551197d37ee1383b61babb04bdd29775e72881e3
[libav.git] / libavcodec / h264idct.c
1 /*
2 * H.264 IDCT
3 * Copyright (c) 2004 Michael Niedermayer <michaelni@gmx.at>
4 *
5 * This library is free software; you can redistribute it and/or
6 * modify it under the terms of the GNU Lesser General Public
7 * License as published by the Free Software Foundation; either
8 * version 2 of the License, or (at your option) any later version.
9 *
10 * This library is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * Lesser General Public License for more details.
14 *
15 * You should have received a copy of the GNU Lesser General Public
16 * License along with this library; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
18 *
19 */
20
21 /**
22 * @file h264-idct.c
23 * H.264 IDCT.
24 * @author Michael Niedermayer <michaelni@gmx.at>
25 */
26
27 #include "dsputil.h"
28
29 static always_inline void idct_internal(uint8_t *dst, DCTELEM *block, int stride, int block_stride, int shift, int add){
30 int i;
31 uint8_t *cm = cropTbl + MAX_NEG_CROP;
32
33 block[0] += 1<<(shift-1);
34
35 for(i=0; i<4; i++){
36 const int z0= block[0 + block_stride*i] + block[2 + block_stride*i];
37 const int z1= block[0 + block_stride*i] - block[2 + block_stride*i];
38 const int z2= (block[1 + block_stride*i]>>1) - block[3 + block_stride*i];
39 const int z3= block[1 + block_stride*i] + (block[3 + block_stride*i]>>1);
40
41 block[0 + block_stride*i]= z0 + z3;
42 block[1 + block_stride*i]= z1 + z2;
43 block[2 + block_stride*i]= z1 - z2;
44 block[3 + block_stride*i]= z0 - z3;
45 }
46
47 for(i=0; i<4; i++){
48 const int z0= block[i + block_stride*0] + block[i + block_stride*2];
49 const int z1= block[i + block_stride*0] - block[i + block_stride*2];
50 const int z2= (block[i + block_stride*1]>>1) - block[i + block_stride*3];
51 const int z3= block[i + block_stride*1] + (block[i + block_stride*3]>>1);
52
53 dst[i + 0*stride]= cm[ add*dst[i + 0*stride] + ((z0 + z3) >> shift) ];
54 dst[i + 1*stride]= cm[ add*dst[i + 1*stride] + ((z1 + z2) >> shift) ];
55 dst[i + 2*stride]= cm[ add*dst[i + 2*stride] + ((z1 - z2) >> shift) ];
56 dst[i + 3*stride]= cm[ add*dst[i + 3*stride] + ((z0 - z3) >> shift) ];
57 }
58 }
59
60 void ff_h264_idct_add_c(uint8_t *dst, DCTELEM *block, int stride){
61 idct_internal(dst, block, stride, 4, 6, 1);
62 }
63
64 void ff_h264_lowres_idct_add_c(uint8_t *dst, int stride, DCTELEM *block){
65 idct_internal(dst, block, stride, 8, 3, 1);
66 }
67
68 void ff_h264_lowres_idct_put_c(uint8_t *dst, int stride, DCTELEM *block){
69 idct_internal(dst, block, stride, 8, 3, 0);
70 }