1/*
2 * H.26L/H.264/AVC/JVT/14496-10/... encoder/decoder
3 * Copyright (c) 2003-2010 Michael Niedermayer <michaelni@gmx.at>
4 *
5 * This file is part of FFmpeg.
6 *
7 * FFmpeg is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
11 *
12 * FFmpeg is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
15 * Lesser General Public License for more details.
16 *
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with FFmpeg; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 */
21
22#include "libavutil/common.h"
23#include "libavutil/intreadwrite.h"
24
25#include "bit_depth_template.c"
26#include "hpel_template.c"
27#include "pel_template.c"
28
29static inline void FUNC(copy_block2)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
30{
31    int i;
32    for(i=0; i<h; i++)
33    {
34        AV_WN2P(dst   , AV_RN2P(src   ));
35        dst+=dstStride;
36        src+=srcStride;
37    }
38}
39
40static inline void FUNC(copy_block4)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
41{
42    int i;
43    for(i=0; i<h; i++)
44    {
45        AV_WN4P(dst   , AV_RN4P(src   ));
46        dst+=dstStride;
47        src+=srcStride;
48    }
49}
50
51static inline void FUNC(copy_block8)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
52{
53    int i;
54    for(i=0; i<h; i++)
55    {
56        AV_WN4P(dst                , AV_RN4P(src                ));
57        AV_WN4P(dst+4*sizeof(pixel), AV_RN4P(src+4*sizeof(pixel)));
58        dst+=dstStride;
59        src+=srcStride;
60    }
61}
62
63static inline void FUNC(copy_block16)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
64{
65    int i;
66    for(i=0; i<h; i++)
67    {
68        AV_WN4P(dst                 , AV_RN4P(src                 ));
69        AV_WN4P(dst+ 4*sizeof(pixel), AV_RN4P(src+ 4*sizeof(pixel)));
70        AV_WN4P(dst+ 8*sizeof(pixel), AV_RN4P(src+ 8*sizeof(pixel)));
71        AV_WN4P(dst+12*sizeof(pixel), AV_RN4P(src+12*sizeof(pixel)));
72        dst+=dstStride;
73        src+=srcStride;
74    }
75}
76
77#define H264_LOWPASS(OPNAME, OP, OP2) \
78static av_unused void FUNC(OPNAME ## h264_qpel2_h_lowpass)(uint8_t *p_dst, const uint8_t *p_src, int dstStride, int srcStride){\
79    const int h=2;\
80    INIT_CLIP\
81    int i;\
82    pixel *dst = (pixel*)p_dst;\
83    const pixel *src = (const pixel*)p_src;\
84    dstStride >>= sizeof(pixel)-1;\
85    srcStride >>= sizeof(pixel)-1;\
86    for(i=0; i<h; i++)\
87    {\
88        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]));\
89        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]));\
90        dst+=dstStride;\
91        src+=srcStride;\
92    }\
93}\
94\
95static av_unused void FUNC(OPNAME ## h264_qpel2_v_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
96    const int w=2;\
97    INIT_CLIP\
98    int i;\
99    pixel *dst = (pixel*)_dst;\
100    const pixel *src = (const pixel*)_src;\
101    dstStride >>= sizeof(pixel)-1;\
102    srcStride >>= sizeof(pixel)-1;\
103    for(i=0; i<w; i++)\
104    {\
105        const int srcB= src[-2*srcStride];\
106        const int srcA= src[-1*srcStride];\
107        const int src0= src[0 *srcStride];\
108        const int src1= src[1 *srcStride];\
109        const int src2= src[2 *srcStride];\
110        const int src3= src[3 *srcStride];\
111        const int src4= src[4 *srcStride];\
112        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
113        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
114        dst++;\
115        src++;\
116    }\
117}\
118\
119static av_unused void FUNC(OPNAME ## h264_qpel2_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *_src, int dstStride, int tmpStride, int srcStride){\
120    const int h=2;\
121    const int w=2;\
122    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
123    INIT_CLIP\
124    int i;\
125    pixel *dst = (pixel*)_dst;\
126    const pixel *src = (const pixel*)_src;\
127    dstStride >>= sizeof(pixel)-1;\
128    srcStride >>= sizeof(pixel)-1;\
129    src -= 2*srcStride;\
130    for(i=0; i<h+5; i++)\
131    {\
132        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]) + pad;\
133        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]) + pad;\
134        tmp+=tmpStride;\
135        src+=srcStride;\
136    }\
137    tmp -= tmpStride*(h+5-2);\
138    for(i=0; i<w; i++)\
139    {\
140        const int tmpB= tmp[-2*tmpStride] - pad;\
141        const int tmpA= tmp[-1*tmpStride] - pad;\
142        const int tmp0= tmp[0 *tmpStride] - pad;\
143        const int tmp1= tmp[1 *tmpStride] - pad;\
144        const int tmp2= tmp[2 *tmpStride] - pad;\
145        const int tmp3= tmp[3 *tmpStride] - pad;\
146        const int tmp4= tmp[4 *tmpStride] - pad;\
147        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
148        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
149        dst++;\
150        tmp++;\
151    }\
152}\
153static void FUNC(OPNAME ## h264_qpel4_h_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
154    const int h=4;\
155    INIT_CLIP\
156    int i;\
