view bswap.h @ 728:1fa3820b1a84 libavutil

ARM asm for AV_RN*() ARMv6 and later support unaligned loads and stores for single word/halfword but not double/multiple. GCC is ignorant of this and will always use bytewise accesses for unaligned data. Casting to an int32_t pointer is dangerous since a load/store double or multiple instruction might be used (this happens with some code in FFmpeg). Implementing the AV_[RW]* macros with inline asm using only supported instructions gives fast and safe unaligned accesses. ARM RVCT does the right thing with generic code. This gives an overall speedup of up to 10%.

/*
 * copyright (c) 2006 Michael Niedermayer <[e-mail]>
 *
 * 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
 */

/**
 * @file libavutil/bswap.h
 * byte swapping routines
 */

#ifndef AVUTIL_BSWAP_H
#define AVUTIL_BSWAP_H

#include <stdint.h>
#include "config.h"
#include "common.h"

#if   ARCH_ARM
#   include "arm/bswap.h"
#elif ARCH_BFIN
#   include "bfin/bswap.h"
#elif ARCH_SH4
#   include "sh4/bswap.h"
#elif ARCH_X86
#   include "x86/bswap.h"
#endif

#ifndef bswap_16
static av_always_inline av_const uint16_t bswap_16(uint16_t x)
{
    x= (x>>8) | (x<<8);
    return x;
}
#endif

#ifndef bswap_32
static av_always_inline av_const uint32_t bswap_32(uint32_t x)
{
    x= ((x<<8)&0xFF00FF00) | ((x>>8)&0x00FF00FF);
    x= (x>>16) | (x<<16);
    return x;
}
#endif

#ifndef bswap_64
static inline uint64_t av_const bswap_64(uint64_t x)
{
#if 0
    x= ((x<< 8)&0xFF00FF00FF00FF00ULL) | ((x>> 8)&0x00FF00FF00FF00FFULL);
    x= ((x<<16)&0xFFFF0000FFFF0000ULL) | ((x>>16)&0x0000FFFF0000FFFFULL);
    return (x>>32) | (x<<32);
#else
    union {
        uint64_t ll;
        uint32_t l[2];
    } w, r;
    w.ll = x;
    r.l[0] = bswap_32 (w.l[1]);
    r.l[1] = bswap_32 (w.l[0]);
    return r.ll;
#endif
}
#endif

// be2me ... big-endian to machine-endian
// le2me ... little-endian to machine-endian

#ifdef WORDS_BIGENDIAN
#define be2me_16(x) (x)
#define be2me_32(x) (x)
#define be2me_64(x) (x)
#define le2me_16(x) bswap_16(x)
#define le2me_32(x) bswap_32(x)
#define le2me_64(x) bswap_64(x)
#else
#define be2me_16(x) bswap_16(x)
#define be2me_32(x) bswap_32(x)
#define be2me_64(x) bswap_64(x)
#define le2me_16(x) (x)
#define le2me_32(x) (x)
#define le2me_64(x) (x)
#endif

#endif /* AVUTIL_BSWAP_H */