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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
dnl Intel Pentium mpn_mul_1 -- mpn by limb multiplication.
dnl Copyright 1992, 1994, 1996, 1999, 2000, 2002 Free Software Foundation,
dnl Inc.
dnl This file is part of the GNU MP Library.
dnl
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of either:
dnl
dnl * the GNU Lesser General Public License as published by the Free
dnl Software Foundation; either version 3 of the License, or (at your
dnl option) any later version.
dnl
dnl or
dnl
dnl * the GNU General Public License as published by the Free Software
dnl Foundation; either version 2 of the License, or (at your option) any
dnl later version.
dnl
dnl or both in parallel, as here.
dnl
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
dnl for more details.
dnl
dnl You should have received copies of the GNU General Public License and the
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
dnl see https://www.gnu.org/licenses/.
include(`../config.m4')
C P5: 12.0 cycles/limb
C mp_limb_t mpn_mul_1 (mp_ptr dst, mp_srcptr src, mp_size_t size,
C mp_limb_t multiplier);
C mp_limb_t mpn_mul_1c (mp_ptr dst, mp_srcptr src, mp_size_t size,
C mp_limb_t multiplier, mp_limb_t carry);
C
defframe(PARAM_CARRY, 20)
defframe(PARAM_MULTIPLIER,16)
defframe(PARAM_SIZE, 12)
defframe(PARAM_SRC, 8)
defframe(PARAM_DST, 4)
TEXT
ALIGN(8)
PROLOGUE(mpn_mul_1c)
deflit(`FRAME',0)
movl PARAM_CARRY, %ecx
pushl %esi FRAME_pushl()
jmp L(start_1c)
EPILOGUE()
ALIGN(8)
PROLOGUE(mpn_mul_1)
deflit(`FRAME',0)
xorl %ecx, %ecx
pushl %esi FRAME_pushl()
L(start_1c):
movl PARAM_SRC, %esi
movl PARAM_SIZE, %eax
shrl %eax
jnz L(two_or_more)
C one limb only
movl (%esi), %eax
mull PARAM_MULTIPLIER
addl %eax, %ecx
movl PARAM_DST, %eax
adcl $0, %edx
popl %esi
movl %ecx, (%eax)
movl %edx, %eax
ret
L(two_or_more):
C eax size/2
C ebx
C ecx carry
C edx
C esi src
C edi
C ebp
pushl %edi FRAME_pushl()
pushl %ebx FRAME_pushl()
movl PARAM_DST, %edi
leal -1(%eax), %ebx C size/2-1
notl %ebx C -size, preserve carry
leal (%esi,%eax,8), %esi C src end
leal (%edi,%eax,8), %edi C dst end
pushl %ebp FRAME_pushl()
jnc L(top)
C size was odd, process one limb separately
movl (%esi,%ebx,8), %eax
addl $4, %esi
mull PARAM_MULTIPLIER
addl %ecx, %eax
movl %edx, %ecx
movl %eax, (%edi,%ebx,8)
leal 4(%edi), %edi
L(top):
C eax
C ebx counter, negative
C ecx carry
C edx
C esi src end
C edi dst end
C ebp
adcl $0, %ecx
movl (%esi,%ebx,8), %eax
mull PARAM_MULTIPLIER
movl %edx, %ebp
addl %eax, %ecx
adcl $0, %ebp
movl 4(%esi,%ebx,8), %eax
mull PARAM_MULTIPLIER
movl %ecx, (%edi,%ebx,8)
addl %ebp, %eax
movl %eax, 4(%edi,%ebx,8)
incl %ebx
movl %edx, %ecx
jnz L(top)
adcl $0, %ecx
popl %ebp
movl %ecx, %eax
popl %ebx
popl %edi
popl %esi
ret
EPILOGUE()
|
