type - 1 evaluate operations and constants of type float and double - to the range and precision of the double type, evaluate - long double operations and constants to the range and - precision of the long double type - 2 evaluate all operations and constants to the range and - precision of the long double type - - ??? This ought to change with the setting of the fp control word; - the value provided by the compiler assumes the widest setting. */ -#undef FLT_EVAL_METHOD -#define FLT_EVAL_METHOD __FLT_EVAL_METHOD__ - -/* Number of decimal digits, n, such that any floating-point number in the - widest supported floating type with pmax radix b digits can be rounded - to a floating-point number with n decimal digits and back again without - change to the value, - - pmax * log10(b) if b is a power of 10 - ceil(1 + pmax * log10(b)) otherwise -*/ -#undef DECIMAL_DIG -#define DECIMAL_DIG __DECIMAL_DIG__ - -#endif /* C99 */ - -#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 201112L -/* Versions of DECIMAL_DIG for each floating-point type. */ -#undef FLT_DECIMAL_DIG -#undef DBL_DECIMAL_DIG -#undef LDBL_DECIMAL_DIG -#define FLT_DECIMAL_DIG __FLT_DECIMAL_DIG__ -#define DBL_DECIMAL_DIG __DBL_DECIMAL_DIG__ -#define LDBL_DECIMAL_DIG __DECIMAL_DIG__ - -/* Whether types support subnormal numbers. */ -#undef FLT_HAS_SUBNORM -#undef DBL_HAS_SUBNORM -#undef LDBL_HAS_SUBNORM -#define FLT_HAS_SUBNORM __FLT_HAS_DENORM__ -#define DBL_HAS_SUBNORM __DBL_HAS_DENORM__ -#define LDBL_HAS_SUBNORM __LDBL_HAS_DENORM__ - -/* Minimum positive values, including subnormals. */ -#undef FLT_TRUE_MIN -#undef DBL_TRUE_MIN -#undef LDBL_TRUE_MIN -#if __FLT_HAS_DENORM__ -#define FLT_TRUE_MIN __FLT_DENORM_MIN__ -#else -#define FLT_TRUE_MIN __FLT_MIN__ -#endif -#if __DBL_HAS_DENORM__ -#define DBL_TRUE_MIN __DBL_DENORM_MIN__ -#else -#define DBL_TRUE_MIN __DBL_MIN__ -#endif -#if __LDBL_HAS_DENORM__ -#define LDBL_TRUE_MIN __LDBL_DENORM_MIN__ -#else -#define LDBL_TRUE_MIN __LDBL_MIN__ -#endif - -#endif /* C11 */ - -#ifdef __STDC_WANT_DEC_FP__ -/* Draft Technical Report 24732, extension for decimal floating-point - arithmetic: Characteristic of decimal floating types <float.h>. */ - -/* Number of base-FLT_RADIX digits in the significand, p. */ -#undef DEC32_MANT_DIG -#undef DEC64_MANT_DIG -#undef DEC128_MANT_DIG -#define DEC32_MANT_DIG __DEC32_MANT_DIG__ -#define DEC64_MANT_DIG __DEC64_MANT_DIG__ -#define DEC128_MANT_DIG __DEC128_MANT_DIG__ - -/* Minimum exponent. */ -#undef DEC32_MIN_EXP -#undef DEC64_MIN_EXP -#undef DEC128_MIN_EXP -#define DEC32_MIN_EXP __DEC32_MIN_EXP__ -#define DEC64_MIN_EXP __DEC64_MIN_EXP__ -#define DEC128_MIN_EXP __DEC128_MIN_EXP__ - -/* Maximum exponent. */ -#undef DEC32_MAX_EXP -#undef DEC64_MAX_EXP -#undef DEC128_MAX_EXP -#define DEC32_MAX_EXP __DEC32_MAX_EXP__ -#define DEC64_MAX_EXP __DEC64_MAX_EXP__ -#define DEC128_MAX_EXP __DEC128_MAX_EXP__ - -/* Maximum representable finite decimal floating-point number - (there are 6, 15, and 33 9s after the decimal points respectively). */ -#undef DEC32_MAX -#undef DEC64_MAX -#undef DEC128_MAX -#define DEC32_MAX __DEC32_MAX__ -#define DEC64_MAX __DEC64_MAX__ -#define DEC128_MAX __DEC128_MAX__ - -/* The difference between 1 and the least value greater than 1 that is - representable in the given floating point type. */ -#undef DEC32_EPSILON -#undef DEC64_EPSILON -#undef DEC128_EPSILON -#define DEC32_EPSILON __DEC32_EPSILON__ -#define DEC64_EPSILON __DEC64_EPSILON__ -#define DEC128_EPSILON __DEC128_EPSILON__ - -/* Minimum normalized positive floating-point number. */ -#undef DEC32_MIN -#undef DEC64_MIN -#undef DEC128_MIN -#define DEC32_MIN __DEC32_MIN__ -#define DEC64_MIN __DEC64_MIN__ -#define DEC128_MIN __DEC128_MIN__ - -/* Minimum subnormal positive floating-point number. */ -#undef DEC32_SUBNORMAL_MIN -#undef DEC64_SUBNORMAL_MIN -#undef DEC128_SUBNORMAL_MIN -#define DEC32_SUBNORMAL_MIN __DEC32_SUBNORMAL_MIN__ -#define DEC64_SUBNORMAL_MIN __DEC64_SUBNORMAL_MIN__ -#define DEC128_SUBNORMAL_MIN __DEC128_SUBNORMAL_MIN__ - -/* The floating-point expression evaluation method. - -1 indeterminate - 0 evaluate all operations and constants just to the range and - precision of the type - 1 evaluate operations and constants of type _Decimal32 - and _Decimal64 to the range and precision of the _Decimal64 - type, evaluate _Decimal128 operations and constants to the - range and precision of the _Decimal128 type; - 2 evaluate all operations and constants to the range and - precision of the _Decimal128 type. */ - -#undef DEC_EVAL_METHOD -#define DEC_EVAL_METHOD __DEC_EVAL_METHOD__ - -#endif /* __STDC_WANT_DEC_FP__ */ - -#endif /* _FLOAT_H___ */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/iso646.h b/lib/gcc/aarch64-linux-android/4.8/include/iso646.h deleted file mode 100644 index 36dec91..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/iso646.h +++ /dev/null @@ -1,45 +0,0 @@ -/* Copyright (C) 1997-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* - * ISO C Standard: 7.9 Alternative spellings <iso646.h> - */ - -#ifndef _ISO646_H -#define _ISO646_H - -#ifndef __cplusplus -#define and && -#define and_eq &= -#define bitand & -#define bitor | -#define compl ~ -#define not ! -#define not_eq != -#define or || -#define or_eq |= -#define xor ^ -#define xor_eq ^= -#endif - -#endif diff --git a/lib/gcc/aarch64-linux-android/4.8/include/omp.h b/lib/gcc/aarch64-linux-android/4.8/include/omp.h deleted file mode 100644 index 429c3fc..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/omp.h +++ /dev/null @@ -1,107 +0,0 @@ -/* Copyright (C) 2005-2013 Free Software Foundation, Inc. - Contributed by Richard Henderson <rth@redhat.com>. - - This file is part of the GNU OpenMP Library (libgomp). - - Libgomp is free software; you can redistribute it and/or modify it - under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 3, or (at your option) - any later version. - - Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY - WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS - FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - Under Section 7 of GPL version 3, you are granted additional - permissions described in the GCC Runtime Library Exception, version - 3.1, as published by the Free Software Foundation. - - You should have received a copy of the GNU General Public License and - a copy of the GCC Runtime Library Exception along with this program; - see the files COPYING3 and COPYING.RUNTIME respectively. If not, see - <http://www.gnu.org/licenses/>. */ - -#ifndef OMP_H -#define OMP_H 1 - -#ifndef _LIBGOMP_OMP_LOCK_DEFINED -#define _LIBGOMP_OMP_LOCK_DEFINED 1 -/* These