FFmpeg
h264_intrapred_init.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2010 Fiona Glaser <fiona@x264.com>
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include <stddef.h>
22 #include <stdint.h>
23 #include "config.h"
24 #include "libavutil/attributes.h"
25 #include "libavutil/cpu.h"
26 #include "libavutil/x86/cpu.h"
27 #include "libavcodec/codec_id.h"
28 #include "libavcodec/h264pred.h"
29 
30 #define PRED4x4(TYPE, DEPTH, OPT) \
31 void ff_pred4x4_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, \
32  const uint8_t *topright, \
33  ptrdiff_t stride);
34 
35 PRED4x4(dc, 10, mmxext)
36 PRED4x4(down_left, 10, sse2)
37 PRED4x4(down_left, 10, avx)
38 PRED4x4(down_right, 10, sse2)
39 PRED4x4(down_right, 10, ssse3)
40 PRED4x4(down_right, 10, avx)
41 PRED4x4(vertical_left, 10, sse2)
42 PRED4x4(vertical_left, 10, avx)
43 PRED4x4(vertical_right, 10, sse2)
44 PRED4x4(vertical_right, 10, ssse3)
45 PRED4x4(vertical_right, 10, avx)
46 PRED4x4(horizontal_up, 10, mmxext)
47 PRED4x4(horizontal_down, 10, sse2)
48 PRED4x4(horizontal_down, 10, ssse3)
49 PRED4x4(horizontal_down, 10, avx)
50 
51 #define PRED8x8(TYPE, DEPTH, OPT) \
52 void ff_pred8x8_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, \
53  ptrdiff_t stride);
54 
55 PRED8x8(dc, 10, mmxext)
56 PRED8x8(dc, 10, sse2)
57 PRED8x8(top_dc, 10, sse2)
58 PRED8x8(plane, 10, sse2)
59 PRED8x8(vertical, 10, sse2)
60 PRED8x8(horizontal, 10, sse2)
61 
62 #define PRED8x8L(TYPE, DEPTH, OPT)\
63 void ff_pred8x8l_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, \
64  int has_topleft, \
65  int has_topright, \
66  ptrdiff_t stride);
67 
68 PRED8x8L(dc, 10, sse2)
69 PRED8x8L(dc, 10, avx)
70 PRED8x8L(128_dc, 10, mmxext)
71 PRED8x8L(128_dc, 10, sse2)
72 PRED8x8L(top_dc, 10, sse2)
73 PRED8x8L(top_dc, 10, avx)
74 PRED8x8L(vertical, 10, sse2)
75 PRED8x8L(vertical, 10, avx)
76 PRED8x8L(horizontal, 10, sse2)
77 PRED8x8L(horizontal, 10, ssse3)
78 PRED8x8L(horizontal, 10, avx)
79 PRED8x8L(down_left, 10, sse2)
80 PRED8x8L(down_left, 10, ssse3)
81 PRED8x8L(down_left, 10, avx)
82 PRED8x8L(down_right, 10, sse2)
83 PRED8x8L(down_right, 10, ssse3)
84 PRED8x8L(down_right, 10, avx)
85 PRED8x8L(vertical_right, 10, sse2)
86 PRED8x8L(vertical_right, 10, ssse3)
87 PRED8x8L(vertical_right, 10, avx)
88 PRED8x8L(horizontal_up, 10, sse2)
89 PRED8x8L(horizontal_up, 10, ssse3)
90 PRED8x8L(horizontal_up, 10, avx)
91 
92 #define PRED16x16(TYPE, DEPTH, OPT)\
93 void ff_pred16x16_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, \
94  ptrdiff_t stride);
95 
96 PRED16x16(dc, 10, mmxext)
97 PRED16x16(dc, 10, sse2)
98 PRED16x16(top_dc, 10, mmxext)
99 PRED16x16(top_dc, 10, sse2)
100 PRED16x16(128_dc, 10, mmxext)
101 PRED16x16(128_dc, 10, sse2)