157    pixel *dst = (pixel*)_dst;\
158    const pixel *src = (const pixel*)_src;\
159    dstStride >>= sizeof(pixel)-1;\
160    srcStride >>= sizeof(pixel)-1;\
161    for(i=0; i<h; i++)\
162    {\
163        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]));\
164        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]));\
165        OP(dst[2], (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5]));\
166        OP(dst[3], (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6]));\
167        dst+=dstStride;\
168        src+=srcStride;\
169    }\
170}\
171\
172static void FUNC(OPNAME ## h264_qpel4_v_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
173    const int w=4;\
174    INIT_CLIP\
175    int i;\
176    pixel *dst = (pixel*)_dst;\
177    const pixel *src = (const pixel*)_src;\
178    dstStride >>= sizeof(pixel)-1;\
179    srcStride >>= sizeof(pixel)-1;\
180    for(i=0; i<w; i++)\
181    {\
182        const int srcB= src[-2*srcStride];\
183        const int srcA= src[-1*srcStride];\
184        const int src0= src[0 *srcStride];\
185        const int src1= src[1 *srcStride];\
186        const int src2= src[2 *srcStride];\
187        const int src3= src[3 *srcStride];\
188        const int src4= src[4 *srcStride];\
189        const int src5= src[5 *srcStride];\
190        const int src6= src[6 *srcStride];\
191        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
192        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
193        OP(dst[2*dstStride], (src2+src3)*20 - (src1+src4)*5 + (src0+src5));\
194        OP(dst[3*dstStride], (src3+src4)*20 - (src2+src5)*5 + (src1+src6));\
195        dst++;\
196        src++;\
197    }\
198}\
199\
200static void FUNC(OPNAME ## h264_qpel4_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *_src, int dstStride, int tmpStride, int srcStride){\
201    const int h=4;\
202    const int w=4;\
203    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
204    INIT_CLIP\
205    int i;\
206    pixel *dst = (pixel*)_dst;\
207    const pixel *src = (const pixel*)_src;\
208    dstStride >>= sizeof(pixel)-1;\
209    srcStride >>= sizeof(pixel)-1;\
210    src -= 2*srcStride;\
211    for(i=0; i<h+5; i++)\
212    {\
213        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]) + pad;\
214        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]) + pad;\
215        tmp[2]= (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5]) + pad;\
216        tmp[3]= (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6]) + pad;\
217        tmp+=tmpStride;\
218        src+=srcStride;\
219    }\
220    tmp -= tmpStride*(h+5-2);\
221    for(i=0; i<w; i++)\
222    {\
223        const int tmpB= tmp[-2*tmpStride] - pad;\
224        const int tmpA= tmp[-1*tmpStride] - pad;\
225        const int tmp0= tmp[0 *tmpStride] - pad;\
226        const int tmp1= tmp[1 *tmpStride] - pad;\
227        const int tmp2= tmp[2 *tmpStride] - pad;\
228        const int tmp3= tmp[3 *tmpStride] - pad;\
229        const int tmp4= tmp[4 *tmpStride] - pad;\
230        const int tmp5= tmp[5 *tmpStride] - pad;\
231        const int tmp6= tmp[6 *tmpStride] - pad;\
232        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
233        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
234        OP2(dst[2*dstStride], (tmp2+tmp3)*20 - (tmp1+tmp4)*5 + (tmp0+tmp5));\
235        OP2(dst[3*dstStride], (tmp3+tmp4)*20 - (tmp2+tmp5)*5 + (tmp1+tmp6));\
236        dst++;\
237        tmp++;\
238    }\
239}\
240\
241static void FUNC(OPNAME ## h264_qpel8_h_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
242    const int h=8;\
243    INIT_CLIP\
244    int i;\
245    pixel *dst = (pixel*)_dst;\
246    const pixel *src = (const pixel*)_src;\
247    dstStride >>= sizeof(pixel)-1;\
248    srcStride >>= sizeof(pixel)-1;\
249    for(i=0; i<h; i++)\
250    {\
251        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3 ]));\
252        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4 ]));\
253        OP(dst[2], (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5 ]));\
254        OP(dst[3], (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6 ]));\
255        OP(dst[4], (src[4]+src[5])*20 - (src[3 ]+src[6])*5 + (src[2 ]+src[7 ]));\
256        OP(dst[5], (src[5]+src[6])*20 - (src[4 ]+src[7])*5 + (src[3 ]+src[8 ]));\
257        OP(dst[6], (src[6]+src[7])*20 - (src[5 ]+src[8])*5 + (src[4 ]+src[9 ]));\
258        OP(dst[7], (src[7]+src[8])*20 - (src[6 ]+src[9])*5 + (src[5 ]+src[10]));\
259        dst+=dstStride;\
260        src+=srcStride;\
261    }\
262}\
263\
264static void FUNC(OPNAME ## h264_qpel8_v_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
265    const int w=8;\
266    INIT_CLIP\
267    int i;\
268    pixel *dst = (pixel*)_dst;\
269    const pixel *src = (const pixel*)_src;\
270    dstStride >>= sizeof(pixel)-1;\
271    srcStride >>= sizeof(pixel)-1;\
272    for(i=0; i<w; i++)\
273    {\
274        const int srcB= src[-2*srcStride];\
275        const int srcA= src[-1*srcStride];\
276        const int src0= src[0 *srcStride];\
