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
|
/* x86-64 __mpn_lshift --
Copyright (C) 2007, 2009 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
The GNU MP Library is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1 of the License, or (at your
option) any later version.
The GNU MP Library is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with the GNU MP Library; see the file COPYING.LIB. If not,
see <http://www.gnu.org/licenses/>. */
#include "sysdep.h"
#include "asm-syntax.h"
#define rp %rdi
#define up %rsi
#define n %rdx
#define cnt %cl
.text
ENTRY (__mpn_lshift)
lea -8(rp,n,8), rp
lea -8(up,n,8), up
mov %edx, %eax
and $3, %eax
jne L(nb00)
L(b00): /* n = 4, 8, 12, ... */
mov (up), %r10
mov -8(up), %r11
xor %eax, %eax
shld %cl, %r10, %rax
mov -16(up), %r8
lea 24(rp), rp
sub $4, n
jmp L(00)
L(nb00):/* n = 1, 5, 9, ... */
cmp $2, %eax
jae L(nb01)
L(b01): mov (up), %r9
xor %eax, %eax
shld %cl, %r9, %rax
sub $2, n
jb L(le1)
mov -8(up), %r10
mov -16(up), %r11
lea -8(up), up
lea 16(rp), rp
jmp L(01)
L(le1): shl %cl, %r9
mov %r9, (rp)
ret
L(nb01):/* n = 2, 6, 10, ... */
jne L(b11)
L(b10): mov (up), %r8
mov -8(up), %r9
xor %eax, %eax
shld %cl, %r8, %rax
sub $3, n
jb L(le2)
mov -16(up), %r10
lea -16(up), up
lea 8(rp), rp
jmp L(10)
L(le2): shld %cl, %r9, %r8
mov %r8, (rp)
shl %cl, %r9
mov %r9, -8(rp)
ret
.p2align 4 /* performance critical! */
L(b11): /* n = 3, 7, 11, ... */
mov (up), %r11
mov -8(up), %r8
xor %eax, %eax
shld %cl, %r11, %rax
mov -16(up), %r9
lea -24(up), up
sub $4, n
jb L(end)
.p2align 4
L(top): shld %cl, %r8, %r11
mov (up), %r10
mov %r11, (rp)
L(10): shld %cl, %r9, %r8
mov -8(up), %r11
mov %r8, -8(rp)
L(01): shld %cl, %r10, %r9
mov -16(up), %r8
mov %r9, -16(rp)
L(00): shld %cl, %r11, %r10
mov -24(up), %r9
mov %r10, -24(rp)
add $-32, up
lea -32(rp), rp
sub $4, n
jnc L(top)
L(end): shld %cl, %r8, %r11
mov %r11, (rp)
shld %cl, %r9, %r8
mov %r8, -8(rp)
shl %cl, %r9
mov %r9, -16(rp)
ret
END (__mpn_lshift)
|
