forked from HiFi-LoFi/FFTConvolver
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathUtilities.cpp
117 lines (106 loc) · 4.04 KB
/
Utilities.cpp
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
// ==================================================================================
// Copyright (c) 2017 HiFi-LoFi
//
// 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.
// ==================================================================================
#include "Utilities.h"
namespace fftconvolver
{
bool SSEEnabled()
{
#if defined(FFTCONVOLVER_USE_SSE)
return true;
#else
return false;
#endif
}
void Sum(Sample* FFTCONVOLVER_RESTRICT result,
const Sample* FFTCONVOLVER_RESTRICT a,
const Sample* FFTCONVOLVER_RESTRICT b,
size_t len)
{
const size_t end4 = 4 * (len / 4);
for (size_t i=0; i<end4; i+=4)
{
result[i+0] = a[i+0] + b[i+0];
result[i+1] = a[i+1] + b[i+1];
result[i+2] = a[i+2] + b[i+2];
result[i+3] = a[i+3] + b[i+3];
}
for (size_t i=end4; i<len; ++i)
{
result[i] = a[i] + b[i];
}
}
void ComplexMultiplyAccumulate(SplitComplex& result, const SplitComplex& a, const SplitComplex& b)
{
assert(result.size() == a.size());
assert(result.size() == b.size());
ComplexMultiplyAccumulate(result.re(), result.im(), a.re(), a.im(), b.re(), b.im(), result.size());
}
void ComplexMultiplyAccumulate(Sample* FFTCONVOLVER_RESTRICT re,
Sample* FFTCONVOLVER_RESTRICT im,
const Sample* FFTCONVOLVER_RESTRICT reA,
const Sample* FFTCONVOLVER_RESTRICT imA,
const Sample* FFTCONVOLVER_RESTRICT reB,
const Sample* FFTCONVOLVER_RESTRICT imB,
const size_t len)
{
#if defined(FFTCONVOLVER_USE_SSE)
const size_t end4 = 4 * (len / 4);
for (size_t i=0; i<end4; i+=4)
{
const __m128 ra = _mm_load_ps(&reA[i]);
const __m128 rb = _mm_load_ps(&reB[i]);
const __m128 ia = _mm_load_ps(&imA[i]);
const __m128 ib = _mm_load_ps(&imB[i]);
__m128 real = _mm_load_ps(&re[i]);
__m128 imag = _mm_load_ps(&im[i]);
real = _mm_add_ps(real, _mm_mul_ps(ra, rb));
real = _mm_sub_ps(real, _mm_mul_ps(ia, ib));
_mm_store_ps(&re[i], real);
imag = _mm_add_ps(imag, _mm_mul_ps(ra, ib));
imag = _mm_add_ps(imag, _mm_mul_ps(ia, rb));
_mm_store_ps(&im[i], imag);
}
for (size_t i=end4; i<len; ++i)
{
re[i] += reA[i] * reB[i] - imA[i] * imB[i];
im[i] += reA[i] * imB[i] + imA[i] * reB[i];
}
#else
const size_t end4 = 4 * (len / 4);
for (size_t i=0; i<end4; i+=4)
{
re[i+0] += reA[i+0] * reB[i+0] - imA[i+0] * imB[i+0];
re[i+1] += reA[i+1] * reB[i+1] - imA[i+1] * imB[i+1];
re[i+2] += reA[i+2] * reB[i+2] - imA[i+2] * imB[i+2];
re[i+3] += reA[i+3] * reB[i+3] - imA[i+3] * imB[i+3];
im[i+0] += reA[i+0] * imB[i+0] + imA[i+0] * reB[i+0];
im[i+1] += reA[i+1] * imB[i+1] + imA[i+1] * reB[i+1];
im[i+2] += reA[i+2] * imB[i+2] + imA[i+2] * reB[i+2];
im[i+3] += reA[i+3] * imB[i+3] + imA[i+3] * reB[i+3];
}
for (size_t i=end4; i<len; ++i)
{
re[i] += reA[i] * reB[i] - imA[i] * imB[i];
im[i] += reA[i] * imB[i] + imA[i] * reB[i];
}
#endif
}
} // End of namespace fftconvolver