277        const int src1= src[1 *srcStride];\
278        const int src2= src[2 *srcStride];\
279        const int src3= src[3 *srcStride];\
280        const int src4= src[4 *srcStride];\
281        const int src5= src[5 *srcStride];\
282        const int src6= src[6 *srcStride];\
283        const int src7= src[7 *srcStride];\
284        const int src8= src[8 *srcStride];\
285        const int src9= src[9 *srcStride];\
286        const int src10=src[10*srcStride];\
287        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
288        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
289        OP(dst[2*dstStride], (src2+src3)*20 - (src1+src4)*5 + (src0+src5));\
290        OP(dst[3*dstStride], (src3+src4)*20 - (src2+src5)*5 + (src1+src6));\
291        OP(dst[4*dstStride], (src4+src5)*20 - (src3+src6)*5 + (src2+src7));\
292        OP(dst[5*dstStride], (src5+src6)*20 - (src4+src7)*5 + (src3+src8));\
293        OP(dst[6*dstStride], (src6+src7)*20 - (src5+src8)*5 + (src4+src9));\
294        OP(dst[7*dstStride], (src7+src8)*20 - (src6+src9)*5 + (src5+src10));\
295        dst++;\
296        src++;\
297    }\
298}\
299\
300static void FUNC(OPNAME ## h264_qpel8_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *_src, int dstStride, int tmpStride, int srcStride){\
301    const int h=8;\
302    const int w=8;\
303    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
304    INIT_CLIP\
305    int i;\
306    pixel *dst = (pixel*)_dst;\
307    const pixel *src = (const pixel*)_src;\
308    dstStride >>= sizeof(pixel)-1;\
309    srcStride >>= sizeof(pixel)-1;\
310    src -= 2*srcStride;\
311    for(i=0; i<h+5; i++)\
312    {\
313        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3 ]) + pad;\
314        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4 ]) + pad;\
315        tmp[2]= (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5 ]) + pad;\
316        tmp[3]= (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6 ]) + pad;\
317        tmp[4]= (src[4]+src[5])*20 - (src[3 ]+src[6])*5 + (src[2 ]+src[7 ]) + pad;\
318        tmp[5]= (src[5]+src[6])*20 - (src[4 ]+src[7])*5 + (src[3 ]+src[8 ]) + pad;\
319        tmp[6]= (src[6]+src[7])*20 - (src[5 ]+src[8])*5 + (src[4 ]+src[9 ]) + pad;\
320        tmp[7]= (src[7]+src[8])*20 - (src[6 ]+src[9])*5 + (src[5 ]+src[10]) + pad;\
321        tmp+=tmpStride;\
322        src+=srcStride;\
323    }\
324    tmp -= tmpStride*(h+5-2);\
325    for(i=0; i<w; i++)\
326    {\
327        const int tmpB= tmp[-2*tmpStride] - pad;\
328        const int tmpA= tmp[-1*tmpStride] - pad;\
329        const int tmp0= tmp[0 *tmpStride] - pad;\
330        const int tmp1= tmp[1 *tmpStride] - pad;\
331        const int tmp2= tmp[2 *tmpStride] - pad;\
332        const int tmp3= tmp[3 *tmpStride] - pad;\
333        const int tmp4= tmp[4 *tmpStride] - pad;\
334        const int tmp5= tmp[5 *tmpStride] - pad;\
335        const int tmp6= tmp[6 *tmpStride] - pad;\
336        const int tmp7= tmp[7 *tmpStride] - pad;\
337        const int tmp8= tmp[8 *tmpStride] - pad;\
338        const int tmp9= tmp[9 *tmpStride] - pad;\
339        const int tmp10=tmp[10*tmpStride] - pad;\
340        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
341        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
342        OP2(dst[2*dstStride], (tmp2+tmp3)*20 - (tmp1+tmp4)*5 + (tmp0+tmp5));\
343        OP2(dst[3*dstStride], (tmp3+tmp4)*20 - (tmp2+tmp5)*5 + (tmp1+tmp6));\
344        OP2(dst[4*dstStride], (tmp4+tmp5)*20 - (tmp3+tmp6)*5 + (tmp2+tmp7));\
345        OP2(dst[5*dstStride], (tmp5+tmp6)*20 - (tmp4+tmp7)*5 + (tmp3+tmp8));\
346        OP2(dst[6*dstStride], (tmp6+tmp7)*20 - (tmp5+tmp8)*5 + (tmp4+tmp9));\
347        OP2(dst[7*dstStride], (tmp7+tmp8)*20 - (tmp6+tmp9)*5 + (tmp5+tmp10));\
348        dst++;\
349        tmp++;\
350    }\
351}\
352\
353static void FUNC(OPNAME ## h264_qpel16_v_lowpass)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
354    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst                , src                , dstStride, srcStride);\
355    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst+8*sizeof(pixel), src+8*sizeof(pixel), dstStride, srcStride);\
356    src += 8*srcStride;\
357    dst += 8*dstStride;\
358    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst                , src                , dstStride, srcStride);\
359    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst+8*sizeof(pixel), src+8*sizeof(pixel), dstStride, srcStride);\
360}\
361\
362static void FUNC(OPNAME ## h264_qpel16_h_lowpass)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
363    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst                , src                , dstStride, srcStride);\
364    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst+8*sizeof(pixel), src+8*sizeof(pixel), dstStride, srcStride);\
365    src += 8*srcStride;\
366    dst += 8*dstStride;\
367    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst                , src                , dstStride, srcStride);\
