h264qpel_template.c 24.6 KB
Newer Older
1 2 3 4
/*
 * H.26L/H.264/AVC/JVT/14496-10/... encoder/decoder
 * Copyright (c) 2003-2010 Michael Niedermayer <michaelni@gmx.at>
 *
5
 * This file is part of FFmpeg.
6
 *
7
 * FFmpeg is free software; you can redistribute it and/or
8 9 10 11
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
12
 * FFmpeg is distributed in the hope that it will be useful,
13 14 15 16 17
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * 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 20 21 22
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "libavutil/common.h"
23 24
#include "libavutil/intreadwrite.h"

25 26
#include "bit_depth_template.c"
#include "hpel_template.c"
27
#include "pel_template.c"
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

static inline void FUNC(copy_block2)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
{
    int i;
    for(i=0; i<h; i++)
    {
        AV_WN2P(dst   , AV_RN2P(src   ));
        dst+=dstStride;
        src+=srcStride;
    }
}

static inline void FUNC(copy_block4)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
{
    int i;
    for(i=0; i<h; i++)
    {
        AV_WN4P(dst   , AV_RN4P(src   ));
        dst+=dstStride;
        src+=srcStride;
    }
}

static inline void FUNC(copy_block8)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
{
    int i;
    for(i=0; i<h; i++)
    {
        AV_WN4P(dst                , AV_RN4P(src                ));
        AV_WN4P(dst+4*sizeof(pixel), AV_RN4P(src+4*sizeof(pixel)));
        dst+=dstStride;
        src+=srcStride;
    }
}

static inline void FUNC(copy_block16)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h)
{
    int i;
    for(i=0; i<h; i++)
    {
        AV_WN4P(dst                 , AV_RN4P(src                 ));
        AV_WN4P(dst+ 4*sizeof(pixel), AV_RN4P(src+ 4*sizeof(pixel)));
        AV_WN4P(dst+ 8*sizeof(pixel), AV_RN4P(src+ 8*sizeof(pixel)));
        AV_WN4P(dst+12*sizeof(pixel), AV_RN4P(src+12*sizeof(pixel)));
        dst+=dstStride;
        src+=srcStride;
    }
}

