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
92
|
/* Copyright (C) 2011 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/>. */
#if !defined _X86INTRIN_H_INCLUDED && !defined _IMMINTRIN_H_INCLUDED
# error "Never use <f16intrin.h> directly; include <x86intrin.h> or <immintrin.h> instead."
#endif
#ifndef __F16C__
# error "F16C instruction set not enabled"
#else
#ifndef _F16CINTRIN_H_INCLUDED
#define _F16CINTRIN_H_INCLUDED
extern __inline float __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_cvtsh_ss (unsigned short __S)
{
__v8hi __H = __extension__ (__v8hi){ __S, 0, 0, 0, 0, 0, 0, 0 };
__v4sf __A = __builtin_ia32_vcvtph2ps (__H);
return __builtin_ia32_vec_ext_v4sf (__A, 0);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtph_ps (__m128i __A)
{
return (__m128) __builtin_ia32_vcvtph2ps ((__v8hi) __A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtph_ps (__m128i __A)
{
return (__m256) __builtin_ia32_vcvtph2ps256 ((__v8hi) __A);
}
#ifdef __OPTIMIZE__
extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_cvtss_sh (float __F, const int __I)
{
__v4sf __A = __extension__ (__v4sf){ __F, 0, 0, 0 };
__v8hi __H = __builtin_ia32_vcvtps2ph (__A, __I);
return (unsigned short) __builtin_ia32_vec_ext_v8hi (__H, 0);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtps_ph (__m128 __A, const int __I)
{
return (__m128i) __builtin_ia32_vcvtps2ph ((__v4sf) __A, __I);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtps_ph (__m256 __A, const int __I)
{
return (__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf) __A, __I);
}
#else
#define _cvtss_sh(__F, __I) \
(__extension__ \
({ \
__v4sf __A = __extension__ (__v4sf){ __F, 0, 0, 0 }; \
__v8hi __H = __builtin_ia32_vcvtps2ph (__A, __I); \
(unsigned short) __builtin_ia32_vec_ext_v8hi (__H, 0); \
}))
#define _mm_cvtps_ph(A, I) \
((__m128i) __builtin_ia32_vcvtps2ph ((__v4sf)(__m128) A, (int) (I)))
#define _mm256_cvtps_ph(A, I) \
((__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf)(__m256) A, (int) (I)))
#endif /* __OPTIMIZE */
#endif /* _F16CINTRIN_H_INCLUDED */
#endif /* __F16C__ */
|
