ffmpeg/libavcodec/x86/dnxhdenc.asm

   1 ;************************************************************************
   2 ;* VC3/DNxHD SIMD functions
   3 ;* Copyright (c) 2007 Baptiste Coudurier <baptiste dot coudurier at smartjog dot com>
   4 ;* Copyright (c) 2014 Tiancheng "Timothy" Gu <timothygu99@gmail.com>
   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 ;* 51, Inc., Foundation Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  21 ;******************************************************************************
  22
  23 %include "libavutil/x86/x86util.asm"
  24
  25 section .text
  26
  27 ; void get_pixels_8x4_sym_sse2(int16_t *block, const uint8_t *pixels,
  28 ;                              ptrdiff_t line_size)
  29 INIT_XMM sse2
  30 cglobal get_pixels_8x4_sym, 3,3,5, block, pixels, linesize
  31     pxor      m4,       m4
  32     movq      m0,       [pixelsq]
  33     add       pixelsq,  linesizeq
  34     movq      m1,       [pixelsq]
  35     movq      m2,       [pixelsq+linesizeq]
  36     movq      m3,       [pixelsq+linesizeq*2]
  37     punpcklbw m0,       m4
  38     punpcklbw m1,       m4
  39     punpcklbw m2,       m4
  40     punpcklbw m3,       m4
  41     mova  [blockq    ], m0
  42     mova  [blockq+16 ], m1
  43     mova  [blockq+32 ], m2
  44     mova  [blockq+48 ], m3
  45     mova  [blockq+64 ], m3
  46     mova  [blockq+80 ], m2
  47     mova  [blockq+96 ], m1
  48     mova  [blockq+112], m0
  49     RET