Mercurial > libavcodec.hg

view x86/h264_idct_sse2.asm @ 12194:80b142c2e9f7 libavcodec

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Change function prototypes for width=8 inner and mbedge loopfilter functions so that it does both U and V planes at the same time. This will have speed advantages when using SSE2 (or higher) optimizations, since we can do both the U and V rows together in a single xmm register. This also renames filter16 to filter16y and filter8 to filter8uv so that it's more obvious what each function is used for.
author rbultje
date Mon, 19 Jul 2010 21:18:04 +0000
parents 980030a3e315
children 14896fa76003
line wrap: on
line source

;*****************************************************************************
;* SSE2-optimized H.264 iDCT
;*****************************************************************************
;* Copyright (C) 2003-2008 x264 project
;*
;* Authors: Laurent Aimar <fenrir@via.ecp.fr>
;*          Loren Merritt <lorenm@u.washington.edu>
;*          Holger Lubitz <hal@duncan.ol.sub.de>
;*          Min Chen <chenm001.163.com>
;*
;* This program is free software; you can redistribute it and/or modify
;* it under the terms of the GNU General Public License as published by
;* the Free Software Foundation; either version 2 of the License, or
;* (at your option) any later version.
;*
;* This program 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 General Public License for more details.
;*
;* You should have received a copy of the GNU General Public License
;* along with this program; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
;*****************************************************************************

%include "x86inc.asm"
%include "x86util.asm"

SECTION_RODATA
pw_32: times 8 dw 32

SECTION .text

INIT_XMM
cglobal x264_add8x4_idct_sse2, 3,3,8
    movq   m0, [r1+ 0]
    movq   m1, [r1+ 8]
    movq   m2, [r1+16]
    movq   m3, [r1+24]
    movhps m0, [r1+32]
    movhps m1, [r1+40]
    movhps m2, [r1+48]
    movhps m3, [r1+56]
    IDCT4_1D 0,1,2,3,4,5
    TRANSPOSE2x4x4W 0,1,2,3,4
    paddw m0, [pw_32]
    IDCT4_1D 0,1,2,3,4,5
    pxor  m7, m7
    STORE_DIFF  m0, m4, m7, [r0]
    STORE_DIFF  m1, m4, m7, [r0+r2]
    lea   r0, [r0+r2*2]
    STORE_DIFF  m2, m4, m7, [r0]
    STORE_DIFF  m3, m4, m7, [r0+r2]
    RET