mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-07 11:13:41 +02:00
9f088a1ed4
* qatar/master: mpegvideo: reduce excessive inlining of mpeg_motion() mpegvideo: convert mpegvideo_common.h to a .c file build: factor out mpegvideo.o dependencies to CONFIG_MPEGVIDEO Move MASK_ABS macro to libavcodec/mathops.h x86: move MANGLE() and related macros to libavutil/x86/asm.h x86: rename libavutil/x86_cpu.h to libavutil/x86/asm.h aacdec: Don't fall back to the old output configuration when no old configuration is present. rtmp: Add message tracking rtsp: Support mpegts in raw udp packets rtsp: Support receiving plain data over UDP without any RTP encapsulation rtpdec: Remove an unused include rtpenc: Remove an av_abort() that depends on user-supplied data vsrc_movie: discourage its use with avconv. avconv: allow no input files. avconv: prevent invalid reads in transcode_init() avconv: rename OutputStream.is_past_recording_time to finished. Conflicts: configure doc/filters.texi ffmpeg.c ffmpeg.h libavcodec/Makefile libavcodec/aacdec.c libavcodec/mpegvideo.c libavformat/version.h Merged-by: Michael Niedermayer <michaelni@gmx.at>
71 lines
2.7 KiB
C
71 lines
2.7 KiB
C
/*
|
|
* Copyright (c) 2012 Michael Niedermayer <michaelni@gmx.at>
|
|
*
|
|
* 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 "libavutil/x86/asm.h"
|
|
#include "libavutil/cpu.h"
|
|
#include "libswresample/swresample_internal.h"
|
|
|
|
int swri_resample_int16_mmx2 (struct ResampleContext *c, int16_t *dst, const int16_t *src, int *consumed, int src_size, int dst_size, int update_ctx);
|
|
int swri_resample_int16_ssse3(struct ResampleContext *c, int16_t *dst, const int16_t *src, int *consumed, int src_size, int dst_size, int update_ctx);
|
|
|
|
DECLARE_ALIGNED(16, const uint64_t, ff_resample_int16_rounder)[2] = { 0x0000000000004000ULL, 0x0000000000000000ULL};
|
|
|
|
#define COMMON_CORE_INT16_MMX2 \
|
|
x86_reg len= -2*c->filter_length;\
|
|
__asm__ volatile(\
|
|
"movq "MANGLE(ff_resample_int16_rounder)", %%mm0 \n\t"\
|
|
"1: \n\t"\
|
|
"movq (%1, %0), %%mm1 \n\t"\
|
|
"pmaddwd (%2, %0), %%mm1 \n\t"\
|
|
"paddd %%mm1, %%mm0 \n\t"\
|
|
"add $8, %0 \n\t"\
|
|
" js 1b \n\t"\
|
|
"pshufw $0x0E, %%mm0, %%mm1 \n\t"\
|
|
"paddd %%mm1, %%mm0 \n\t"\
|
|
"psrad $15, %%mm0 \n\t"\
|
|
"packssdw %%mm0, %%mm0 \n\t"\
|
|
"movd %%mm0, (%3) \n\t"\
|
|
: "+r" (len)\
|
|
: "r" (((uint8_t*)(src+sample_index))-len),\
|
|
"r" (((uint8_t*)filter)-len),\
|
|
"r" (dst+dst_index)\
|
|
);
|
|
|
|
#define COMMON_CORE_INT16_SSSE3 \
|
|
x86_reg len= -2*c->filter_length;\
|
|
__asm__ volatile(\
|
|
"movdqa "MANGLE(ff_resample_int16_rounder)", %%xmm0 \n\t"\
|
|
"1: \n\t"\
|
|
"movdqu (%1, %0), %%xmm1 \n\t"\
|
|
"pmaddwd (%2, %0), %%xmm1 \n\t"\
|
|
"paddd %%xmm1, %%xmm0 \n\t"\
|
|
"add $16, %0 \n\t"\
|
|
" js 1b \n\t"\
|
|
"phaddd %%xmm0, %%xmm0 \n\t"\
|
|
"phaddd %%xmm0, %%xmm0 \n\t"\
|
|
"psrad $15, %%xmm0 \n\t"\
|
|
"packssdw %%xmm0, %%xmm0 \n\t"\
|
|
"movd %%xmm0, (%3) \n\t"\
|
|
: "+r" (len)\
|
|
: "r" (((uint8_t*)(src+sample_index))-len),\
|
|
"r" (((uint8_t*)filter)-len),\
|
|
"r" (dst+dst_index)\
|
|
);
|