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
|
dnl ARM mpn_mod_1_1p
dnl Contributed to the GNU project by Torbjörn Granlund.
dnl Copyright 2012 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 cycles/limb
C StrongARM -
C XScale ?
C Cortex-A7 ?
C Cortex-A8 ?
C Cortex-A9 7
C Cortex-A15 6
define(`ap', `r0')
define(`n', `r1')
define(`d', `r2')
define(`cps',`r3')
ASM_START()
PROLOGUE(mpn_mod_1_1p)
push {r4-r10}
add r0, r0, r1, asl #2
ldr r5, [r0, #-4]!
ldr r12, [r0, #-4]!
subs r1, r1, #2
ble L(4)
ldr r8, [r3, #12]
mov r4, r12
mov r10, r5
umull r7, r5, r10, r8
sub r1, r1, #1
b L(mid)
L(top): adds r12, r6, r7
adcs r10, r4, r5
sub r1, r1, #1
mov r6, #0
movcs r6, r8
umull r7, r5, r10, r8
adds r4, r12, r6
subcs r4, r4, r2
L(mid): ldr r6, [r0, #-4]!
teq r1, #0
bne L(top)
adds r12, r6, r7
adcs r5, r4, r5
subcs r5, r5, r2
L(4): ldr r1, [r3, #4]
cmp r1, #0
beq L(7)
ldr r4, [r3, #8]
umull r0, r6, r5, r4
adds r12, r0, r12
addcs r6, r6, #1
rsb r0, r1, #32
mov r0, r12, lsr r0
orr r5, r0, r6, asl r1
mov r12, r12, asl r1
b L(8)
L(7): cmp r5, r2
subcs r5, r5, r2
L(8): ldr r0, [r3, #0]
umull r4, r3, r5, r0
add r5, r5, #1
adds r0, r4, r12
adc r5, r3, r5
mul r5, r2, r5
sub r12, r12, r5
cmp r12, r0
addhi r12, r12, r2
cmp r2, r12
subls r12, r12, r2
mov r0, r12, lsr r1
pop {r4-r10}
bx r14
EPILOGUE()
PROLOGUE(mpn_mod_1_1p_cps)
stmfd sp!, {r4, r5, r6, r14}
mov r5, r0
clz r4, r1
mov r0, r1, asl r4
rsb r6, r0, #0
bl mpn_invert_limb
str r0, [r5, #0]
str r4, [r5, #4]
cmp r4, #0
beq L(2)
rsb r1, r4, #32
mov r3, #1
mov r3, r3, asl r4
orr r3, r3, r0, lsr r1
mul r3, r6, r3
mov r4, r3, lsr r4
str r4, [r5, #8]
L(2): mul r0, r6, r0
str r0, [r5, #12]
ldmfd sp!, {r4, r5, r6, pc}
EPILOGUE()
|