102 PRED16x16(left_dc, 10, mmxext)
103 PRED16x16(left_dc, 10, sse2)
104 PRED16x16(vertical, 10, mmxext)
105 PRED16x16(vertical, 10, sse2)
106 PRED16x16(horizontal, 10, mmxext)
107 PRED16x16(horizontal, 10, sse2)
108 
109 /* 8-bit versions */
110 PRED16x16(vertical, 8, mmx)
111 PRED16x16(vertical, 8, sse)
112 PRED16x16(horizontal, 8, mmx)
113 PRED16x16(horizontal, 8, mmxext)
114 PRED16x16(horizontal, 8, ssse3)
115 PRED16x16(dc, 8, mmxext)
116 PRED16x16(dc, 8, sse2)
117 PRED16x16(dc, 8, ssse3)
118 PRED16x16(plane_h264, 8, mmx)
119 PRED16x16(plane_h264, 8, mmxext)
120 PRED16x16(plane_h264, 8, sse2)
121 PRED16x16(plane_h264, 8, ssse3)
122 PRED16x16(plane_rv40, 8, mmx)
123 PRED16x16(plane_rv40, 8, mmxext)
124 PRED16x16(plane_rv40, 8, sse2)
125 PRED16x16(plane_rv40, 8, ssse3)
126 PRED16x16(plane_svq3, 8, mmx)
127 PRED16x16(plane_svq3, 8, mmxext)
128 PRED16x16(plane_svq3, 8, sse2)
129 PRED16x16(plane_svq3, 8, ssse3)
130 PRED16x16(tm_vp8, 8, mmx)
131 PRED16x16(tm_vp8, 8, mmxext)
132 PRED16x16(tm_vp8, 8, sse2)
133 PRED16x16(tm_vp8, 8, avx2)
134 
135 PRED8x8(top_dc, 8, mmxext)
136 PRED8x8(dc_rv40, 8, mmxext)
137 PRED8x8(dc, 8, mmxext)
138 PRED8x8(vertical, 8, mmx)
139 PRED8x8(horizontal, 8, mmx)
140 PRED8x8(horizontal, 8, mmxext)
141 PRED8x8(horizontal, 8, ssse3)
142 PRED8x8(plane, 8, mmx)
143 PRED8x8(plane, 8, mmxext)
144 PRED8x8(plane, 8, sse2)
145 PRED8x8(plane, 8, ssse3)
146 PRED8x8(tm_vp8, 8, mmx)
147 PRED8x8(tm_vp8, 8, mmxext)
148 PRED8x8(tm_vp8, 8, sse2)
149 PRED8x8(tm_vp8, 8, ssse3)
150 
151 PRED8x8L(top_dc, 8, mmxext)
152 PRED8x8L(top_dc, 8, ssse3)
153 PRED8x8L(dc, 8, mmxext)
154 PRED8x8L(dc, 8, ssse3)
155 PRED8x8L(horizontal, 8, mmxext)
156 PRED8x8L(horizontal, 8, ssse3)
157 PRED8x8L(vertical, 8, mmxext)
158 PRED8x8L(vertical, 8, ssse3)
159 PRED8x8L(down_left, 8, mmxext)
160 PRED8x8L(down_left, 8, sse2)
161 PRED8x8L(down_left, 8, ssse3)
162 PRED8x8L(down_right, 8, mmxext)
163 PRED8x8L(down_right, 8, sse2)
164 PRED8x8L(down_right, 8, ssse3)
165 PRED8x8L(vertical_right, 8, mmxext)
166 PRED8x8L(vertical_right, 8, sse2)
167 PRED8x8L(vertical_right, 8, ssse3)
168 PRED8x8L(vertical_left, 8, sse2)
169 PRED8x8L(vertical_left, 8, ssse3)
170 PRED8x8L(horizontal_up, 8, mmxext)
171 PRED8x8L(horizontal_up, 8, ssse3)
172 PRED8x8L(horizontal_down, 8, mmxext)
173 PRED8x8L(horizontal_down, 8, sse2)
174 PRED8x8L(horizontal_down, 8, ssse3)
175 
176 PRED4x4(dc, 8, mmxext)
177 PRED4x4(down_left, 8, mmxext)
178 PRED4x4(down_right, 8, mmxext)
179 PRED4x4(vertical_left, 8, mmxext)
180 PRED4x4(vertical_right, 8, mmxext)
181 PRED4x4(horizontal_up, 8, mmxext)
182 PRED4x4(horizontal_down, 8, mmxext)
183 PRED4x4(tm_vp8, 8, mmx)
184 PRED4x4(tm_vp8, 8, mmxext)
185 PRED4x4(tm_vp8, 8, ssse3)
186 PRED4x4(vertical_vp8, 8, mmxext)