two structures get edited by the libgomp build process to - reflect the shape of the two types. Their internals are private - to the library. */ - -typedef struct -{ - unsigned char _x[4] - __attribute__((__aligned__(4))); -} omp_lock_t; - -typedef struct -{ - unsigned char _x[16] - __attribute__((__aligned__(8))); -} omp_nest_lock_t; -#endif - -typedef enum omp_sched_t -{ - omp_sched_static = 1, - omp_sched_dynamic = 2, - omp_sched_guided = 3, - omp_sched_auto = 4 -} omp_sched_t; - -#ifdef __cplusplus -extern "C" { -# define __GOMP_NOTHROW throw () -#else -# define __GOMP_NOTHROW __attribute__((__nothrow__)) -#endif - -extern void omp_set_num_threads (int) __GOMP_NOTHROW; -extern int omp_get_num_threads (void) __GOMP_NOTHROW; -extern int omp_get_max_threads (void) __GOMP_NOTHROW; -extern int omp_get_thread_num (void) __GOMP_NOTHROW; -extern int omp_get_num_procs (void) __GOMP_NOTHROW; - -extern int omp_in_parallel (void) __GOMP_NOTHROW; - -extern void omp_set_dynamic (int) __GOMP_NOTHROW; -extern int omp_get_dynamic (void) __GOMP_NOTHROW; - -extern void omp_set_nested (int) __GOMP_NOTHROW; -extern int omp_get_nested (void) __GOMP_NOTHROW; - -extern void omp_init_lock (omp_lock_t *) __GOMP_NOTHROW; -extern void omp_destroy_lock (omp_lock_t *) __GOMP_NOTHROW; -extern void omp_set_lock (omp_lock_t *) __GOMP_NOTHROW; -extern void omp_unset_lock (omp_lock_t *) __GOMP_NOTHROW; -extern int omp_test_lock (omp_lock_t *) __GOMP_NOTHROW; - -extern void omp_init_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; -extern void omp_destroy_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; -extern void omp_set_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; -extern void omp_unset_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; -extern int omp_test_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; - -extern double omp_get_wtime (void) __GOMP_NOTHROW; -extern double omp_get_wtick (void) __GOMP_NOTHROW; - -void omp_set_schedule (omp_sched_t, int) __GOMP_NOTHROW; -void omp_get_schedule (omp_sched_t *, int *) __GOMP_NOTHROW; -int omp_get_thread_limit (void) __GOMP_NOTHROW; -void omp_set_max_active_levels (int) __GOMP_NOTHROW; -int omp_get_max_active_levels (void) __GOMP_NOTHROW; -int omp_get_level (void) __GOMP_NOTHROW; -int omp_get_ancestor_thread_num (int) __GOMP_NOTHROW; -int omp_get_team_size (int) __GOMP_NOTHROW; -int omp_get_active_level (void) __GOMP_NOTHROW; - -int omp_in_final (void) __GOMP_NOTHROW; - -#ifdef __cplusplus -} -#endif - -#endif /* OMP_H */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdalign.h b/lib/gcc/aarch64-linux-android/4.8/include/stdalign.h deleted file mode 100644 index fe545dd..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdalign.h +++ /dev/null @@ -1,39 +0,0 @@ -/* Copyright (C) 2011-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* ISO C1X: 7.15 Alignment <stdalign.h>. */ - -#ifndef _STDALIGN_H -#define _STDALIGN_H - -#ifndef __cplusplus - -#define alignas _Alignas -#define alignof _Alignof - -#define __alignas_is_defined 1 -#define __alignof_is_defined 1 - -#endif - -#endif /* stdalign.h */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdarg.h b/lib/gcc/aarch64-linux-android/4.8/include/stdarg.h deleted file mode 100644 index fb4e0d6..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdarg.h +++ /dev/null @@ -1,126 +0,0 @@ -/* Copyright (C) 1989-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* - * ISO C Standard: 7.15 Variable arguments <stdarg.h> - */ - -#ifndef _STDARG_H -#ifndef _ANSI_STDARG_H_ -#ifndef __need___va_list -#define _STDARG_H -#define _ANSI_STDARG_H_ -#endif /* not __need___va_list */ -#undef __need___va_list - -/* Define __gnuc_va_list. */ - -#ifndef __GNUC_VA_LIST -#define __GNUC_VA_LIST -typedef __builtin_va_list __gnuc_va_list; -#endif - -/* Define the standard macros for the user, - if this invocation was from the user program. */ -#ifdef _STDARG_H - -#define va_start(v,l) __builtin_va_start(v,l) -#define va_end(v) __builtin_va_end(v) -#define va_arg(v,l) __builtin_va_arg(v,l) -#if !defined(__STRICT_ANSI__) || __STDC_VERSION__ + 0 >= 199900L || defined(__GXX_EXPERIMENTAL_CXX0X__) -#define va_copy(d,s) __builtin_va_copy(d,s) -#endif -#define __va_copy(d,s) __builtin_va_copy(d,s) - -/* Define va_list, if desired, from __gnuc_va_list. */ -/* We deliberately do not define va_list when called from - stdio.h, because ANSI C says that stdio.h is not supposed to define - va_list. stdio.h needs to have access to that data type, - but must not use that name. It should use the name __gnuc_va_list, - which is safe because it is reserved for the implementation. */ - -#ifdef _BSD_VA_LIST -#undef _BSD_VA_LIST -#endif - -#if defined(__svr4__) || (defined(_SCO_DS) && !defined(__VA_LIST)) -/* SVR4.2 uses _VA_LIST for an internal alias for va_list, - so we must avoid testing it and setting it here. - SVR4 uses _VA_LIST as a flag in stdarg.h, but we should - have no conflict with that. */ -#ifndef _VA_LIST_ -#define _VA_LIST_ -#ifdef __i860__ -#ifndef _VA_LIST -#define _VA_LIST va_list -#endif -#endif /* __i860__ */ -typedef __gnuc_va_list va_list; -#ifdef _SCO_DS -#define __VA_LIST -#endif -#endif /* _VA_LIST_ */ -#else /* not __svr4__ || _SCO_DS */ - -/* The macro _VA_LIST_ is the same thing used by this file in Ultrix. - But on BSD NET2 we must not test or define or undef it. - (Note that the comments in NET 2's ansi.h - are incorrect for _VA_LIST_--see stdio.h!) */ -#if !defined (_VA_LIST_) || defined (__BSD_NET2__) || defined (____386BSD____) || defined (__bsdi__) || defined (__sequent__) || defined (__FreeBSD__) || defined(WINNT) -/* The macro _VA_LIST_DEFINED is used in Windows NT 3.5 */ -#ifndef _VA_LIST_DEFINED -/* The macro _VA_LIST is used in SCO Unix 3.2. */ -#ifndef _VA_LIST -/* The macro _VA_LIST_T_H is used in the Bull dpx2 */ -#ifndef _VA_LIST_T_H -/* The macro __va_list__ is used by BeOS. */ -#ifndef __va_list__ -typedef __gnuc_va_list va_list; -#endif /* not __va_list__ */ -#endif /* not _VA_LIST_T_H */ -#endif /* not _VA_LIST */ -#endif /* not _VA_LIST_DEFINED */ -#if !(defined (__BSD_NET2__) || defined (____386BSD____) || defined (__bsdi__) || defined (__sequent__) || defined (__FreeBSD__)) -#define _VA_LIST_ -#endif -#ifndef _VA_LIST -#define _VA_LIST -#endif -#ifndef _VA_LIST_DEFINED -#define _VA_LIST_DEFINED -#endif -#ifndef _VA_LIST_T_H -#define _VA_LIST_T_H -#endif -#ifndef __va_list__ -#define __va_list__ -#endif - -#endif /* not _VA_LIST_, except on certain systems */ - -#endif /* not __svr4__ */ - -#endif /* _STDARG_H */ - -#endif /* not _ANSI_STDARG_H_ */ -#endif /* not _STDARG_H */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdbool.h b/lib/gcc/aarch64-linux-android/4.8/include/stdbool.h deleted file mode 100644 index 7146e63..