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
|
/*===---- smmintrin.h - Implementation of SSE4 intrinsics on PowerPC -------===
*
* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
* See https://llvm.org/LICENSE.txt for license information.
* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
*
*===-----------------------------------------------------------------------===
*/
/* Implemented from the specification included in the Intel C++ Compiler
User Guide and Reference, version 9.0.
NOTE: This is NOT a complete implementation of the SSE4 intrinsics! */
#ifndef NO_WARN_X86_INTRINSICS
/* This header is distributed to simplify porting x86_64 code that
makes explicit use of Intel intrinsics to powerp64/powerpc64le.
It is the user's responsibility to determine if the results are
acceptable and make additional changes as necessary.
Note that much code that uses Intel intrinsics can be rewritten in
standard C or GNU C extensions, which are more portable and better
optimized across multiple targets. */
#error \
"Please read comment above. Use -DNO_WARN_X86_INTRINSICS to disable this error."
#endif
#ifndef SMMINTRIN_H_
#define SMMINTRIN_H_
#if defined(__linux__) && defined(__ppc64__)
#include <altivec.h>
#include <emmintrin.h>
extern __inline int
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi8(__m128i __X, const int __N) {
return (unsigned char)((__v16qi)__X)[__N & 15];
}
extern __inline int
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi32(__m128i __X, const int __N) {
return ((__v4si)__X)[__N & 3];
}
extern __inline int
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi64(__m128i __X, const int __N) {
return ((__v2di)__X)[__N & 1];
}
extern __inline int
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_ps(__m128 __X, const int __N) {
return ((__v4si)__X)[__N & 3];
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_epi16(__m128i __A, __m128i __B, const int __imm8) {
__v16qi __charmask = vec_splats((signed char)__imm8);
__charmask = vec_gb(__charmask);
__v8hu __shortmask = (__v8hu)vec_unpackh(__charmask);
#ifdef __BIG_ENDIAN__
__shortmask = vec_reve(__shortmask);
#endif
return (__m128i)vec_sel((__v8hu)__A, (__v8hu)__B, __shortmask);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_epi8(__m128i __A, __m128i __B, __m128i __mask) {
const __v16qu __seven = vec_splats((unsigned char)0x07);
__v16qu __lmask = vec_sra((__v16qu)__mask, __seven);
return (__m128i)vec_sel((__v16qu)__A, (__v16qu)__B, __lmask);
}
#else
#include_next <smmintrin.h>
#endif /* defined(__linux__) && defined(__ppc64__) */
#endif /* _SMMINTRIN_H_ */
|
