mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-24 04:45:45 +08:00
Compare commits
1 Commits
hnsw-read-
...
sparsevec-
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
434ef7a5ab |
@@ -169,7 +169,7 @@ BitJaccardDistanceAvx512Popcount(uint32 bytes, unsigned char *ax, unsigned char
|
|||||||
#endif
|
#endif
|
||||||
|
|
||||||
TARGET_XSAVE static bool
|
TARGET_XSAVE static bool
|
||||||
SupportsAvx512Popcount(void)
|
SupportsAvx512Popcount()
|
||||||
{
|
{
|
||||||
unsigned int exx[4] = {0, 0, 0, 0};
|
unsigned int exx[4] = {0, 0, 0, 0};
|
||||||
|
|
||||||
|
|||||||
@@ -13,7 +13,6 @@
|
|||||||
#include "hnsw.h"
|
#include "hnsw.h"
|
||||||
#include "miscadmin.h"
|
#include "miscadmin.h"
|
||||||
#include "nodes/pg_list.h"
|
#include "nodes/pg_list.h"
|
||||||
#include "storage/lwlock.h"
|
|
||||||
#include "utils/float.h"
|
#include "utils/float.h"
|
||||||
#include "utils/guc.h"
|
#include "utils/guc.h"
|
||||||
#include "utils/relcache.h"
|
#include "utils/relcache.h"
|
||||||
|
|||||||
15
src/hnsw.h
15
src/hnsw.h
@@ -10,10 +10,6 @@
|
|||||||
#include "lib/pairingheap.h"
|
#include "lib/pairingheap.h"
|
||||||
#include "nodes/execnodes.h"
|
#include "nodes/execnodes.h"
|
||||||
#include "port.h" /* for random() */
|
#include "port.h" /* for random() */
|
||||||
#include "storage/bufpage.h"
|
|
||||||
#include "storage/condition_variable.h"
|
|
||||||
#include "storage/lwlock.h"
|
|
||||||
#include "storage/s_lock.h"
|
|
||||||
#include "utils/relptr.h"
|
#include "utils/relptr.h"
|
||||||
#include "utils/sampling.h"
|
#include "utils/sampling.h"
|
||||||
#include "vector.h"
|
#include "vector.h"
|
||||||
@@ -372,13 +368,6 @@ typedef union
|
|||||||
ItemPointerData indextid;
|
ItemPointerData indextid;
|
||||||
} HnswUnvisited;
|
} HnswUnvisited;
|
||||||
|
|
||||||
typedef struct HnswReadStreamData
|
|
||||||
{
|
|
||||||
HnswUnvisited *unvisited;
|
|
||||||
int unvisitedLength;
|
|
||||||
int visited;
|
|
||||||
} HnswReadStreamData;
|
|
||||||
|
|
||||||
typedef struct HnswScanOpaqueData
|
typedef struct HnswScanOpaqueData
|
||||||
{
|
{
|
||||||
const HnswTypeInfo *typeInfo;
|
const HnswTypeInfo *typeInfo;
|
||||||
@@ -434,13 +423,13 @@ bool HnswCheckNorm(HnswSupport * support, Datum value);
|
|||||||
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
|
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
|
||||||
void HnswInitPage(Buffer buf, Page page);
|
void HnswInitPage(Buffer buf, Page page);
|
||||||
void HnswInit(void);
|
void HnswInit(void);
|
||||||
List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples, bool maintenance);
|
List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
|
||||||
HnswElement HnswGetEntryPoint(Relation index);
|
HnswElement HnswGetEntryPoint(Relation index);
|
||||||
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
|
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
|
||||||
void *HnswAlloc(HnswAllocator * allocator, Size size);
|
void *HnswAlloc(HnswAllocator * allocator, Size size);
|
||||||
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
|
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
|
||||||
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
|
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
|
||||||
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool maintenance);
|
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
|
||||||
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec);
|
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec);
|
||||||
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
|
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
|
||||||
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
|
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