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdbool.h +++ /dev/null @@ -1,50 +0,0 @@ -/* Copyright (C) 1998-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* - * ISO C Standard: 7.16 Boolean type and values <stdbool.h> - */ - -#ifndef _STDBOOL_H -#define _STDBOOL_H - -#ifndef __cplusplus - -#define bool _Bool -#define true 1 -#define false 0 - -#else /* __cplusplus */ - -/* Supporting <stdbool.h> in C++ is a GCC extension. */ -#define _Bool bool -#define bool bool -#define false false -#define true true - -#endif /* __cplusplus */ - -/* Signal that all the definitions are present. */ -#define __bool_true_false_are_defined 1 - -#endif /* stdbool.h */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stddef.h b/lib/gcc/aarch64-linux-android/4.8/include/stddef.h deleted file mode 100644 index b04dd65..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stddef.h +++ /dev/null @@ -1,439 +0,0 @@ -/* Copyright (C) 1989-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* - * ISO C Standard: 7.17 Common definitions <stddef.h> - */ -#if (!defined(_STDDEF_H) && !defined(_STDDEF_H_) && !defined(_ANSI_STDDEF_H) \ - && !defined(__STDDEF_H__)) \ - || defined(__need_wchar_t) || defined(__need_size_t) \ - || defined(__need_ptrdiff_t) || defined(__need_NULL) \ - || defined(__need_wint_t) - -/* Any one of these symbols __need_* means that GNU libc - wants us just to define one data type. So don't define - the symbols that indicate this file's entire job has been done. */ -#if (!defined(__need_wchar_t) && !defined(__need_size_t) \ - && !defined(__need_ptrdiff_t) && !defined(__need_NULL) \ - && !defined(__need_wint_t)) -#define _STDDEF_H -#define _STDDEF_H_ -/* snaroff@next.com says the NeXT needs this. */ -#define _ANSI_STDDEF_H -#endif - -#ifndef __sys_stdtypes_h -/* This avoids lossage on SunOS but only if stdtypes.h comes first. - There's no way to win with the other order! Sun lossage. */ - -/* On 4.3bsd-net2, make sure ansi.h is included, so we have - one less case to deal with in the following. */ -#if defined (__BSD_NET2__) || defined (____386BSD____) || (defined (__FreeBSD__) && (__FreeBSD__ < 5)) || defined(__NetBSD__) -#include <machine/ansi.h> -#endif -/* On FreeBSD 5, machine/ansi.h does not exist anymore... */ -#if defined (__FreeBSD__) && (__FreeBSD__ >= 5) -#include <sys/_types.h> -#endif - -/* In 4.3bsd-net2, machine/ansi.h defines these symbols, which are - defined if the corresponding type is *not* defined. - FreeBSD-2.1 defines _MACHINE_ANSI_H_ instead of _ANSI_H_. - NetBSD defines _I386_ANSI_H_ and _X86_64_ANSI_H_ instead of _ANSI_H_ */ -#if defined(_ANSI_H_) || defined(_MACHINE_ANSI_H_) || defined(_X86_64_ANSI_H_) || defined(_I386_ANSI_H_) -#if !defined(_SIZE_T_) && !defined(_BSD_SIZE_T_) -#define _SIZE_T -#endif -#if !defined(_PTRDIFF_T_) && !defined(_BSD_PTRDIFF_T_) -#define _PTRDIFF_T -#endif -/* On BSD/386 1.1, at least, machine/ansi.h defines _BSD_WCHAR_T_ - instead of _WCHAR_T_. */ -#if !defined(_WCHAR_T_) && !defined(_BSD_WCHAR_T_) -#ifndef _BSD_WCHAR_T_ -#define _WCHAR_T -#endif -#endif -/* Undef _FOO_T_ if we are supposed to define foo_t. */ -#if defined (__need_ptrdiff_t) || defined (_STDDEF_H_) -#undef _PTRDIFF_T_ -#undef _BSD_PTRDIFF_T_ -#endif -#if defined (__need_size_t) || defined (_STDDEF_H_) -#undef _SIZE_T_ -#undef _BSD_SIZE_T_ -#endif -#if defined (__need_wchar_t) || defined (_STDDEF_H_) -#undef _WCHAR_T_ -#undef _BSD_WCHAR_T_ -#endif -#endif /* defined(_ANSI_H_) || defined(_MACHINE_ANSI_H_) || defined(_X86_64_ANSI_H_) || defined(_I386_ANSI_H_) */ - -/* Sequent's header files use _PTRDIFF_T_ in some conflicting way. - Just ignore it. */ -#if defined (__sequent__) && defined (_PTRDIFF_T_) -#undef _PTRDIFF_T_ -#endif - -/* On VxWorks, <type/vxTypesBase.h> may have defined macros like - _TYPE_size_t which will typedef size_t. fixincludes patched the - vxTypesBase.h so that this macro is only defined if _GCC_SIZE_T is - not defined, and so that defining this macro defines _GCC_SIZE_T. - If we find that the macros are still defined at this point, we must - invoke them so that the type is defined as expected. */ -#if defined (_TYPE_ptrdiff_t) && (defined (__need_ptrdiff_t) || defined (_STDDEF_H_)) -_TYPE_ptrdiff_t; -#undef _TYPE_ptrdiff_t -#endif -#if defined (_TYPE_size_t) && (defined (__need_size_t) || defined (_STDDEF_H_)) -_TYPE_size_t; -#undef _TYPE_size_t -#endif -#if defined (_TYPE_wchar_t) && (defined (__need_wchar_t) || defined (_STDDEF_H_)) -_TYPE_wchar_t; -#undef _TYPE_wchar_t -#endif - -/* In case nobody has defined these types, but we aren't running under - GCC 2.00, make sure that __PTRDIFF_TYPE__, __SIZE_TYPE__, and - __WCHAR_TYPE__ have reasonable values. This can happen if the - parts of GCC is compiled by an older compiler, that actually - include gstddef.h, such as collect2. */ - -/* Signed type of difference of two pointers. */ - -/* Define this type if we are doing the whole job, - or if we want this type in particular. */ -#if defined (_STDDEF_H) || defined (__need_ptrdiff_t) -#ifndef _PTRDIFF_T /* in case <sys/types.h> has defined it. */ -#ifndef _T_PTRDIFF_ -#ifndef _T_PTRDIFF -#ifndef __PTRDIFF_T -#ifndef _PTRDIFF_T_ -#ifndef _BSD_PTRDIFF_T_ -#ifndef ___int_ptrdiff_t_h -#ifndef _GCC_PTRDIFF_T -#define _PTRDIFF_T -#define _T_PTRDIFF_ -#define _T_PTRDIFF -#define __PTRDIFF_T -#define _PTRDIFF_T_ -#define _BSD_PTRDIFF_T_ -#define ___int_ptrdiff_t_h -#define _GCC_PTRDIFF_T -#ifndef __PTRDIFF_TYPE__ -#define __PTRDIFF_TYPE__ long int -#endif -typedef __PTRDIFF_TYPE__ ptrdiff_t; -#endif /* _GCC_PTRDIFF_T */ -#endif /* ___int_ptrdiff_t_h */ -#endif /* _BSD_PTRDIFF_T_ */ -#endif /* _PTRDIFF_T_ */ -#endif /* __PTRDIFF_T */ -#endif /* _T_PTRDIFF */ -#endif /* _T_PTRDIFF_ */ -#endif /* _PTRDIFF_T */ - -/* If this symbol has done its job, get rid of it. */ -#undef __need_ptrdiff_t - -#endif /* _STDDEF_H or __need_ptrdiff_t. */ - -/* Unsigned type of `sizeof' something. */ - -/* Define this type if we are doing the whole job, - or if we want this type in particular. */ -#if defined (_STDDEF_H) || defined (__need_size_t) -#ifndef __size_t__ /* BeOS */ -#ifndef __SIZE_T__ /* Cray Unicos/Mk */ -#ifndef _SIZE_T /* in case <sys/types.h> has defined it. */ -#ifndef _SYS_SIZE_T_H -#ifndef _T_SIZE_ -#ifndef _T_SIZE -#ifndef __SIZE_T -#ifndef _SIZE_T_ -#ifndef _BSD_SIZE_T_ -#ifndef _SIZE_T_DEFINED_ -#ifndef _SIZE_T_DEFINED -#ifndef _BSD_SIZE_T_DEFINED_ /* Darwin */ -#ifndef _SIZE_T_DECLARED /* FreeBSD 5 */ -#ifndef ___int_size_t_h -#ifndef _GCC_SIZE_T -#ifndef _SIZET_ -#ifndef __size_t -#define __size_t__ /* BeOS */ -#define __SIZE_T__ /* Cray Unicos/Mk */ -#define _SIZE_T -#define _SYS_SIZE_T_H -#define _T_SIZE_ -#define _T_SIZE -#define __SIZE_T -#define _SIZE_T_ -#define _BSD_SIZE_T_ -#define _SIZE_T_DEFINED_ -#define _SIZE_T_DEFINED -#define _BSD_SIZE_T_DEFINED_ /* Darwin */ -#define _SIZE_T_DECLARED /* FreeBSD 5 */ -#define ___int_size_t_h -#define _GCC_SIZE_T -#define _SIZET_ -#if (defined (__FreeBSD__) && (__FreeBSD__ >= 5)) \ - || defined(__FreeBSD_kernel__) -/* __size_t is a typedef on FreeBSD 5, must not trash it. */ -#elif defined (__VMS__) -/* __size_t is also a typedef on VMS. */ -#else -#define __size_t -#endif -#ifndef __SIZE_TYPE__ -#define __SIZE_TYPE__ long unsigned int -#endif -#if !