#define H264_LOWPASS(OPNAME, OP, OP2) \
78
static av_unused void FUNC(OPNAME ## h264_qpel2_h_lowpass)(uint8_t *p_dst, const uint8_t *p_src, int dstStride, int srcStride){\
79 80 81
    const int h=2;\
    INIT_CLIP\
    int i;\
82
    pixel *dst = (pixel*)p_dst;\
83
    const pixel *src = (const pixel*)p_src;\
84 85
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
86 87 88 89 90 91 92 93 94
    for(i=0; i<h; i++)\
    {\
        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]));\
        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]));\
        dst+=dstStride;\
        src+=srcStride;\
    }\
}\
\
95
static av_unused void FUNC(OPNAME ## h264_qpel2_v_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
96 97 98 99
    const int w=2;\
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
100
    const pixel *src = (const pixel*)_src;\
101 102
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118
    for(i=0; i<w; i++)\
    {\
        const int srcB= src[-2*srcStride];\
        const int srcA= src[-1*srcStride];\
        const int src0= src[0 *srcStride];\
        const int src1= src[1 *srcStride];\
        const int src2= src[2 *srcStride];\
        const int src3= src[3 *srcStride];\
        const int src4= src[4 *srcStride];\
        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
        dst++;\
        src++;\
    }\
}\
\
119
static av_unused void FUNC(OPNAME ## h264_qpel2_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *_src, int dstStride, int tmpStride, int srcStride){\
120 121
    const int h=2;\
    const int w=2;\
122
    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
123 124 125
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
126
    const pixel *src = (const pixel*)_src;\
127 128
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152
    src -= 2*srcStride;\
    for(i=0; i<h+5; i++)\
    {\
        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]) + pad;\
        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]) + pad;\
        tmp+=tmpStride;\
        src+=srcStride;\
    }\
    tmp -= tmpStride*(h+5-2);\
    for(i=0; i<w; i++)\
    {\
        const int tmpB= tmp[-2*tmpStride] - pad;\
        const int tmpA= tmp[-1*tmpStride] - pad;\
        const int tmp0= tmp[0 *tmpStride] - pad;\
        const int tmp1= tmp[1 *tmpStride] - pad;\
        const int tmp2= tmp[2 *tmpStride] - pad;\
        const int tmp3= tmp[3 *tmpStride] - pad;\
        const int tmp4= tmp[4 *tmpStride] - pad;\
        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
        dst++;\
        tmp++;\
    }\
}\
153
static void FUNC(OPNAME ## h264_qpel4_h_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
154 155 156 157
    const int h=4;\
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
158
    const pixel *src = (const pixel*)_src;\
159 160
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
161 162 163 164 165 166 167 168 169 170 171
    for(i=0; i<h; i++)\
    {\
        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]));\
        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]));\
        OP(dst[2], (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5]));\
        OP(dst[3], (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6]));\
        dst+=dstStride;\
        src+=srcStride;\
    }\
}\
\
172
static void FUNC(OPNAME ## h264_qpel4_v_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
173 174 175 176
    const int w=4;\
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
177
    const pixel *src = (const pixel*)_src;\
178 179
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
    for(i=0; i<w; i++)\
    {\
        const int srcB= src[-2*srcStride];\
        const int srcA= src[-1*srcStride];\
        const int src0= src[0 *srcStride];\
        const int src1= src[1 *srcStride];\
        const int src2= src[2 *srcStride];\
        const int src3= src[3 *srcStride];\
        const int src4= src[4 *srcStride];\
        const int src5= src[5 *srcStride];\
        const int src6= src[6 *srcStride];\
        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
        OP(dst[2*dstStride], (src2+src3)*20 - (src1+src4)*5 + (src0+src5));\
        OP(dst[3*dstStride], (src3+src4)*20 - (src2+src5)*5 + (src1+src6));\
        dst++;\
        src++;\
    }\
}\
\
200
static void FUNC(OPNAME ## h264_qpel4_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *_src, int dstStride, int tmpStride, int srcStride){\
