libavcodec/x86/h264_idct_sse2.asm

   1 ;*****************************************************************************
   2 ;* SSE2-optimized H.264 iDCT
   3 ;*****************************************************************************
   4 ;* Copyright (C) 2003-2008 x264 project
   5 ;*
   6 ;* Authors: Laurent Aimar <fenrir@via.ecp.fr>
   7 ;*          Loren Merritt <lorenm@u.washington.edu>
   8 ;*          Holger Lubitz <hal@duncan.ol.sub.de>
   9 ;*          Min Chen <chenm001.163.com>
  10 ;*
  11 ;* This program is free software; you can redistribute it and/or modify
  12 ;* it under the terms of the GNU General Public License as published by
  13 ;* the Free Software Foundation; either version 2 of the License, or
  14 ;* (at your option) any later version.
  15 ;*
  16 ;* This program is distributed in the hope that it will be useful,
  17 ;* but WITHOUT ANY WARRANTY; without even the implied warranty of
  18 ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  19 ;* GNU General Public License for more details.
  20 ;*
  21 ;* You should have received a copy of the GNU General Public License
  22 ;* along with this program; if not, write to the Free Software
  23 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
  24 ;*****************************************************************************
  25
  26 %include "x86inc.asm"
  27 %include "x86util.asm"
  28
  29 SECTION_RODATA
  30 pw_32: times 8 dw 32
  31
  32 SECTION .text
  33
  34 INIT_XMM
  35 cglobal x264_add8x4_idct_sse2, 3,3,8
  36     movq   m0, [r1+ 0]
  37     movq   m1, [r1+ 8]
  38     movq   m2, [r1+16]
  39     movq   m3, [r1+24]
  40     movhps m0, [r1+32]
  41     movhps m1, [r1+40]
  42     movhps m2, [r1+48]
  43     movhps m3, [r1+56]
  44     IDCT4_1D 0,1,2,3,4,5
  45     TRANSPOSE2x4x4W 0,1,2,3,4
  46     paddw m0, [pw_32 GLOBAL]
  47     IDCT4_1D 0,1,2,3,4,5
  48     pxor  m7, m7
  49     STORE_DIFF  m0, m4, m7, [r0]
  50     STORE_DIFF  m1, m4, m7, [r0+r2]
  51     lea   r0, [r0+r2*2]
  52     STORE_DIFF  m2, m4, m7, [r0]
  53     STORE_DIFF  m3, m4, m7, [r0+r2]
  54     RET