(defined (__GNUG__) && defined (size_t)) -typedef __SIZE_TYPE__ size_t; -#ifdef __BEOS__ -typedef long ssize_t; -#endif /* __BEOS__ */ -#endif /* !(defined (__GNUG__) && defined (size_t)) */ -#endif /* __size_t */ -#endif /* _SIZET_ */ -#endif /* _GCC_SIZE_T */ -#endif /* ___int_size_t_h */ -#endif /* _SIZE_T_DECLARED */ -#endif /* _BSD_SIZE_T_DEFINED_ */ -#endif /* _SIZE_T_DEFINED */ -#endif /* _SIZE_T_DEFINED_ */ -#endif /* _BSD_SIZE_T_ */ -#endif /* _SIZE_T_ */ -#endif /* __SIZE_T */ -#endif /* _T_SIZE */ -#endif /* _T_SIZE_ */ -#endif /* _SYS_SIZE_T_H */ -#endif /* _SIZE_T */ -#endif /* __SIZE_T__ */ -#endif /* __size_t__ */ -#undef __need_size_t -#endif /* _STDDEF_H or __need_size_t. */ - - -/* Wide character type. - Locale-writers should change this as necessary to - be big enough to hold unique values not between 0 and 127, - and not (wchar_t) -1, for each defined multibyte character. */ - -/* Define this type if we are doing the whole job, - or if we want this type in particular. */ -#if defined (_STDDEF_H) || defined (__need_wchar_t) -#ifndef __wchar_t__ /* BeOS */ -#ifndef __WCHAR_T__ /* Cray Unicos/Mk */ -#ifndef _WCHAR_T -#ifndef _T_WCHAR_ -#ifndef _T_WCHAR -#ifndef __WCHAR_T -#ifndef _WCHAR_T_ -#ifndef _BSD_WCHAR_T_ -#ifndef _BSD_WCHAR_T_DEFINED_ /* Darwin */ -#ifndef _BSD_RUNE_T_DEFINED_ /* Darwin */ -#ifndef _WCHAR_T_DECLARED /* FreeBSD 5 */ -#ifndef _WCHAR_T_DEFINED_ -#ifndef _WCHAR_T_DEFINED -#ifndef _WCHAR_T_H -#ifndef ___int_wchar_t_h -#ifndef __INT_WCHAR_T_H -#ifndef _GCC_WCHAR_T -#define __wchar_t__ /* BeOS */ -#define __WCHAR_T__ /* Cray Unicos/Mk */ -#define _WCHAR_T -#define _T_WCHAR_ -#define _T_WCHAR -#define __WCHAR_T -#define _WCHAR_T_ -#define _BSD_WCHAR_T_ -#define _WCHAR_T_DEFINED_ -#define _WCHAR_T_DEFINED -#define _WCHAR_T_H -#define ___int_wchar_t_h -#define __INT_WCHAR_T_H -#define _GCC_WCHAR_T -#define _WCHAR_T_DECLARED - -/* On BSD/386 1.1, at least, machine/ansi.h defines _BSD_WCHAR_T_ - instead of _WCHAR_T_, and _BSD_RUNE_T_ (which, unlike the other - symbols in the _FOO_T_ family, stays defined even after its - corresponding type is defined). If we define wchar_t, then we - must undef _WCHAR_T_; for BSD/386 1.1 (and perhaps others), if - we undef _WCHAR_T_, then we must also define rune_t, since - headers like runetype.h assume that if machine/ansi.h is included, - and _BSD_WCHAR_T_ is not defined, then rune_t is available. - machine/ansi.h says, "Note that _WCHAR_T_ and _RUNE_T_ must be of - the same type." */ -#ifdef _BSD_WCHAR_T_ -#undef _BSD_WCHAR_T_ -#ifdef _BSD_RUNE_T_ -#if !defined (_ANSI_SOURCE) && !defined (_POSIX_SOURCE) -typedef _BSD_RUNE_T_ rune_t; -#define _BSD_WCHAR_T_DEFINED_ -#define _BSD_RUNE_T_DEFINED_ /* Darwin */ -#if defined (__FreeBSD__) && (__FreeBSD__ < 5) -/* Why is this file so hard to maintain properly? In contrast to - the comment above regarding BSD/386 1.1, on FreeBSD for as long - as the symbol has existed, _BSD_RUNE_T_ must not stay defined or - redundant typedefs will occur when stdlib.h is included after this file. */ -#undef _BSD_RUNE_T_ -#endif -#endif -#endif -#endif -/* FreeBSD 5 can't be handled well using "traditional" logic above - since it no longer defines _BSD_RUNE_T_ yet still desires to export - rune_t in some cases... */ -#if defined (__FreeBSD__) && (__FreeBSD__ >= 5) -#if !defined (_ANSI_SOURCE) && !defined (_POSIX_SOURCE) -#if __BSD_VISIBLE -#ifndef _RUNE_T_DECLARED -typedef __rune_t rune_t; -#define _RUNE_T_DECLARED -#endif -#endif -#endif -#endif - -#ifndef __WCHAR_TYPE__ -#define __WCHAR_TYPE__ int -#endif -#ifndef __cplusplus -typedef __WCHAR_TYPE__ wchar_t; -#endif -#endif -#endif -#endif -#endif -#endif -#endif -#endif /* _WCHAR_T_DECLARED */ -#endif /* _BSD_RUNE_T_DEFINED_ */ -#endif -#endif -#endif -#endif -#endif -#endif -#endif -#endif /* __WCHAR_T__ */ -#endif /* __wchar_t__ */ -#undef __need_wchar_t -#endif /* _STDDEF_H or __need_wchar_t. */ - -#if defined (__need_wint_t) -#ifndef _WINT_T -#define _WINT_T - -#ifndef __WINT_TYPE__ -#define __WINT_TYPE__ unsigned int -#endif -typedef __WINT_TYPE__ wint_t; -#endif -#undef __need_wint_t -#endif - -/* In 4.3bsd-net2, leave these undefined to indicate that size_t, etc. - are already defined. */ -/* BSD/OS 3.1 and FreeBSD [23].x require the MACHINE_ANSI_H check here. */ -/* NetBSD 5 requires the I386_ANSI_H and X86_64_ANSI_H checks here. */ -#if defined(_ANSI_H_) || defined(_MACHINE_ANSI_H_) || defined(_X86_64_ANSI_H_) || defined(_I386_ANSI_H_) -/* The references to _GCC_PTRDIFF_T_, _GCC_SIZE_T_, and _GCC_WCHAR_T_ - are probably typos and should be removed before 2.8 is released. */ -#ifdef _GCC_PTRDIFF_T_ -#undef _PTRDIFF_T_ -#undef _BSD_PTRDIFF_T_ -#endif -#ifdef _GCC_SIZE_T_ -#undef _SIZE_T_ -#undef _BSD_SIZE_T_ -#endif -#ifdef _GCC_WCHAR_T_ -#undef _WCHAR_T_ -#undef _BSD_WCHAR_T_ -#endif -/* The following ones are the real ones. */ -#ifdef _GCC_PTRDIFF_T -#undef _PTRDIFF_T_ -#undef _BSD_PTRDIFF_T_ -#endif -#ifdef _GCC_SIZE_T -#undef _SIZE_T_ -#undef _BSD_SIZE_T_ -#endif -#ifdef _GCC_WCHAR_T -#undef _WCHAR_T_ -#undef _BSD_WCHAR_T_ -#endif -#endif /* _ANSI_H_ || _MACHINE_ANSI_H_ || _X86_64_ANSI_H_ || _I386_ANSI_H_ */ - -#endif /* __sys_stdtypes_h */ - -/* A null pointer constant. */ - -#if defined (_STDDEF_H) || defined (__need_NULL) -#undef NULL /* in case <stdio.h> has defined it. */ -#ifdef __GNUG__ -#define NULL __null -#else /* G++ */ -#ifndef __cplusplus -#define NULL ((void *)0) -#else /* C++ */ -#define NULL 0 -#endif /* C++ */ -#endif /* G++ */ -#endif /* NULL not defined and <stddef.h> or need NULL. */ -#undef __need_NULL - -#ifdef _STDDEF_H - -/* Offset of member MEMBER in a struct of type TYPE. */ -#define offsetof(TYPE, MEMBER) __builtin_offsetof (TYPE, MEMBER) - -#if (defined (__STDC_VERSION__) && __STDC_VERSION__ >= 201112L) \ - || (defined(__cplusplus) && __cplusplus >= 201103L) -#ifndef _GCC_MAX_ALIGN_T -#define _GCC_MAX_ALIGN_T -/* Type whose alignment is supported in every context and is at least - as great as that of any standard type not using alignment - specifiers. */ -typedef struct { - long long __max_align_ll __attribute__((__aligned__(__alignof__(long long)))); - long double __max_align_ld __attribute__((__aligned__(__alignof__(long double)))); -} max_align_t; -#endif -#endif /* C11 or C++11. */ - -#if defined(__cplusplus) && __cplusplus >= 201103L -#ifndef _GXX_NULLPTR_T -#define _GXX_NULLPTR_T - typedef decltype(nullptr) nullptr_t; -#endif -#endif /* C++11. */ - -#endif /* _STDDEF_H was defined this time */ - -#endif /* !