1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
|
/*
* Copyright (C) 2009 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*------------------------------------------------------------------------------
Table of contents
1. Include headers
2. External compiler flags
3. Module defines
4. Local function prototypes
5. Functions
h264bsdWriteMacroblock
h264bsdWriteOutputBlocks
------------------------------------------------------------------------------*/
/*------------------------------------------------------------------------------
1. Include headers
------------------------------------------------------------------------------*/
#include "h264bsd_image.h"
#include "h264bsd_util.h"
#include "h264bsd_neighbour.h"
/*------------------------------------------------------------------------------
2. External compiler flags
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
3. Module defines
------------------------------------------------------------------------------*/
/* x- and y-coordinates for each block, defined in h264bsd_intra_prediction.c */
extern const u32 h264bsdBlockX[];
extern const u32 h264bsdBlockY[];
/* clipping table, defined in h264bsd_intra_prediction.c */
extern const u8 h264bsdClip[];
/*------------------------------------------------------------------------------
4. Local function prototypes
------------------------------------------------------------------------------*/
/*------------------------------------------------------------------------------
Function: h264bsdWriteMacroblock
Functional description:
Write one macroblock into the image. Both luma and chroma
components will be written at the same time.
Inputs:
data pointer to macroblock data to be written, 256 values for
luma followed by 64 values for both chroma components
Outputs:
image pointer to the image where the macroblock will be written
Returns:
none
------------------------------------------------------------------------------*/
#ifndef H264DEC_NEON
void h264bsdWriteMacroblock(image_t *image, u8 *data)
{
/* Variables */
u32 i;
u32 width;
u32 *lum, *cb, *cr;
u32 *ptr;
u32 tmp1, tmp2;
/* Code */
ASSERT(image);
ASSERT(data);
ASSERT(!((u32)data&0x3));
width = image->width;
/*lint -save -e826 lum, cb and cr used to copy 4 bytes at the time, disable
* "area too small" info message */
lum = (u32*)image->luma;
cb = (u32*)image->cb;
cr = (u32*)image->cr;
ASSERT(!((u32)lum&0x3));
ASSERT(!((u32)cb&0x3));
ASSERT(!((u32)cr&0x3));
ptr = (u32*)data;
width *= 4;
for (i = 16; i ; i--)
{
tmp1 = *ptr++;
tmp2 = *ptr++;
*lum++ = tmp1;
*lum++ = tmp2;
tmp1 = *ptr++;
tmp2 = *ptr++;
*lum++ = tmp1;
*lum++ = tmp2;
lum += width-4;
}
width >>= 1;
for (i = 8; i ; i--)
{
tmp1 = *ptr++;
tmp2 = *ptr++;
*cb++ = tmp1;
*cb++ = tmp2;
cb += width-2;
}
for (i = 8; i ; i--)
{
tmp1 = *ptr++;
tmp2 = *ptr++;
*cr++ = tmp1;
*cr++ = tmp2;
cr += width-2;
}
}
#endif
#ifndef H264DEC_OMXDL
/*------------------------------------------------------------------------------
Function: h264bsdWriteOutputBlocks
Functional description:
Write one macroblock into the image. Prediction for the macroblock
and the residual are given separately and will be combined while
writing the data to the image
Inputs:
data pointer to macroblock prediction data, 256 values for
luma followed by 64 values for both chroma components
mbNum number of the macroblock
