liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-11 23:26:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use float instead of double for k-means to save memory

Browse Source
This commit is contained in:
Andrew Kane
2022-02-11 01:56:28 -08:00
parent d390cc9fa6
commit 46ed56d80f
1 changed files with 13 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/ivfkmeans.c
View File

@@ -11,7 +11,7 @@
* https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf * https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf
*/ */
static void static void
InitCenters(Relation index, VectorArray samples, VectorArray centers, double *lowerBound) InitCenters(Relation index, VectorArray samples, VectorArray centers, float *lowerBound)
{ {
FmgrInfo *procinfo; FmgrInfo *procinfo;
Oid collation; Oid collation;
@@ -21,7 +21,7 @@ InitCenters(Relation index, VectorArray samples, VectorArray centers, double *lo
double sum; double sum;
double choice; double choice;
Vector *vec; Vector *vec;
double *weight = palloc(samples->length * sizeof(double)); float *weight = palloc(samples->length * sizeof(float));
int numCenters = centers->maxlen; int numCenters = centers->maxlen;
int numSamples = samples->length; int numSamples = samples->length;
@@ -177,11 +177,11 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
VectorArray newCenters; VectorArray newCenters;
int *centerCounts; int *centerCounts;
int *closestCenters; int *closestCenters;
double *lowerBound; float *lowerBound;
double *upperBound; float *upperBound;
double *s; float *s;
double *halfcdist; float *halfcdist;
double *newcdist; float *newcdist;
int changes; int changes;
double minDistance; double minDistance;
int closestCenter; int closestCenter;
@@ -197,13 +197,14 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
collation = index->rd_indcollation[0]; collation = index->rd_indcollation[0];
/* Allocate space */ /* Allocate space */
/* Use float instead of double to save memory */
centerCounts = palloc(sizeof(int) * numCenters); centerCounts = palloc(sizeof(int) * numCenters);
closestCenters = palloc(sizeof(int) * numSamples); closestCenters = palloc(sizeof(int) * numSamples);
lowerBound = palloc(sizeof(double) * numSamples * numCenters); lowerBound = palloc(sizeof(float) * numSamples * numCenters);
upperBound = palloc(sizeof(double) * numSamples); upperBound = palloc(sizeof(float) * numSamples);
s = palloc(sizeof(double) * numCenters); s = palloc(sizeof(float) * numCenters);
halfcdist = palloc(sizeof(double) * numCenters * numCenters); halfcdist = palloc(sizeof(float) * numCenters * numCenters);
newcdist = palloc(sizeof(double) * numCenters); newcdist = palloc(sizeof(float) * numCenters);
newCenters = VectorArrayInit(numCenters, dimensions); newCenters = VectorArrayInit(numCenters, dimensions);
for (j = 0; j < numCenters; j++) for (j = 0; j < numCenters; j++)