187 
189  const int bit_depth,
190  const int chroma_format_idc)
191 {
192  int cpu_flags = av_get_cpu_flags();
193 
194  if (bit_depth == 8) {
195  if (EXTERNAL_MMX(cpu_flags)) {
196  h->pred16x16[VERT_PRED8x8 ] = ff_pred16x16_vertical_8_mmx;
197  h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_8_mmx;
198  if (chroma_format_idc <= 1) {
199  h->pred8x8 [VERT_PRED8x8 ] = ff_pred8x8_vertical_8_mmx;
200  h->pred8x8 [HOR_PRED8x8 ] = ff_pred8x8_horizontal_8_mmx;
201  }
203  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_tm_vp8_8_mmx;
204  h->pred8x8 [PLANE_PRED8x8 ] = ff_pred8x8_tm_vp8_8_mmx;
205  h->pred4x4 [TM_VP8_PRED ] = ff_pred4x4_tm_vp8_8_mmx;
206  } else {
207  if (chroma_format_idc <= 1)
208  h->pred8x8 [PLANE_PRED8x8] = ff_pred8x8_plane_8_mmx;
209  if (codec_id == AV_CODEC_ID_SVQ3) {
211  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_svq3_8_mmx;
212  } else if (codec_id == AV_CODEC_ID_RV40) {
213  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_rv40_8_mmx;
214  } else {
215  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_h264_8_mmx;
216  }
217  }
218  }
219 
220  if (EXTERNAL_MMXEXT(cpu_flags)) {
221  h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_8_mmxext;
222  h->pred16x16[DC_PRED8x8 ] = ff_pred16x16_dc_8_mmxext;
223  if (chroma_format_idc <= 1)
224  h->pred8x8[HOR_PRED8x8 ] = ff_pred8x8_horizontal_8_mmxext;
225  h->pred8x8l [TOP_DC_PRED ] = ff_pred8x8l_top_dc_8_mmxext;
226  h->pred8x8l [DC_PRED ] = ff_pred8x8l_dc_8_mmxext;
227  h->pred8x8l [HOR_PRED ] = ff_pred8x8l_horizontal_8_mmxext;
228  h->pred8x8l [VERT_PRED ] = ff_pred8x8l_vertical_8_mmxext;
229  h->pred8x8l [DIAG_DOWN_RIGHT_PRED ] = ff_pred8x8l_down_right_8_mmxext;
230  h->pred8x8l [VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_8_mmxext;
231  h->pred8x8l [HOR_UP_PRED ] = ff_pred8x8l_horizontal_up_8_mmxext;
232  h->pred8x8l [DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_8_mmxext;
233  h->pred8x8l [HOR_DOWN_PRED ] = ff_pred8x8l_horizontal_down_8_mmxext;
234  h->pred4x4 [DIAG_DOWN_RIGHT_PRED ] = ff_pred4x4_down_right_8_mmxext;
235  h->pred4x4 [VERT_RIGHT_PRED ] = ff_pred4x4_vertical_right_8_mmxext;
236  h->pred4x4 [HOR_DOWN_PRED ] = ff_pred4x4_horizontal_down_8_mmxext;
237  h->pred4x4 [DC_PRED ] = ff_pred4x4_dc_8_mmxext;
240  h->pred4x4 [DIAG_DOWN_LEFT_PRED] = ff_pred4x4_down_left_8_mmxext;
241  }
243  h->pred4x4 [VERT_LEFT_PRED ] = ff_pred4x4_vertical_left_8_mmxext;
244  }
245  if (codec_id != AV_CODEC_ID_RV40) {
246  h->pred4x4 [HOR_UP_PRED ] = ff_pred4x4_horizontal_up_8_mmxext;
247  }
249  if (chroma_format_idc <= 1) {
250  h->pred8x8[TOP_DC_PRED8x8 ] = ff_pred8x8_top_dc_8_mmxext;
251  h->pred8x8[DC_PRED8x8 ] = ff_pred8x8_dc_8_mmxext;
252  }