|
||||||
|
|||||||
@@ -54,7 +54,6 @@
|
|||||||
#include "nodes/execnodes.h"
|
#include "nodes/execnodes.h"
|
||||||
#include "optimizer/optimizer.h"
|
#include "optimizer/optimizer.h"
|
||||||
#include "storage/bufmgr.h"
|
#include "storage/bufmgr.h"
|
||||||
#include "storage/condition_variable.h"
|
|
||||||
#include "tcop/tcopprot.h"
|
#include "tcop/tcopprot.h"
|
||||||
#include "utils/datum.h"
|
#include "utils/datum.h"
|
||||||
#include "utils/memutils.h"
|
#include "utils/memutils.h"
|
||||||
@@ -470,7 +469,7 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
|||||||
}
|
}
|
||||||
|
|
||||||
/* Find neighbors for element */
|
/* Find neighbors for element */
|
||||||
HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false, true);
|
HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
|
||||||
|
|
||||||
/* Update graph in memory */
|
/* Update graph in memory */
|
||||||
UpdateGraphInMemory(support, element, m, entryPoint, buildstate);
|
UpdateGraphInMemory(support, element, m, entryPoint, buildstate);
|
||||||
@@ -803,11 +802,7 @@ HnswParallelScanAndInsert(Relation heapRel, Relation indexRel, HnswShared * hnsw
|
|||||||
buildstate.hnswarea = hnswarea;
|
buildstate.hnswarea = hnswarea;
|
||||||
InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
|
InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
|
||||||
scan = table_beginscan_parallel(heapRel,
|
scan = table_beginscan_parallel(heapRel,
|
||||||
ParallelTableScanFromHnswShared(hnswshared)
|
ParallelTableScanFromHnswShared(hnswshared));
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
,SO_NONE
|
|
||||||
#endif
|
|
||||||
);
|
|
||||||
reltuples = table_index_build_scan(heapRel, indexRel, indexInfo,
|
reltuples = table_index_build_scan(heapRel, indexRel, indexInfo,
|
||||||
true, progress, BuildCallback,
|
true, progress, BuildCallback,
|
||||||
(void *) &buildstate, scan);
|
(void *) &buildstate, scan);
|
||||||
|
|||||||
@@ -6,7 +6,6 @@
|
|||||||
#include "nodes/execnodes.h"
|
#include "nodes/execnodes.h"
|
||||||
#include "storage/bufmgr.h"
|
#include "storage/bufmgr.h"
|
||||||
#include "storage/lmgr.h"
|
#include "storage/lmgr.h"
|
||||||
#include "storage/lwlock.h"
|
|
||||||
#include "utils/datum.h"
|
#include "utils/datum.h"
|
||||||
#include "utils/memutils.h"
|
#include "utils/memutils.h"
|
||||||
#include "utils/rel.h"
|
#include "utils/rel.h"
|
||||||
@@ -731,7 +730,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
|
|||||||
}
|
}
|
||||||
|
|
||||||
/* Find neighbors for element */
|
/* Find neighbors for element */
|
||||||
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, building);
|
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
|
||||||
|
|
||||||
/* Update graph on disk */
|
/* Update graph on disk */
|
||||||
UpdateGraphOnDisk(index, support, element, m, entryPoint, building);
|
UpdateGraphOnDisk(index, support, element, m, entryPoint, building);
|
||||||
|
|||||||
@@ -48,11 +48,11 @@ GetScanItems(IndexScanDesc scan, Datum value)
|
|||||||
|
|
||||||
for (int lc = entryPoint->level; lc >= 1; lc--)
|
for (int lc = entryPoint->level; lc >= 1; lc--)
|
||||||
{
|
{
|
||||||
w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL, false);
|
w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
|
||||||
ep = w;
|
ep = w;
|
||||||
}
|
}
|
||||||
|
|
||||||
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples, false);
|
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples);
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -83,7 +83,7 @@ ResumeScanItems(IndexScanDesc scan)
|
|||||||
ep = lappend(ep, sc);
|
ep = lappend(ep, sc);
|
||||||
}
|
}
|
||||||
|
|
||||||
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples, false);