368    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst+8*sizeof(pixel), src+8*sizeof(pixel), dstStride, srcStride);\
369}\
370\
371static void FUNC(OPNAME ## h264_qpel16_hv_lowpass)(uint8_t *dst, pixeltmp *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride){\
372    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst                , tmp  , src                , dstStride, tmpStride, srcStride);\
373    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst+8*sizeof(pixel), tmp+8, src+8*sizeof(pixel), dstStride, tmpStride, srcStride);\
374    src += 8*srcStride;\
375    dst += 8*dstStride;\
376    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst                , tmp  , src                , dstStride, tmpStride, srcStride);\
377    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst+8*sizeof(pixel), tmp+8, src+8*sizeof(pixel), dstStride, tmpStride, srcStride);\
378}\
379
380#define H264_MC(OPNAME, SIZE) \
381static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc00)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
382{\
383    FUNCC(OPNAME ## pixels ## SIZE)(dst, src, stride, SIZE);\
384}\
385\
386static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc10)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
387{\
388    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
389    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(half, src, SIZE*sizeof(pixel), stride);\
390    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, src, half, stride, stride, SIZE*sizeof(pixel), SIZE);\
391}\
392\
393static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc20)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
394{\
395    FUNC(OPNAME ## h264_qpel ## SIZE ## _h_lowpass)(dst, src, stride, stride);\
396}\
397\
398static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc30)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
399{\
400    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
401    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(half, src, SIZE*sizeof(pixel), stride);\
402    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, src+sizeof(pixel), half, stride, stride, SIZE*sizeof(pixel), SIZE);\
403}\
404\
405static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc01)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
406{\
407    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
408    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
409    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
410    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
411    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(half, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
412    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, full_mid, half, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
413}\
414\
415static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc02)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
416{\
417    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
418    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
419    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
420    FUNC(OPNAME ## h264_qpel ## SIZE ## _v_lowpass)(dst, full_mid, stride, SIZE*sizeof(pixel));\
421}\
422\
423static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc03)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
424{\
425    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
426    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
427    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
428    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
429    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(half, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
430    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, full_mid+SIZE*sizeof(pixel), half, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
431}\
432\
433static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc11)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
434{\
435    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
436    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
437    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
438    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
439    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src, SIZE*sizeof(pixel), stride);\
440    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
441    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
442    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
443}\
444\
445static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc31)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
446{\
447    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
448    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
449    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
450    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
451    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src, SIZE*sizeof(pixel), stride);\
