blob: d698124121a43daa5e4b18dd750cba8bbbc7b99c (
plain)
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
|
/*-------------------------------------------------------------------------
*
* pg_crc32c_sse42.c
* Compute CRC-32C checksum using Intel SSE 4.2 instructions.
*
* Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/port/pg_crc32c_sse42.c
*
*-------------------------------------------------------------------------
*/
#include "c.h"
#include "port/pg_crc32c.h"
#include <nmmintrin.h>
pg_crc32c
pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len)
{
const unsigned char *p = data;
const unsigned char *pend = p + len;
/*
* Process eight bytes of data at a time.
*
* NB: We do unaligned accesses here. The Intel architecture allows that,
* and performance testing didn't show any performance gain from aligning
* the begin address.
*/
#ifdef __x86_64__
while (p + 8 <= pend)
{
crc = (uint32) _mm_crc32_u64(crc, *((const uint64 *) p));
p += 8;
}
/* Process remaining full four bytes if any */
if (p + 4 <= pend)
{
crc = _mm_crc32_u32(crc, *((const unsigned int *) p));
p += 4;
}
#else
/*
* Process four bytes at a time. (The eight byte instruction is not
* available on the 32-bit x86 architecture).
*/
while (p + 4 <= pend)
{
crc = _mm_crc32_u32(crc, *((const unsigned int *) p));
p += 4;
}
#endif /* __x86_64__ */
/* Process any remaining bytes one at a time. */
while (p < pend)
{
crc = _mm_crc32_u8(crc, *p);
p++;
}
return crc;
}
|
