/* Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009
|
/* Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009
|
Free Software Foundation, Inc.
|
Free Software Foundation, Inc.
|
|
|
This file is part of GCC.
|
This file is part of GCC.
|
|
|
GCC is free software; you can redistribute it and/or modify
|
GCC is free software; you can redistribute it and/or modify
|
it under the terms of the GNU General Public License as published by
|
it under the terms of the GNU General Public License as published by
|
the Free Software Foundation; either version 3, or (at your option)
|
the Free Software Foundation; either version 3, or (at your option)
|
any later version.
|
any later version.
|
|
|
GCC is distributed in the hope that it will be useful,
|
GCC is distributed in the hope that it will be useful,
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
GNU General Public License for more details.
|
GNU General Public License for more details.
|
|
|
Under Section 7 of GPL version 3, you are granted additional
|
Under Section 7 of GPL version 3, you are granted additional
|
permissions described in the GCC Runtime Library Exception, version
|
permissions described in the GCC Runtime Library Exception, version
|
3.1, as published by the Free Software Foundation.
|
3.1, as published by the Free Software Foundation.
|
|
|
You should have received a copy of the GNU General Public License and
|
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;
|
a copy of the GCC Runtime Library Exception along with this program;
|
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
|
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
|
<http://www.gnu.org/licenses/>. */
|
<http://www.gnu.org/licenses/>. */
|
|
|
/* Implemented from the specification included in the Intel C++ Compiler
|
/* Implemented from the specification included in the Intel C++ Compiler
|
User Guide and Reference, version 9.0. */
|
User Guide and Reference, version 9.0. */
|
|
|
#ifndef _PMMINTRIN_H_INCLUDED
|
#ifndef _PMMINTRIN_H_INCLUDED
|
#define _PMMINTRIN_H_INCLUDED
|
#define _PMMINTRIN_H_INCLUDED
|
|
|
#ifndef __SSE3__
|
#ifndef __SSE3__
|
# error "SSE3 instruction set not enabled"
|
# error "SSE3 instruction set not enabled"
|
#else
|
#else
|
|
|
/* We need definitions from the SSE2 and SSE header files*/
|
/* We need definitions from the SSE2 and SSE header files*/
|
#include <emmintrin.h>
|
#include <emmintrin.h>
|
|
|
/* Additional bits in the MXCSR. */
|
/* Additional bits in the MXCSR. */
|
#define _MM_DENORMALS_ZERO_MASK 0x0040
|
#define _MM_DENORMALS_ZERO_MASK 0x0040
|
#define _MM_DENORMALS_ZERO_ON 0x0040
|
#define _MM_DENORMALS_ZERO_ON 0x0040
|
#define _MM_DENORMALS_ZERO_OFF 0x0000
|
#define _MM_DENORMALS_ZERO_OFF 0x0000
|
|
|
#define _MM_SET_DENORMALS_ZERO_MODE(mode) \
|
#define _MM_SET_DENORMALS_ZERO_MODE(mode) \
|
_mm_setcsr ((_mm_getcsr () & ~_MM_DENORMALS_ZERO_MASK) | (mode))
|
_mm_setcsr ((_mm_getcsr () & ~_MM_DENORMALS_ZERO_MASK) | (mode))
|
#define _MM_GET_DENORMALS_ZERO_MODE() \
|
#define _MM_GET_DENORMALS_ZERO_MODE() \
|
(_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)
|
(_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)
|
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_addsub_ps (__m128 __X, __m128 __Y)
|
_mm_addsub_ps (__m128 __X, __m128 __Y)
|
{
|
{
|
return (__m128) __builtin_ia32_addsubps ((__v4sf)__X, (__v4sf)__Y);