_STDDEF_H && !_STDDEF_H_ && !_ANSI_STDDEF_H && !__STDDEF_H__ - || __need_XXX was not defined before */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdfix.h b/lib/gcc/aarch64-linux-android/4.8/include/stdfix.h deleted file mode 100644 index fdcef1e..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdfix.h +++ /dev/null @@ -1,204 +0,0 @@ -/* Copyright (C) 2007-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* ISO/IEC JTC1 SC22 WG14 N1169 - * Date: 2006-04-04 - * ISO/IEC TR 18037 - * Programming languages - C - Extensions to support embedded processors - */ - -#ifndef _STDFIX_H -#define _STDFIX_H - -/* 7.18a.1 Introduction. */ - -#undef fract -#undef accum -#undef sat -#define fract _Fract -#define accum _Accum -#define sat _Sat - -/* 7.18a.3 Precision macros. */ - -#undef SFRACT_FBIT -#undef SFRACT_MIN -#undef SFRACT_MAX -#undef SFRACT_EPSILON -#define SFRACT_FBIT __SFRACT_FBIT__ -#define SFRACT_MIN __SFRACT_MIN__ -#define SFRACT_MAX __SFRACT_MAX__ -#define SFRACT_EPSILON __SFRACT_EPSILON__ - -#undef USFRACT_FBIT -#undef USFRACT_MIN -#undef USFRACT_MAX -#undef USFRACT_EPSILON -#define USFRACT_FBIT __USFRACT_FBIT__ -#define USFRACT_MIN __USFRACT_MIN__ /* GCC extension. */ -#define USFRACT_MAX __USFRACT_MAX__ -#define USFRACT_EPSILON __USFRACT_EPSILON__ - -#undef FRACT_FBIT -#undef FRACT_MIN -#undef FRACT_MAX -#undef FRACT_EPSILON -#define FRACT_FBIT __FRACT_FBIT__ -#define FRACT_MIN __FRACT_MIN__ -#define FRACT_MAX __FRACT_MAX__ -#define FRACT_EPSILON __FRACT_EPSILON__ - -#undef UFRACT_FBIT -#undef UFRACT_MIN -#undef UFRACT_MAX -#undef UFRACT_EPSILON -#define UFRACT_FBIT __UFRACT_FBIT__ -#define UFRACT_MIN __UFRACT_MIN__ /* GCC extension. */ -#define UFRACT_MAX __UFRACT_MAX__ -#define UFRACT_EPSILON __UFRACT_EPSILON__ - -#undef LFRACT_FBIT -#undef LFRACT_MIN -#undef LFRACT_MAX -#undef LFRACT_EPSILON -#define LFRACT_FBIT __LFRACT_FBIT__ -#define LFRACT_MIN __LFRACT_MIN__ -#define LFRACT_MAX __LFRACT_MAX__ -#define LFRACT_EPSILON __LFRACT_EPSILON__ - -#undef ULFRACT_FBIT -#undef ULFRACT_MIN -#undef ULFRACT_MAX -#undef ULFRACT_EPSILON -#define ULFRACT_FBIT __ULFRACT_FBIT__ -#define ULFRACT_MIN __ULFRACT_MIN__ /* GCC extension. */ -#define ULFRACT_MAX __ULFRACT_MAX__ -#define ULFRACT_EPSILON __ULFRACT_EPSILON__ - -#undef LLFRACT_FBIT -#undef LLFRACT_MIN -#undef LLFRACT_MAX -#undef LLFRACT_EPSILON -#define LLFRACT_FBIT __LLFRACT_FBIT__ /* GCC extension. */ -#define LLFRACT_MIN __LLFRACT_MIN__ /* GCC extension. */ -#define LLFRACT_MAX __LLFRACT_MAX__ /* GCC extension. */ -#define LLFRACT_EPSILON __LLFRACT_EPSILON__ /* GCC extension. */ - -#undef ULLFRACT_FBIT -#undef ULLFRACT_MIN -#undef ULLFRACT_MAX -#undef ULLFRACT_EPSILON -#define ULLFRACT_FBIT __ULLFRACT_FBIT__ /* GCC extension. */ -#define ULLFRACT_MIN __ULLFRACT_MIN__ /* GCC extension. */ -#define ULLFRACT_MAX __ULLFRACT_MAX__ /* GCC extension. */ -#define ULLFRACT_EPSILON __ULLFRACT_EPSILON__ /* GCC extension. */ - -#undef SACCUM_FBIT -#undef SACCUM_IBIT -#undef SACCUM_MIN -#undef SACCUM_MAX -#undef SACCUM_EPSILON -#define SACCUM_FBIT __SACCUM_FBIT__ -#define SACCUM_IBIT __SACCUM_IBIT__ -#define SACCUM_MIN __SACCUM_MIN__ -#define SACCUM_MAX __SACCUM_MAX__ -#define SACCUM_EPSILON __SACCUM_EPSILON__ - -#undef USACCUM_FBIT -#undef USACCUM_IBIT -#undef USACCUM_MIN -#undef USACCUM_MAX -#undef USACCUM_EPSILON -#define USACCUM_FBIT __USACCUM_FBIT__ -#define USACCUM_IBIT __USACCUM_IBIT__ -#define USACCUM_MIN __USACCUM_MIN__ /* GCC extension. */ -#define USACCUM_MAX __USACCUM_MAX__ -#define USACCUM_EPSILON __USACCUM_EPSILON__ - -#undef ACCUM_FBIT -#undef ACCUM_IBIT -#undef ACCUM_MIN -#undef ACCUM_MAX -#undef ACCUM_EPSILON -#define ACCUM_FBIT __ACCUM_FBIT__ -#define ACCUM_IBIT __ACCUM_IBIT__ -#define ACCUM_MIN __ACCUM_MIN__ -#define ACCUM_MAX __ACCUM_MAX__ -#define ACCUM_EPSILON __ACCUM_EPSILON__ - -#undef UACCUM_FBIT -#undef UACCUM_IBIT -#undef UACCUM_MIN -#undef UACCUM_MAX -#undef UACCUM_EPSILON -#define UACCUM_FBIT __UACCUM_FBIT__ -#define UACCUM_IBIT __UACCUM_IBIT__ -#define UACCUM_MIN __UACCUM_MIN__ /* GCC extension. */ -#define UACCUM_MAX __UACCUM_MAX__ -#define UACCUM_EPSILON __UACCUM_EPSILON__ - -#undef LACCUM_FBIT -#undef LACCUM_IBIT -#undef LACCUM_MIN -#undef LACCUM_MAX -#undef LACCUM_EPSILON -#define LACCUM_FBIT __LACCUM_FBIT__ -#define LACCUM_IBIT __LACCUM_IBIT__ -#define LACCUM_MIN __LACCUM_MIN__ -#define LACCUM_MAX __LACCUM_MAX__ -#define LACCUM_EPSILON __LACCUM_EPSILON__ - -#undef ULACCUM_FBIT -#undef ULACCUM_IBIT -#undef ULACCUM_MIN -#undef ULACCUM_MAX -#undef ULACCUM_EPSILON -#define ULACCUM_FBIT __ULACCUM_FBIT__ -#define ULACCUM_IBIT __ULACCUM_IBIT__ -#define ULACCUM_MIN __ULACCUM_MIN__ /* GCC extension. */ -#define ULACCUM_MAX __ULACCUM_MAX__ -#define ULACCUM_EPSILON __ULACCUM_EPSILON__ - -#undef LLACCUM_FBIT -#undef LLACCUM_IBIT -#undef LLACCUM_MIN -#undef LLACCUM_MAX -#undef LLACCUM_EPSILON -#define LLACCUM_FBIT __LLACCUM_FBIT__ /* GCC extension. */ -#define LLACCUM_IBIT __LLACCUM_IBIT__ /* GCC extension. */ -#define LLACCUM_MIN __LLACCUM_MIN__ /* GCC extension. */ -#define LLACCUM_MAX __LLACCUM_MAX__ /* GCC extension. */ -#define LLACCUM_EPSILON __LLACCUM_EPSILON__ /* GCC extension. */ - -#undef ULLACCUM_FBIT -#undef ULLACCUM_IBIT -#undef ULLACCUM_MIN -#undef ULLACCUM_MAX -#undef ULLACCUM_EPSILON -#define ULLACCUM_FBIT __ULLACCUM_FBIT__ /* GCC extension. */ -#define ULLACCUM_IBIT __ULLACCUM_IBIT__ /* GCC extension. */ -#define ULLACCUM_MIN __ULLACCUM_MIN__ /* GCC extension. */ -#define ULLACCUM_MAX __ULLACCUM_MAX__ /* GCC extension. */ -#define ULLACCUM_EPSILON __ULLACCUM_EPSILON__ /* GCC extension. */ - -#endif /* _STDFIX_H */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdint-gcc.h b/lib/gcc/aarch64-linux-android/4.8/include/stdint-gcc.h deleted file mode 100644 index 97339e2..