201 202
    const int h=4;\
    const int w=4;\
203
    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
204 205 206
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
207
    const pixel *src = (const pixel*)_src;\
208 209
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
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
    src -= 2*srcStride;\
    for(i=0; i<h+5; i++)\
    {\
        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3]) + pad;\
        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4]) + pad;\
        tmp[2]= (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5]) + pad;\
        tmp[3]= (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6]) + pad;\
        tmp+=tmpStride;\
        src+=srcStride;\
    }\
    tmp -= tmpStride*(h+5-2);\
    for(i=0; i<w; i++)\
    {\
        const int tmpB= tmp[-2*tmpStride] - pad;\
        const int tmpA= tmp[-1*tmpStride] - pad;\
        const int tmp0= tmp[0 *tmpStride] - pad;\
        const int tmp1= tmp[1 *tmpStride] - pad;\
        const int tmp2= tmp[2 *tmpStride] - pad;\
        const int tmp3= tmp[3 *tmpStride] - pad;\
        const int tmp4= tmp[4 *tmpStride] - pad;\
        const int tmp5= tmp[5 *tmpStride] - pad;\
        const int tmp6= tmp[6 *tmpStride] - pad;\
        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
        OP2(dst[2*dstStride], (tmp2+tmp3)*20 - (tmp1+tmp4)*5 + (tmp0+tmp5));\
        OP2(dst[3*dstStride], (tmp3+tmp4)*20 - (tmp2+tmp5)*5 + (tmp1+tmp6));\
        dst++;\
        tmp++;\
    }\
}\
\
241
static void FUNC(OPNAME ## h264_qpel8_h_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
242 243 244 245
    const int h=8;\
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
246
    const pixel *src = (const pixel*)_src;\
247 248
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
249 250 251 252 253 254 255 256 257 258 259 260 261 262 263
    for(i=0; i<h; i++)\
    {\
        OP(dst[0], (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3 ]));\
        OP(dst[1], (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4 ]));\
        OP(dst[2], (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5 ]));\
        OP(dst[3], (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6 ]));\
        OP(dst[4], (src[4]+src[5])*20 - (src[3 ]+src[6])*5 + (src[2 ]+src[7 ]));\
        OP(dst[5], (src[5]+src[6])*20 - (src[4 ]+src[7])*5 + (src[3 ]+src[8 ]));\
        OP(dst[6], (src[6]+src[7])*20 - (src[5 ]+src[8])*5 + (src[4 ]+src[9 ]));\
        OP(dst[7], (src[7]+src[8])*20 - (src[6 ]+src[9])*5 + (src[5 ]+src[10]));\
        dst+=dstStride;\
        src+=srcStride;\
    }\
}\
\
264
static void FUNC(OPNAME ## h264_qpel8_v_lowpass)(uint8_t *_dst, const uint8_t *_src, int dstStride, int srcStride){\
265 266 267 268
    const int w=8;\
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
269
    const pixel *src = (const pixel*)_src;\
270 271
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
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
    for(i=0; i<w; i++)\
    {\
        const int srcB= src[-2*srcStride];\
        const int srcA= src[-1*srcStride];\
        const int src0= src[0 *srcStride];\
        const int src1= src[1 *srcStride];\
        const int src2= src[2 *srcStride];\
        const int src3= src[3 *srcStride];\
        const int src4= src[4 *srcStride];\
        const int src5= src[5 *srcStride];\
        const int src6= src[6 *srcStride];\
        const int src7= src[7 *srcStride];\
        const int src8= src[8 *srcStride];\
        const int src9= src[9 *srcStride];\
        const int src10=src[10*srcStride];\
        OP(dst[0*dstStride], (src0+src1)*20 - (srcA+src2)*5 + (srcB+src3));\
        OP(dst[1*dstStride], (src1+src2)*20 - (src0+src3)*5 + (srcA+src4));\
        OP(dst[2*dstStride], (src2+src3)*20 - (src1+src4)*5 + (src0+src5));\
        OP(dst[3*dstStride], (src3+src4)*20 - (src2+src5)*5 + (src1+src6));\
        OP(dst[4*dstStride], (src4+src5)*20 - (src3+src6)*5 + (src2+src7));\
        OP(dst[5*dstStride], (src5+src6)*20 - (src4+src7)*5 + (src3+src8));\
        OP(dst[6*dstStride], (src6+src7)*20 - (src5+src8)*5 + (src4+src9));\
        OP(dst[7*dstStride], (src7+src8)*20 - (src6+src9)*5 + (src5+src10));\
        dst++;\
        src++;\
    }\
}\
\
300