253  }
255  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_tm_vp8_8_mmxext;
256  h->pred8x8 [DC_PRED8x8 ] = ff_pred8x8_dc_rv40_8_mmxext;
257  h->pred8x8 [PLANE_PRED8x8 ] = ff_pred8x8_tm_vp8_8_mmxext;
258  h->pred4x4 [TM_VP8_PRED ] = ff_pred4x4_tm_vp8_8_mmxext;
259  h->pred4x4 [VERT_PRED ] = ff_pred4x4_vertical_vp8_8_mmxext;
260  } else {
261  if (chroma_format_idc <= 1)
262  h->pred8x8 [PLANE_PRED8x8] = ff_pred8x8_plane_8_mmxext;
263  if (codec_id == AV_CODEC_ID_SVQ3) {
264  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_plane_svq3_8_mmxext;
265  } else if (codec_id == AV_CODEC_ID_RV40) {
266  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_plane_rv40_8_mmxext;
267  } else {
268  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_plane_h264_8_mmxext;
269  }
270  }
271  }
272 
273  if (EXTERNAL_SSE(cpu_flags)) {
274  h->pred16x16[VERT_PRED8x8] = ff_pred16x16_vertical_8_sse;
275  }
276 
277  if (EXTERNAL_SSE2(cpu_flags)) {
278  h->pred16x16[DC_PRED8x8 ] = ff_pred16x16_dc_8_sse2;
279  h->pred8x8l [DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_8_sse2;
280  h->pred8x8l [DIAG_DOWN_RIGHT_PRED ] = ff_pred8x8l_down_right_8_sse2;
281  h->pred8x8l [VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_8_sse2;
282  h->pred8x8l [VERT_LEFT_PRED ] = ff_pred8x8l_vertical_left_8_sse2;
283  h->pred8x8l [HOR_DOWN_PRED ] = ff_pred8x8l_horizontal_down_8_sse2;
285  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_tm_vp8_8_sse2;
286  h->pred8x8 [PLANE_PRED8x8 ] = ff_pred8x8_tm_vp8_8_sse2;
287  } else {
288  if (chroma_format_idc <= 1)
289  h->pred8x8 [PLANE_PRED8x8] = ff_pred8x8_plane_8_sse2;
290  if (codec_id == AV_CODEC_ID_SVQ3) {
291  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_svq3_8_sse2;
292  } else if (codec_id == AV_CODEC_ID_RV40) {
293  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_rv40_8_sse2;
294  } else {
295  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_h264_8_sse2;
296  }
297  }
298  }
299 
300  if (EXTERNAL_SSSE3(cpu_flags)) {
301  h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_8_ssse3;
302  h->pred16x16[DC_PRED8x8 ] = ff_pred16x16_dc_8_ssse3;
303  if (chroma_format_idc <= 1)
304  h->pred8x8 [HOR_PRED8x8 ] = ff_pred8x8_horizontal_8_ssse3;
305  h->pred8x8l [TOP_DC_PRED ] = ff_pred8x8l_top_dc_8_ssse3;
306  h->pred8x8l [DC_PRED ] = ff_pred8x8l_dc_8_ssse3;
307  h->pred8x8l [HOR_PRED ] = ff_pred8x8l_horizontal_8_ssse3;
308  h->pred8x8l [VERT_PRED ] = ff_pred8x8l_vertical_8_ssse3;
309  h->pred8x8l [DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_8_ssse3;
310  h->pred8x8l [DIAG_DOWN_RIGHT_PRED ] = ff_pred8x8l_down_right_8_ssse3;
311  h->pred8x8l [VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_8_ssse3;
