memmove.S
2.59 KB
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
/*
* arch/alpha/lib/memmove.S
*
* Barely optimized memmove routine for Alpha EV5.
*
* This is hand-massaged output from the original memcpy.c. We defer to
* memcpy whenever possible; the backwards copy loops are not unrolled.
*/
.set noat
.set noreorder
.text
.align 4
.globl memmove
.ent memmove
memmove:
ldgp $29, 0($27)
unop
nop
.prologue 1
addq $16,$18,$4
addq $17,$18,$5
cmpule $4,$17,$1 /* dest + n <= src */
cmpule $5,$16,$2 /* dest >= src + n */
bis $1,$2,$1
mov $16,$0
xor $16,$17,$2
bne $1,memcpy !samegp
and $2,7,$2 /* Test for src/dest co-alignment. */
and $16,7,$1
cmpule $16,$17,$3
bne $3,$memmove_up /* dest < src */
and $4,7,$1
bne $2,$misaligned_dn
unop
beq $1,$skip_aligned_byte_loop_head_dn
$aligned_byte_loop_head_dn:
lda $4,-1($4)
lda $5,-1($5)
unop
ble $18,$egress
ldq_u $3,0($5)
ldq_u $2,0($4)
lda $18,-1($18)
extbl $3,$5,$1
insbl $1,$4,$1
mskbl $2,$4,$2
bis $1,$2,$1
and $4,7,$6
stq_u $1,0($4)
bne $6,$aligned_byte_loop_head_dn
$skip_aligned_byte_loop_head_dn:
lda $18,-8($18)
blt $18,$skip_aligned_word_loop_dn
$aligned_word_loop_dn:
ldq $1,-8($5)
nop
lda $5,-8($5)
lda $18,-8($18)
stq $1,-8($4)
nop
lda $4,-8($4)
bge $18,$aligned_word_loop_dn
$skip_aligned_word_loop_dn:
lda $18,8($18)
bgt $18,$byte_loop_tail_dn
unop
ret $31,($26),1
.align 4
$misaligned_dn:
nop
fnop
unop
beq $18,$egress
$byte_loop_tail_dn:
ldq_u $3,-1($5)
ldq_u $2,-1($4)
lda $5,-1($5)
lda $4,-1($4)
lda $18,-1($18)
extbl $3,$5,$1
insbl $1,$4,$1
mskbl $2,$4,$2
bis $1,$2,$1
stq_u $1,0($4)
bgt $18,$byte_loop_tail_dn
br $egress
$memmove_up:
mov $16,$4
mov $17,$5
bne $2,$misaligned_up
beq $1,$skip_aligned_byte_loop_head_up
$aligned_byte_loop_head_up:
unop
ble $18,$egress
ldq_u $3,0($5)
ldq_u $2,0($4)
lda $18,-1($18)
extbl $3,$5,$1
insbl $1,$4,$1
mskbl $2,$4,$2
bis $1,$2,$1
lda $5,1($5)
stq_u $1,0($4)
lda $4,1($4)
and $4,7,$6
bne $6,$aligned_byte_loop_head_up
$skip_aligned_byte_loop_head_up:
lda $18,-8($18)
blt $18,$skip_aligned_word_loop_up
$aligned_word_loop_up:
ldq $1,0($5)
nop
lda $5,8($5)
lda $18,-8($18)
stq $1,0($4)
nop
lda $4,8($4)
bge $18,$aligned_word_loop_up
$skip_aligned_word_loop_up:
lda $18,8($18)
bgt $18,$byte_loop_tail_up
unop
ret $31,($26),1
.align 4
$misaligned_up:
nop
fnop
unop
beq $18,$egress
$byte_loop_tail_up:
ldq_u $3,0($5)
ldq_u $2,0($4)
lda $18,-1($18)
extbl $3,$5,$1
insbl $1,$4,$1
mskbl $2,$4,$2
bis $1,$2,$1
stq_u $1,0($4)
lda $5,1($5)
lda $4,1($4)
nop
bgt $18,$byte_loop_tail_up
$egress:
ret $31,($26),1
nop
nop
nop
.end memmove