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
|
/* Optimized memcpy implementation for PowerPC64/POWER8.
Copyright (C) 2017 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C 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 C 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 C Library; if not, see
<http://www.gnu.org/licenses/>. */
#include <sysdep.h>
/* __ptr_t [r3] memcpy (__ptr_t dst [r3], __ptr_t src [r4], size_t len [r5]);
Returns 'dst'. */
#ifndef MEMCPY
# define MEMCPY memcpy
#endif
.machine power8
ENTRY_TOCLESS (MEMCPY, 5)
CALL_MCOUNT 3
cmpldi 7,5,15
bgt 7,L(copy_gt_32)
andi. 9,5,0x1
mr 9,3
beq 0,1f
lbz 10,0(4)
addi 9,3,1
addi 4,4,1
stb 10,0(3)
1:
andi. 10,5,0x2
beq 0,2f
lhz 10,0(4)
addi 9,9,2
addi 4,4,2
sth 10,-2(9)
2:
andi. 10,5,0x4
beq 0,3f
lwz 10,0(4)
addi 9,9,4
addi 4,4,4
stw 10,-4(9)
3:
andi. 10,5,0x8
beqlr 0
ld 10,0(4)
std 10,0(9)
blr
.align 4
L(copy_gt_32):
cmpldi 7,5,32
ble 7,L(copy_gt_16_le_32)
cmpldi 7,5,64
ble 7,L(copy_gt_32_le_64)
cmpldi 7,5,127
mr 9,3
ble 7,L(copy_gt_64_le_128)
addi 8,5,-128
li 11,16
rldicr 8,8,0,56
li 6,32
srdi 10,8,7
addi 0,8,128
addi 10,10,1
li 7,48
mtctr 10
.align 4
L(copy_128):
lxvd2x 10,0,4
lxvd2x 11,4,11
addi 8,4,64
addi 10,9,64
lxvd2x 12,4,6
lxvd2x 0,4,7
addi 4,4,128
stxvd2x 10,0,9
stxvd2x 11,9,11
stxvd2x 12,9,6
stxvd2x 0,9,7
addi 9,9,128
lxvd2x 10,0,8
lxvd2x 11,8,11
lxvd2x 12,8,6
lxvd2x 0,8,7
stxvd2x 10,0,10
stxvd2x 11,10,11
stxvd2x 12,10,6
stxvd2x 0,10,7
bdnz L(copy_128)
add 9,3,0
rldicl 5,5,0,57
L(copy_gt_64_le_128):
cmpldi 7,5,63
ble 7,L(copy_tail_le_64)
li 7,16
li 8,32
lxvd2x 10,0,4
li 10,48
addi 5,5,-64
lxvd2x 11,4,7
lxvd2x 12,4,8
lxvd2x 0,4,10
addi 4,4,64
stxvd2x 10,0,9
stxvd2x 11,9,7
stxvd2x 12,9,8
stxvd2x 0,9,10
addi 9,9,64
L(copy_tail_le_64):
cmpldi 7,5,32
bgt 7,L(copy_tail_gt_32_le_64)
cmpdi 7,5,0
beqlr 7
addi 5,5,-32
li 10,16
add 7,4,5
add 8,9,5
lxvd2x 12,4,5
lxvd2x 0,7,10
stxvd2x 12,9,5
stxvd2x 0,8,10
blr
.align 4
L(copy_gt_16_le_32):
lxvd2x 0,0,4
addi 5,5,-16
lxvd2x 12,4,5
stxvd2x 0,0,3
stxvd2x 12,3,5
blr
.align 4
L(copy_gt_32_le_64):
li 9,16
lxvd2x 12,0,4
addi 5,5,-32
add 8,4,5
add 10,3,5
lxvd2x 0,4,9
stxvd2x 12,0,3
stxvd2x 0,3,9
lxvd2x 12,4,5
lxvd2x 0,8,9
stxvd2x 12,3,5
stxvd2x 0,10,9
blr
.align 4
L(copy_tail_gt_32_le_64):
li 10,16
lxvd2x 12,0,4
addi 5,5,-32
add 7,4,5
add 8,9,5
lxvd2x 0,4,10
stxvd2x 12,0,9
stxvd2x 0,9,10
lxvd2x 12,4,5
lxvd2x 0,7,10
stxvd2x 12,9,5
stxvd2x 0,8,10
blr
END_GEN_TB (MEMCPY,TB_TOCLESS)
libc_hidden_builtin_def (memcpy)
|