|
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
|||||||
104
src/hnswutils.c
104
src/hnswutils.c
@@ -21,10 +21,6 @@
|
|||||||
#include "varatt.h"
|
#include "varatt.h"
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
#include "storage/read_stream.h"
|
|
||||||
#endif
|
|
||||||
|
|
||||||
#if PG_VERSION_NUM < 170000
|
#if PG_VERSION_NUM < 170000
|
||||||
static inline uint64
|
static inline uint64
|
||||||
murmurhash64(uint64 data)
|
murmurhash64(uint64 data)
|
||||||
@@ -535,12 +531,14 @@ HnswGetDistance(Datum a, Datum b, HnswSupport * support)
|
|||||||
* Load an element and optionally get its distance from q
|
* Load an element and optionally get its distance from q
|
||||||
*/
|
*/
|
||||||
static void
|
static void
|
||||||
HnswLoadElementImpl(Buffer buf, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
|
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
|
||||||
{
|
{
|
||||||
|
Buffer buf;
|
||||||
Page page;
|
Page page;
|
||||||
HnswElementTuple etup;
|
HnswElementTuple etup;
|
||||||
|
|
||||||
/* Read vector */
|
/* Read vector */
|
||||||
|
buf = ReadBuffer(index, blkno);
|
||||||
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
||||||
page = BufferGetPage(buf);
|
page = BufferGetPage(buf);
|
||||||
|
|
||||||
@@ -561,7 +559,7 @@ HnswLoadElementImpl(Buffer buf, OffsetNumber offno, double *distance, HnswQuery
|
|||||||
if (distance == NULL || maxDistance == NULL || *distance < *maxDistance)
|
if (distance == NULL || maxDistance == NULL || *distance < *maxDistance)
|
||||||
{
|
{
|
||||||
if (*element == NULL)
|
if (*element == NULL)
|
||||||
*element = HnswInitElementFromBlock(BufferGetBlockNumber(buf), offno);
|
*element = HnswInitElementFromBlock(blkno, offno);
|
||||||
|
|
||||||
HnswLoadElementFromTuple(*element, etup, true, loadVec);
|
HnswLoadElementFromTuple(*element, etup, true, loadVec);
|
||||||
}
|
}
|
||||||
@@ -575,9 +573,7 @@ HnswLoadElementImpl(Buffer buf, OffsetNumber offno, double *distance, HnswQuery
|
|||||||
void
|
void
|
||||||
HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
|
HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
|
||||||
{
|
{
|
||||||
Buffer buf = ReadBuffer(index, element->blkno);
|
HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
|
||||||
|
|
||||||
HnswLoadElementImpl(buf, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -817,31 +813,11 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
/*
|
|
||||||
* Get next block number for read stream
|
|
||||||
*/
|
|
||||||
static BlockNumber
|
|
||||||
HnswReadStreamNextBlock(ReadStream *stream, void *callback_private_data, void *per_buffer_data)
|
|
||||||
{
|
|
||||||
HnswReadStreamData *streamData = callback_private_data;
|
|
||||||
OffsetNumber *offno = per_buffer_data;
|
|
||||||
HnswUnvisited *uv;
|
|
||||||
|
|
||||||
if (streamData->visited == streamData->unvisitedLength)
|
|
||||||
return InvalidBlockNumber;
|
|
||||||
|
|
||||||
uv = &streamData->unvisited[streamData->visited++];
|
|
||||||
*offno = ItemPointerGetOffsetNumber(&uv->indextid);
|
|
||||||
return ItemPointerGetBlockNumber(&uv->indextid);
|
|
||||||
}
|
|
||||||
#endif
|
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Algorithm 2 from paper
|
* Algorithm 2 from paper
|
||||||
*/
|
*/
|
||||||
List *
|
List *
|
||||||
HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples, bool maintenance)
|
HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
|
||||||
{
|
{
|
||||||
List *w = NIL;
|
List *w = NIL;
|
||||||
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
|
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
|
||||||
@@ -856,21 +832,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
|||||||
int unvisitedLength;
|
