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
|
dnl AMD64 mpn_copyi -- copy limb vector, incrementing.
dnl Copyright 2003, 2005, 2007, 2011, 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 AMD K8,K9 1
C AMD K10 1
C AMD bd1 1.36
C AMD bobcat 1.71
C Intel P4 2-3
C Intel core2 1
C Intel NHM 1
C Intel SBR 1
C Intel atom 2
C VIA nano 2
IFSTD(`define(`rp',`%rdi')')
IFSTD(`define(`up',`%rsi')')
IFSTD(`define(`n', `%rdx')')
IFDOS(`define(`rp',`%rcx')')
IFDOS(`define(`up',`%rdx')')
IFDOS(`define(`n', `%r8')')
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
ASM_START()
TEXT
ALIGN(64)
.byte 0,0,0,0,0,0
PROLOGUE(mpn_copyi)
lea -8(rp), rp
sub $4, n
jc L(end)
L(top): mov (up), %rax
mov 8(up), %r9
lea 32(rp), rp
mov 16(up), %r10
mov 24(up), %r11
lea 32(up), up
mov %rax, -24(rp)
mov %r9, -16(rp)
sub $4, n
mov %r10, -8(rp)
mov %r11, (rp)
jnc L(top)
L(end): shr R32(n)
jnc 1f
mov (up), %rax
mov %rax, 8(rp)
lea 8(rp), rp
lea 8(up), up
1: shr R32(n)
jnc 1f
mov (up), %rax
mov 8(up), %r9
mov %rax, 8(rp)
mov %r9, 16(rp)
1: ret
EPILOGUE()
|
