1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
/* Copyright (C) 2007, 2008 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 2, 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.
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING. If not, write to
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
Boston, MA 02110-1301, USA. */
/* As a special exception, if you include this header file into source
files compiled by GCC, this header file does not by itself cause
the resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License. */
/* Implemented from the specification included in the AMD Programmers
Manual Update, version 2.x */
#ifndef _AMMINTRIN_H_INCLUDED
#define _AMMINTRIN_H_INCLUDED
#ifndef __SSE4A__
# error "SSE4A instruction set not enabled"
#else
/* We need definitions from the SSE3, SSE2 and SSE header files*/
#include <pmmintrin.h>
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_sd (double * __P, __m128d __Y)
{
__builtin_ia32_movntsd (__P, (__v2df) __Y);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_ss (float * __P, __m128 __Y)
{
__builtin_ia32_movntss (__P, (__v4sf) __Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_si64 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_extrq ((__v2di) __X, (__v16qi) __Y);
}
#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extracti_si64 (__m128i __X, unsigned const int __I, unsigned const int __L)
{
return (__m128i) __builtin_ia32_extrqi ((__v2di) __X, __I, __L);
}
#else
#define _mm_extracti_si64(X, I, L) \
((__m128i) __builtin_ia32_extrqi ((__v2di)(__m128i)(X), \
(unsigned int)(I), (unsigned int)(L)))
#endif
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_si64 (__m128i __X,__m128i __Y)
{
return (__m128i) __builtin_ia32_insertq ((__v2di)__X, (__v2di)__Y);
}
#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_inserti_si64(__m128i __X, __m128i __Y, unsigned const int __I, unsigned const int __L)
{
return (__m128i) __builtin_ia32_insertqi ((__v2di)__X, (__v2di)__Y, __I, __L);
}
#else
#define _mm_inserti_si64(X, Y, I, L) \
((__m128i) __builtin_ia32_insertqi ((__v2di)(__m128i)(X), \
(__v2di)(__m128i)(Y), \
(unsigned int)(I), (unsigned int)(L)))
#endif
#endif /* __SSE4A__ */
#endif /* _AMMINTRIN_H_INCLUDED */
|
