Mercurial > libavcodec.hg
view arm/dsputil_armv6.S @ 10994:2179ea01df62 libavcodec
Simplify suffix_length computation, same speed.
author | michael |
---|---|
date | Sun, 24 Jan 2010 18:18:08 +0000 |
parents | e55d957ef1a2 |
children | 0f845e20982a |
line wrap: on
line source
/* * Copyright (c) 2009 Mans Rullgard <mans@mansr.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 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ #include "asm.S" .text function ff_add_pixels_clamped_armv6, export=1 push {r4-r8,lr} mov r3, #8 1: ldm r0!, {r4,r5,r12,lr} ldrd r6, r7, [r1] pkhbt r8, r4, r5, lsl #16 pkhtb r5, r5, r4, asr #16 pkhbt r4, r12, lr, lsl #16 pkhtb lr, lr, r12, asr #16 pld [r1, r2] uxtab16 r8, r8, r6 uxtab16 r5, r5, r6, ror #8 uxtab16 r4, r4, r7 uxtab16 lr, lr, r7, ror #8 usat16 r8, #8, r8 usat16 r5, #8, r5 usat16 r4, #8, r4 usat16 lr, #8, lr orr r6, r8, r5, lsl #8 orr r7, r4, lr, lsl #8 subs r3, r3, #1 strd r6, r7, [r1], r2 bgt 1b pop {r4-r8,pc} .endfunc