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
|
dnl ARM mpn_lshift.
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 3.5
C Cortex-A15 ?
define(`rp', `r0')
define(`up', `r1')
define(`n', `r2')
define(`cnt', `r3')
define(`tnc', `r12')
ASM_START()
PROLOGUE(mpn_lshift)
add up, up, n, lsl #2
push {r4, r6, r7, r8}
ldr r4, [up, #-4]!
add rp, rp, n, lsl #2
rsb tnc, cnt, #32
mov r7, r4, lsl cnt
tst n, #1
beq L(evn) C n even
L(odd): subs n, n, #2
bcc L(1) C n = 1
ldr r8, [up, #-4]!
b L(mid)
L(evn): ldr r6, [up, #-4]!
subs n, n, #2
beq L(end)
L(top): ldr r8, [up, #-4]!
orr r7, r7, r6, lsr tnc
str r7, [rp, #-4]!
mov r7, r6, lsl cnt
L(mid): ldr r6, [up, #-4]!
orr r7, r7, r8, lsr tnc
str r7, [rp, #-4]!
mov r7, r8, lsl cnt
subs n, n, #2
bgt L(top)
L(end): orr r7, r7, r6, lsr tnc
str r7, [rp, #-4]!
mov r7, r6, lsl cnt
L(1): str r7, [rp, #-4]
mov r0, r4, lsr tnc
pop {r4, r6, r7, r8}
return r14
EPILOGUE()
|