static void FUNC(OPNAME ## h264_qpel8_hv_lowpass)(uint8_t *_dst, pixeltmp *tmp, const uint8_t *_src, int dstStride, int tmpStride, int srcStride){\
301 302
    const int h=8;\
    const int w=8;\
303
    const int pad = (BIT_DEPTH == 10) ? (-10 * ((1<<BIT_DEPTH)-1)) : 0;\
304 305 306
    INIT_CLIP\
    int i;\
    pixel *dst = (pixel*)_dst;\
307
    const pixel *src = (const pixel*)_src;\
308 309
    dstStride >>= sizeof(pixel)-1;\
    srcStride >>= sizeof(pixel)-1;\
310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352
    src -= 2*srcStride;\
    for(i=0; i<h+5; i++)\
    {\
        tmp[0]= (src[0]+src[1])*20 - (src[-1]+src[2])*5 + (src[-2]+src[3 ]) + pad;\
        tmp[1]= (src[1]+src[2])*20 - (src[0 ]+src[3])*5 + (src[-1]+src[4 ]) + pad;\
        tmp[2]= (src[2]+src[3])*20 - (src[1 ]+src[4])*5 + (src[0 ]+src[5 ]) + pad;\
        tmp[3]= (src[3]+src[4])*20 - (src[2 ]+src[5])*5 + (src[1 ]+src[6 ]) + pad;\
        tmp[4]= (src[4]+src[5])*20 - (src[3 ]+src[6])*5 + (src[2 ]+src[7 ]) + pad;\
        tmp[5]= (src[5]+src[6])*20 - (src[4 ]+src[7])*5 + (src[3 ]+src[8 ]) + pad;\
        tmp[6]= (src[6]+src[7])*20 - (src[5 ]+src[8])*5 + (src[4 ]+src[9 ]) + pad;\
        tmp[7]= (src[7]+src[8])*20 - (src[6 ]+src[9])*5 + (src[5 ]+src[10]) + pad;\
        tmp+=tmpStride;\
        src+=srcStride;\
    }\
    tmp -= tmpStride*(h+5-2);\
    for(i=0; i<w; i++)\
    {\
        const int tmpB= tmp[-2*tmpStride] - pad;\
        const int tmpA= tmp[-1*tmpStride] - pad;\
        const int tmp0= tmp[0 *tmpStride] - pad;\
        const int tmp1= tmp[1 *tmpStride] - pad;\
        const int tmp2= tmp[2 *tmpStride] - pad;\
        const int tmp3= tmp[3 *tmpStride] - pad;\
        const int tmp4= tmp[4 *tmpStride] - pad;\
        const int tmp5= tmp[5 *tmpStride] - pad;\
        const int tmp6= tmp[6 *tmpStride] - pad;\
        const int tmp7= tmp[7 *tmpStride] - pad;\
        const int tmp8= tmp[8 *tmpStride] - pad;\
        const int tmp9= tmp[9 *tmpStride] - pad;\
        const int tmp10=tmp[10*tmpStride] - pad;\
        OP2(dst[0*dstStride], (tmp0+tmp1)*20 - (tmpA+tmp2)*5 + (tmpB+tmp3));\
        OP2(dst[1*dstStride], (tmp1+tmp2)*20 - (tmp0+tmp3)*5 + (tmpA+tmp4));\
        OP2(dst[2*dstStride], (tmp2+tmp3)*20 - (tmp1+tmp4)*5 + (tmp0+tmp5));\
        OP2(dst[3*dstStride], (tmp3+tmp4)*20 - (tmp2+tmp5)*5 + (tmp1+tmp6));\
        OP2(dst[4*dstStride], (tmp4+tmp5)*20 - (tmp3+tmp6)*5 + (tmp2+tmp7));\
        OP2(dst[5*dstStride], (tmp5+tmp6)*20 - (tmp4+tmp7)*5 + (tmp3+tmp8));\
        OP2(dst[6*dstStride], (tmp6+tmp7)*20 - (tmp5+tmp8)*5 + (tmp4+tmp9));\
        OP2(dst[7*dstStride], (tmp7+tmp8)*20 - (tmp6+tmp9)*5 + (tmp5+tmp10));\
        dst++;\
        tmp++;\
    }\
}\
\
353
static void FUNC(OPNAME ## h264_qpel16_v_lowpass)(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
354 355 356 357 358 359 360 361
    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst                , src                , dstStride, srcStride);\
    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst+8*sizeof(pixel), src+8*sizeof(pixel), dstStride, srcStride);\
    src += 8*srcStride;\
    dst += 8*dstStride;\
    FUNC(OPNAME ## h264_qpel8_v_lowpass)(dst                , src                , dstStride, srcStride);\
    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){\
363 364 365 366 367 368 369 370
    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst                , src                , dstStride, srcStride);\
    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst+8*sizeof(pixel), src+8*sizeof(pixel), dstStride, srcStride);\
    src += 8*srcStride;\
    dst += 8*dstStride;\
    FUNC(OPNAME ## h264_qpel8_h_lowpass)(dst                , src                , dstStride, srcStride);\
    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){\
372 373 374 375 376 377 378 379 380
    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst                , tmp  , src                , dstStride, tmpStride, srcStride);\
    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst+8*sizeof(pixel), tmp+8, src+8*sizeof(pixel), dstStride, tmpStride, srcStride);\
    src += 8*srcStride;\
    dst += 8*dstStride;\
    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst                , tmp  , src                , dstStride, tmpStride, srcStride);\
    FUNC(OPNAME ## h264_qpel8_hv_lowpass)(dst+8*sizeof(pixel), tmp+8, src+8*sizeof(pixel), dstStride, tmpStride, srcStride);\
}\

