ffmpeg/libavcodec/x86/idctdsp.asm

   1 ;******************************************************************************
   2 ;* SIMD-optimized IDCT-related routines
   3 ;* Copyright (c) 2008 Loren Merritt
   4 ;* Copyright (c) 2003-2013 Michael Niedermayer
   5 ;* Copyright (c) 2013 Daniel Kang
   6 ;*
   7 ;* This file is part of FFmpeg.
   8 ;*
   9 ;* FFmpeg is free software; you can redistribute it and/or
  10 ;* modify it under the terms of the GNU Lesser General Public
  11 ;* License as published by the Free Software Foundation; either
  12 ;* version 2.1 of the License, or (at your option) any later version.
  13 ;*
  14 ;* FFmpeg is distributed in the hope that it will be useful,
  15 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
  16 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  17 ;* Lesser General Public License for more details.
  18 ;*
  19 ;* You should have received a copy of the GNU Lesser General Public
  20 ;* License along with FFmpeg; if not, write to the Free Software
  21 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  22 ;******************************************************************************
  23
  24 %include "libavutil/x86/x86util.asm"
  25
  26 SECTION_RODATA
  27
  28 cextern pb_80
  29
  30 SECTION_TEXT
  31
  32 ;--------------------------------------------------------------------------
  33 ;void ff_put_signed_pixels_clamped(const int16_t *block, uint8_t *pixels,
  34 ;                                  int line_size)
  35 ;--------------------------------------------------------------------------
  36
  37 %macro PUT_SIGNED_PIXELS_CLAMPED_HALF 1
  38     mova     m1, [blockq+mmsize*0+%1]
  39     mova     m2, [blockq+mmsize*2+%1]
  40 %if mmsize == 8
  41     mova     m3, [blockq+mmsize*4+%1]
  42     mova     m4, [blockq+mmsize*6+%1]
  43 %endif
  44     packsswb m1, [blockq+mmsize*1+%1]
  45     packsswb m2, [blockq+mmsize*3+%1]
  46 %if mmsize == 8
  47     packsswb m3, [blockq+mmsize*5+%1]
  48     packsswb m4, [blockq+mmsize*7+%1]
  49 %endif
  50     paddb    m1, m0
  51     paddb    m2, m0
  52 %if mmsize == 8
  53     paddb    m3, m0
  54     paddb    m4, m0
  55     movq     [pixelsq+lsizeq*0], m1
  56     movq     [pixelsq+lsizeq*1], m2
  57     movq     [pixelsq+lsizeq*2], m3
  58     movq     [pixelsq+lsize3q ], m4
  59 %else
  60     movq     [pixelsq+lsizeq*0], m1
  61     movhps   [pixelsq+lsizeq*1], m1
  62     movq     [pixelsq+lsizeq*2], m2
  63     movhps   [pixelsq+lsize3q ], m2
  64 %endif
  65 %endmacro
  66
  67 %macro PUT_SIGNED_PIXELS_CLAMPED 1
  68 cglobal put_signed_pixels_clamped, 3, 4, %1, block, pixels, lsize, lsize3
  69     mova     m0, [pb_80]
  70     lea      lsize3q, [lsizeq*3]
  71     PUT_SIGNED_PIXELS_CLAMPED_HALF 0
  72     lea      pixelsq, [pixelsq+lsizeq*4]
  73     PUT_SIGNED_PIXELS_CLAMPED_HALF 64
  74     RET
  75 %endmacro
  76
  77 INIT_MMX mmx
  78 PUT_SIGNED_PIXELS_CLAMPED 0
  79 INIT_XMM sse2
  80 PUT_SIGNED_PIXELS_CLAMPED 3