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdint-gcc.h +++ /dev/null @@ -1,263 +0,0 @@ -/* Copyright (C) 2008-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* - * ISO C Standard: 7.18 Integer types <stdint.h> - */ - -#ifndef _GCC_STDINT_H -#define _GCC_STDINT_H - -/* 7.8.1.1 Exact-width integer types */ - -#ifdef __INT8_TYPE__ -typedef __INT8_TYPE__ int8_t; -#endif -#ifdef __INT16_TYPE__ -typedef __INT16_TYPE__ int16_t; -#endif -#ifdef __INT32_TYPE__ -typedef __INT32_TYPE__ int32_t; -#endif -#ifdef __INT64_TYPE__ -typedef __INT64_TYPE__ int64_t; -#endif -#ifdef __UINT8_TYPE__ -typedef __UINT8_TYPE__ uint8_t; -#endif -#ifdef __UINT16_TYPE__ -typedef __UINT16_TYPE__ uint16_t; -#endif -#ifdef __UINT32_TYPE__ -typedef __UINT32_TYPE__ uint32_t; -#endif -#ifdef __UINT64_TYPE__ -typedef __UINT64_TYPE__ uint64_t; -#endif - -/* 7.8.1.2 Minimum-width integer types */ - -typedef __INT_LEAST8_TYPE__ int_least8_t; -typedef __INT_LEAST16_TYPE__ int_least16_t; -typedef __INT_LEAST32_TYPE__ int_least32_t; -typedef __INT_LEAST64_TYPE__ int_least64_t; -typedef __UINT_LEAST8_TYPE__ uint_least8_t; -typedef __UINT_LEAST16_TYPE__ uint_least16_t; -typedef __UINT_LEAST32_TYPE__ uint_least32_t; -typedef __UINT_LEAST64_TYPE__ uint_least64_t; - -/* 7.8.1.3 Fastest minimum-width integer types */ - -typedef __INT_FAST8_TYPE__ int_fast8_t; -typedef __INT_FAST16_TYPE__ int_fast16_t; -typedef __INT_FAST32_TYPE__ int_fast32_t; -typedef __INT_FAST64_TYPE__ int_fast64_t; -typedef __UINT_FAST8_TYPE__ uint_fast8_t; -typedef __UINT_FAST16_TYPE__ uint_fast16_t; -typedef __UINT_FAST32_TYPE__ uint_fast32_t; -typedef __UINT_FAST64_TYPE__ uint_fast64_t; - -/* 7.8.1.4 Integer types capable of holding object pointers */ - -#ifdef __INTPTR_TYPE__ -typedef __INTPTR_TYPE__ intptr_t; -#endif -#ifdef __UINTPTR_TYPE__ -typedef __UINTPTR_TYPE__ uintptr_t; -#endif - -/* 7.8.1.5 Greatest-width integer types */ - -typedef __INTMAX_TYPE__ intmax_t; -typedef __UINTMAX_TYPE__ uintmax_t; - -#if (!defined __cplusplus || __cplusplus >= 201103L \ - || defined __STDC_LIMIT_MACROS) - -/* 7.18.2 Limits of specified-width integer types */ - -#ifdef __INT8_MAX__ -# undef INT8_MAX -# define INT8_MAX __INT8_MAX__ -# undef INT8_MIN -# define INT8_MIN (-INT8_MAX - 1) -#endif -#ifdef __UINT8_MAX__ -# undef UINT8_MAX -# define UINT8_MAX __UINT8_MAX__ -#endif -#ifdef __INT16_MAX__ -# undef INT16_MAX -# define INT16_MAX __INT16_MAX__ -# undef INT16_MIN -# define INT16_MIN (-INT16_MAX - 1) -#endif -#ifdef __UINT16_MAX__ -# undef UINT16_MAX -# define UINT16_MAX __UINT16_MAX__ -#endif -#ifdef __INT32_MAX__ -# undef INT32_MAX -# define INT32_MAX __INT32_MAX__ -# undef INT32_MIN -# define INT32_MIN (-INT32_MAX - 1) -#endif -#ifdef __UINT32_MAX__ -# undef UINT32_MAX -# define UINT32_MAX __UINT32_MAX__ -#endif -#ifdef __INT64_MAX__ -# undef INT64_MAX -# define INT64_MAX __INT64_MAX__ -# undef INT64_MIN -# define INT64_MIN (-INT64_MAX - 1) -#endif -#ifdef __UINT64_MAX__ -# undef UINT64_MAX -# define UINT64_MAX __UINT64_MAX__ -#endif - -#undef INT_LEAST8_MAX -#define INT_LEAST8_MAX __INT_LEAST8_MAX__ -#undef INT_LEAST8_MIN -#define INT_LEAST8_MIN (-INT_LEAST8_MAX - 1) -#undef UINT_LEAST8_MAX -#define UINT_LEAST8_MAX __UINT_LEAST8_MAX__ -#undef INT_LEAST16_MAX -#define INT_LEAST16_MAX __INT_LEAST16_MAX__ -#undef INT_LEAST16_MIN -#define INT_LEAST16_MIN (-INT_LEAST16_MAX - 1) -#undef UINT_LEAST16_MAX -#define UINT_LEAST16_MAX __UINT_LEAST16_MAX__ -#undef INT_LEAST32_MAX -#define INT_LEAST32_MAX __INT_LEAST32_MAX__ -#undef INT_LEAST32_MIN -#define INT_LEAST32_MIN (-INT_LEAST32_MAX - 1) -#undef UINT_LEAST32_MAX -#define UINT_LEAST32_MAX __UINT_LEAST32_MAX__ -#undef INT_LEAST64_MAX -#define INT_LEAST64_MAX __INT_LEAST64_MAX__ -#undef INT_LEAST64_MIN -#define INT_LEAST64_MIN (-INT_LEAST64_MAX - 1) -#undef UINT_LEAST64_MAX -#define UINT_LEAST64_MAX __UINT_LEAST64_MAX__ - -#undef INT_FAST8_MAX -#define INT_FAST8_MAX __INT_FAST8_MAX__ -#undef INT_FAST8_MIN -#define INT_FAST8_MIN (-INT_FAST8_MAX - 1) -#undef UINT_FAST8_MAX -#define UINT_FAST8_MAX __UINT_FAST8_MAX__ -#undef INT_FAST16_MAX -#define INT_FAST16_MAX __INT_FAST16_MAX__ -#undef INT_FAST16_MIN -#define INT_FAST16_MIN (-INT_FAST16_MAX - 1) -#undef UINT_FAST16_MAX -#define UINT_FAST16_MAX __UINT_FAST16_MAX__ -#undef INT_FAST32_MAX -#define INT_FAST32_MAX __INT_FAST32_MAX__ -#undef INT_FAST32_MIN -#define INT_FAST32_MIN (-INT_FAST32_MAX - 1) -#undef UINT_FAST32_MAX -#define UINT_FAST32_MAX __UINT_FAST32_MAX__ -#undef INT_FAST64_MAX -#define INT_FAST64_MAX __INT_FAST64_MAX__ -#undef INT_FAST64_MIN -#define INT_FAST64_MIN (-INT_FAST64_MAX - 1) -#undef UINT_FAST64_MAX -#define UINT_FAST64_MAX __UINT_FAST64_MAX__ - -#ifdef __INTPTR_MAX__ -# undef INTPTR_MAX -# define INTPTR_MAX __INTPTR_MAX__ -# undef INTPTR_MIN -# define INTPTR_MIN (-INTPTR_MAX - 1) -#endif -#ifdef __UINTPTR_MAX__ -# undef UINTPTR_MAX -# define UINTPTR_MAX __UINTPTR_MAX__ -#endif - -#undef INTMAX_MAX -#define INTMAX_MAX __INTMAX_MAX__ -#undef INTMAX_MIN -#define INTMAX_MIN (-INTMAX_MAX - 1) -#undef UINTMAX_MAX -#define UINTMAX_MAX __UINTMAX_MAX__ - -/* 7.18.3 Limits of other integer types */ - -#undef PTRDIFF_MAX -#define PTRDIFF_MAX __PTRDIFF_MAX__ -#undef PTRDIFF_MIN -#define PTRDIFF_MIN (-PTRDIFF_MAX - 1) - -#undef SIG_ATOMIC_MAX -#define SIG_ATOMIC_MAX __SIG_ATOMIC_MAX__ -#undef SIG_ATOMIC_MIN -#define SIG_ATOMIC_MIN __SIG_ATOMIC_MIN__ - -#undef SIZE_MAX -#define SIZE_MAX __SIZE_MAX__ - -#undef WCHAR_MAX -#define WCHAR_MAX __WCHAR_MAX__ -#undef WCHAR_MIN -#define WCHAR_MIN __WCHAR_MIN__ - -#undef WINT_MAX -#define WINT_MAX __WINT_MAX__ -#undef WINT_MIN -#define WINT_MIN __WINT_MIN__ - -#endif /* (!defined __cplusplus || __cplusplus >= 201103L - || defined __STDC_LIMIT_MACROS) */ - -#if (!defined __cplusplus || __cplusplus >= 201103L \ - || defined __STDC_CONSTANT_MACROS) - -#undef INT8_C -#define INT8_C(c) __INT8_C(c) -#undef INT16_C -#define INT16_C(c) __INT16_C(c) -#undef INT32_C -#define INT32_C(c) __INT32_C(c) -#undef INT64_C -#define INT64_C(c) __INT64_C(c) -#undef UINT8_C -#define UINT8_C(c) __UINT8_C(c) -#undef UINT16_C -#define UINT16_C(c) __UINT16_C(c) -#undef UINT32_C -#define UINT32_C(c) __UINT32_C(c) -#undef UINT64_C -#define UINT64_C(c) __UINT64_C(c) -#undef INTMAX_C -#define INTMAX_C(c) __INTMAX_C(c) -#undef UINTMAX_C -#define UINTMAX_C(c) __UINTMAX_C(c) - -#endif /* (!defined __cplusplus || __cplusplus >= 201103L - || defined __STDC_CONSTANT_MACROS) */ - -#endif /* _GCC_STDINT_H */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdint.h b/lib/gcc/aarch64-linux-android/4.8/include/stdint.h deleted file mode 100644 index 83b6f70..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdint.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef _GCC_WRAP_STDINT_H -#if __STDC_HOSTED__ -# if defined __cplusplus && __cplusplus >= 201103L -# undef __STDC_LIMIT_MACROS -# define __STDC_LIMIT_MACROS -# undef __STDC_CONSTANT_MACROS -# define __STDC_CONSTANT_MACROS -# endif -# include_next <stdint.h> -#else -# include "stdint-gcc.h" -#endif -#define _GCC_WRAP_STDINT_H -#endif diff --git a/lib/gcc/aarch64-linux-android/4.8/include/stdnoreturn.h b/lib/gcc/aarch64-linux-android/4.8/include/stdnoreturn.h deleted file mode 100644 index ce4bec9..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/stdnoreturn.h +++ /dev/null @@ -1,35 +0,0 @@ -/* Copyright (C) 2011-2013 Free Software Foundation, Inc. - -This file is part of GCC. - -GCC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 3, or (at your option) -any later version. - -GCC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -Under Section 7 of GPL version 3, you are granted additional -permissions described in the GCC Runtime Library Exception, version -3.1, as published by the Free Software Foundation. - -You should have received a copy of the GNU General Public License and -a copy of the GCC Runtime Library Exception along with this program; -see the files COPYING3 and COPYING.RUNTIME respectively. If not, see -<http://www.gnu.org/licenses/>. */ - -/* ISO C1X: 7.23 _Noreturn <stdnoreturn.h>. */ - -#ifndef _STDNORETURN_H -#define _STDNORETURN_H - -#ifndef __cplusplus - -#define noreturn _Noreturn - -#endif - -#endif /* stdnoreturn.h */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/unwind.h b/lib/gcc/aarch64-linux-android/4.8/include/unwind.h deleted file mode 100644 index b8d78b9..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/unwind.h +++ /dev/null @@ -1,293 +0,0 @@ -/* Exception handling and frame unwind runtime interface routines. - Copyright (C) 2001-2013 Free Software Foundation, Inc. - - This file is part of GCC. - - GCC is free software; you can redistribute it and/or modify it - under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 3, or (at your option) - any later version. - - GCC is distributed in the hope that it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public - License for more details. - - Under Section 7 of GPL version 3, you are granted additional - permissions described in the GCC Runtime Library Exception, version - 3.1, as published by the Free Software Foundation. - - You should have received a copy of the GNU General Public License and - a copy of the GCC Runtime Library Exception along with this program; - see the files COPYING3 and COPYING.RUNTIME respectively. If not, see - <http://www.gnu.org/licenses/>. */ - -/* This is derived from the C++ ABI for IA-64. Where we diverge - for cross-architecture compatibility are noted with "@@@". */ - -#ifndef _UNWIND_H -#define _UNWIND_H - -#if defined (__SEH__) && !defined (__USING_SJLJ_EXCEPTIONS__) -/* Only for _GCC_specific_handler. */ -#include <windows.h> -#endif - -#ifndef HIDE_EXPORTS -#pragma GCC visibility push(default) -#endif - -#ifdef __cplusplus -extern "C" { -#endif - -/* Level 1: Base ABI */ - -/* @@@ The IA-64 ABI uses uint64 throughout. Most places this is - inefficient for 32-bit and smaller machines. */ -typedef unsigned _Unwind_Word __attribute__((__mode__(__unwind_word__))); -typedef signed _Unwind_Sword __attribute__((__mode__(__unwind_word__))); -#if defined(__ia64__) && defined(__hpux__) -typedef unsigned _Unwind_Ptr __attribute__((__mode__(__word__))); -#else -typedef unsigned _Unwind_Ptr __attribute__((__mode__(__pointer__))); -#endif -typedef unsigned _Unwind_Internal_Ptr __attribute__((__mode__(__pointer__))); - -/* @@@ The IA-64 ABI uses a 64-bit word to identify the producer and - consumer of an exception. We'll go along with this for now even on - 32-bit machines. We'll need to provide some other option for - 16-bit machines and for machines with > 8 bits per byte. */ -typedef unsigned _Unwind_Exception_Class __attribute__((__mode__(__DI__))); - -/* The unwind interface uses reason codes in several contexts to - identify the reasons for failures or other actions. */ -typedef enum -{ - _URC_NO_REASON = 0, - _URC_FOREIGN_EXCEPTION_CAUGHT = 1, - _URC_FATAL_PHASE2_ERROR = 2, - _URC_FATAL_PHASE1_ERROR = 3, - _URC_NORMAL_STOP = 4, - _URC_END_OF_STACK = 5, - _URC_HANDLER_FOUND = 6, - _URC_INSTALL_CONTEXT = 7, - _URC_CONTINUE_UNWIND = 8 -} _Unwind_Reason_Code; - - -/* The unwind interface uses a pointer to an exception header object - as its representation of an exception being thrown. In general, the - full representation of an exception object is language- and - implementation-specific, but it will be prefixed by a header - understood by the unwind interface. */ - -struct _Unwind_Exception; - -typedef void (*_Unwind_Exception_Cleanup_Fn) (_Unwind_Reason_Code, - struct _Unwind_Exception *); - -struct _Unwind_Exception -{ - _Unwind_Exception_Class exception_class; - _Unwind_Exception_Cleanup_Fn exception_cleanup; - -#if !defined (__USING_SJLJ_EXCEPTIONS__) && defined (__SEH__) - _Unwind_Word private_[6]; -#else - _Unwind_Word private_1; - _Unwind_Word private_2; -#endif - - /* @@@ The IA-64 ABI says that this structure must be double-word aligned. - Taking that literally does not make much sense generically. Instead we - provide the maximum alignment required by any type for the machine. */ -} __attribute__((__aligned__)); - - -/* The ACTIONS argument to the personality routine is a bitwise OR of one - or more of the following constants. */ -typedef int _Unwind_Action; - -#define _UA_SEARCH_PHASE 1 -#define _UA_CLEANUP_PHASE 2 -#define _UA_HANDLER_FRAME 4 -#define _UA_FORCE_UNWIND 8 -#define _UA_END_OF_STACK 16 - -/* The target can override this macro to define any back-end-specific - attributes required for the lowest-level stack frame. */ -#ifndef LIBGCC2_UNWIND_ATTRIBUTE -#define LIBGCC2_UNWIND_ATTRIBUTE -#endif - -/* This is an opaque type used to refer to a system-specific data - structure used by the system unwinder. This context is created and - destroyed by the system, and passed to the personality routine - during unwinding. */ -struct _Unwind_Context; - -/* Raise an exception, passing along the given exception object. */ -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_RaiseException (struct _Unwind_Exception *); - -/* Raise an exception for forced unwinding. */ - -typedef _Unwind_Reason_Code (*_Unwind_Stop_Fn) - (int, _Unwind_Action, _Unwind_Exception_Class, - struct _Unwind_Exception *, struct _Unwind_Context *, void *); - -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_ForcedUnwind (struct _Unwind_Exception *, _Unwind_Stop_Fn, void *); - -/* Helper