int unvisitedLength;
|
||||||
bool inMemory = index == NULL;
|
bool inMemory = index == NULL;
|
||||||
|
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
HnswReadStreamData streamData;
|
|
||||||
ReadStream *stream = NULL;
|
|
||||||
|
|
||||||
if (!inMemory)
|
|
||||||
{
|
|
||||||
int flags = READ_STREAM_USE_BATCHING;
|
|
||||||
|
|
||||||
if (maintenance)
|
|
||||||
flags |= READ_STREAM_MAINTENANCE;
|
|
||||||
|
|
||||||
stream = read_stream_begin_relation(flags, NULL, index, MAIN_FORKNUM, HnswReadStreamNextBlock, &streamData, sizeof(OffsetNumber));
|
|
||||||
}
|
|
||||||
#endif
|
|
||||||
|
|
||||||
if (v == NULL)
|
if (v == NULL)
|
||||||
{
|
{
|
||||||
v = &vh;
|
v = &vh;
|
||||||
@@ -933,23 +894,13 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
|||||||
if (inMemory)
|
if (inMemory)
|
||||||
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, v, lc, localNeighborhood, neighborhoodSize);
|
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, v, lc, localNeighborhood, neighborhoodSize);
|
||||||
else
|
else
|
||||||
{
|
|
||||||
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
|
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
|
||||||
|
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
read_stream_resume(stream);
|
|
||||||
|
|
||||||
streamData.unvisited = unvisited;
|
|
||||||
streamData.unvisitedLength = unvisitedLength;
|
|
||||||
streamData.visited = 0;
|
|
||||||
#endif
|
|
||||||
}
|
|
||||||
|
|
||||||
/* OK to count elements instead of tuples */
|
/* OK to count elements instead of tuples */
|
||||||
if (tuples != NULL)
|
if (tuples != NULL)
|
||||||
(*tuples) += unvisitedLength;
|
(*tuples) += unvisitedLength;
|
||||||
|
|
||||||
for (int i = 0;; i++)
|
for (int i = 0; i < unvisitedLength; i++)
|
||||||
{
|
{
|
||||||
HnswElement eElement;
|
HnswElement eElement;
|
||||||
HnswSearchCandidate *e;
|
HnswSearchCandidate *e;
|
||||||
@@ -960,40 +911,18 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
|||||||
|
|
||||||
if (inMemory)
|
if (inMemory)
|
||||||
{
|
{
|
||||||
if (i == unvisitedLength)
|
|
||||||
break;
|
|
||||||
|
|
||||||
eElement = unvisited[i].element;
|
eElement = unvisited[i].element;
|
||||||
eDistance = GetElementDistance(base, eElement, q, support);
|
eDistance = GetElementDistance(base, eElement, q, support);
|
||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
Buffer buf;
|
ItemPointer indextid = &unvisited[i].indextid;
|
||||||
OffsetNumber offno;
|
BlockNumber blkno = ItemPointerGetBlockNumber(indextid);
|
||||||
|
OffsetNumber offno = ItemPointerGetOffsetNumber(indextid);
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
void *offnoPtr;
|
|
||||||
|
|
||||||
buf = read_stream_next_buffer(stream, &offnoPtr);
|
|
||||||
|
|
||||||
if (!BufferIsValid(buf))
|
|
||||||
break;
|
|
||||||
|
|
||||||
offno = *((OffsetNumber *) offnoPtr);
|
|
||||||
#else
|
|
||||||
ItemPointer indextid;
|
|
||||||
|
|
||||||
if (i == unvisitedLength)
|
|
||||||
break;
|
|
||||||
|
|
||||||
indextid = &unvisited[i].indextid;
|
|
||||||
buf = ReadBuffer(index, ItemPointerGetBlockNumber(indextid));
|
|
||||||
offno = ItemPointerGetOffsetNumber(indextid);
|
|
||||||
#endif
|
|
||||||
|
|
||||||
/* Avoid any allocations if not adding */
|
/* Avoid any allocations if not adding */
|
||||||
eElement = NULL;
|
eElement = NULL;
|
||||||
HnswLoadElementImpl(buf, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
|
HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
|
||||||
|
|
||||||
if (eElement == NULL)
|
if (eElement == NULL)
|
||||||
continue;
|
continue;
|
||||||
@@ -1049,11 +978,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
|||||||
w = lappend(w, sc);
|
w = lappend(w, sc);
|
||||||
}
|
}
|
