xref: /third_party/ffmpeg/libavcodec/h264qpel_template.c

29 static inline void FUNC(copy_block2)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
34         AV_WN2P(dst   , AV_RN2P(src   ));
36         src+=srcStride;
40 static inline void FUNC(copy_block4)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
45         AV_WN4P(dst   , AV_RN4P(src   ));
47         src+=srcStride;
51 static inline void FUNC(copy_block8)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
56         AV_WN4P(dst                , AV_RN4P(src                ));
57         AV_WN4P(dst+4*sizeof(pixel), AV_RN4P(src+4*sizeof(pixel)));
59         src+=srcStride;
63 static inline void FUNC(copy_block16)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
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)));
73         src+=srcStride;
83     const pixel *src = (const pixel*)p_src;\
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]));\
91         src+=srcStride;\
100     const pixel *src = (const pixel*)_src;\
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];\
115         src++;\
126     const pixel *src = (const pixel*)_src;\
129     src -= 2*srcStride;\
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;\
135         src+=srcStride;\
158     const pixel *src = (const pixel*)_src;\
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]));\
168         src+=srcStride;\
177     const pixel *src = (const pixel*)_src;\
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];\
196         src++;\
207     const pixel *src = (const pixel*)_src;\
210     src -= 2*srcStride;\
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;\
218         src+=srcStride;\
246     const pixel *src = (const pixel*)_src;\
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]));\
260         src+=srcStride;\
269     const pixel *src = (const pixel*)_src;\
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];\
296         src++;\
307     const pixel *src = (const pixel*)_src;\
310     src -= 2*srcStride;\
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;\
322         src+=srcStride;\
353 static 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;\
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);\
362 static 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;\
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);\
371 static 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;\
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);\
381 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc00)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
383     FUNCC(OPNAME ## pixels ## SIZE)(dst, src, stride, SIZE);\
386 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc10)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
393 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc20)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
395     FUNC(OPNAME ## h264_qpel ## SIZE ## _h_lowpass)(dst, src, stride, stride);\
398 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc30)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
405 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc01)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
410     FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
415 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc02)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
419     FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
423 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc03)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
428     FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
433 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc11)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
445 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc31)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
457 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc13)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
469 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc33)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
481 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc22)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
484     FUNC(OPNAME ## h264_qpel ## SIZE ## _hv_lowpass)(dst, tmp, src, stride, SIZE*sizeof(pixel), stride);\
487 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc21)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
497 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc23)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
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);\
507 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc12)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
514     FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
516     FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
520 static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc32)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
527     FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
529     FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\

Indexes created Thu Nov 07 10:32:03 CST 2024