annotate mathops.h @ 10874:bcfe2acbf190 libavcodec

AAC: Compress codebook tables and optimise sign bit handling The codebooks each consist of small number of values repeated in groups of 2 or 4. Storing the codebooks as a packed list of 2- or 4-bit indexes into a table reduces their size substantially (from 7.5k to 1.5k), resulting in less cache pressure. For the band types with sign bits in the bitstream, storing the number and position of non-zero codebook values using a few bits avoids multiple get_bits() calls and floating-point comparisons which gcc handles miserably. Some float/int type punning also avoids gcc brain damage. Overall speedup 20-35% on Cortex-A8, 20% on Core i7.

/*
 * simple math operations
 * Copyright (c) 2001, 2002 Fabrice Bellard
 * Copyright (c) 2006 Michael Niedermayer <[e-mail]> et al
 *
 * 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
 */
#ifndef AVCODEC_MATHOPS_H
#define AVCODEC_MATHOPS_H

#include "libavutil/common.h"

#if   ARCH_ARM
#   include "arm/mathops.h"
#elif ARCH_AVR32
#   include "avr32/mathops.h"
#elif ARCH_BFIN
#   include "bfin/mathops.h"
#elif ARCH_MIPS
#   include "mips/mathops.h"
#elif ARCH_PPC
#   include "ppc/mathops.h"
#elif ARCH_X86
#   include "x86/mathops.h"
#endif

/* generic implementation */

#ifndef MULL
#   define MULL(a,b,s) (((int64_t)(a) * (int64_t)(b)) >> (s))
#endif

#ifndef MULH
//gcc 3.4 creates an incredibly bloated mess out of this
//#    define MULH(a,b) (((int64_t)(a) * (int64_t)(b))>>32)

static av_always_inline int MULH(int a, int b){
    return ((int64_t)(a) * (int64_t)(b))>>32;
}
#endif

#ifndef MUL64
#   define MUL64(a,b) ((int64_t)(a) * (int64_t)(b))
#endif

#ifndef MAC64
#   define MAC64(d, a, b) ((d) += MUL64(a, b))
#endif

#ifndef MLS64
#   define MLS64(d, a, b) ((d) -= MUL64(a, b))
#endif

/* signed 16x16 -> 32 multiply add accumulate */
#ifndef MAC16
#   define MAC16(rt, ra, rb) rt += (ra) * (rb)
#endif

/* signed 16x16 -> 32 multiply */
#ifndef MUL16
#   define MUL16(ra, rb) ((ra) * (rb))
#endif

#ifndef MLS16
#   define MLS16(rt, ra, rb) ((rt) -= (ra) * (rb))
#endif

/* median of 3 */
#ifndef mid_pred
#define mid_pred mid_pred
static inline av_const int mid_pred(int a, int b, int c)
{
#if 0
    int t= (a-b)&((a-b)>>31);
    a-=t;
    b+=t;
    b-= (b-c)&((b-c)>>31);
    b+= (a-b)&((a-b)>>31);

    return b;
#else
    if(a>b){
        if(c>b){
            if(c>a) b=a;
            else    b=c;
        }
    }else{
        if(b>c){
            if(c>a) b=c;
            else    b=a;
        }
    }
    return b;
#endif
}
#endif

#ifndef sign_extend
static inline av_const int sign_extend(int val, unsigned bits)
{
    return (val << (INT_BIT - bits)) >> (INT_BIT - bits);
}
#endif

#endif /* AVCODEC_MATHOPS_H */