Mercurial > libavcodec.hg
changeset 10372:e55d957ef1a2 libavcodec
ARM: ARMv6 optimised add_pixels_clamped()
author | mru |
---|---|
date | Tue, 06 Oct 2009 21:55:35 +0000 |
parents | e1cddc20418c |
children | 9a46f75a47ee |
files | Makefile arm/dsputil_armv6.S arm/dsputil_init_armv6.c |
diffstat | 3 files changed, 57 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- a/Makefile Tue Oct 06 21:55:30 2009 +0000 +++ b/Makefile Tue Oct 06 21:55:35 2009 +0000 @@ -493,6 +493,7 @@ arm/simple_idct_armv5te.o \ OBJS-$(HAVE_ARMV6) += arm/dsputil_init_armv6.o \ + arm/dsputil_armv6.o \ arm/simple_idct_armv6.o \ OBJS-$(HAVE_ARMVFP) += arm/dsputil_vfp.o \
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/arm/dsputil_armv6.S Tue Oct 06 21:55:35 2009 +0000 @@ -0,0 +1,50 @@ +/* + * 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
--- a/arm/dsputil_init_armv6.c Tue Oct 06 21:55:30 2009 +0000 +++ b/arm/dsputil_init_armv6.c Tue Oct 06 21:55:35 2009 +0000 @@ -25,6 +25,10 @@ void ff_simple_idct_put_armv6(uint8_t *dest, int line_size, DCTELEM *data); void ff_simple_idct_add_armv6(uint8_t *dest, int line_size, DCTELEM *data); +void ff_add_pixels_clamped_armv6(const DCTELEM *block, + uint8_t *restrict pixels, + int line_size); + void av_cold ff_dsputil_init_armv6(DSPContext* c, AVCodecContext *avctx) { if (!avctx->lowres && (avctx->idct_algo == FF_IDCT_AUTO || @@ -34,4 +38,6 @@ c->idct = ff_simple_idct_armv6; c->idct_permutation_type = FF_LIBMPEG2_IDCT_PERM; } + + c->add_pixels_clamped = ff_add_pixels_clamped_armv6; }