to invoke the exception_cleanup routine. */ -extern void _Unwind_DeleteException (struct _Unwind_Exception *); - -/* Resume propagation of an existing exception. This is used after - e.g. executing cleanup code, and not to implement rethrowing. */ -extern void LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_Resume (struct _Unwind_Exception *); - -/* @@@ Resume propagation of a FORCE_UNWIND exception, or to rethrow - a normal exception that was handled. */ -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_Resume_or_Rethrow (struct _Unwind_Exception *); - -/* @@@ Use unwind data to perform a stack backtrace. The trace callback - is called for every stack frame in the call chain, but no cleanup - actions are performed. */ -typedef _Unwind_Reason_Code (*_Unwind_Trace_Fn) - (struct _Unwind_Context *, void *); - -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_Backtrace (_Unwind_Trace_Fn, void *); - -/* These functions are used for communicating information about the unwind - context (i.e. the unwind descriptors and the user register state) between - the unwind library and the personality routine and landing pad. Only - selected registers may be manipulated. */ - -extern _Unwind_Word _Unwind_GetGR (struct _Unwind_Context *, int); -extern void _Unwind_SetGR (struct _Unwind_Context *, int, _Unwind_Word); - -extern _Unwind_Ptr _Unwind_GetIP (struct _Unwind_Context *); -extern _Unwind_Ptr _Unwind_GetIPInfo (struct _Unwind_Context *, int *); -extern void _Unwind_SetIP (struct _Unwind_Context *, _Unwind_Ptr); - -/* @@@ Retrieve the CFA of the given context. */ -extern _Unwind_Word _Unwind_GetCFA (struct _Unwind_Context *); - -extern void *_Unwind_GetLanguageSpecificData (struct _Unwind_Context *); - -extern _Unwind_Ptr _Unwind_GetRegionStart (struct _Unwind_Context *); - - -/* The personality routine is the function in the C++ (or other language) - runtime library which serves as an interface between the system unwind - library and language-specific exception handling semantics. It is - specific to the code fragment described by an unwind info block, and - it is always referenced via the pointer in the unwind info block, and - hence it has no ABI-specified name. - - Note that this implies that two different C++ implementations can - use different names, and have different contents in the language - specific data area. Moreover, that the language specific data - area contains no version info because name of the function invoked - provides more effective versioning by detecting at link time the - lack of code to handle the different data format. */ - -typedef _Unwind_Reason_Code (*_Unwind_Personality_Fn) - (int, _Unwind_Action, _Unwind_Exception_Class, - struct _Unwind_Exception *, struct _Unwind_Context *); - -/* @@@ The following alternate entry points are for setjmp/longjmp - based unwinding. */ - -struct SjLj_Function_Context; -extern void _Unwind_SjLj_Register (struct SjLj_Function_Context *); -extern void _Unwind_SjLj_Unregister (struct SjLj_Function_Context *); - -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_SjLj_RaiseException (struct _Unwind_Exception *); -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_SjLj_ForcedUnwind (struct _Unwind_Exception *, _Unwind_Stop_Fn, void *); -extern void LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_SjLj_Resume (struct _Unwind_Exception *); -extern _Unwind_Reason_Code LIBGCC2_UNWIND_ATTRIBUTE -_Unwind_SjLj_Resume_or_Rethrow (struct _Unwind_Exception *); - -/* @@@ The following provide access to the base addresses for text - and data-relative addressing in the LDSA. In order to stay link - compatible with the standard ABI for IA-64, we inline these. */ - -#ifdef __ia64__ -#include <stdlib.h> - -static inline _Unwind_Ptr -_Unwind_GetDataRelBase (struct _Unwind_Context *_C) -{ - /* The GP is stored in R1. */ - return _Unwind_GetGR (_C, 1); -} - -static inline _Unwind_Ptr -_Unwind_GetTextRelBase (struct _Unwind_Context *_C __attribute__ ((__unused__))) -{ - abort (); - return 0; -} - -/* @@@ Retrieve the Backing Store Pointer of the given context. */ -extern _Unwind_Word _Unwind_GetBSP (struct _Unwind_Context *); -#else -extern _Unwind_Ptr _Unwind_GetDataRelBase (struct _Unwind_Context *); -extern _Unwind_Ptr _Unwind_GetTextRelBase (struct _Unwind_Context *); -#endif - -/* @@@ Given an address, return the entry point of the function that - contains it. */ -extern void * _Unwind_FindEnclosingFunction (void *pc); - -#ifndef __SIZEOF_LONG__ - #error "__SIZEOF_LONG__ macro not defined" -#endif - -#ifndef __SIZEOF_POINTER__ - #error "__SIZEOF_POINTER__ macro not defined" -#endif - - -/* leb128 type numbers have a potentially unlimited size. - The target of the following definitions of _sleb128_t and _uleb128_t - is to have efficient data types large enough to hold the leb128 type - numbers used in the unwind code. - Mostly these types will simply be defined to long and unsigned long - except when a unsigned long data type on the target machine is not - capable of storing a pointer. */ - -#if __SIZEOF_LONG__ >= __SIZEOF_POINTER__ - typedef long _sleb128_t; - typedef unsigned long _uleb128_t; -#elif __SIZEOF_LONG_LONG__ >= __SIZEOF_POINTER__ - typedef long long _sleb128_t; - typedef unsigned long long _uleb128_t; -#else -# error "What type shall we use for _sleb128_t?" -#endif - -#if defined (__SEH__) && !defined (__USING_SJLJ_EXCEPTIONS__) -/* Handles the mapping from SEH to GCC interfaces. */ -EXCEPTION_DISPOSITION _GCC_specific_handler (PEXCEPTION_RECORD, void *, - PCONTEXT, PDISPATCHER_CONTEXT, - _Unwind_Personality_Fn); -#endif - -#ifdef __cplusplus -} -#endif - -#ifndef HIDE_EXPORTS -#pragma GCC visibility pop -#endif - -#endif /* unwind.h */ diff --git a/lib/gcc/aarch64-linux-android/4.8/include/varargs.h b/lib/gcc/aarch64-linux-android/4.8/include/varargs.h deleted file mode 100644 index 4b9803e..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/include/varargs.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _VARARGS_H -#define _VARARGS_H - -#error "GCC no longer implements <varargs.h>." -#error "Revise your code to use <stdarg.h>." - -#endif diff --git a/lib/gcc/aarch64-linux-android/4.8/libgcc.a b/lib/gcc/aarch64-linux-android/4.8/libgcc.a Binary files differdeleted file mode 100644 index 2fc4a79..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/libgcc.a +++ /dev/null diff --git a/lib/gcc/aarch64-linux-android/4.8/libgcov.a b/lib/gcc/aarch64-linux-android/4.8/libgcov.a Binary files differdeleted file mode 100644 index 7064050..0000000 --- a/lib/gcc/aarch64-linux-android/4.8/libgcov.a +++ /dev/null |