||||||
|
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
if (!inMemory)
|
|
||||||
read_stream_end(stream);
|
|
||||||
#endif
|
|
||||||
|
|
||||||
return w;
|
return w;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1349,7 +1273,7 @@ PrecomputeHash(char *base, HnswElement element)
|
|||||||
* Algorithm 1 from paper
|
* Algorithm 1 from paper
|
||||||
*/
|
*/
|
||||||
void
|
void
|
||||||
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool maintenance)
|
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
|
||||||
{
|
{
|
||||||
List *ep;
|
List *ep;
|
||||||
List *w;
|
List *w;
|
||||||
@@ -1376,7 +1300,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
|||||||
/* 1st phase: greedy search to insert level */
|
/* 1st phase: greedy search to insert level */
|
||||||
for (int lc = entryLevel; lc >= level + 1; lc--)
|
for (int lc = entryLevel; lc >= level + 1; lc--)
|
||||||
{
|
{
|
||||||
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL, maintenance);
|
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
|
||||||
ep = w;
|
ep = w;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1395,7 +1319,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
|||||||
List *lw = NIL;
|
List *lw = NIL;
|
||||||
ListCell *lc2;
|
ListCell *lc2;
|
||||||
|
|
||||||
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL, maintenance);
|
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
|
||||||
|
|
||||||
/* Convert search candidates to candidates */
|
/* Convert search candidates to candidates */
|
||||||
foreach(lc2, w)
|
foreach(lc2, w)
|
||||||
|
|||||||
@@ -218,7 +218,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
|||||||
element->heaptidsLength = 0;
|
element->heaptidsLength = 0;
|
||||||
|
|
||||||
/* Find neighbors for element, skipping itself */
|
/* Find neighbors for element, skipping itself */
|
||||||
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true, true);
|
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
|
||||||
|
|
||||||
/* Zero memory for each element */
|
/* Zero memory for each element */
|
||||||
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
|
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
|
||||||
|
|||||||
@@ -22,7 +22,6 @@
|
|||||||
#include "nodes/execnodes.h"
|
#include "nodes/execnodes.h"
|
||||||
#include "optimizer/optimizer.h"
|
#include "optimizer/optimizer.h"
|
||||||
#include "storage/bufmgr.h"
|
#include "storage/bufmgr.h"
|
||||||
#include "storage/condition_variable.h"
|
|
||||||
#include "tcop/tcopprot.h"
|
#include "tcop/tcopprot.h"
|
||||||
#include "utils/memutils.h"
|
#include "utils/memutils.h"
|
||||||
#include "utils/rel.h"
|
#include "utils/rel.h"
|
||||||
@@ -63,13 +62,15 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
|
|||||||
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
|
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Check with KMEANS_NORM_PROC that the value can be normalized since
|
* Normalize with KMEANS_NORM_PROC since spherical distance function
|
||||||
* spherical distance function expects unit vectors
|
* expects unit vectors
|
||||||
*/
|
*/
|
||||||
if (buildstate->kmeansnormprocinfo != NULL)
|
if (buildstate->kmeansnormprocinfo != NULL)
|
||||||
{
|
{
|
||||||
if (!IvfflatCheckNorm(buildstate->kmeansnormprocinfo, buildstate->collation, value))
|
if (!IvfflatCheckNorm(buildstate->kmeansnormprocinfo, buildstate->collation, value))
|
||||||
return;
|
return;
|
||||||
|
|
||||||
|
value = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
|
||||||
}
|
}
|
||||||
|
|
||||||
if (samples->length < targsamples)
|
if (samples->length < targsamples)
|
||||||
@@ -80,7 +81,7 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
|
|||||||
