3 * Copyright (c) 2004 Michael Niedermayer <michaelni@gmx.at>
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.
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.
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
24 * @author Michael Niedermayer <michaelni@gmx.at>
29 static always_inline void idct_internal(uint8_t *dst, DCTELEM *block, int stride, int block_stride, int shift, int add){
31 uint8_t *cm = cropTbl + MAX_NEG_CROP;
33 block[0] += 1<<(shift-1);
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);
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;
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);
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) ];
60 void ff_h264_idct_add_c(uint8_t *dst, DCTELEM *block, int stride){
61 idct_internal(dst, block, stride, 4, 6, 1);
64 void ff_h264_lowres_idct_add_c(uint8_t *dst, int stride, DCTELEM *block){
65 idct_internal(dst, block, stride, 8, 3, 1);
68 void ff_h264_lowres_idct_put_c(uint8_t *dst, int stride, DCTELEM *block){
69 idct_internal(dst, block, stride, 8, 3, 0);