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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
|
/* Copyright (C) 2017-2018 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, falkor, unaligned accesses. */
#define dstin x0
#define src x1
#define count x2
#define dstlen x3
#define dst x3
#define srcend x4
#define dstend x5
#define A_l x6
#define A_lw w6
#define A_h x7
#define A_hw w7
#define B_l x8
#define B_lw w8
#define B_h x9
#define C_l x10
#define C_h x11
#define D_l x12
#define D_h x13
#define E_l src
#define E_h count
#define F_l srcend
#define F_h dst
#define tmp1 x14
/* Alias with A_l and A_h to train the prefetcher. */
#define Q_l x22
#define Q_h x23
/* RATIONALE:
The copy has 4 distinct parts:
* Small copies of 16 bytes and under
* Medium sized copies of 17-96 bytes
* Large copies where the source address is higher than the destination
(forward copies)
* Large copies where the destination address is higher than the source
(copy backward, or move).
We use only two registerpairs x6,x7 and x22,x23 for the copies and copy 32
bytes at a time to correctly train the hardware prefetcher for better
throughput. */
ENTRY_ALIGN (__memmove_falkor, 6)
sub tmp1, dstin, src
add srcend, src, count
add dstend, dstin, count
cmp count, 96
ccmp tmp1, count, 2, hi
b.lo L(move_long)
cmp count, 16
b.ls L(copy16)
cmp count, 96
b.hi L(copy_long)
/* Medium copies: 17..96 bytes. */
sub tmp1, count, 1
ldp A_l, A_h, [src]
tbnz tmp1, 6, L(copy96)
ldp D_l, D_h, [srcend, -16]
tbz tmp1, 5, 1f
ldp B_l, B_h, [src, 16]
ldp C_l, C_h, [srcend, -32]
stp B_l, B_h, [dstin, 16]
stp C_l, C_h, [dstend, -32]
1:
stp A_l, A_h, [dstin]
stp D_l, D_h, [dstend, -16]
ret
.p2align 4
/* Small copies: 0..16 bytes. */
L(copy16):
cmp count, 8
b.lo 1f
ldr A_l, [src]
ldr A_h, [srcend, -8]
str A_l, [dstin]
str A_h, [dstend, -8]
ret
.p2align 4
1:
/* 4-7 */
tbz count, 2, 1f
ldr A_lw, [src]
ldr A_hw, [srcend, -4]
str A_lw, [dstin]
str A_hw, [dstend, -4]
ret
.p2align 4
1:
/* 2-3 */
tbz count, 1, 1f
ldrh A_lw, [src]
ldrh A_hw, [srcend, -2]
strh A_lw, [dstin]
strh A_hw, [dstend, -2]
ret
.p2align 4
1:
/* 0-1 */
tbz count, 0, 1f
ldrb A_lw, [src]
strb A_lw, [dstin]
1: ret
.p2align 4
/* Copy 64..96 bytes. Copy 64 bytes from the start and
32 bytes from the end. */
L(copy96):
ldp B_l, B_h, [src, 16]
ldp C_l, C_h, [src, 32]
ldp D_l, D_h, [src, 48]
ldp E_l, E_h, [srcend, -32]
ldp F_l, F_h, [srcend, -16]
stp A_l, A_h, [dstin]
stp B_l, B_h, [dstin, 16]
stp C_l, C_h, [dstin, 32]
stp D_l, D_h, [dstin, 48]
stp E_l, E_h, [dstend, -32]
stp F_l, F_h, [dstend, -16]
ret
/* Align SRC to 16 byte alignment so that we don't cross cache line
boundaries on both loads and stores. There are at least 96 bytes
to copy, so copy 16 bytes unaligned and then align. The loop
copies 32 bytes per iteration and prefetches one iteration ahead. */
.p2align 4
L(copy_long):
sub count, count, 64 + 16 /* Test and readjust count. */
mov B_l, Q_l
mov B_h, Q_h
ldp A_l, A_h, [src]
and tmp1, src, 15
bic src, src, 15
sub dst, dstin, tmp1
add count, count, tmp1 /* Count is now 16 too large. */
ldp Q_l, Q_h, [src, 16]!
stp A_l, A_h, [dstin]
ldp A_l, A_h, [src, 16]!
L(loop64):
subs count, count, 32
stp Q_l, Q_h, [dst, 16]
ldp Q_l, Q_h, [src, 16]!
stp A_l, A_h, [dst, 32]!
ldp A_l, A_h, [src, 16]!
b.hi L(loop64)
/* Write the last full set of 32 bytes. The remainder is at most 32
bytes, so it is safe to always copy 32 bytes from the end even if
there is just 1 byte left. */
L(last64):
ldp C_l, C_h, [srcend, -32]
stp Q_l, Q_h, [dst, 16]
ldp Q_l, Q_h, [srcend, -16]
stp A_l, A_h, [dst, 32]
stp C_l, C_h, [dstend, -32]
stp Q_l, Q_h, [dstend, -16]
mov Q_l, B_l
mov Q_h, B_h
ret
.p2align 4
L(move_long):
cbz tmp1, 3f
mov B_l, Q_l
mov B_h, Q_h
/* Align SRCEND to 16 byte alignment so that we don't cross cache line
boundaries on both loads and stores. There are at least 96 bytes
to copy, so copy 16 bytes unaligned and then align. The loop
copies 32 bytes per iteration and prefetches one iteration ahead. */
ldp A_l, A_h, [srcend, -16]
and tmp1, srcend, 15
sub srcend, srcend, tmp1
ldp Q_l, Q_h, [srcend, -16]!
stp A_l, A_h, [dstend, -16]
sub count, count, tmp1
ldp A_l, A_h, [srcend, -16]!
sub dstend, dstend, tmp1
sub count, count, 64
1:
subs count, count, 32
stp Q_l, Q_h, [dstend, -16]
ldp Q_l, Q_h, [srcend, -16]!
stp A_l, A_h, [dstend, -32]!
ldp A_l, A_h, [srcend, -16]!
b.hi 1b
/* Write the last full set of 32 bytes. The remainder is at most 32
bytes, so it is safe to always copy 32 bytes from the start even if
there is just 1 byte left. */
2:
ldp C_l, C_h, [src, 16]
stp Q_l, Q_h, [dstend, -16]
ldp Q_l, Q_h, [src]
stp A_l, A_h, [dstend, -32]
stp C_l, C_h, [dstin, 16]
stp Q_l, Q_h, [dstin]
mov Q_l, B_l
mov Q_h, B_h
3: ret
END (__memmove_falkor)
libc_hidden_builtin_def (__memmove_falkor)
|
