libavcodec/h264chroma_template.c
79dad2a9
 /*
  * Copyright (c) 2000, 2001 Fabrice Bellard
  * Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
  *
c4e394e4
  * This file is part of FFmpeg.
79dad2a9
  *
c4e394e4
  * FFmpeg is free software; you can redistribute it and/or
79dad2a9
  * 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.
  *
c4e394e4
  * FFmpeg is distributed in the hope that it will be useful,
79dad2a9
  * 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
c4e394e4
  * License along with FFmpeg; if not, write to the Free Software
79dad2a9
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
c4e394e4
 #include "libavutil/avassert.h"
79dad2a9
 
 #include "bit_depth_template.c"
 
 #define H264_CHROMA_MC(OPNAME, OP)\
c2625c26
 static void FUNCC(OPNAME ## h264_chroma_mc1)(uint8_t *_dst/*align 8*/, uint8_t *_src/*align 1*/, int stride, int h, int x, int y){\
     pixel *dst = (pixel*)_dst;\
     pixel *src = (pixel*)_src;\
     const int A=(8-x)*(8-y);\
     const int B=(  x)*(8-y);\
     const int C=(8-x)*(  y);\
     const int D=(  x)*(  y);\
     int i;\
     stride >>= sizeof(pixel)-1;\
     \
     av_assert2(x<8 && y<8 && x>=0 && y>=0);\
 \
     if(D){\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
             dst+= stride;\
             src+= stride;\
         }\
4d943cec
     } else if (B + C) {\
c2625c26
         const int E= B+C;\
         const int step= C ? stride : 1;\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + E*src[step+0]));\
             dst+= stride;\
             src+= stride;\
         }\
4d943cec
     } else {\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0]));\
             dst+= stride;\
             src+= stride;\
         }\
c2625c26
     }\
 }\
79dad2a9
 static void FUNCC(OPNAME ## h264_chroma_mc2)(uint8_t *_dst/*align 8*/, uint8_t *_src/*align 1*/, int stride, int h, int x, int y){\
     pixel *dst = (pixel*)_dst;\
     pixel *src = (pixel*)_src;\
     const int A=(8-x)*(8-y);\
     const int B=(  x)*(8-y);\
     const int C=(8-x)*(  y);\
     const int D=(  x)*(  y);\
     int i;\
c4e394e4
     stride >>= sizeof(pixel)-1;\
79dad2a9
     \
c4e394e4
     av_assert2(x<8 && y<8 && x>=0 && y>=0);\
79dad2a9
 \
     if(D){\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
             OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2]));\
             dst+= stride;\
             src+= stride;\
         }\
982b596e
     } else if (B + C) {\
79dad2a9
         const int E= B+C;\
         const int step= C ? stride : 1;\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + E*src[step+0]));\
             OP(dst[1], (A*src[1] + E*src[step+1]));\
             dst+= stride;\
             src+= stride;\
         }\
982b596e
     } else {\
         for ( i = 0; i < h; i++){\
             OP(dst[0], A * src[0]);\
             OP(dst[1], A * src[1]);\
             dst += stride;\
             src += stride;\
         }\
79dad2a9
     }\
 }\
 \
 static void FUNCC(OPNAME ## h264_chroma_mc4)(uint8_t *_dst/*align 8*/, uint8_t *_src/*align 1*/, int stride, int h, int x, int y){\
     pixel *dst = (pixel*)_dst;\
     pixel *src = (pixel*)_src;\
     const int A=(8-x)*(8-y);\
     const int B=(  x)*(8-y);\
     const int C=(8-x)*(  y);\
     const int D=(  x)*(  y);\
     int i;\
c4e394e4
     stride >>= sizeof(pixel)-1;\
79dad2a9
     \
c4e394e4
     av_assert2(x<8 && y<8 && x>=0 && y>=0);\
79dad2a9
 \
     if(D){\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
             OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2]));\
             OP(dst[2], (A*src[2] + B*src[3] + C*src[stride+2] + D*src[stride+3]));\
             OP(dst[3], (A*src[3] + B*src[4] + C*src[stride+3] + D*src[stride+4]));\
             dst+= stride;\
             src+= stride;\
         }\
982b596e
     } else if (B + C) {\
79dad2a9
         const int E= B+C;\
         const int step= C ? stride : 1;\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + E*src[step+0]));\
             OP(dst[1], (A*src[1] + E*src[step+1]));\
             OP(dst[2], (A*src[2] + E*src[step+2]));\
             OP(dst[3], (A*src[3] + E*src[step+3]));\
             dst+= stride;\
             src+= stride;\
         }\
982b596e
     } else {\
         for ( i = 0; i < h; i++){\
             OP(dst[0], A * src[0]);\
             OP(dst[1], A * src[1]);\
             OP(dst[2], A * src[2]);\
             OP(dst[3], A * src[3]);\
             dst += stride;\
             src += stride;\
         }\
79dad2a9
     }\
 }\
 \
 static void FUNCC(OPNAME ## h264_chroma_mc8)(uint8_t *_dst/*align 8*/, uint8_t *_src/*align 1*/, int stride, int h, int x, int y){\
     pixel *dst = (pixel*)_dst;\
     pixel *src = (pixel*)_src;\
     const int A=(8-x)*(8-y);\
     const int B=(  x)*(8-y);\
     const int C=(8-x)*(  y);\
     const int D=(  x)*(  y);\
     int i;\
c4e394e4
     stride >>= sizeof(pixel)-1;\
79dad2a9
     \
c4e394e4
     av_assert2(x<8 && y<8 && x>=0 && y>=0);\
79dad2a9
 \
     if(D){\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
             OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2]));\
             OP(dst[2], (A*src[2] + B*src[3] + C*src[stride+2] + D*src[stride+3]));\
             OP(dst[3], (A*src[3] + B*src[4] + C*src[stride+3] + D*src[stride+4]));\
             OP(dst[4], (A*src[4] + B*src[5] + C*src[stride+4] + D*src[stride+5]));\
             OP(dst[5], (A*src[5] + B*src[6] + C*src[stride+5] + D*src[stride+6]));\
             OP(dst[6], (A*src[6] + B*src[7] + C*src[stride+6] + D*src[stride+7]));\
             OP(dst[7], (A*src[7] + B*src[8] + C*src[stride+7] + D*src[stride+8]));\
             dst+= stride;\
             src+= stride;\
         }\
982b596e
     } else if (B + C) {\
79dad2a9
         const int E= B+C;\
         const int step= C ? stride : 1;\
         for(i=0; i<h; i++){\
             OP(dst[0], (A*src[0] + E*src[step+0]));\
             OP(dst[1], (A*src[1] + E*src[step+1]));\
             OP(dst[2], (A*src[2] + E*src[step+2]));\
             OP(dst[3], (A*src[3] + E*src[step+3]));\
             OP(dst[4], (A*src[4] + E*src[step+4]));\
             OP(dst[5], (A*src[5] + E*src[step+5]));\
             OP(dst[6], (A*src[6] + E*src[step+6]));\
             OP(dst[7], (A*src[7] + E*src[step+7]));\
             dst+= stride;\
             src+= stride;\
         }\
982b596e
     } else {\
         for ( i = 0; i < h; i++){\
             OP(dst[0], A * src[0]);\
             OP(dst[1], A * src[1]);\
             OP(dst[2], A * src[2]);\
             OP(dst[3], A * src[3]);\
             OP(dst[4], A * src[4]);\
             OP(dst[5], A * src[5]);\
             OP(dst[6], A * src[6]);\
             OP(dst[7], A * src[7]);\
             dst += stride;\
             src += stride;\
         }\
79dad2a9
     }\
 }
 
 #define op_avg(a, b) a = (((a)+(((b) + 32)>>6)+1)>>1)
 #define op_put(a, b) a = (((b) + 32)>>6)
 
 H264_CHROMA_MC(put_       , op_put)
 H264_CHROMA_MC(avg_       , op_avg)
 #undef op_avg
 #undef op_put