#define H264_MC(OPNAME, SIZE) \
381
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc00)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
382
{\
383 384 385
    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)\
387
{\
388 389 390 391 392
    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(half, src, SIZE*sizeof(pixel), stride);\
    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)\
394
{\
395 396 397
    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)\
399
{\
400 401 402 403 404
    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(half, src, SIZE*sizeof(pixel), stride);\
    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)\
406
{\
407 408 409 410 411 412 413 414
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(half, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, full_mid, half, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
415
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc02)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
416
{\
417 418 419 420 421 422
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(OPNAME ## h264_qpel ## SIZE ## _v_lowpass)(dst, full_mid, stride, SIZE*sizeof(pixel));\
}\
\
423
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc03)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
424
{\
425 426 427 428 429 430 431 432
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    uint8_t half[SIZE*SIZE*sizeof(pixel)];\
    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(half, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, full_mid+SIZE*sizeof(pixel), half, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
433
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc11)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
434
{\
435 436 437 438 439 440 441 442 443 444
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src, SIZE*sizeof(pixel), stride);\
    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
445
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc31)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
446
{\
447 448 449 450 451 452 453 454 455 456
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src, SIZE*sizeof(pixel), stride);\
    FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
457
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc13)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
458
{\
459 460 461 462 463 464 465 466 467 468
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src + stride, SIZE*sizeof(pixel), stride);\
    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
469
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc33)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
470
{\
471 472 473 474 475 476 477 478 479 480
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src + stride, SIZE*sizeof(pixel), stride);\
    FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
481
static 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)];\
484 485 486
    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)\
488
{\
489
    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
490 491 492 493 494 495 496
    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src, SIZE*sizeof(pixel), stride);\
    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
497
static 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)];\
500 501 502 503 504 505 506
    uint8_t halfH[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(put_h264_qpel ## SIZE ## _h_lowpass)(halfH, src + stride, SIZE*sizeof(pixel), stride);\
    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfH, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
507
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc12)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
508
{\
509 510
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
511
    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
512 513 514 515 516 517 518 519
    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(copy_block ## SIZE )(full, src - stride*2, SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfV, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\
\
520
static void FUNCC(OPNAME ## h264_qpel ## SIZE ## _mc32)(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
521
{\
522 523
    uint8_t full[SIZE*(SIZE+5)*sizeof(pixel)];\
    uint8_t * const full_mid= full + SIZE*2*sizeof(pixel);\
524
    pixeltmp tmp[SIZE*(SIZE+5)*sizeof(pixel)];\
525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552
    uint8_t halfV[SIZE*SIZE*sizeof(pixel)];\
    uint8_t halfHV[SIZE*SIZE*sizeof(pixel)];\
    FUNC(copy_block ## SIZE )(full, src - stride*2 + sizeof(pixel), SIZE*sizeof(pixel),  stride, SIZE + 5);\
    FUNC(put_h264_qpel ## SIZE ## _v_lowpass)(halfV, full_mid, SIZE*sizeof(pixel), SIZE*sizeof(pixel));\
    FUNC(put_h264_qpel ## SIZE ## _hv_lowpass)(halfHV, tmp, src, SIZE*sizeof(pixel), SIZE*sizeof(pixel), stride);\
    FUNC(OPNAME ## pixels ## SIZE ## _l2)(dst, halfV, halfHV, stride, SIZE*sizeof(pixel), SIZE*sizeof(pixel), SIZE);\
}\

#define op_avg(a, b)  a = (((a)+CLIP(((b) + 16)>>5)+1)>>1)
//#define op_avg2(a, b) a = (((a)*w1+cm[((b) + 16)>>5]*w2 + o + 64)>>7)
#define op_put(a, b)  a = CLIP(((b) + 16)>>5)
#define op2_avg(a, b)  a = (((a)+CLIP(((b) + 512)>>10)+1)>>1)
#define op2_put(a, b)  a = CLIP(((b) + 512)>>10)

H264_LOWPASS(put_       , op_put, op2_put)
H264_LOWPASS(avg_       , op_avg, op2_avg)
H264_MC(put_, 2)
H264_MC(put_, 4)
H264_MC(put_, 8)
H264_MC(put_, 16)
H264_MC(avg_, 4)
H264_MC(avg_, 8)
H264_MC(avg_, 16)

#undef op_avg
#undef op_put
#undef op2_avg
#undef op2_put