312  h->pred8x8l [VERT_LEFT_PRED ] = ff_pred8x8l_vertical_left_8_ssse3;
313  h->pred8x8l [HOR_UP_PRED ] = ff_pred8x8l_horizontal_up_8_ssse3;
314  h->pred8x8l [HOR_DOWN_PRED ] = ff_pred8x8l_horizontal_down_8_ssse3;
316  h->pred8x8 [PLANE_PRED8x8 ] = ff_pred8x8_tm_vp8_8_ssse3;
317  h->pred4x4 [TM_VP8_PRED ] = ff_pred4x4_tm_vp8_8_ssse3;
318  } else {
319  if (chroma_format_idc <= 1)
320  h->pred8x8 [PLANE_PRED8x8] = ff_pred8x8_plane_8_ssse3;
321  if (codec_id == AV_CODEC_ID_SVQ3) {
322  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_svq3_8_ssse3;
323  } else if (codec_id == AV_CODEC_ID_RV40) {
324  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_rv40_8_ssse3;
325  } else {
326  h->pred16x16[PLANE_PRED8x8] = ff_pred16x16_plane_h264_8_ssse3;
327  }
328  }
329  }
330 
332  if (codec_id == AV_CODEC_ID_VP8) {
333  h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_tm_vp8_8_avx2;
334  }
335  }
336  } else if (bit_depth == 10) {
337  if (EXTERNAL_MMXEXT(cpu_flags)) {
338  h->pred4x4[DC_PRED ] = ff_pred4x4_dc_10_mmxext;
339  h->pred4x4[HOR_UP_PRED ] = ff_pred4x4_horizontal_up_10_mmxext;
340 
341  if (chroma_format_idc <= 1)
342  h->pred8x8[DC_PRED8x8 ] = ff_pred8x8_dc_10_mmxext;
343 
344  h->pred8x8l[DC_128_PRED ] = ff_pred8x8l_128_dc_10_mmxext;
345 
346  h->pred16x16[DC_PRED8x8 ] = ff_pred16x16_dc_10_mmxext;
347  h->pred16x16[TOP_DC_PRED8x8 ] = ff_pred16x16_top_dc_10_mmxext;
348  h->pred16x16[DC_128_PRED8x8 ] = ff_pred16x16_128_dc_10_mmxext;
349  h->pred16x16[LEFT_DC_PRED8x8 ] = ff_pred16x16_left_dc_10_mmxext;
350  h->pred16x16[VERT_PRED8x8 ] = ff_pred16x16_vertical_10_mmxext;
351  h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_10_mmxext;
352  }
353  if (EXTERNAL_SSE2(cpu_flags)) {
354  h->pred4x4[DIAG_DOWN_LEFT_PRED ] = ff_pred4x4_down_left_10_sse2;
355  h->pred4x4[DIAG_DOWN_RIGHT_PRED] = ff_pred4x4_down_right_10_sse2;
356  h->pred4x4[VERT_LEFT_PRED ] = ff_pred4x4_vertical_left_10_sse2;
357  h->pred4x4[VERT_RIGHT_PRED ] = ff_pred4x4_vertical_right_10_sse2;
358  h->pred4x4[HOR_DOWN_PRED ] = ff_pred4x4_horizontal_down_10_sse2;
359 
360  if (chroma_format_idc <= 1) {
361  h->pred8x8[DC_PRED8x8 ] = ff_pred8x8_dc_10_sse2;
362  h->pred8x8[TOP_DC_PRED8x8 ] = ff_pred8x8_top_dc_10_sse2;
363  h->pred8x8[PLANE_PRED8x8 ] = ff_pred8x8_plane_10_sse2;
364  h->pred8x8[VERT_PRED8x8 ] = ff_pred8x8_vertical_10_sse2;
365  h->pred8x8[HOR_PRED8x8 ] = ff_pred8x8_horizontal_10_sse2;
366  }
367 
368  h->pred8x8l[VERT_PRED ] = ff_pred8x8l_vertical_10_sse2;
369  h->pred8x8l[HOR_PRED ] = ff_pred8x8l_horizontal_10_sse2;
370  h->pred8x8l[DC_PRED ] = ff_pred8x8l_dc_10_sse2;
371  h->pred8x8l[DC_128_PRED ] = ff_pred8x8l_128_dc_10_sse2;
372  h->pred8x8l[TOP_DC_PRED ] = ff_pred8x8l_top_dc_10_sse2;
