aboutsummaryrefslogtreecommitdiffstats
path: root/libavutil/float_dsp.c
blob: 50c9e60c321e2b2bb0acd94db4bb61e8bc1c5b0b (plain) (blame)
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
138
139
/*
 * Copyright 2005 Balatoni Denes
 * Copyright 2006 Loren Merritt
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "config.h"

#include "float_dsp.h"

static void vector_fmul_c(float *dst, const float *src0, const float *src1,
                          int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] = src0[i] * src1[i];
}

static void vector_fmac_scalar_c(float *dst, const float *src, float mul,
                                 int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] += src[i] * mul;
}

static void vector_fmul_scalar_c(float *dst, const float *src, float mul,
                                 int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] = src[i] * mul;
}

static void vector_dmul_scalar_c(double *dst, const double *src, double mul,
                                 int len)
{
    int i;
    for (i = 0; i < len; i++)
        dst[i] = src[i] * mul;
}

static void vector_fmul_window_c(float *dst, const float *src0,
                                 const float *src1, const float *win, int len)
{
    int i, j;

    dst  += len;
    win  += len;
    src0 += len;

    for (i = -len, j = len - 1; i < 0; i++, j--) {
        float s0 = src0[i];
        float s1 = src1[j];
        float wi = win[i];
        float wj = win[j];
        dst[i] = s0 * wj - s1 * wi;
        dst[j] = s0 * wi + s1 * wj;
    }
}

static void vector_fmul_add_c(float *dst, const float *src0, const float *src1,
                              const float *src2, int len){
    int i;

    for (i = 0; i < len; i++)
        dst[i] = src0[i] * src1[i] + src2[i];
}

static void vector_fmul_reverse_c(float *dst, const float *src0,
                                  const float *src1, int len)
{
    int i;

    src1 += len-1;
    for (i = 0; i < len; i++)
        dst[i] = src0[i] * src1[-i];
}

static void butterflies_float_c(float *restrict v1, float *restrict v2,
                                int len)
{
    int i;

    for (i = 0; i < len; i++) {
        float t = v1[i] - v2[i];
        v1[i] += v2[i];
        v2[i] = t;
    }
}

float avpriv_scalarproduct_float_c(const float *v1, const float *v2, int len)
{
    float p = 0.0;
    int i;

    for (i = 0; i < len; i++)
        p += v1[i] * v2[i];

    return p;
}

void avpriv_float_dsp_init(AVFloatDSPContext *fdsp, int bit_exact)
{
    fdsp->vector_fmul = vector_fmul_c;
    fdsp->vector_fmac_scalar = vector_fmac_scalar_c;
    fdsp->vector_fmul_scalar = vector_fmul_scalar_c;
    fdsp->vector_dmul_scalar = vector_dmul_scalar_c;
    fdsp->vector_fmul_window = vector_fmul_window_c;
    fdsp->vector_fmul_add = vector_fmul_add_c;
    fdsp->vector_fmul_reverse = vector_fmul_reverse_c;
    fdsp->butterflies_float = butterflies_float_c;
    fdsp->scalarproduct_float = avpriv_scalarproduct_float_c;

#if ARCH_ARM
    ff_float_dsp_init_arm(fdsp);
#elif ARCH_PPC
    ff_float_dsp_init_ppc(fdsp, bit_exact);
#elif ARCH_X86
    ff_float_dsp_init_x86(fdsp);
#elif ARCH_MIPS
    ff_float_dsp_init_mips(fdsp);
#endif
}