else
|
else
|
||||||
{
|
{
|
||||||
if (buildstate->rowstoskip < 0)
|
if (buildstate->rowstoskip < 0)
|
||||||
buildstate->rowstoskip = reservoir_get_next_S(&buildstate->rstate, buildstate->samplerows, targsamples);
|
buildstate->rowstoskip = reservoir_get_next_S(&buildstate->rstate, samples->length, targsamples);
|
||||||
|
|
||||||
if (buildstate->rowstoskip <= 0)
|
if (buildstate->rowstoskip <= 0)
|
||||||
{
|
{
|
||||||
@@ -96,9 +97,6 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
|
|||||||
|
|
||||||
buildstate->rowstoskip -= 1;
|
buildstate->rowstoskip -= 1;
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Increment after reservoir_get_next_S */
|
|
||||||
buildstate->samplerows += 1;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -135,7 +133,6 @@ SampleRows(IvfflatBuildState * buildstate)
|
|||||||
int targsamples = buildstate->samples->maxlen;
|
int targsamples = buildstate->samples->maxlen;
|
||||||
BlockNumber totalblocks = RelationGetNumberOfBlocks(buildstate->heap);
|
BlockNumber totalblocks = RelationGetNumberOfBlocks(buildstate->heap);
|
||||||
|
|
||||||
buildstate->samplerows = 0;
|
|
||||||
buildstate->rowstoskip = -1;
|
buildstate->rowstoskip = -1;
|
||||||
|
|
||||||
BlockSampler_Init(&buildstate->bs, totalblocks, targsamples, RandomInt());
|
BlockSampler_Init(&buildstate->bs, totalblocks, targsamples, RandomInt());
|
||||||
@@ -148,21 +145,6 @@ SampleRows(IvfflatBuildState * buildstate)
|
|||||||
table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
|
table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
|
||||||
false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
|
false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Normalize if needed */
|
|
||||||
if (buildstate->kmeansnormprocinfo != NULL)
|
|
||||||
{
|
|
||||||
VectorArray samples = buildstate->samples;
|
|
||||||
|
|
||||||
for (int i = 0; i < samples->length; i++)
|
|
||||||
{
|
|
||||||
Datum value = PointerGetDatum(VectorArrayGet(samples, i));
|
|
||||||
Datum normValue = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
|
|
||||||
|
|
||||||
VectorArraySet(samples, i, DatumGetPointer(normValue));
|
|
||||||
pfree(DatumGetPointer(normValue));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -392,9 +374,6 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
|
|||||||
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
|
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
|
||||||
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
|
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
|
||||||
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", TupleDescAttr(buildstate->tupdesc, 0)->atttypid, -1, 0);
|
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", TupleDescAttr(buildstate->tupdesc, 0)->atttypid, -1, 0);
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
TupleDescFinalize(buildstate->sortdesc);
|
|
||||||
#endif
|
|
||||||
|
|
||||||
buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
|
buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
|
||||||
|
|
||||||
@@ -456,7 +435,7 @@ ComputeCenters(IvfflatBuildState * buildstate)
|
|||||||
buildstate->samples = VectorArrayInit(numSamples, buildstate->dimensions, buildstate->centers->itemsize);
|
buildstate->samples = VectorArrayInit(numSamples, buildstate->dimensions, buildstate->centers->itemsize);
|
||||||
if (buildstate->heap != NULL)
|
if (buildstate->heap != NULL)
|
||||||
{
|
{
|
||||||
IvfflatBench("sample rows", SampleRows(buildstate));
|
SampleRows(buildstate);
|
||||||
|
|
||||||
if (buildstate->samples->length < buildstate->lists)
|
if (buildstate->samples->length < buildstate->lists)
|
||||||
{
|
{
|
||||||
@@ -671,11 +650,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
