xref: /third_party/ffmpeg/libavutil/fixed_dsp.c (revision cabdff1a)
1/*
2 * Copyright (c) 2012
3 *      MIPS Technologies, Inc., California.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 * 3. Neither the name of the MIPS Technologies, Inc., nor the names of its
14 *    contributors may be used to endorse or promote products derived from
15 *    this software without specific prior written permission.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE MIPS TECHNOLOGIES, INC. ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED.  IN NO EVENT SHALL THE MIPS TECHNOLOGIES, INC. BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * SUCH DAMAGE.
28 *
29 * Author:  Nedeljko Babic (nedeljko.babic imgtec com)
30 *
31 * This file is part of FFmpeg.
32 *
33 * FFmpeg is free software; you can redistribute it and/or
34 * modify it under the terms of the GNU Lesser General Public
35 * License as published by the Free Software Foundation; either
36 * version 2.1 of the License, or (at your option) any later version.
37 *
38 * FFmpeg is distributed in the hope that it will be useful,
39 * but WITHOUT ANY WARRANTY; without even the implied warranty of
40 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
41 * Lesser General Public License for more details.
42 *
43 * You should have received a copy of the GNU Lesser General Public
44 * License along with FFmpeg; if not, write to the Free Software
45 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
46 */
47
48#include "common.h"
49#include "fixed_dsp.h"
50
51static void vector_fmul_add_c(int *dst, const int *src0, const int *src1, const int *src2, int len){
52    int i;
53    int64_t accu;
54
55    for (i=0; i<len; i++) {
56        accu = (int64_t)src0[i] * src1[i];
57        dst[i] = src2[i] + (int)((accu + 0x40000000) >> 31);
58    }
59}
60
61static void vector_fmul_reverse_c(int *dst, const int *src0, const int *src1, int len)
62{
63    int i;
64    int64_t accu;
65
66    src1 += len-1;
67    for (i=0; i<len; i++) {
68        accu = (int64_t)src0[i] * src1[-i];
69        dst[i] = (int)((accu+0x40000000) >> 31);
70    }
71}
72
73static void vector_fmul_window_scaled_c(int16_t *dst, const int32_t *src0,
74                                       const int32_t *src1, const int32_t *win,
75                                       int len, uint8_t bits)
76{
77    int32_t s0, s1, wi, wj, i,j, round;
78
79    dst += len;
80    win += len;
81    src0+= len;
82    round = bits? 1 << (bits-1) : 0;
83
84    for (i=-len, j=len-1; i<0; i++, j--) {
85        s0 = src0[i];
86        s1 = src1[j];
87        wi = win[i];
88        wj = win[j];
89        dst[i] = av_clip_int16(((((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31) + round) >> bits);
90        dst[j] = av_clip_int16(((((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31) + round) >> bits);
91    }
92}
93
94static void vector_fmul_window_c(int32_t *dst, const int32_t *src0,
95                                       const int32_t *src1, const int32_t *win,
96                                       int len)
97{
98    int32_t s0, s1, wi, wj, i, j;
99
100    dst += len;
101    win += len;
102    src0+= len;
103
104    for (i=-len, j=len-1; i<0; i++, j--) {
105        s0 = src0[i];
106        s1 = src1[j];
107        wi = win[i];
108        wj = win[j];
109        dst[i] = ((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31;
110        dst[j] = ((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31;
111    }
112}
113
114static void vector_fmul_c(int *dst, const int *src0, const int *src1, int len)
115{
116    int i;
117    int64_t accu;
118
119    for (i = 0; i < len; i++){
120        accu = (int64_t)src0[i] * src1[i];
121        dst[i] = (int)((accu+0x40000000) >> 31);
122    }
123}
124
125static int scalarproduct_fixed_c(const int *v1, const int *v2, int len)
126{
127    /** p is initialized with 0x40000000 so that the proper rounding will occur
128      * at the end */
129    int64_t p = 0x40000000;
130    int i;
131
132    for (i = 0; i < len; i++)
133        p += (int64_t)v1[i] * v2[i];
134
135    return (int)(p >> 31);
136}
137
138static void butterflies_fixed_c(int *v1s, int *v2, int len)
139{
140    int i;
141    unsigned int *v1 = v1s;
142
143    for (i = 0; i < len; i++){
144        int t = v1[i] - v2[i];
145        v1[i] += v2[i];
146        v2[i] = t;
147    }
148}
149
150AVFixedDSPContext * avpriv_alloc_fixed_dsp(int bit_exact)
151{
152    AVFixedDSPContext * fdsp = av_malloc(sizeof(AVFixedDSPContext));
153
154    if (!fdsp)
155        return NULL;
156
157    fdsp->vector_fmul_window_scaled = vector_fmul_window_scaled_c;
158    fdsp->vector_fmul_window = vector_fmul_window_c;
159    fdsp->vector_fmul = vector_fmul_c;
160    fdsp->vector_fmul_add = vector_fmul_add_c;
161    fdsp->vector_fmul_reverse = vector_fmul_reverse_c;
162    fdsp->butterflies_fixed = butterflies_fixed_c;
163    fdsp->scalarproduct_fixed = scalarproduct_fixed_c;
164
165#if ARCH_X86
166    ff_fixed_dsp_init_x86(fdsp);
167#endif
168
169    return fdsp;
170}
171