liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-06-06 05:51:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

optimize: defer sample normalization when building ivfflat

Browse Source
This commit is contained in:
lychen0613
2026-04-14 21:59:56 +08:00
committed by Andrew Kane
parent 8af675cd25
commit 5c9a97af3b
1 changed files with 18 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/ivfbuild.c
View File

@@ -63,15 +63,13 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
/*
* Normalize with KMEANS_NORM_PROC since spherical distance function
* expects unit vectors
* Check with KMEANS_NORM_PROC that the value can be normalized
* since spherical distance function expects unit vectors
*/
if (buildstate->kmeansnormprocinfo != NULL)
{
if (!IvfflatCheckNorm(buildstate->kmeansnormprocinfo, buildstate->collation, value))
return;
value = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
}
if (samples->length < targsamples)
@@ -150,6 +148,22 @@ SampleRows(IvfflatBuildState * buildstate)
table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
}
/* Normalize if needed */
if (buildstate->kmeansnormprocinfo)
{
VectorArray samples = buildstate->samples;
Datum value;
Datum nvalue;
for (int i = 0; i < samples->length; i++)
{
value = PointerGetDatum(VectorArrayGet(samples, i));
nvalue = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
VectorArraySet(samples, i, DatumGetPointer(nvalue));
pfree(DatumGetPointer(nvalue));
}
}
}
/*