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
|
dnl ARM mpn_submul_1.
dnl Copyright 2012, 2013 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 3.75
C Cortex-A15 4.0
C This loop complements U on the fly,
C U' = B^n - 1 - U
C and then uses that
C R - U*v = R + U'*v + v - B^n v
C TODO
C * Micro-optimise feed-in code.
C * Optimise for n=1,2 by delaying register saving.
C * Try using ldm/stm.
define(`rp',`r0')
define(`up',`r1')
define(`n', `r2')
define(`v0',`r3')
ASM_START()
PROLOGUE(mpn_submul_1)
stmfd sp!, { r4, r5, r6, r7 }
ands r6, n, #3
mov r12, v0
beq L(fi0)
cmp r6, #2
bcc L(fi1)
beq L(fi2)
L(fi3): ldr r4, [up], #12
mvn r4, r4
ldr r6, [rp, #0]
ldr r5, [up, #-8]
b L(lo3)
L(fi0): ldr r5, [up], #16
mvn r5, r5
ldr r7, [rp], #4
ldr r4, [up, #-12]
b L(lo0)
L(fi1): ldr r4, [up], #4
mvn r4, r4
ldr r6, [rp], #8
subs n, n, #1
beq L(1)
ldr r5, [up]
b L(lo1)
L(fi2): ldr r5, [up], #8
mvn r5, r5
ldr r7, [rp], #12
ldr r4, [up, #-4]
b L(lo2)
ALIGN(16)
L(top): ldr r6, [rp, #-8]
ldr r5, [up]
str r7, [rp, #-12]
L(lo1): umaal r6, r12, r4, v0
add up, up, #16
mvn r5, r5
ldr r7, [rp, #-4]
ldr r4, [up, #-12]
str r6, [rp, #-8]
L(lo0): umaal r7, r12, r5, v0
mvn r4, r4
ldr r6, [rp, #0]
ldr r5, [up, #-8]
str r7, [rp, #-4]
L(lo3): umaal r6, r12, r4, v0
mvn r5, r5
ldr r7, [rp, #4]
ldr r4, [up, #-4]
str r6, [rp], #16
L(lo2): umaal r7, r12, r5, v0
mvn r4, r4
subs n, n, #4
bhi L(top)
ldr r6, [rp, #-8]
str r7, [rp, #-12]
L(1): umaal r6, r12, r4, v0
str r6, [rp, #-8]
sub r0, v0, r12
ldmfd sp!, { r4, r5, r6, r7 }
bx lr
EPILOGUE()
|
