ffmpeg/libavcodec/x86/deinterlace.asm

   1 ;******************************************************************************
   2 ;* SIMD-optimized deinterlacing functions
   3 ;* Copyright (c) 2010 Vitor Sessak
   4 ;* Copyright (c) 2002 Michael Niedermayer
   5 ;*
   6 ;* This file is part of FFmpeg.
   7 ;*
   8 ;* FFmpeg is free software; you can redistribute it and/or
   9 ;* modify it under the terms of the GNU Lesser General Public
  10 ;* License as published by the Free Software Foundation; either
  11 ;* version 2.1 of the License, or (at your option) any later version.
  12 ;*
  13 ;* FFmpeg is distributed in the hope that it will be useful,
  14 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16 ;* Lesser General Public License for more details.
  17 ;*
  18 ;* You should have received a copy of the GNU Lesser General Public
  19 ;* License along with FFmpeg; if not, write to the Free Software
  20 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  21 ;******************************************************************************
  22
  23 %include "libavutil/x86/x86util.asm"
  24
  25 SECTION_RODATA
  26
  27 cextern pw_4
  28
  29 SECTION .text
  30
  31 %macro DEINTERLACE 1
  32 %ifidn %1, inplace
  33 ;void ff_deinterlace_line_inplace_mmx(const uint8_t *lum_m4, const uint8_t *lum_m3, const uint8_t *lum_m2, const uint8_t *lum_m1, const uint8_t *lum,  int size)
  34 cglobal deinterlace_line_inplace_mmx, 6,6,7,      lum_m4, lum_m3, lum_m2, lum_m1, lum, size
  35 %else
  36 ;void ff_deinterlace_line_mmx(uint8_t *dst, const uint8_t *lum_m4, const uint8_t *lum_m3, const uint8_t *lum_m2, const uint8_t *lum_m1, const uint8_t *lum,  int size)
  37 cglobal deinterlace_line_mmx,         7,7,7, dst, lum_m4, lum_m3, lum_m2, lum_m1, lum, size
  38 %endif
  39     pxor  mm7, mm7
  40     movq  mm6, [pw_4]
  41 .nextrow:
  42     movd  mm0, [lum_m4q]
  43     movd  mm1, [lum_m3q]
  44     movd  mm2, [lum_m2q]
  45 %ifidn %1, inplace
  46     movd [lum_m4q], mm2
  47 %endif
  48     movd  mm3, [lum_m1q]
  49     movd  mm4, [lumq]
  50     punpcklbw mm0, mm7
  51     punpcklbw mm1, mm7
  52     punpcklbw mm2, mm7
  53     punpcklbw mm3, mm7
  54     punpcklbw mm4, mm7
  55     paddw     mm1, mm3
  56     psllw     mm2, 1
  57     paddw     mm0, mm4
  58     psllw     mm1, 2
  59     paddw     mm2, mm6
  60     paddw     mm1, mm2
  61     psubusw   mm1, mm0
  62     psrlw     mm1, 3
  63     packuswb  mm1, mm7
  64 %ifidn %1, inplace
  65     movd [lum_m2q], mm1
  66 %else
  67     movd   [dstq], mm1
  68     add       dstq, 4
  69 %endif
  70     add    lum_m4q, 4
  71     add    lum_m3q, 4
  72     add    lum_m2q, 4
  73     add    lum_m1q, 4
  74     add       lumq, 4
  75     sub      sized, 4
  76     jg .nextrow
  77     REP_RET
  78 %endmacro
  79
  80 DEINTERLACE ""
  81
  82 DEINTERLACE inplace