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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
|
dnl Intel Pentium mpn_com -- mpn ones complement.
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: 1.75 cycles/limb
NAILS_SUPPORT(0-31)
C void mpn_com (mp_ptr dst, mp_srcptr src, mp_size_t size);
C
C This code is similar to mpn_copyi, basically there's just some "xorl
C $GMP_NUMB_MASK"s inserted.
C
C Alternatives:
C
C On P55 some MMX code could be 1.25 c/l (8 limb unrolled) if src and dst
C are the same alignment mod 8, but it doesn't seem worth the trouble for
C just that case (there'd need to be some plain integer available too for
C the unaligned case).
defframe(PARAM_SIZE,12)
defframe(PARAM_SRC, 8)
defframe(PARAM_DST, 4)
TEXT
ALIGN(8)
PROLOGUE(mpn_com)
deflit(`FRAME',0)
movl PARAM_SRC, %eax
movl PARAM_SIZE, %ecx
pushl %esi FRAME_pushl()
pushl %edi FRAME_pushl()
leal (%eax,%ecx,4), %eax
xorl $-1, %ecx C -size-1
movl PARAM_DST, %edx
addl $8, %ecx C -size+7
jns L(end)
movl (%edx), %esi C fetch destination cache line
nop
L(top):
C eax &src[size]
C ebx
C ecx counter, limbs, negative
C edx dst, incrementing
C esi scratch
C edi scratch
C ebp
movl 28(%edx), %esi C destination prefetch
addl $32, %edx
movl -28(%eax,%ecx,4), %esi
movl -24(%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, -32(%edx)
movl %edi, -28(%edx)
movl -20(%eax,%ecx,4), %esi
movl -16(%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, -24(%edx)
movl %edi, -20(%edx)
movl -12(%eax,%ecx,4), %esi
movl -8(%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, -16(%edx)
movl %edi, -12(%edx)
movl -4(%eax,%ecx,4), %esi
movl (%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, -8(%edx)
movl %edi, -4(%edx)
addl $8, %ecx
js L(top)
L(end):
C eax &src[size]
C ecx 0 to 7, representing respectively 7 to 0 limbs remaining
C edx dst, next location to store
subl $4, %ecx
nop
jns L(no4)
movl -12(%eax,%ecx,4), %esi
movl -8(%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, (%edx)
movl %edi, 4(%edx)
movl -4(%eax,%ecx,4), %esi
movl (%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, 8(%edx)
movl %edi, 12(%edx)
addl $16, %edx
addl $4, %ecx
L(no4):
subl $2, %ecx
nop
jns L(no2)
movl -4(%eax,%ecx,4), %esi
movl (%eax,%ecx,4), %edi
xorl $GMP_NUMB_MASK, %esi
xorl $GMP_NUMB_MASK, %edi
movl %esi, (%edx)
movl %edi, 4(%edx)
addl $8, %edx
addl $2, %ecx
L(no2):
popl %edi
jnz L(done)
movl -4(%eax), %ecx
xorl $GMP_NUMB_MASK, %ecx
popl %esi
movl %ecx, (%edx)
ret
L(done):
popl %esi
ret
EPILOGUE()
|
