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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
/*
* Simd Library (http://ermig1979.github.io/Simd).
*
* Copyright (c) 2011-2022 Yermalayeu Ihar.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef __SimdSet_h__
#define __SimdSet_h__
#include "Simd/SimdDefs.h"
#include "Simd/SimdConst.h"
namespace Simd
{
#ifdef SIMD_SSE41_ENABLE
namespace Sse41
{
SIMD_INLINE __m128i SetInt8(char a0, char a1)
{
return _mm_unpacklo_epi8(_mm_set1_epi8(a0), _mm_set1_epi8(a1));
}
SIMD_INLINE __m128i SetInt16(short a0, short a1)
{
return _mm_unpacklo_epi16(_mm_set1_epi16(a0), _mm_set1_epi16(a1));
}
SIMD_INLINE __m128i SetInt32(int a0, int a1)
{
return _mm_unpacklo_epi32(_mm_set1_epi32(a0), _mm_set1_epi32(a1));
}
SIMD_INLINE __m128 SetFloat(float a0, float a1)
{
return _mm_unpacklo_ps(_mm_set_ps1(a0), _mm_set_ps1(a1));
}
}
#endif// SIMD_SSE41_ENABLE
#ifdef SIMD_AVX_ENABLE
namespace Avx
{
SIMD_INLINE __m256 Set(__m128 a0, __m128 a1)
{
return _mm256_insertf128_ps(_mm256_castps128_ps256(a0), a1, 1);
}
SIMD_INLINE __m256 Set(__m128 a)
{
return _mm256_insertf128_ps(_mm256_castps128_ps256(a), a, 1);
}
}
#endif// SIMD_AVX_ENABLE
#ifdef SIMD_AVX2_ENABLE
namespace Avx2
{
SIMD_INLINE __m256i SetInt8(char a0, char a1)
{
return _mm256_unpacklo_epi8(_mm256_set1_epi8(a0), _mm256_set1_epi8(a1));
}
SIMD_INLINE __m256i SetInt16(short a0, short a1)
{
return _mm256_unpacklo_epi16(_mm256_set1_epi16(a0), _mm256_set1_epi16(a1));
}
SIMD_INLINE __m256i SetInt32(int a0, int a1)
{
return _mm256_unpacklo_epi32(_mm256_set1_epi32(a0), _mm256_set1_epi32(a1));
}
SIMD_INLINE __m256 SetFloat(float a0, float a1)
{
return _mm256_unpacklo_ps(_mm256_set1_ps(a0), _mm256_set1_ps(a1));
}
SIMD_INLINE __m256i Set(__m128i a0, __m128i a1)
{
return _mm256_inserti128_si256(_mm256_castsi128_si256(a0), a1, 1);
}
SIMD_INLINE __m256i Set(__m128i a)
{
return _mm256_inserti128_si256(_mm256_castsi128_si256(a), a, 1);
}
template <class T> SIMD_INLINE __m256i SetMask(T first, size_t position, T second)
{
const size_t size = A / sizeof(T);
assert(position <= size);
T mask[size];
for (size_t i = 0; i < position; ++i)
mask[i] = first;
for (size_t i = position; i < size; ++i)
mask[i] = second;
return _mm256_loadu_si256((__m256i*)mask);
}
}
#endif// SIMD_AVX2_ENABLE
#ifdef SIMD_NEON_ENABLE
namespace Neon
{
SIMD_INLINE float32x4_t SetF32(float a0, float a1, float a2, float a3)
{
const float a[4] = { a0, a1, a2, a3 };
return vld1q_f32(a);
}
SIMD_INLINE int32x4_t SetI32(int32_t a0, int32_t a1, int32_t a2, int32_t a3)
{
const int32_t a[4] = { a0, a1, a2, a3 };
return vld1q_s32(a);
}
}
#endif// SIMD_NEON_ENABLE
}
#endif//__SimdSet_h__
|
