mirror of
https://github.com/postgres/postgres.git
synced 2025-12-09 02:08:45 +03:00
Use ARMv8 CRC instructions where available.
ARMv8 introduced special CPU instructions for calculating CRC-32C. Use them, when available, for speed. Like with the similar Intel CRC instructions, several factors affect whether the instructions can be used. The compiler intrinsics for them must be supported by the compiler, and the instructions must be supported by the target architecture. If the compilation target architecture does not support the instructions, but adding "-march=armv8-a+crc" makes them available, then we compile the code with a runtime check to determine if the host we're running on supports them or not. For the runtime check, use glibc getauxval() function. Unfortunately, that's not very portable, but I couldn't find any more portable way to do it. If getauxval() is not available, the CRC instructions will still be used if the target architecture supports them without any additional compiler flags, but the runtime check will not be available. Original patch by Yuqi Gu, heavily modified by me. Reviewed by Andres Freund, Thomas Munro. Discussion: https://www.postgresql.org/message-id/HE1PR0801MB1323D171938EABC04FFE7FA9E3110%40HE1PR0801MB1323.eurprd08.prod.outlook.com
This commit is contained in:
72
src/port/pg_crc32c_armv8.c
Normal file
72
src/port/pg_crc32c_armv8.c
Normal file
@@ -0,0 +1,72 @@
|
||||
/*-------------------------------------------------------------------------
|
||||
*
|
||||
* pg_crc32c_armv8.c
|
||||
* Compute CRC-32C checksum using ARMv8 CRC Extension instructions
|
||||
*
|
||||
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
*
|
||||
* IDENTIFICATION
|
||||
* src/port/pg_crc32c_armv8.c
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
#include "c.h"
|
||||
|
||||
#include "port/pg_crc32c.h"
|
||||
|
||||
#include <arm_acle.h>
|
||||
|
||||
pg_crc32c
|
||||
pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len)
|
||||
{
|
||||
const unsigned char *p = data;
|
||||
const unsigned char *pend = p + len;
|
||||
|
||||
/*
|
||||
* ARMv8 doesn't require alignment, but aligned memory access is
|
||||
* significantly faster. Process leading bytes so that the loop below
|
||||
* starts with a pointer aligned to eight bytes.
|
||||
*/
|
||||
if (!PointerIsAligned(p, uint16) && p < pend)
|
||||
{
|
||||
crc = __crc32cb(crc, *p);
|
||||
p += 1;
|
||||
}
|
||||
if (!PointerIsAligned(p, uint32) && p < pend)
|
||||
{
|
||||
crc = __crc32ch(crc, *(uint16 *) p);
|
||||
p += 2;
|
||||
}
|
||||
if (!PointerIsAligned(p, uint64) && p < pend)
|
||||
{
|
||||
crc = __crc32cw(crc, *(uint32 *) p);
|
||||
p += 4;
|
||||
}
|
||||
|
||||
/* Process eight bytes at a time, as far as we can. */
|
||||
while (p + 8 <= pend)
|
||||
{
|
||||
crc = __crc32cd(crc, *(uint64 *) p);
|
||||
p += 8;
|
||||
}
|
||||
|
||||
/* Process remaining 0-7 bytes. */
|
||||
if (p + 4 <= pend)
|
||||
{
|
||||
crc = __crc32cw(crc, *(uint32 *) p);
|
||||
p += 4;
|
||||
}
|
||||
if (p + 2 <= pend)
|
||||
{
|
||||
crc = __crc32ch(crc, *(uint16 *) p);
|
||||
p += 2;
|
||||
}
|
||||
if (p < pend)
|
||||
{
|
||||
crc = __crc32cb(crc, *p);
|
||||
}
|
||||
|
||||
return crc;
|
||||
}
|
||||
Reference in New Issue
Block a user