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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
|
dnl Intel Pentium mpn_copyd -- copy limb vector, decrementing.
dnl Copyright 1996, 2001, 2002, 2006 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 P5: 1.25 cycles/limb
C void mpn_copyd (mp_ptr dst, mp_srcptr src, mp_size_t size);
C
C See comments in copyi.asm.
defframe(PARAM_SIZE,12)
defframe(PARAM_SRC, 8)
defframe(PARAM_DST, 4)
TEXT
ALIGN(8)
PROLOGUE(mpn_copyd)
deflit(`FRAME',0)
movl PARAM_SRC, %eax
movl PARAM_SIZE, %ecx
pushl %esi FRAME_pushl()
pushl %edi FRAME_pushl()
leal -4(%eax,%ecx,4), %eax C &src[size-1]
movl PARAM_DST, %edx
subl $7, %ecx C size-7
jle L(end)
movl 28-4(%edx,%ecx,4), %esi C prefetch cache, dst[size-1]
nop
L(top):
C eax src, decrementing
C ebx
C ecx counter, limbs
C edx dst
C esi scratch
C edi scratch
C ebp
movl 28-32(%edx,%ecx,4), %esi C prefetch dst cache line
subl $8, %ecx
movl (%eax), %esi C read words pairwise
movl -4(%eax), %edi
movl %esi, 56(%edx,%ecx,4) C store words pairwise
movl %edi, 52(%edx,%ecx,4)
movl -8(%eax), %esi
movl -12(%eax), %edi
movl %esi, 48(%edx,%ecx,4)
movl %edi, 44(%edx,%ecx,4)
movl -16(%eax), %esi
movl -20(%eax), %edi
movl %esi, 40(%edx,%ecx,4)
movl %edi, 36(%edx,%ecx,4)
movl -24(%eax), %esi
movl -28(%eax), %edi
movl %esi, 32(%edx,%ecx,4)
movl %edi, 28(%edx,%ecx,4)
leal -32(%eax), %eax
jg L(top)
L(end):
C ecx -7 to 0, representing respectively 0 to 7 limbs remaining
C eax src end
C edx dst, next location to store
addl $4, %ecx
jle L(no4)
movl (%eax), %esi
movl -4(%eax), %edi
movl %esi, 8(%edx,%ecx,4)
movl %edi, 4(%edx,%ecx,4)
movl -8(%eax), %esi
movl -12(%eax), %edi
movl %esi, (%edx,%ecx,4)
movl %edi, -4(%edx,%ecx,4)
subl $16, %eax
subl $4, %ecx
L(no4):
addl $2, %ecx
jle L(no2)
movl (%eax), %esi
movl -4(%eax), %edi
movl %esi, (%edx,%ecx,4)
movl %edi, -4(%edx,%ecx,4)
subl $8, %eax
subl $2, %ecx
L(no2):
jnz L(done)
movl (%eax), %ecx
movl %ecx, (%edx) C risk of cache bank clash here
L(done):
popl %edi
popl %esi
ret
EPILOGUE()
|
