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
|
;--------------------------------------------------------------------------
; memcpy.s
;
; Copyright (C) 2018, Benedikt Freisen
;
; This library is free software; you can redistribute it and/or modify it
; under the terms of the GNU General Public License as published by the
; Free Software Foundation; either version 2, or (at your option) any
; later version.
;
; This 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 General Public License for more details.
;
; You should have received a copy of the GNU General Public License
; along with this library; see the file COPYING. If not, write to the
; Free Software Foundation, 51 Franklin Street, Fifth Floor, Boston,
; MA 02110-1301, USA.
;
; As a special exception, if you link this library with other files,
; some of which are compiled with SDCC, to produce an executable,
; this library does not by itself cause the resulting executable to
; be covered by the GNU General Public License. This exception does
; not however invalidate any other reasons why the executable file
; might be covered by the GNU General Public License.
;--------------------------------------------------------------------------
; This memcpy() implementation has been optimized for speed using 4x loop
; unrolling and index relative addressing.
; void *memcpy(void *dest, const void *src, size_t n);
.globl ___memcpy
.globl _memcpy
.area CODE
___memcpy:
_memcpy:
ldw y, (4, sp)
ldw x, (6, sp)
srl (8, sp)
rrc (9, sp)
jrnc n_x0
ld a, (x)
ld (y), a
incw x
incw y
n_x0:
srl (8, sp)
rrc (9, sp)
jrnc n_00
ld a, (x)
ld (y), a
incw x
incw y
ld a, (x)
ld (y), a
incw x
incw y
n_00:
tnz (9, sp)
jrne loop_ent
dec (8, sp)
jrmi end
jra loop_ent
loop:
addw x, #4
addw y, #4
loop_ent:
ld a, (x)
ld (y), a
ld a, (1, x)
ld (1, y), a
ld a, (2, x)
ld (2, y), a
ld a, (3, x)
ld (3, y), a
dec (9, sp)
jrne loop
dec (8, sp)
jrpl loop
end:
ldw x, (4, sp)
retf
|
