database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-17 06:41:09 +03:00
Code Activity

Add basic support for using the POPCNT and SSE4.2s LZCNT opcodes

Browse Source 
These opcodes have been around in the AMD world since 2007, and 2008 in
the case of intel.  They're supported in GCC and Clang via some __builtin
macros.  The opcodes may be unavailable during runtime, in which case we
fall back on a C-based implementation of the code.  In order to get the
POPCNT instruction we must pass the -mpopcnt option to the compiler.  We
do this only for the pg_bitutils.c file.

David Rowley (with fragments taken from a patch by Thomas Munro)

Discussion: https://postgr.es/m/CAKJS1f9WTAGG1tPeJnD18hiQW5gAk59fQ6WK-vfdAKEHyRg2RA@mail.gmail.com
This commit is contained in:
Alvaro Herrera
2019-02-13 16:10:06 -03:00
parent 754ca99314
commit 711bab1e4d
13 changed files with 912 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
src/backend/access/heap/visibilitymap.c
View File

@ -89,12 +89,12 @@
#include "access/visibilitymap.h"
#include "access/xlog.h"
#include "miscadmin.h"
#include "port/pg_bitutils.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "storage/smgr.h"
#include "utils/inval.h"
/*#define TRACE_VISIBILITYMAP */
/*
@ -115,43 +115,9 @@
#define HEAPBLK_TO_MAPBYTE(x) (((x) % HEAPBLOCKS_PER_PAGE) / HEAPBLOCKS_PER_BYTE)
#define HEAPBLK_TO_OFFSET(x) (((x) % HEAPBLOCKS_PER_BYTE) * BITS_PER_HEAPBLOCK)
/* tables for fast counting of set bits for visible and frozen */
static const uint8 number_of_ones_for_visible[256] = {
0, 1, 0, 1, 1, 2, 1, 2, 0, 1, 0, 1, 1, 2, 1, 2,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
0, 1, 0, 1, 1, 2, 1, 2, 0, 1, 0, 1, 1, 2, 1, 2,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
2, 3, 2, 3, 3, 4, 3, 4, 2, 3, 2, 3, 3, 4, 3, 4,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
2, 3, 2, 3, 3, 4, 3, 4, 2, 3, 2, 3, 3, 4, 3, 4,
0, 1, 0, 1, 1, 2, 1, 2, 0, 1, 0, 1, 1, 2, 1, 2,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
0, 1, 0, 1, 1, 2, 1, 2, 0, 1, 0, 1, 1, 2, 1, 2,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
2, 3, 2, 3, 3, 4, 3, 4, 2, 3, 2, 3, 3, 4, 3, 4,
1, 2, 1, 2, 2, 3, 2, 3, 1, 2, 1, 2, 2, 3, 2, 3,
2, 3, 2, 3, 3, 4, 3, 4, 2, 3, 2, 3, 3, 4, 3, 4
};
static const uint8 number_of_ones_for_frozen[256] = {
0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 2, 2, 1, 1, 2, 2,
0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 2, 2, 1, 1, 2, 2,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 2, 2, 1, 1, 2, 2,
0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 2, 2, 1, 1, 2, 2,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
2, 2, 3, 3, 2, 2, 3, 3, 3, 3, 4, 4, 3, 3, 4, 4,
2, 2, 3, 3, 2, 2, 3, 3, 3, 3, 4, 4, 3, 3, 4, 4,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 3, 3, 2, 2, 3, 3,
2, 2, 3, 3, 2, 2, 3, 3, 3, 3, 4, 4, 3, 3, 4, 4,
2, 2, 3, 3, 2, 2, 3, 3, 3, 3, 4, 4, 3, 3, 4, 4
};
/* Masks for bit counting bits in the visibility map. */
#define VISIBLE_MASK64 0x5555555555555555 /* The lower bit of each bit pair */
#define FROZEN_MASK64 0xaaaaaaaaaaaaaaaa /* The upper bit of each bit pair */
/* prototypes for internal routines */
static Buffer vm_readbuf(Relation rel, BlockNumber blkno, bool extend);
@ -408,18 +374,16 @@ void
visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_frozen)
{
BlockNumber mapBlock;
BlockNumber nvisible = 0;
BlockNumber nfrozen = 0;
/* all_visible must be specified */
Assert(all_visible);
*all_visible = 0;
if (all_frozen)
*all_frozen = 0;
for (mapBlock = 0;; mapBlock++)
{
Buffer mapBuffer;
unsigned char *map;
uint64 *map;
int i;
/*
@ -436,17 +400,30 @@ visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_fro
* immediately stale anyway if anyone is concurrently setting or
* clearing bits, and we only really need an approximate value.
*/
map = (unsigned char *) PageGetContents(BufferGetPage(mapBuffer));
map = (uint64 *) PageGetContents(BufferGetPage(mapBuffer));
for (i = 0; i < MAPSIZE; i++)
StaticAssertStmt(MAPSIZE % sizeof(uint64) == 0,
"unsupported MAPSIZE");
if (all_frozen == NULL)
{
*all_visible += number_of_ones_for_visible[map[i]];
if (all_frozen)
*all_frozen += number_of_ones_for_frozen[map[i]];
for (i = 0; i < MAPSIZE / sizeof(uint64); i++)
nvisible += pg_popcount64(map[i] & VISIBLE_MASK64);
}
else
{
for (i = 0; i < MAPSIZE / sizeof(uint64); i++)
{
nvisible += pg_popcount64(map[i] & VISIBLE_MASK64);
nfrozen += pg_popcount64(map[i] & FROZEN_MASK64);
}
}
ReleaseBuffer(mapBuffer);
}
*all_visible = nvisible;
if (all_frozen)
*all_frozen = nfrozen;
}
/*