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
|
/* memcmp - compare memory
Copyright (C) 2013-2018 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>
/* Assumptions:
*
* ARMv8-a, AArch64, unaligned accesses.
*/
/* Parameters and result. */
#define src1 x0
#define src2 x1
#define limit x2
#define result w0
/* Internal variables. */
#define data1 x3
#define data1w w3
#define data2 x4
#define data2w w4
#define tmp1 x5
ENTRY_ALIGN (memcmp, 6)
DELOUSE (0)
DELOUSE (1)
DELOUSE (2)
subs limit, limit, 8
b.lo .Lless8
/* Limit >= 8, so check first 8 bytes using unaligned loads. */
ldr data1, [src1], 8
ldr data2, [src2], 8
and tmp1, src1, 7
add limit, limit, tmp1
cmp data1, data2
bne .Lreturn
/* Align src1 and adjust src2 with bytes not yet done. */
sub src1, src1, tmp1
sub src2, src2, tmp1
subs limit, limit, 8
b.ls .Llast_bytes
/* Loop performing 8 bytes per iteration using aligned src1.
Limit is pre-decremented by 8 and must be larger than zero.
Exit if <= 8 bytes left to do or if the data is not equal. */
.p2align 4
.Lloop8:
ldr data1, [src1], 8
ldr data2, [src2], 8
subs limit, limit, 8
ccmp data1, data2, 0, hi /* NZCV = 0b0000. */
b.eq .Lloop8
cmp data1, data2
bne .Lreturn
/* Compare last 1-8 bytes using unaligned access. */
.Llast_bytes:
ldr data1, [src1, limit]
ldr data2, [src2, limit]
/* Compare data bytes and set return value to 0, -1 or 1. */
.Lreturn:
#ifndef __AARCH64EB__
rev data1, data1
rev data2, data2
#endif
cmp data1, data2
.Lret_eq:
cset result, ne
cneg result, result, lo
ret
.p2align 4
/* Compare up to 8 bytes. Limit is [-8..-1]. */
.Lless8:
adds limit, limit, 4
b.lo .Lless4
ldr data1w, [src1], 4
ldr data2w, [src2], 4
cmp data1w, data2w
b.ne .Lreturn
sub limit, limit, 4
.Lless4:
adds limit, limit, 4
beq .Lret_eq
.Lbyte_loop:
ldrb data1w, [src1], 1
ldrb data2w, [src2], 1
subs limit, limit, 1
ccmp data1w, data2w, 0, ne /* NZCV = 0b0000. */
b.eq .Lbyte_loop
sub result, data1w, data2w
ret
END (memcmp)
#undef bcmp
weak_alias (memcmp, bcmp)
libc_hidden_builtin_def (memcmp)
|
