blob: 8c018581df8339c7b4f451818f284dfc4efd7a31
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 "fixed_dsp.h" |
49 | |
50 | static void vector_fmul_add_c(int *dst, const int *src0, const int *src1, const int *src2, int len){ |
51 | int i; |
52 | int64_t accu; |
53 | |
54 | for (i=0; i<len; i++) { |
55 | accu = (int64_t)src0[i] * src1[i]; |
56 | dst[i] = src2[i] + (int)((accu + 0x40000000) >> 31); |
57 | } |
58 | } |
59 | |
60 | static void vector_fmul_reverse_c(int *dst, const int *src0, const int *src1, int len) |
61 | { |
62 | int i; |
63 | int64_t accu; |
64 | |
65 | src1 += len-1; |
66 | for (i=0; i<len; i++) { |
67 | accu = (int64_t)src0[i] * src1[-i]; |
68 | dst[i] = (int)((accu+0x40000000) >> 31); |
69 | } |
70 | } |
71 | |
72 | static void vector_fmul_window_scaled_c(int16_t *dst, const int32_t *src0, |
73 | const int32_t *src1, const int32_t *win, |
74 | int len, uint8_t bits) |
75 | { |
76 | int32_t s0, s1, wi, wj, i,j, round; |
77 | |
78 | dst += len; |
79 | win += len; |
80 | src0+= len; |
81 | round = bits? 1 << (bits-1) : 0; |
82 | |
83 | for (i=-len, j=len-1; i<0; i++, j--) { |
84 | s0 = src0[i]; |
85 | s1 = src1[j]; |
86 | wi = win[i]; |
87 | wj = win[j]; |
88 | dst[i] = av_clip_int16(((((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31) + round) >> bits); |
89 | dst[j] = av_clip_int16(((((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31) + round) >> bits); |
90 | } |
91 | } |
92 | |
93 | static void vector_fmul_window_c(int32_t *dst, const int32_t *src0, |
94 | const int32_t *src1, const int32_t *win, |
95 | int len) |
96 | { |
97 | int32_t s0, s1, wi, wj, i, j; |
98 | |
99 | dst += len; |
100 | win += len; |
101 | src0+= len; |
102 | |
103 | for (i=-len, j=len-1; i<0; i++, j--) { |
104 | s0 = src0[i]; |
105 | s1 = src1[j]; |
106 | wi = win[i]; |
107 | wj = win[j]; |
108 | dst[i] = ((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31; |
109 | dst[j] = ((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31; |
110 | } |
111 | } |
112 | |
113 | static void vector_fmul_c(int *dst, const int *src0, const int *src1, int len) |
114 | { |
115 | int i; |
116 | int64_t accu; |
117 | |
118 | for (i = 0; i < len; i++){ |
119 | accu = (int64_t)src0[i] * src1[i]; |
120 | dst[i] = (int)((accu+0x40000000) >> 31); |
121 | } |
122 | } |
123 | |
124 | static int scalarproduct_fixed_c(const int *v1, const int *v2, int len) |
125 | { |
126 | /** p is initialized with 0x40000000 so that the proper rounding will occur |
127 | * at the end */ |
128 | int64_t p = 0x40000000; |
129 | int i; |
130 | |
131 | for (i = 0; i < len; i++) |
132 | p += (int64_t)v1[i] * v2[i]; |
133 | |
134 | return (int)(p >> 31); |
135 | } |
136 | |
137 | static void butterflies_fixed_c(int *v1, int *v2, int len) |
138 | { |
139 | int i; |
140 | |
141 | for (i = 0; i < len; i++){ |
142 | int t = v1[i] - v2[i]; |
143 | v1[i] += v2[i]; |
144 | v2[i] = t; |
145 | } |
146 | } |
147 | |
148 | AVFixedDSPContext * avpriv_alloc_fixed_dsp(int bit_exact) |
149 | { |
150 | AVFixedDSPContext * fdsp = av_malloc(sizeof(AVFixedDSPContext)); |
151 | |
152 | if (!fdsp) |
153 | return NULL; |
154 | |
155 | fdsp->vector_fmul_window_scaled = vector_fmul_window_scaled_c; |
156 | fdsp->vector_fmul_window = vector_fmul_window_c; |
157 | fdsp->vector_fmul = vector_fmul_c; |
158 | fdsp->vector_fmul_add = vector_fmul_add_c; |
159 | fdsp->vector_fmul_reverse = vector_fmul_reverse_c; |
160 | fdsp->butterflies_fixed = butterflies_fixed_c; |
161 | fdsp->scalarproduct_fixed = scalarproduct_fixed_c; |
162 | |
163 | if (ARCH_X86) |
164 | ff_fixed_dsp_init_x86(fdsp); |
165 | |
166 | return fdsp; |
167 | } |
168 |