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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
|
dnl Intel P5 mpn_mod_34lsub1 -- mpn remainder modulo 2**24-1.
dnl Copyright 2000-2002 Free Software Foundation, 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: 1.66 cycles/limb
C mp_limb_t mpn_mod_34lsub1 (mp_srcptr src, mp_size_t size)
C
defframe(PARAM_SIZE, 8)
defframe(PARAM_SRC, 4)
TEXT
ALIGN(16)
PROLOGUE(mpn_mod_34lsub1)
deflit(`FRAME',0)
movl PARAM_SIZE, %ecx
movl PARAM_SRC, %edx
subl $2, %ecx
ja L(three_or_more)
movl (%edx), %eax
jne L(one)
movl 4(%edx), %ecx
movl %eax, %edx
shrl $24, %edx
andl $0xFFFFFF, %eax
addl %edx, %eax
movl %ecx, %edx
shrl $16, %ecx
andl $0xFFFF, %edx
shll $8, %edx
addl %ecx, %eax
addl %edx, %eax
L(one):
ret
L(three_or_more):
C eax
C ebx
C ecx size-2
C edx src
C esi
C edi
C ebp
pushl %ebx FRAME_pushl()
pushl %esi FRAME_pushl()
pushl %edi FRAME_pushl()
pushl %ebp FRAME_pushl()
xorl %esi, %esi C 0mod3
xorl %edi, %edi C 1mod3
xorl %ebp, %ebp C 2mod3, and clear carry
L(top):
C eax scratch
C ebx scratch
C ecx counter, limbs
C edx src
C esi 0mod3
C edi 1mod3
C ebp 2mod3
movl (%edx), %eax
movl 4(%edx), %ebx
adcl %eax, %esi
movl 8(%edx), %eax
adcl %ebx, %edi
leal 12(%edx), %edx
adcl %eax, %ebp
leal -2(%ecx), %ecx
decl %ecx
jg L(top)
C ecx is -2, -1 or 0, representing 0, 1 or 2 more limbs, respectively
movl $0xFFFFFFFF, %ebx C mask
incl %ecx
js L(combine) C 0 more
movl (%edx), %eax
movl $0xFFFFFF00, %ebx
adcl %eax, %esi
decl %ecx
js L(combine) C 1 more
movl 4(%edx), %eax
movl $0xFFFF0000, %ebx
adcl %eax, %edi
L(combine):
C eax
C ebx mask
C ecx
C edx
C esi 0mod3
C edi 1mod3
C ebp 2mod3
sbbl %ecx, %ecx C carry
movl %esi, %eax C 0mod3
andl %ebx, %ecx C masked for position
andl $0xFFFFFF, %eax C 0mod3 low
shrl $24, %esi C 0mod3 high
subl %ecx, %eax C apply carry
addl %esi, %eax C apply 0mod3
movl %edi, %ebx C 1mod3
shrl $16, %edi C 1mod3 high
andl $0x0000FFFF, %ebx
shll $8, %ebx C 1mod3 low
addl %edi, %eax C apply 1mod3 high
addl %ebx, %eax C apply 1mod3 low
movl %ebp, %ebx C 2mod3
shrl $8, %ebp C 2mod3 high
andl $0xFF, %ebx
shll $16, %ebx C 2mod3 low
addl %ebp, %eax C apply 2mod3 high
addl %ebx, %eax C apply 2mod3 low
popl %ebp
popl %edi
popl %esi
popl %ebx
ret
EPILOGUE()
|
