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
|
/* IBM_PROLOG_BEGIN_TAG */
/* This is an automatically generated prolog. */
/* */
/* $Source: src/lib/common/memcpy.c $ */
/* */
/* OpenPOWER OnChipController Project */
/* */
/* Contributors Listed Below - COPYRIGHT 2015,2016 */
/* [+] International Business Machines Corp. */
/* */
/* */
/* Licensed under the Apache License, Version 2.0 (the "License"); */
/* you may not use this file except in compliance with the License. */
/* You may obtain a copy of the License at */
/* */
/* http://www.apache.org/licenses/LICENSE-2.0 */
/* */
/* Unless required by applicable law or agreed to in writing, software */
/* distributed under the License is distributed on an "AS IS" BASIS, */
/* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or */
/* implied. See the License for the specific language governing */
/* permissions and limitations under the License. */
/* */
/* IBM_PROLOG_END_TAG */
/// \file memcpy.c
/// \brief The memcpy() function
#include "kernel.h"
/// The memcpy() function copies \a n bytes from memory area \a src to memory
/// area \a dest. The memory areas should not overlap. Use memmove(3) if the
/// memory areas do overlap. The memcpy() function returns a pointer to dest.
// This implementation should work well for both 32-bit and 64-bit machines,
// assuming they can handle unaligned accesses. The implementation assumes that
// it is better to avoid the loop setup overhead by a test and branch for
// cases where loops can be bypassed.
//void *
//memcpy(void *dest, const void *src, size_t n)
//{
// while(n--) {
// *dest++ = *src++;
// }
//
// return s;
//}
void *
memcpy(void *dest, const void *src, size_t n)
{
uint8_t *d8, *s8;
uint64_t *d64, *s64;
size_t doublewords, octawords;
// First copy memory 32 bytes at a time.
d64 = (uint64_t *)dest;
s64 = (uint64_t *)src;
octawords = n / 32;
if (octawords) {
n -= octawords * 32;
while(octawords--) {
*d64++ = *s64++;
*d64++ = *s64++;
*d64++ = *s64++;
*d64++ = *s64++;
}
}
// Now set memory 8 bytes at a time. This might actually be better done
// explicitly rather than as a loop because the maximum loop count is 3
// here.
doublewords = n / 8;
if (doublewords) {
n -= doublewords * 8;
while (doublewords--) {
*d64++ = *s64++;
}
}
// Finally finish any remaining memory bytewise
if (n) {
d8 = (uint8_t *)d64;
s8 = (uint8_t *)s64;
while (n--) {
*d8++ = *s8++;
}
}
return dest;
}
|