|
|||||||
ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
|
ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
|
||||||
buildstate.sortstate = ivfspool->sortstate;
|
buildstate.sortstate = ivfspool->sortstate;
|
||||||
scan = table_beginscan_parallel(ivfspool->heap,
|
scan = table_beginscan_parallel(ivfspool->heap,
|
||||||
ParallelTableScanFromIvfflatShared(ivfshared)
|
ParallelTableScanFromIvfflatShared(ivfshared));
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
,SO_NONE
|
|
||||||
#endif
|
|
||||||
);
|
|
||||||
reltuples = table_index_build_scan(ivfspool->heap, ivfspool->index, indexInfo,
|
reltuples = table_index_build_scan(ivfspool->heap, ivfspool->index, indexInfo,
|
||||||
true, progress, BuildCallback,
|
true, progress, BuildCallback,
|
||||||
(void *) &buildstate, scan);
|
(void *) &buildstate, scan);
|
||||||
|
|||||||
@@ -9,7 +9,6 @@
|
|||||||
#include "lib/pairingheap.h"
|
#include "lib/pairingheap.h"
|
||||||
#include "nodes/execnodes.h"
|
#include "nodes/execnodes.h"
|
||||||
#include "port.h" /* for random() */
|
#include "port.h" /* for random() */
|
||||||
#include "storage/condition_variable.h"
|
|
||||||
#include "utils/sampling.h"
|
#include "utils/sampling.h"
|
||||||
#include "utils/tuplesort.h"
|
#include "utils/tuplesort.h"
|
||||||
#include "vector.h"
|
#include "vector.h"
|
||||||
@@ -214,8 +213,7 @@ typedef struct IvfflatBuildState
|
|||||||
/* Sampling */
|
/* Sampling */
|
||||||
BlockSamplerData bs;
|
BlockSamplerData bs;
|
||||||
ReservoirStateData rstate;
|
ReservoirStateData rstate;
|
||||||
double samplerows;
|
int rowstoskip;
|
||||||
double rowstoskip;
|
|
||||||
|
|
||||||
/* Sorting */
|
/* Sorting */
|
||||||
Tuplesortstate *sortstate;
|
Tuplesortstate *sortstate;
|
||||||
|
|||||||
@@ -298,9 +298,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
|
|||||||
so->tupdesc = CreateTemplateTupleDesc(2);
|
so->tupdesc = CreateTemplateTupleDesc(2);
|
||||||
TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
|
TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
|
||||||
TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
|
TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
|
||||||
#if PG_VERSION_NUM >= 190000
|
|
||||||
TupleDescFinalize(so->tupdesc);
|
|
||||||
#endif
|
|
||||||
|
|
||||||
/* Prep sort */
|
/* Prep sort */
|
||||||
so->sortstate = InitScanSortState(so->tupdesc);
|
so->sortstate = InitScanSortState(so->tupdesc);
|
||||||
|
|||||||
@@ -895,28 +895,24 @@ SparsevecInnerProduct(SparseVector * a, SparseVector * b)
|
|||||||
float *ax = SPARSEVEC_VALUES(a);
|
float *ax = SPARSEVEC_VALUES(a);
|
||||||
float *bx = SPARSEVEC_VALUES(b);
|
float *bx = SPARSEVEC_VALUES(b);
|
||||||
float distance = 0.0;
|
float distance = 0.0;
|
||||||
int bpos = 0;
|
int i = 0;
|
||||||
|
int j = 0;
|
||||||
|
|
||||||
for (int i = 0; i < a->nnz; i++)
|
while (i < a->nnz && j < b->nnz)
|
||||||
{
|
{
|
||||||
int ai = a->indices[i];
|
int ai = a->indices[i];
|
||||||
|
|
||||||
for (int j = bpos; j < b->nnz; j++)
|
|
||||||
{
|
|
||||||
int bi = b->indices[j];
|
int bi = b->indices[j];
|
||||||
|
|
||||||
/* Only update when the same index */
|
|
||||||
if (ai == bi)
|
if (ai == bi)
|
||||||
|
{
|
||||||
distance += ax[i] * bx[j];
|
distance += ax[i] * bx[j];
|
||||||
|
i++;
|
||||||
/* Update start for next iteration */
|
j++;
|
||||||
if (ai >= bi)
|
|
||||||
bpos = j + 1;
|
|
||||||
|
|
||||||
/* Found or passed it */
|
|
||||||
if (bi >= ai)
|
|
||||||
break;
|
|
||||||
}
|
}
|
||||||
|
else if (ai < bi)
|
||||||
|
i++;
|
||||||
|
else
|
||||||
|
j++;
|
||||||
}
|
}
|
||||||
|
|
||||||
return distance;
|
return distance;
|
||||||
|
|||||||
Reference in New Issue
Block a user