mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-11-26 19:01:44 +02:00
a22ae9f0c5
The common case of the pointer having increased by one packet (which results
in no change to the modulus) can be detected with a 64-bit subtraction,
which is far cheaper than a division on many platforms.
Before After
Mean StdDev Mean StdDev Change
Divisions 248.3 8.8 51.5 7.4 +381.7%
Overall 2773.2 25.6 2372.5 43.1 +16.9%
Signed-off-by: Martin Storsjö <martin@martin.st>
228 lines
5.3 KiB
C
228 lines
5.3 KiB
C
/*
|
|
* simple math operations
|
|
* Copyright (c) 2001, 2002 Fabrice Bellard
|
|
* Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
|
|
*
|
|
* This file is part of Libav.
|
|
*
|
|
* Libav 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.
|
|
*
|
|
* Libav 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 Libav; 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 <stdint.h>
|
|
|
|
#include "libavutil/common.h"
|
|
#include "config.h"
|
|
|
|
extern const uint32_t ff_inverse[257];
|
|
extern const uint8_t ff_reverse[256];
|
|
extern const uint8_t ff_sqrt_tab[256];
|
|
|
|
#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 MUL64
|
|
# define MUL64(a,b) ((int64_t)(a) * (int64_t)(b))
|
|
#endif
|
|
|
|
#ifndef MULL
|
|
# define MULL(a,b,s) (MUL64(a, b) >> (s))
|
|
#endif
|
|
|
|
#ifndef MULH
|
|
static av_always_inline int MULH(int a, int b){
|
|
return MUL64(a, b) >> 32;
|
|
}
|
|
#endif
|
|
|
|
#ifndef UMULH
|
|
static av_always_inline unsigned UMULH(unsigned a, unsigned b){
|
|
return ((uint64_t)(a) * (uint64_t)(b))>>32;
|
|
}
|
|
#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)
|
|
{
|
|
unsigned shift = 8 * sizeof(int) - bits;
|
|
union { unsigned u; int s; } v = { (unsigned) val << shift };
|
|
return v.s >> shift;
|
|
}
|
|
#endif
|
|
|
|
#ifndef zero_extend
|
|
static inline av_const unsigned zero_extend(unsigned val, unsigned bits)
|
|
{
|
|
return (val << ((8 * sizeof(int)) - bits)) >> ((8 * sizeof(int)) - bits);
|
|
}
|
|
#endif
|
|
|
|
#ifndef COPY3_IF_LT
|
|
#define COPY3_IF_LT(x, y, a, b, c, d)\
|
|
if ((y) < (x)) {\
|
|
(x) = (y);\
|
|
(a) = (b);\
|
|
(c) = (d);\
|
|
}
|
|
#endif
|
|
|
|
#ifndef MASK_ABS
|
|
#define MASK_ABS(mask, level) do { \
|
|
mask = level >> 31; \
|
|
level = (level ^ mask) - mask; \
|
|
} while (0)
|
|
#endif
|
|
|
|
#ifndef NEG_SSR32
|
|
# define NEG_SSR32(a,s) ((( int32_t)(a))>>(32-(s)))
|
|
#endif
|
|
|
|
#ifndef NEG_USR32
|
|
# define NEG_USR32(a,s) (((uint32_t)(a))>>(32-(s)))
|
|
#endif
|
|
|
|
#if HAVE_BIGENDIAN
|
|
# ifndef PACK_2U8
|
|
# define PACK_2U8(a,b) (((a) << 8) | (b))
|
|
# endif
|
|
# ifndef PACK_4U8
|
|
# define PACK_4U8(a,b,c,d) (((a) << 24) | ((b) << 16) | ((c) << 8) | (d))
|
|
# endif
|
|
# ifndef PACK_2U16
|
|
# define PACK_2U16(a,b) (((a) << 16) | (b))
|
|
# endif
|
|
#else
|
|
# ifndef PACK_2U8
|
|
# define PACK_2U8(a,b) (((b) << 8) | (a))
|
|
# endif
|
|
# ifndef PACK_4U2
|
|
# define PACK_4U8(a,b,c,d) (((d) << 24) | ((c) << 16) | ((b) << 8) | (a))
|
|
# endif
|
|
# ifndef PACK_2U16
|
|
# define PACK_2U16(a,b) (((b) << 16) | (a))
|
|
# endif
|
|
#endif
|
|
|
|
#ifndef PACK_2S8
|
|
# define PACK_2S8(a,b) PACK_2U8((a)&255, (b)&255)
|
|
#endif
|
|
#ifndef PACK_4S8
|
|
# define PACK_4S8(a,b,c,d) PACK_4U8((a)&255, (b)&255, (c)&255, (d)&255)
|
|
#endif
|
|
#ifndef PACK_2S16
|
|
# define PACK_2S16(a,b) PACK_2U16((a)&0xffff, (b)&0xffff)
|
|
#endif
|
|
|
|
#ifndef FASTDIV
|
|
# define FASTDIV(a,b) ((uint32_t)((((uint64_t)a) * ff_inverse[b]) >> 32))
|
|
#endif /* FASTDIV */
|
|
|
|
#ifndef MOD_UNLIKELY
|
|
# define MOD_UNLIKELY(modulus, dividend, divisor, prev_dividend) \
|
|
do { \
|
|
if ((prev_dividend) == 0 || (dividend) - (prev_dividend) != (divisor)) \
|
|
(modulus) = (dividend) % (divisor); \
|
|
(prev_dividend) = (dividend); \
|
|
} while (0)
|
|
#endif
|
|
|
|
static inline av_const unsigned int ff_sqrt(unsigned int a)
|
|
{
|
|
unsigned int b;
|
|
|
|
if (a < 255) return (ff_sqrt_tab[a + 1] - 1) >> 4;
|
|
else if (a < (1 << 12)) b = ff_sqrt_tab[a >> 4] >> 2;
|
|
#if !CONFIG_SMALL
|
|
else if (a < (1 << 14)) b = ff_sqrt_tab[a >> 6] >> 1;
|
|
else if (a < (1 << 16)) b = ff_sqrt_tab[a >> 8] ;
|
|
#endif
|
|
else {
|
|
int s = av_log2_16bit(a >> 16) >> 1;
|
|
unsigned int c = a >> (s + 2);
|
|
b = ff_sqrt_tab[c >> (s + 8)];
|
|
b = FASTDIV(c,b) + (b << s);
|
|
}
|
|
|
|
return b - (a < b * b);
|
|
}
|
|
|
|
#endif /* AVCODEC_MATHOPS_H */
|