|
return (__m128) __builtin_ia32_addsubps ((__v4sf)__X, (__v4sf)__Y);
|
}
|
}
|
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_hadd_ps (__m128 __X, __m128 __Y)
|
_mm_hadd_ps (__m128 __X, __m128 __Y)
|
{
|
{
|
return (__m128) __builtin_ia32_haddps ((__v4sf)__X, (__v4sf)__Y);
|
return (__m128) __builtin_ia32_haddps ((__v4sf)__X, (__v4sf)__Y);
|
}
|
}
|
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_hsub_ps (__m128 __X, __m128 __Y)
|
_mm_hsub_ps (__m128 __X, __m128 __Y)
|
{
|
{
|
return (__m128) __builtin_ia32_hsubps ((__v4sf)__X, (__v4sf)__Y);
|
return (__m128) __builtin_ia32_hsubps ((__v4sf)__X, (__v4sf)__Y);
|
}
|
}
|
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_movehdup_ps (__m128 __X)
|
_mm_movehdup_ps (__m128 __X)
|
{
|
{
|
return (__m128) __builtin_ia32_movshdup ((__v4sf)__X);
|
return (__m128) __builtin_ia32_movshdup ((__v4sf)__X);
|
}
|
}
|
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_moveldup_ps (__m128 __X)
|
_mm_moveldup_ps (__m128 __X)
|
{
|
{
|
return (__m128) __builtin_ia32_movsldup ((__v4sf)__X);
|
return (__m128) __builtin_ia32_movsldup ((__v4sf)__X);
|
}
|
}
|
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_addsub_pd (__m128d __X, __m128d __Y)
|
_mm_addsub_pd (__m128d __X, __m128d __Y)
|
{
|
{
|
return (__m128d) __builtin_ia32_addsubpd ((__v2df)__X, (__v2df)__Y);
|
return (__m128d) __builtin_ia32_addsubpd ((__v2df)__X, (__v2df)__Y);
|
}
|
}
|
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_hadd_pd (__m128d __X, __m128d __Y)
|
_mm_hadd_pd (__m128d __X, __m128d __Y)
|
{
|
{
|
return (__m128d) __builtin_ia32_haddpd ((__v2df)__X, (__v2df)__Y);
|
return (__m128d) __builtin_ia32_haddpd ((__v2df)__X, (__v2df)__Y);
|
}
|
}
|
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_hsub_pd (__m128d __X, __m128d __Y)
|
_mm_hsub_pd (__m128d __X, __m128d __Y)
|
{
|
{
|
return (__m128d) __builtin_ia32_hsubpd ((__v2df)__X, (__v2df)__Y);
|
return (__m128d) __builtin_ia32_hsubpd ((__v2df)__X, (__v2df)__Y);
|
}
|
}
|
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_loaddup_pd (double const *__P)
|
_mm_loaddup_pd (double const *__P)
|
{
|
{
|
return _mm_load1_pd (__P);
|
return _mm_load1_pd (__P);
|
}
|
}
|
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_movedup_pd (__m128d __X)
|
_mm_movedup_pd (__m128d __X)
|
{
|
{
|
return _mm_shuffle_pd (__X, __X, _MM_SHUFFLE2 (0,0));
|
return _mm_shuffle_pd (__X, __X, _MM_SHUFFLE2 (0,0));
|
}
|
}
|
|
|
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_lddqu_si128 (__m128i const *__P)
|
_mm_lddqu_si128 (__m128i const *__P)
|
{
|
{
|
return (__m128i) __builtin_ia32_lddqu ((char const *)__P);
|
return (__m128i) __builtin_ia32_lddqu ((char const *)__P);
|
}
|
}
|
|
|
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_monitor (void const * __P, unsigned int __E, unsigned int __H)
|
_mm_monitor (void const * __P, unsigned int __E, unsigned int __H)
|
{
|
{
|
__builtin_ia32_monitor (__P, __E, __H);
|
__builtin_ia32_monitor (__P, __E, __H);
|
}
|
}
|
|
|
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
_mm_mwait (unsigned int __E, unsigned int __H)
|
_mm_mwait (unsigned int __E, unsigned int __H)
|
{
|
{
|
__builtin_ia32_mwait (__E, __H);
|
__builtin_ia32_mwait (__E, __H);
|
}
|
}
|
|
|
#endif /* __SSE3__ */
|
#endif /* __SSE3__ */
|
|
|
#endif /* _PMMINTRIN_H_INCLUDED */
|
#endif /* _PMMINTRIN_H_INCLUDED */
|
|
|
