Blame view

ffmpeg-4.2.2/libavcodec/x86/dnxhdenc.asm 1.85 KB
aac5773f   hucm   功能基本完成,接口待打磨
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
  ;************************************************************************
  ;* VC3/DNxHD SIMD functions
  ;* Copyright (c) 2007 Baptiste Coudurier <baptiste dot coudurier at smartjog dot com>
  ;* Copyright (c) 2014 Tiancheng "Timothy" Gu <timothygu99@gmail.com>
  ;*
  ;* This file is part of FFmpeg.
  ;*
  ;* FFmpeg is free software; you can redistribute it and/or
  ;* 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.
  ;*
  ;* FFmpeg is distributed in the hope that it will be useful,
  ;* 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
  ;* License along with FFmpeg; if not, write to the Free Software
  ;* 51, Inc., Foundation Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  ;******************************************************************************
  
  %include "libavutil/x86/x86util.asm"
  
  SECTION .text
  
  ; void get_pixels_8x4_sym_sse2(int16_t *block, const uint8_t *pixels,
  ;                              ptrdiff_t line_size)
  INIT_XMM sse2
  cglobal get_pixels_8x4_sym, 3,3,5, block, pixels, linesize
      pxor      m4,       m4
      movq      m0,       [pixelsq]
      add       pixelsq,  linesizeq
      movq      m1,       [pixelsq]
      movq      m2,       [pixelsq+linesizeq]
      movq      m3,       [pixelsq+linesizeq*2]
      punpcklbw m0,       m4
      punpcklbw m1,       m4
      punpcklbw m2,       m4
      punpcklbw m3,       m4
      mova  [blockq    ], m0
      mova  [blockq+16 ], m1
      mova  [blockq+32 ], m2
      mova  [blockq+48 ], m3
      mova  [blockq+64 ], m3
      mova  [blockq+80 ], m2
      mova  [blockq+96 ], m1
      mova  [blockq+112], m0
      RET