373  h->pred8x8l[DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_10_sse2;
374  h->pred8x8l[DIAG_DOWN_RIGHT_PRED] = ff_pred8x8l_down_right_10_sse2;
375  h->pred8x8l[VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_10_sse2;
376  h->pred8x8l[HOR_UP_PRED ] = ff_pred8x8l_horizontal_up_10_sse2;
377 
378  h->pred16x16[DC_PRED8x8 ] = ff_pred16x16_dc_10_sse2;
379  h->pred16x16[TOP_DC_PRED8x8 ] = ff_pred16x16_top_dc_10_sse2;
380  h->pred16x16[DC_128_PRED8x8 ] = ff_pred16x16_128_dc_10_sse2;
381  h->pred16x16[LEFT_DC_PRED8x8 ] = ff_pred16x16_left_dc_10_sse2;
382  h->pred16x16[VERT_PRED8x8 ] = ff_pred16x16_vertical_10_sse2;
383  h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_10_sse2;
384  }
385  if (EXTERNAL_SSSE3(cpu_flags)) {
386  h->pred4x4[DIAG_DOWN_RIGHT_PRED] = ff_pred4x4_down_right_10_ssse3;
387  h->pred4x4[VERT_RIGHT_PRED ] = ff_pred4x4_vertical_right_10_ssse3;
388  h->pred4x4[HOR_DOWN_PRED ] = ff_pred4x4_horizontal_down_10_ssse3;
389 
390  h->pred8x8l[HOR_PRED ] = ff_pred8x8l_horizontal_10_ssse3;
391  h->pred8x8l[DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_10_ssse3;
392  h->pred8x8l[DIAG_DOWN_RIGHT_PRED] = ff_pred8x8l_down_right_10_ssse3;
393  h->pred8x8l[VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_10_ssse3;
394  h->pred8x8l[HOR_UP_PRED ] = ff_pred8x8l_horizontal_up_10_ssse3;
395  }
396  if (EXTERNAL_AVX(cpu_flags)) {
397  h->pred4x4[DIAG_DOWN_LEFT_PRED ] = ff_pred4x4_down_left_10_avx;
398  h->pred4x4[DIAG_DOWN_RIGHT_PRED] = ff_pred4x4_down_right_10_avx;
399  h->pred4x4[VERT_LEFT_PRED ] = ff_pred4x4_vertical_left_10_avx;
400  h->pred4x4[VERT_RIGHT_PRED ] = ff_pred4x4_vertical_right_10_avx;
401  h->pred4x4[HOR_DOWN_PRED ] = ff_pred4x4_horizontal_down_10_avx;
402 
403  h->pred8x8l[VERT_PRED ] = ff_pred8x8l_vertical_10_avx;
404  h->pred8x8l[HOR_PRED ] = ff_pred8x8l_horizontal_10_avx;
405  h->pred8x8l[DC_PRED ] = ff_pred8x8l_dc_10_avx;
406  h->pred8x8l[TOP_DC_PRED ] = ff_pred8x8l_top_dc_10_avx;
407  h->pred8x8l[DIAG_DOWN_RIGHT_PRED] = ff_pred8x8l_down_right_10_avx;
408  h->pred8x8l[DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_10_avx;
409  h->pred8x8l[VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_10_avx;
410  h->pred8x8l[HOR_UP_PRED ] = ff_pred8x8l_horizontal_up_10_avx;
411  }
412  }
413 }
HOR_PRED8x8
#define HOR_PRED8x8
Definition: h264pred.h:69
bit_depth
static void bit_depth(AudioStatsContext *s, uint64_t mask, uint64_t imask, AVRational *depth)
Definition: af_astats.c:226
cpu.h
DC_PRED8x8
#define DC_PRED8x8
Definition: h264pred.h:68
DC_128_PRED
@ DC_128_PRED
Definition: vp9.h:58
TM_VP8_PRED
@ TM_VP8_PRED
Definition: vp9.h:55
DC_PRED
@ DC_PRED
Definition: vp9.h:48
PRED8x8
#define PRED8x8(TYPE, DEPTH, OPT)
VERT_LEFT_PRED
