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
|
/* Optimized strcmp implementation using basic LoongArch instructions.
Copyright (C) 2023 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
<https://www.gnu.org/licenses/>. */
#include <sysdep.h>
#include <sys/regdef.h>
#include <sys/asm.h>
#if IS_IN (libc)
# define STRCMP_NAME __strcmp_aligned
#else
# define STRCMP_NAME strcmp
#endif
LEAF(STRCMP_NAME, 6)
lu12i.w a4, 0x01010
andi a2, a0, 0x7
ori a4, a4, 0x101
andi a3, a1, 0x7
bstrins.d a4, a4, 63, 32
li.d t7, -1
li.d t8, 8
slli.d a5, a4, 7
bne a2, a3, L(unaligned)
bstrins.d a0, zero, 2, 0
bstrins.d a1, zero, 2, 0
ld.d t0, a0, 0
ld.d t1, a1, 0
slli.d t3, a2, 3
sll.d t2, t7, t3
orn t0, t0, t2
orn t1, t1, t2
sub.d t2, t0, a4
andn t3, a5, t0
and t2, t2, t3
bne t0, t1, L(al_end)
L(al_loop):
bnez t2, L(ret0)
ldx.d t0, a0, t8
ldx.d t1, a1, t8
addi.d t8, t8, 8
sub.d t2, t0, a4
andn t3, a5, t0
and t2, t2, t3
beq t0, t1, L(al_loop)
L(al_end):
xor t3, t0, t1
or t2, t2, t3
ctz.d t3, t2
bstrins.d t3, zero, 2, 0
srl.d t0, t0, t3
srl.d t1, t1, t3
andi t0, t0, 0xff
andi t1, t1, 0xff
sub.d a0, t0, t1
jr ra
nop
L(ret0):
move a0, zero
jr ra
nop
nop
L(unaligned):
slt a6, a3, a2
xor t0, a0, a1
maskeqz t0, t0, a6
xor a0, a0, t0
xor a1, a1, t0
andi a2, a0, 0x7
andi a3, a1, 0x7
bstrins.d a0, zero, 2, 0
bstrins.d a1, zero, 2, 0
ld.d t4, a0, 0
ld.d t1, a1, 0
slli.d a2, a2, 3
slli.d a3, a3, 3
srl.d t0, t4, a2
srl.d t1, t1, a3
srl.d t5, t7, a3
orn t0, t0, t5
orn t1, t1, t5
bne t0, t1, L(not_equal)
sll.d t5, t7, a2
sub.d a3, a2, a3
orn t4, t4, t5
sub.d a2, zero, a3
sub.d t2, t4, a4
andn t3, a5, t4
and t2, t2, t3
bnez t2, L(find_zero)
L(un_loop):
srl.d t5, t4, a3
ldx.d t4, a0, t8
ldx.d t1, a1, t8
addi.d t8, t8, 8
sll.d t0, t4, a2
or t0, t0, t5
bne t0, t1, L(not_equal)
sub.d t2, t4, a4
andn t3, a5, t4
and t2, t2, t3
beqz t2, L(un_loop)
L(find_zero):
sub.d t2, t0, a4
andn t3, a5, t0
and t2, t2, t3
bnez t2, L(ret0)
ldx.d t1, a1, t8
srl.d t0, t4, a3
L(not_equal):
sub.d t2, t0, a4
andn t3, a5, t0
and t2, t2, t3
xor t3, t0, t1
or t2, t2, t3
L(un_end):
ctz.d t3, t2
bstrins.d t3, zero, 2, 0
srl.d t0, t0, t3
srl.d t1, t1, t3
andi t0, t0, 0xff
andi t1, t1, 0xff
sub.d t2, t0, t1
sub.d t3, t1, t0
masknez t0, t2, a6
maskeqz t1, t3, a6
or a0, t0, t1
jr ra
END(STRCMP_NAME)
libc_hidden_builtin_def (STRCMP_NAME)
|
