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
|
/* Copyright (c) 2012-2013, Linaro Limited
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the Linaro nor the
names of its contributors may be used to endorse or promote products
derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES ; LOSS OF USE,
DATA, OR PROFITS ; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */
/* Assumptions:
*
* ARMv8-a, AArch64
* Unaligned accesses
*
*/
#define dstin x0
#define val w1
#define count x2
#define tmp1 x3
#define tmp1w w3
#define tmp2 x4
#define tmp2w w4
#define zva_len_x x5
#define zva_len w5
#define zva_bits_x x6
#define A_l x7
#define A_lw w7
#define dst x8
#define tmp3w w9
.macro def_fn f p2align=0
.text
.p2align \p2align
.global \f
.type \f, %function
\f:
.endm
def_fn memset p2align=6
mov dst, dstin /* Preserve return value. */
ands A_lw, val, #255
orr A_lw, A_lw, A_lw, lsl #8
orr A_lw, A_lw, A_lw, lsl #16
orr A_l, A_l, A_l, lsl #32
.Ltail_maybe_long:
cmp count, #64
b.ge .Lnot_short
.Ltail_maybe_tiny:
cmp count, #15
b.le .Ltail15tiny
.Ltail63:
ands tmp1, count, #0x30
b.eq .Ltail15
add dst, dst, tmp1
cmp tmp1w, #0x20
b.eq 1f
b.lt 2f
stp A_l, A_l, [dst, #-48]
1:
stp A_l, A_l, [dst, #-32]
2:
stp A_l, A_l, [dst, #-16]
.Ltail15:
and count, count, #15
add dst, dst, count
stp A_l, A_l, [dst, #-16] /* Repeat some/all of last store. */
ret
.Ltail15tiny:
/* Set up to 15 bytes. Does not assume earlier memory
being set. */
tbz count, #3, 1f
str A_l, [dst], #8
1:
tbz count, #2, 1f
str A_lw, [dst], #4
1:
tbz count, #1, 1f
strh A_lw, [dst], #2
1:
tbz count, #0, 1f
strb A_lw, [dst]
1:
ret
/* Critical loop. Start at a new cache line boundary. Assuming
* 64 bytes per line, this ensures the entire loop is in one line. */
.p2align 6
.Lnot_short:
neg tmp2, dst
ands tmp2, tmp2, #15
b.eq 2f
/* Bring DST to 128-bit (16-byte) alignment. We know that there's
* more than that to set, so we simply store 16 bytes and advance by
* the amount required to reach alignment. */
sub count, count, tmp2
stp A_l, A_l, [dst]
add dst, dst, tmp2
/* There may be less than 63 bytes to go now. */
cmp count, #63
b.le .Ltail63
2:
sub dst, dst, #16 /* Pre-bias. */
sub count, count, #64
1:
stp A_l, A_l, [dst, #16]
stp A_l, A_l, [dst, #32]
stp A_l, A_l, [dst, #48]
stp A_l, A_l, [dst, #64]!
subs count, count, #64
b.ge 1b
tst count, #0x3f
add dst, dst, #16
b.ne .Ltail63
ret
|