@ VERT_LEFT_PRED
Definition: vp9.h:53
av_get_cpu_flags
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:98
cpu_flags
static atomic_int cpu_flags
Definition: cpu.c:50
VERT_PRED
@ VERT_PRED
Definition: vp9.h:46
DIAG_DOWN_RIGHT_PRED
@ DIAG_DOWN_RIGHT_PRED
Definition: vp9.h:50
EXTERNAL_AVX2
#define EXTERNAL_AVX2(flags)
Definition: cpu.h:78
HOR_PRED
@ HOR_PRED
Definition: vp9.h:47
av_cold
#define av_cold
Definition: attributes.h:90
codec_id.h
EXTERNAL_SSE
#define EXTERNAL_SSE(flags)
Definition: cpu.h:58
sse
static int sse(MpegEncContext *s, uint8_t *src1, uint8_t *src2, int w, int h, int stride)
Definition: mpegvideo_enc.c:2571
codec_id
enum AVCodecID codec_id
Definition: vaapi_decode.c:369
AV_CODEC_ID_SVQ3
@ AV_CODEC_ID_SVQ3
Definition: codec_id.h:73
PRED8x8L
#define PRED8x8L(TYPE, DEPTH, OPT)
AV_CODEC_ID_H264
@ AV_CODEC_ID_H264
Definition: codec_id.h:77
TOP_DC_PRED8x8
#define TOP_DC_PRED8x8
Definition: h264pred.h:75
ff_h264_pred_init_x86
void ff_h264_pred_init_x86(H264PredContext *h, int codec_id, const int bit_depth, const int chroma_format_idc)
VERT_PRED8x8
#define VERT_PRED8x8
Definition: h264pred.h:70
PRED16x16
#define PRED16x16(TYPE, DEPTH, OPT)
AV_CPU_FLAG_CMOV
#define AV_CPU_FLAG_CMOV
supports cmov instruction
Definition: cpu.h:51
dc
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled top and top right vectors is used as motion vector prediction the used motion vector is the sum of the predictor and(mvx_diff, mvy_diff) *mv_scale Intra DC Prediction block[y][x] dc[1]
Definition: snow.txt:400
cpu.h
PRED4x4
#define PRED4x4(TYPE, DEPTH, OPT)
Definition: h264_intrapred_init.c:30
VERT_RIGHT_PRED
@ VERT_RIGHT_PRED
Definition: vp9.h:51
DC_128_PRED8x8
#define DC_128_PRED8x8
Definition: h264pred.h:76
attributes.h
EXTERNAL_SSE2
#define EXTERNAL_SSE2(flags)
Definition: cpu.h:59
PLANE_PRED8x8
#define PLANE_PRED8x8
Definition: h264pred.h:71
AV_CODEC_ID_VP7
@ AV_CODEC_ID_VP7
Definition: codec_id.h:231
AV_CODEC_ID_RV40
@ AV_CODEC_ID_RV40
Definition: codec_id.h:119
LEFT_DC_PRED8x8
#define LEFT_DC_PRED8x8
Definition: h264pred.h:74
EXTERNAL_AVX
#define EXTERNAL_AVX(flags)
Definition: cpu.h:70
h264pred.h
HOR_UP_PRED
@ HOR_UP_PRED
Definition: vp9.h:54
HOR_DOWN_PRED
@ HOR_DOWN_PRED
Definition: vp9.h:52
H264PredContext
Context for storing H.264 prediction functions.
Definition: h264pred.h:92
TOP_DC_PRED
@ TOP_DC_PRED
Definition: vp9.h:57
DIAG_DOWN_LEFT_PRED
@ DIAG_DOWN_LEFT_PRED
Definition: vp9.h:49
AV_CODEC_ID_VP8
@ AV_CODEC_ID_VP8
Definition: codec_id.h:190
h
h
Definition: vp9dsp_template.c:2038
EXTERNAL_SSSE3
#define EXTERNAL_SSSE3(flags)
Definition: cpu.h:65
EXTERNAL_MMX
#define EXTERNAL_MMX(flags)
Definition: cpu.h:56
EXTERNAL_MMXEXT
#define EXTERNAL_MMXEXT(flags)
Definition: cpu.h:57