452    FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
453    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
454    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
455}\
456\
457static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc13)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
458{\
459    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
460    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
461    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
462    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
463    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src + stride, SIZE*sizeof(pixel), stride);\
464    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
465    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
466    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
467}\
468\
469static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc33)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
470{\
471    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
472    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
473    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
474    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
475    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src + stride, SIZE*sizeof(pixel), stride);\
476    FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
477    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
478    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
479}\
480\
481static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc22)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
482{\
483    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
484    FUNC(OPNAME ## h264_qpel ## SIZE ## _hv_lowpass)(dst, tmp, src, stride, SIZE*sizeof(pixel), stride);\
485}\
486\
487static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc21)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
488{\
489    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
490    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
491    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
492    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src, SIZE*sizeof(pixel), stride);\
493    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
494    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
495}\
496\
497static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc23)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
498{\
499    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
500    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
501    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
502    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src + stride, SIZE*sizeof(pixel), stride);\
503    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
504    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
505}\
506\
507static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc12)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
508{\
509    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
510    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
511    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
512    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
513    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
514    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
515    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
516    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
517    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfV, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
518}\
519\
520static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc32)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
521{\
522    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
523    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
524    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
525    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
526    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
527    FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
528    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
529    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
530    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfV, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
531}\
532
533#define op_avg(a, b)  a = (((a)+CLIP(((b) + 16)>>5)+1)>>1)
534//#define op_avg2(a, b) a = (((a)*w1+cm[((b) + 16)>>5]*w2 + o + 64)>>7)
535#define op_put(a, b)  a = CLIP(((b) + 16)>>5)
536#define op2_avg(a, b)  a = (((a)+CLIP(((b) + 512)>>10)+1)>>1)
537#define op2_put(a, b)  a = CLIP(((b) + 512)>>10)
538
539H264_LOWPASS(put_       , op_put, op2_put)
540H264_LOWPASS(avg_       , op_avg, op2_avg)
541H264_MC(put_, 2)
542H264_MC(put_, 4)
543H264_MC(put_, 8)
544H264_MC(put_, 16)
545H264_MC(avg_, 4)
546H264_MC(avg_, 8)
547H264_MC(avg_, 16)
548
549#undef op_avg
550#undef op_put
551#undef op2_avg
552#undef op2_put
553