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
|
/* Pentium __mpn_add_n -- Add two limb vectors of the same length > 0 and store
sum in a third limb vector.
Copyright (C) 1992, 1994, 1995, 1996 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
The GNU MP Library is free software; you can redistribute it and/or modify
it under the terms of the GNU Library General Public License as published by
the Free Software Foundation; either version 2 of the License, or (at your
option) any later version.
The GNU MP Library 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 Library General Public
License for more details.
You should have received a copy of the GNU Library General Public License
along with the GNU MP Library; see the file COPYING.LIB. If not, write to
the Free Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
/*
INPUT PARAMETERS
res_ptr (sp + 4)
s1_ptr (sp + 8)
s2_ptr (sp + 12)
size (sp + 16)
*/
#include "sysdep.h"
#include "asm-syntax.h"
.text
ALIGN (3)
.globl C_SYMBOL_NAME(__mpn_add_n)
C_SYMBOL_NAME(__mpn_add_n:)
pushl %edi
pushl %esi
pushl %ebx
pushl %ebp
movl 20(%esp),%edi /* res_ptr */
movl 24(%esp),%esi /* s1_ptr */
movl 28(%esp),%ebp /* s2_ptr */
movl 32(%esp),%ecx /* size */
movl (%ebp),%ebx
decl %ecx
movl %ecx,%edx
shrl $3,%ecx
andl $7,%edx
testl %ecx,%ecx /* zero carry flag */
jz Lend
pushl %edx
ALIGN (3)
Loop: movl 28(%edi),%eax /* fetch destination cache line */
leal 32(%edi),%edi
L1: movl (%esi),%eax
movl 4(%esi),%edx
adcl %ebx,%eax
movl 4(%ebp),%ebx
adcl %ebx,%edx
movl 8(%ebp),%ebx
movl %eax,-32(%edi)
movl %edx,-28(%edi)
L2: movl 8(%esi),%eax
movl 12(%esi),%edx
adcl %ebx,%eax
movl 12(%ebp),%ebx
adcl %ebx,%edx
movl 16(%ebp),%ebx
movl %eax,-24(%edi)
movl %edx,-20(%edi)
L3: movl 16(%esi),%eax
movl 20(%esi),%edx
adcl %ebx,%eax
movl 20(%ebp),%ebx
adcl %ebx,%edx
movl 24(%ebp),%ebx
movl %eax,-16(%edi)
movl %edx,-12(%edi)
L4: movl 24(%esi),%eax
movl 28(%esi),%edx
adcl %ebx,%eax
movl 28(%ebp),%ebx
adcl %ebx,%edx
movl 32(%ebp),%ebx
movl %eax,-8(%edi)
movl %edx,-4(%edi)
leal 32(%esi),%esi
leal 32(%ebp),%ebp
decl %ecx
jnz Loop
popl %edx
Lend:
decl %edx /* test %edx w/o clobbering carry */
js Lend2
incl %edx
Loop2:
leal 4(%edi),%edi
movl (%esi),%eax
adcl %ebx,%eax
movl 4(%ebp),%ebx
movl %eax,-4(%edi)
leal 4(%esi),%esi
leal 4(%ebp),%ebp
decl %edx
jnz Loop2
Lend2:
movl (%esi),%eax
adcl %ebx,%eax
movl %eax,(%edi)
sbbl %eax,%eax
negl %eax
popl %ebp
popl %ebx
popl %esi
popl %edi
ret
|
