xref: /third_party/ffmpeg/libavutil/float_dsp.c (revision cabdff1a) 
1/*
2 * Copyright 2005 Balatoni Denes
3 * Copyright 2006 Loren Merritt
4 *
5 * This file is part of FFmpeg.
6 *
7 * FFmpeg is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
11 *
12 * FFmpeg is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
15 * Lesser General Public License for more details.
16 *
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with FFmpeg; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 */
21
22#include "config.h"
23#include "attributes.h"
24#include "float_dsp.h"
25#include "mem.h"
26
27static void vector_fmul_c(float *dst, const float *src0, const float *src1,
28                          int len)
29{
30    int i;
31    for (i = 0; i < len; i++)
32        dst[i] = src0[i] * src1[i];
33}
34
35static void vector_dmul_c(double *dst, const double *src0, const double *src1,
36                          int len)
37{
38    int i;
39    for (i = 0; i < len; i++)
40        dst[i] = src0[i] * src1[i];
41}
42
43static void vector_fmac_scalar_c(float *dst, const float *src, float mul,
44                                 int len)
45{
46    int i;
47    for (i = 0; i < len; i++)
48        dst[i] += src[i] * mul;
49}
50
51static void vector_dmac_scalar_c(double *dst, const double *src, double mul,
52                                 int len)
53{
54    int i;
55    for (i = 0; i < len; i++)
56        dst[i] += src[i] * mul;
57}
58
59static void vector_fmul_scalar_c(float *dst, const float *src, float mul,
60                                 int len)
61{
62    int i;
63    for (i = 0; i < len; i++)
64        dst[i] = src[i] * mul;
65}
66
67static void vector_dmul_scalar_c(double *dst, const double *src, double mul,
68                                 int len)
69{
70    int i;
71    for (i = 0; i < len; i++)
72        dst[i] = src[i] * mul;
73}
74
75static void vector_fmul_window_c(float *dst, const float *src0,
76                                 const float *src1, const float *win, int len)
77{
78    int i, j;
79
80    dst  += len;
81    win  += len;
82    src0 += len;
83
84    for (i = -len, j = len - 1; i < 0; i++, j--) {
85        float s0 = src0[i];
86        float s1 = src1[j];
87        float wi = win[i];
88        float wj = win[j];
89        dst[i] = s0 * wj - s1 * wi;
90        dst[j] = s0 * wi + s1 * wj;
91    }
92}
93
94static void vector_fmul_add_c(float *dst, const float *src0, const float *src1,
95                              const float *src2, int len){
96    int i;
97
98    for (i = 0; i < len; i++)
99        dst[i] = src0[i] * src1[i] + src2[i];
100}
101
102static void vector_fmul_reverse_c(float *dst, const float *src0,
103                                  const float *src1, int len)
104{
105    int i;
106
107    src1 += len-1;
108    for (i = 0; i < len; i++)
109        dst[i] = src0[i] * src1[-i];
110}
111
112static void butterflies_float_c(float *av_restrict v1, float *av_restrict v2,
113                                int len)
114{
115    int i;
116
117    for (i = 0; i < len; i++) {
118        float t = v1[i] - v2[i];
119        v1[i] += v2[i];
120        v2[i] = t;
121    }
122}
123
124float avpriv_scalarproduct_float_c(const float *v1, const float *v2, int len)
125{
126    float p = 0.0;
127    int i;
128
129    for (i = 0; i < len; i++)
130        p += v1[i] * v2[i];
131
132    return p;
133}
134
135av_cold AVFloatDSPContext *avpriv_float_dsp_alloc(int bit_exact)
136{
137    AVFloatDSPContext *fdsp = av_mallocz(sizeof(AVFloatDSPContext));
138    if (!fdsp)
139        return NULL;
140
141    fdsp->vector_fmul = vector_fmul_c;
142    fdsp->vector_dmul = vector_dmul_c;
143    fdsp->vector_fmac_scalar = vector_fmac_scalar_c;
144    fdsp->vector_fmul_scalar = vector_fmul_scalar_c;
145    fdsp->vector_dmac_scalar = vector_dmac_scalar_c;
146    fdsp->vector_dmul_scalar = vector_dmul_scalar_c;
147    fdsp->vector_fmul_window = vector_fmul_window_c;
148    fdsp->vector_fmul_add = vector_fmul_add_c;
149    fdsp->vector_fmul_reverse = vector_fmul_reverse_c;
150    fdsp->butterflies_float = butterflies_float_c;
151    fdsp->scalarproduct_float = avpriv_scalarproduct_float_c;
152
153#if ARCH_AARCH64
154    ff_float_dsp_init_aarch64(fdsp);
155#elif ARCH_ARM
156    ff_float_dsp_init_arm(fdsp);
157#elif ARCH_PPC
158    ff_float_dsp_init_ppc(fdsp, bit_exact);
159#elif ARCH_X86
160    ff_float_dsp_init_x86(fdsp);
161#elif ARCH_MIPS
162    ff_float_dsp_init_mips(fdsp);
163#endif
164    return fdsp;
165}
166