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