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
|
/*
* Alpha optimized DSP utils
* Copyright (c) 2002 Falk Hueffner <falk@debian.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/* This file is intended to be #included with proper definitions of
* PIXOPNAME, BTYPE, AVG2, AVG4 and STORE. */
static void PIXOPNAME(_pixels_axp)(BTYPE *block, const UINT8 *pixels,
int line_size, int h)
{
if ((size_t) pixels & 0x7) {
do {
STORE(uldq(pixels), block);
pixels += line_size;
block += line_size;
} while (--h);
} else {
do {
STORE(ldq(pixels), block);
pixels += line_size;
block += line_size;
} while (--h);
}
}
static void PIXOPNAME(_pixels_x2_axp)(BTYPE *block, const UINT8 *pixels,
int line_size, int h)
{
if ((size_t) pixels & 0x7) {
do {
UINT64 pix1, pix2;
pix1 = uldq(pixels);
pix2 = pix1 >> 8 | ((UINT64) pixels[8] << 56);
STORE(AVG2(pix1, pix2), block);
pixels += line_size;
block += line_size;
} while (--h);
} else {
do {
UINT64 pix1, pix2;
pix1 = ldq(pixels);
pix2 = pix1 >> 8 | ((UINT64) pixels[8] << 56);
STORE(AVG2(pix1, pix2), block);
pixels += line_size;
block += line_size;
} while (--h);
}
}
static void PIXOPNAME(_pixels_y2_axp)(BTYPE *block, const UINT8 *pixels,
int line_size, int h)
{
if ((size_t) pixels & 0x7) {
UINT64 pix = uldq(pixels);
do {
UINT64 next_pix;
pixels += line_size;
next_pix = uldq(pixels);
STORE(AVG2(pix, next_pix), block);
block += line_size;
pix = next_pix;
} while (--h);
} else {
UINT64 pix = ldq(pixels);
do {
UINT64 next_pix;
pixels += line_size;
next_pix = ldq(pixels);
STORE(AVG2(pix, next_pix), block);
block += line_size;
pix = next_pix;
} while (--h);
}
}
/* This could be further sped up by recycling AVG4 intermediate
results from the previous loop pass. */
static void PIXOPNAME(_pixels_xy2_axp)(BTYPE *block, const UINT8 *pixels,
int line_size, int h)
{
if ((size_t) pixels & 0x7) {
UINT64 pix1 = uldq(pixels);
UINT64 pix2 = pix1 >> 8 | ((UINT64) pixels[8] << 56);
do {
UINT64 next_pix1, next_pix2;
pixels += line_size;
next_pix1 = uldq(pixels);
next_pix2 = next_pix1 >> 8 | ((UINT64) pixels[8] << 56);
STORE(AVG4(pix1, pix2, next_pix1, next_pix2), block);
block += line_size;
pix1 = next_pix1;
pix2 = next_pix2;
} while (--h);
} else {
UINT64 pix1 = ldq(pixels);
UINT64 pix2 = pix1 >> 8 | ((UINT64) pixels[8] << 56);
do {
UINT64 next_pix1, next_pix2;
pixels += line_size;
next_pix1 = ldq(pixels);
next_pix2 = next_pix1 >> 8 | ((UINT64) pixels[8] << 56);
STORE(AVG4(pix1, pix2, next_pix1, next_pix2), block);
block += line_size;
pix1 = next_pix1;
pix2 = next_pix2;
} while (--h);
}
}
|
