liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-06-06 14:01:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improved performance of HNSW index builds - closes #292

Browse Source 
Co-authored-by: Heikki Linnakangas <heikki.linnakangas@iki.fi>
This commit is contained in:
Andrew Kane
2023-10-05 13:21:26 -07:00
parent 6e1312ddbe
commit a713e2acaa
3 changed files with 34 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@@ -1,5 +1,6 @@
## 0.5.1 (unreleased)
- Improved performance of HNSW index builds
- Added check for MVCC-compliant snapshot for HNSW index scans
- Improved performance of index scans for IVFFlat after updates and deletes

2
src/hnsw.h
View File

@@ -112,11 +112,13 @@ typedef struct HnswCandidate
{
HnswElement element;
float distance;
bool closer;
} HnswCandidate;
typedef struct HnswNeighborArray
{
int length;
bool closerSet;
HnswCandidate *items;
} HnswNeighborArray;

37
src/hnswutils.c
View File

@@ -139,6 +139,7 @@ HnswInitNeighbors(HnswElement element, int m)
a = &element->neighbors[lc];
a->length = 0;
a->items = palloc(sizeof(HnswCandidate) * lm);
a->closerSet = false;
}
}
@@ -748,11 +749,13 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
* Algorithm 4 from paper
*/
static List *
SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswCandidate * *pruned)
SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned)
{
List *r = NIL;
List *w = list_copy(c);
pairingheap *wd;
bool mustCalculate = !e2->neighbors[lc].closerSet;
bool foundNew = false;
if (list_length(w) <= m)
return w;
@@ -763,18 +766,40 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswC
{
/* Assumes w is already ordered desc */
HnswCandidate *e = llast(w);
bool closer;
w = list_delete_last(w);
closer = CheckElementCloser(e, r, lc, procinfo, collation);
/* Use previous state of r and wd to skip work when possible */
if (mustCalculate)
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
else if (foundNew)
{
/* If new or current candidate is not closer, no change in state */
if (newCandidate->closer && e->closer)
{
/* Only need to compare with new candidate */
float distance = HnswGetDistance(e->element, newCandidate->element, lc, procinfo, collation);
if (closer)
e->closer = e->distance < distance;
if (!e->closer)
mustCalculate = true;
}
}
else if (e == newCandidate)
{
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
foundNew = true;
}
if (e->closer)
r = lappend(r, e);
else
pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
}
e2->neighbors[lc].closerSet = true;
/* Keep pruned connections */
while (!pairingheap_is_empty(wd) && list_length(r) < m)
r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
@@ -909,7 +934,7 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
c = lappend(c, &hc2);
list_sort(c, CompareCandidateDistances);
SelectNeighbors(c, m, lc, procinfo, collation, &pruned);
SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned);
/* Should not happen */
if (pruned == NULL)
@@ -1008,7 +1033,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
else
lw = w;
neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, NULL);
neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, element, NULL, NULL);
AddConnections(element, neighbors, lm, lc);