summaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/mathops.h
blob: 50b0283151294d555a6a2fb4124f8ecd031f94ad (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
/*
 * simple math operations
 * 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_X86_MATHOPS_H
#define AVCODEC_X86_MATHOPS_H

#include "config.h"
#include "libavutil/common.h"

#if ARCH_X86_32

#define MULL MULL
static av_always_inline av_const int MULL(int a, int b, unsigned shift)
{
    int rt, dummy;
    __asm__ (
        "imull %3               \n\t"
        "shrdl %4, %%edx, %%eax \n\t"
        :"=a"(rt), "=d"(dummy)
        :"a"(a), "rm"(b), "ci"((uint8_t)shift)
    );
    return rt;
}

#define MULH MULH
static av_always_inline av_const int MULH(int a, int b)
{
    int rt, dummy;
    __asm__ (
        "imull %3"
        :"=d"(rt), "=a"(dummy)
        :"a"(a), "rm"(b)
    );
    return rt;
}

#define MUL64 MUL64
static av_always_inline av_const int64_t MUL64(int a, int b)
{
    int64_t rt;
    __asm__ (
        "imull %2"
        :"=A"(rt)
        :"a"(a), "rm"(b)
    );
    return rt;
}

#endif /* ARCH_X86_32 */

#if HAVE_CMOV
/* median of 3 */
#define mid_pred mid_pred
static inline av_const int mid_pred(int a, int b, int c)
{
    int i=b;
    __asm__ volatile(
        "cmp    %2, %1 \n\t"
        "cmovg  %1, %0 \n\t"
        "cmovg  %2, %1 \n\t"
        "cmp    %3, %1 \n\t"
        "cmovl  %3, %1 \n\t"
        "cmp    %1, %0 \n\t"
        "cmovg  %1, %0 \n\t"
        :"+&r"(i), "+&r"(a)
        :"r"(b), "r"(c)
    );
    return i;
}
#endif

#if HAVE_CMOV
#define COPY3_IF_LT(x, y, a, b, c, d)\
__asm__ volatile(\
    "cmpl  %0, %3       \n\t"\
    "cmovl %3, %0       \n\t"\
    "cmovl %4, %1       \n\t"\
    "cmovl %5, %2       \n\t"\
    : "+&r" (x), "+&r" (a), "+r" (c)\
    : "r" (y), "r" (b), "r" (d)\
);
#endif

// avoid +32 for shift optimization (gcc should do that ...)
#define NEG_SSR32 NEG_SSR32
static inline  int32_t NEG_SSR32( int32_t a, int8_t s){
    __asm__ ("sarl %1, %0\n\t"
         : "+r" (a)
         : "ic" ((uint8_t)(-s))
    );
    return a;
}

#define NEG_USR32 NEG_USR32
static inline uint32_t NEG_USR32(uint32_t a, int8_t s){
    __asm__ ("shrl %1, %0\n\t"
         : "+r" (a)
         : "ic" ((uint8_t)(-s))
    );
    return a;
}

#endif /* AVCODEC_X86_MATHOPS_H */
OpenPOWER on IntegriCloud