summaryrefslogtreecommitdiff
path: root/libavcodec/x86/fpel_mmx.c
blob: 384ab89d9c50010ec19aa9b832a14464135a56f7 (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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
/*
 * MMX-optimized avg/put pixel routines
 *
 * Copyright (c) 2000, 2001 Fabrice Bellard
 * Copyright (c) 2002-2004 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 <stddef.h>
#include <stdint.h>

#include "config.h"
#include "dsputil_x86.h"

#if HAVE_MMX_INLINE

// in case more speed is needed - unrolling would certainly help
void ff_avg_pixels8_mmx(uint8_t *block, const uint8_t *pixels,
                        ptrdiff_t line_size, int h)
{
    MOVQ_BFE(mm6);
    JUMPALIGN();
    do {
        __asm__ volatile(
             "movq  %0, %%mm0           \n\t"
             "movq  %1, %%mm1           \n\t"
             PAVGB_MMX(%%mm0, %%mm1, %%mm2, %%mm6)
             "movq  %%mm2, %0           \n\t"
             :"+m"(*block)
             :"m"(*pixels)
             :"memory");
        pixels += line_size;
        block += line_size;
    }
    while (--h);
}

void ff_avg_pixels16_mmx(uint8_t *block, const uint8_t *pixels,
                         ptrdiff_t line_size, int h)
{
    MOVQ_BFE(mm6);
    JUMPALIGN();
    do {
        __asm__ volatile(
             "movq  %0, %%mm0           \n\t"
             "movq  %1, %%mm1           \n\t"
             PAVGB_MMX(%%mm0, %%mm1, %%mm2, %%mm6)
             "movq  %%mm2, %0           \n\t"
             "movq  8%0, %%mm0          \n\t"
             "movq  8%1, %%mm1          \n\t"
             PAVGB_MMX(%%mm0, %%mm1, %%mm2, %%mm6)
             "movq  %%mm2, 8%0          \n\t"
             :"+m"(*block)
             :"m"(*pixels)
             :"memory");
        pixels += line_size;
        block += line_size;
    }
    while (--h);
}

void ff_put_pixels8_mmx(uint8_t *block, const uint8_t *pixels,
                        ptrdiff_t line_size, int h)
{
    __asm__ volatile (
        "lea   (%3, %3), %%"REG_a"      \n\t"
        ".p2align     3                 \n\t"
        "1:                             \n\t"
        "movq  (%1    ), %%mm0          \n\t"
        "movq  (%1, %3), %%mm1          \n\t"
        "movq     %%mm0, (%2)           \n\t"
        "movq     %%mm1, (%2, %3)       \n\t"
        "add  %%"REG_a", %1             \n\t"
        "add  %%"REG_a", %2             \n\t"
        "movq  (%1    ), %%mm0          \n\t"
        "movq  (%1, %3), %%mm1          \n\t"
        "movq     %%mm0, (%2)           \n\t"
        "movq     %%mm1, (%2, %3)       \n\t"
        "add  %%"REG_a", %1             \n\t"
        "add  %%"REG_a", %2             \n\t"
        "subl        $4, %0             \n\t"
        "jnz         1b                 \n\t"
        : "+g"(h), "+r"(pixels),  "+r"(block)
        : "r"((x86_reg)line_size)
        : "%"REG_a, "memory"
        );
}

void ff_put_pixels16_mmx(uint8_t *block, const uint8_t *pixels,
                         ptrdiff_t line_size, int h)
{
    __asm__ volatile (
        "lea   (%3, %3), %%"REG_a"      \n\t"
        ".p2align     3                 \n\t"
        "1:                             \n\t"
        "movq  (%1    ), %%mm0          \n\t"
        "movq 8(%1    ), %%mm4          \n\t"
        "movq  (%1, %3), %%mm1          \n\t"
        "movq 8(%1, %3), %%mm5          \n\t"
        "movq     %%mm0,  (%2)          \n\t"
        "movq     %%mm4, 8(%2)          \n\t"
        "movq     %%mm1,  (%2, %3)      \n\t"
        "movq     %%mm5, 8(%2, %3)      \n\t"
        "add  %%"REG_a", %1             \n\t"
        "add  %%"REG_a", %2             \n\t"
        "movq  (%1    ), %%mm0          \n\t"
        "movq 8(%1    ), %%mm4          \n\t"
        "movq  (%1, %3), %%mm1          \n\t"
        "movq 8(%1, %3), %%mm5          \n\t"
        "movq     %%mm0,  (%2)          \n\t"
        "movq     %%mm4, 8(%2)          \n\t"
        "movq     %%mm1,  (%2, %3)      \n\t"
        "movq     %%mm5, 8(%2, %3)      \n\t"
        "add  %%"REG_a", %1             \n\t"
        "add  %%"REG_a", %2             \n\t"
        "subl        $4, %0             \n\t"
        "jnz         1b                 \n\t"
        : "+g"(h), "+r"(pixels),  "+r"(block)
        : "r"((x86_reg)line_size)
        : "%"REG_a, "memory"
        );
}

#endif /* HAVE_MMX_INLINE */