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
| | /* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2013 Regents of the University of California
*/
#define SZREG 8
#define REG_S sd
#define REG_L ld
.global memcpy
.type memcpy,@function
memcpy:
/* Save for return value */
mv t6, a0
/*
* Register allocation for code below:
* a0 - start of uncopied dst
* a1 - start of uncopied src
* t0 - end of uncopied dst
*/
add t0, a0, a2
/*
* Use bytewise copy if too small.
*
* This threshold must be at least 2*SZREG to ensure at least one
* wordwise copy is performed. It is chosen to be 16 because it will
* save at least 7 iterations of bytewise copy, which pays off the
* fixed overhead.
*/
li a3, 16
bltu a2, a3, .Lbyte_copy_tail
/*
* Bytewise copy first to align a0 to word boundary.
*/
addi a2, a0, SZREG-1
andi a2, a2, ~(SZREG-1)
beq a0, a2, 2f
1:
lb a5, 0(a1)
addi a1, a1, 1
sb a5, 0(a0)
addi a0, a0, 1
bne a0, a2, 1b
2:
/*
* Now a0 is word-aligned. If a1 is also word aligned, we could perform
* aligned word-wise copy. Otherwise we need to perform misaligned
* word-wise copy.
*/
andi a3, a1, SZREG-1
bnez a3, .Lmisaligned_word_copy
/* Unrolled wordwise copy */
addi t0, t0, -(16*SZREG-1)
bgeu a0, t0, 2f
1:
REG_L a2, 0(a1)
REG_L a3, SZREG(a1)
REG_L a4, 2*SZREG(a1)
REG_L a5, 3*SZREG(a1)
REG_L a6, 4*SZREG(a1)
REG_L a7, 5*SZREG(a1)
REG_L t1, 6*SZREG(a1)
REG_L t2, 7*SZREG(a1)
REG_L t3, 8*SZREG(a1)
REG_L t4, 9*SZREG(a1)
REG_L t5, 10*SZREG(a1)
REG_S a2, 0(a0)
REG_S a3, SZREG(a0)
REG_S a4, 2*SZREG(a0)
REG_S a5, 3*SZREG(a0)
REG_S a6, 4*SZREG(a0)
REG_S a7, 5*SZREG(a0)
REG_S t1, 6*SZREG(a0)
REG_S t2, 7*SZREG(a0)
REG_S t3, 8*SZREG(a0)
REG_S t4, 9*SZREG(a0)
REG_S t5, 10*SZREG(a0)
REG_L a2, 11*SZREG(a1)
REG_L a3, 12*SZREG(a1)
REG_L a4, 13*SZREG(a1)
REG_L a5, 14*SZREG(a1)
REG_L a6, 15*SZREG(a1)
addi a1, a1, 16*SZREG
REG_S a2, 11*SZREG(a0)
REG_S a3, 12*SZREG(a0)
REG_S a4, 13*SZREG(a0)
REG_S a5, 14*SZREG(a0)
REG_S a6, 15*SZREG(a0)
addi a0, a0, 16*SZREG
bltu a0, t0, 1b
2:
/* Post-loop increment by 16*SZREG-1 and pre-loop decrement by SZREG-1 */
addi t0, t0, 15*SZREG
/* Wordwise copy */
bgeu a0, t0, 2f
1:
REG_L a5, 0(a1)
addi a1, a1, SZREG
REG_S a5, 0(a0)
addi a0, a0, SZREG
bltu a0, t0, 1b
2:
addi t0, t0, SZREG-1
.Lbyte_copy_tail:
/*
* Bytewise copy anything left.
*/
beq a0, t0, 2f
1:
lb a5, 0(a1)
addi a1, a1, 1
sb a5, 0(a0)
addi a0, a0, 1
bne a0, t0, 1b
2:
mv a0, t6
ret
.Lmisaligned_word_copy:
/*
* Misaligned word-wise copy.
* For misaligned copy we still perform word-wise copy, but we need to
* use the value fetched from the previous iteration and do some shifts.
* This is safe because we wouldn't access more words than necessary.
*/
/* Calculate shifts */
slli t3, a3, 3
sub t4, x0, t3 /* negate is okay as shift will only look at LSBs */
/* Load the initial value and align a1 */
andi a1, a1, ~(SZREG-1)
REG_L a5, 0(a1)
addi t0, t0, -(SZREG-1)
/* At least one iteration will be executed here, no check */
1:
srl a4, a5, t3
REG_L a5, SZREG(a1)
addi a1, a1, SZREG
sll a2, a5, t4
or a2, a2, a4
REG_S a2, 0(a0)
addi a0, a0, SZREG
bltu a0, t0, 1b
/* Update pointers to correct value */
addi t0, t0, SZREG-1
add a1, a1, a3
j .Lbyte_copy_tail
|