residual pointer to residual data, 16 16-element arrays for luma
followed by 4 16-element arrays for both chroma
components
Outputs:
image pointer to the image where the data will be written
Returns:
none
------------------------------------------------------------------------------*/
void h264bsdWriteOutputBlocks(image_t *image, u32 mbNum, u8 *data,
i32 residual[][16])
{
/* Variables */
u32 i;
u32 picWidth, picSize;
u8 *lum, *cb, *cr;
u8 *imageBlock;
u8 *tmp;
u32 row, col;
u32 block;
u32 x, y;
i32 *pRes;
i32 tmp1, tmp2, tmp3, tmp4;
const u8 *clp = h264bsdClip + 512;
/* Code */
ASSERT(image);
ASSERT(data);
ASSERT(mbNum < image->width * image->height);
ASSERT(!((u32)data&0x3));
/* Image size in macroblocks */
picWidth = image->width;
picSize = picWidth * image->height;
row = mbNum / picWidth;
col = mbNum % picWidth;
/* Output macroblock position in output picture */
lum = (image->data + row * picWidth * 256 + col * 16);
cb = (image->data + picSize * 256 + row * picWidth * 64 + col * 8);
cr = (cb + picSize * 64);
picWidth *= 16;
for (block = 0; block < 16; block++)
{
x = h264bsdBlockX[block];
y = h264bsdBlockY[block];
pRes = residual[block];
ASSERT(pRes);
tmp = data + y*16 + x;
imageBlock = lum + y*picWidth + x;
ASSERT(!((u32)tmp&0x3));
ASSERT(!((u32)imageBlock&0x3));
if (IS_RESIDUAL_EMPTY(pRes))
{
/*lint -e826 */
i32 *in32 = (i32*)tmp;
i32 *out32 = (i32*)imageBlock;
/* Residual is zero => copy prediction block to output */
tmp1 = *in32; in32 += 4;
tmp2 = *in32; in32 += 4;
*out32 = tmp1; out32 += picWidth/4;
*out32 = tmp2; out32 += picWidth/4;
tmp1 = *in32; in32 += 4;
tmp2 = *in32;
*out32 = tmp1; out32 += picWidth/4;
*out32 = tmp2;
}
else
{
RANGE_CHECK_ARRAY(pRes, -512, 511, 16);
/* Calculate image = prediction + residual
* Process four pixels in a loop */
for (i = 4; i; i--)
{
tmp1 = tmp[0];
tmp2 = *pRes++;
tmp3 = tmp[1];
tmp1 = clp[tmp1 + tmp2];
tmp4 = *pRes++;
imageBlock[0] = (u8)tmp1;
tmp3 = clp[tmp3 + tmp4];
tmp1 = tmp[2];
tmp2 = *pRes++;
imageBlock[1] = (u8)tmp3;
tmp1 = clp[tmp1 + tmp2];
tmp3 = tmp[3];
tmp4 = *pRes++;
imageBlock[2] = (u8)tmp1;
tmp3 = clp[tmp3 + tmp4];
tmp += 16;
imageBlock[3] = (u8)tmp3;
imageBlock += picWidth;
}
}
}
picWidth /= 2;
for (block = 16; block <= 23; block++)
{
x = h264bsdBlockX[block & 0x3];
y = h264bsdBlockY[block & 0x3];
pRes = residual[block];
ASSERT(pRes);
tmp = data + 256;
imageBlock = cb;
if (block >= 20)
{
imageBlock = cr;
tmp += 64;
}
tmp += y*8 + x;
imageBlock += y*picWidth + x;
ASSERT(!((u32)tmp&0x3));
ASSERT(!((u32)imageBlock&0x3));
if (IS_RESIDUAL_EMPTY(pRes))
{
/*lint -e826 */
i32 *in32 = (i32*)tmp;
i32 *out32 = (i32*)imageBlock;
/* Residual is zero => copy prediction block to output */
tmp1 = *in32; in32 += 2;
tmp2 = *in32; in32 += 2;
*out32 = tmp1; out32 += picWidth/4;
*out32 = tmp2; out32 += picWidth/4;
tmp1 = *in32; in32 += 2;
tmp2 = *in32;
*out32 = tmp1; out32 += picWidth/4;
*out32 = tmp2;
}
else
{
RANGE_CHECK_ARRAY(pRes, -512, 511, 16);
for (i = 4; i; i--)
{
tmp1 = tmp[0];
tmp2 = *pRes++;
tmp3 = tmp[1];
tmp1 = clp[tmp1 + tmp2];
tmp4 = *pRes++;
imageBlock[0] = (u8)tmp1;
tmp3 = clp[tmp3 + tmp4];
tmp1 = tmp[2];
tmp2 = *pRes++;
imageBlock[1] = (u8)tmp3;
tmp1 = clp[tmp1 + tmp2];
tmp3 = tmp[3];
tmp4 = *pRes++;
imageBlock[2] = (u8)tmp1;
tmp3 = clp[tmp3 + tmp4];
tmp += 8;
imageBlock[3] = (u8)tmp3;
imageBlock += picWidth;
}
}
}
}
#endif /* H264DEC_OMXDL */
|
