Updated SparsevecInnerProduct [skip ci]

README.md

@@ -11,8 +11,6 @@ Store your vectors with the rest of your data. Supports:
 
 Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres
 
-Have a lot of vectors? Use [quantization](#scaling) to scale
-
 [![Build Status](https://github.com/pgvector/pgvector/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions)
 
 ## Installation
@@ -316,8 +314,6 @@ For a large number of workers, you may need to increase `max_parallel_workers` (
 
 The [index options](#index-options) also have a significant impact on build time (use the defaults unless seeing low recall)
 
-Use [binary quantization](#binary-quantization) for faster build times at scale
-
 ### Indexing Progress
 
 Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
@@ -447,7 +443,13 @@ Exact indexes work well for conditions that match a low percentage of rows. Othe
 CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
 ```
 
-With approximate indexes, filtering is applied *after* the index is scanned. If a condition matches 10% of rows, with HNSW and the default `hnsw.ef_search` of 40, only 4 rows will match on average. For more rows, enable [iterative index scans](#iterative-index-scans), which will automatically scan more of the index when needed.
+With approximate indexes, filtering is applied *after* the index is scanned. If a condition matches 10% of rows, with HNSW and the default `hnsw.ef_search` of 40, only 4 rows will match on average. For more rows, increase `hnsw.ef_search`.
+
+```sql
+SET hnsw.ef_search = 200;
+```
+
+Starting with 0.8.0, you can enable [iterative index scans](#iterative-index-scans), which will automatically scan more of the index when needed.
 
 ```sql
 SET hnsw.iterative_scan = strict_order;
@@ -671,10 +673,6 @@ SHOW shared_buffers;
 
 Be sure to restart Postgres for changes to take effect.
 
-### Storing
-
-Use the `halfvec` type instead of `vector` for a smaller working set.
-
 ### Loading
 
 Use `COPY` for bulk loading data ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/loading/example.py)).
@@ -689,8 +687,6 @@ Add any indexes *after* loading the initial data for best performance.
 
 See index build time for [HNSW](#index-build-time) and [IVFFlat](#index-build-time-1).
 
-Use [binary quantization](#binary-quantization) for smaller indexes and faster build times at scale.
-
 In production environments, create indexes concurrently to avoid blocking writes.
 
 ```sql
@@ -721,8 +717,6 @@ SELECT * FROM items ORDER BY embedding <#> '[3,1,2]' LIMIT 5;
 
 #### Approximate Search
 
-Use [binary quantization](#binary-quantization) with re-ranking to keep indexes in-memory at scale.
-
 To speed up queries with an IVFFlat index, increase the number of inverted lists (at the expense of recall).
 
 ```sql
@@ -738,20 +732,21 @@ REINDEX INDEX CONCURRENTLY index_name;
 VACUUM table_name;
 ```
 
-## Scaling
-
-For a smaller working set:
-
-1. Use the `halfvec` type instead of `vector` for tables
-2. Use [binary quantization](#binary-quantization) for indexes (with re-ranking for search)
-
-Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring).
-
-Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus), [PgDog](https://github.com/pgdogdev/pgdog), or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py)).
-
 ## Monitoring
 
-Use existing tools like [pg_stat_statements](https://www.postgresql.org/docs/current/pgstatstatements.html) or [PgHero](https://github.com/ankane/pghero) to monitor performance.
+Monitor performance with [pg_stat_statements](https://www.postgresql.org/docs/current/pgstatstatements.html) (be sure to add it to `shared_preload_libraries`).
+
+```sql
+CREATE EXTENSION pg_stat_statements;
+```
+
+Get the most time-consuming queries with:
+
+```sql
+SELECT query, calls, ROUND((total_plan_time + total_exec_time) / calls) AS avg_time_ms,
+    ROUND((total_plan_time + total_exec_time) / 60000) AS total_time_min
+    FROM pg_stat_statements ORDER BY total_plan_time + total_exec_time DESC LIMIT 20;
+```
 
 Monitor recall by comparing results from approximate search with exact search.
 
@@ -762,6 +757,14 @@ SELECT ...
 COMMIT;
 ```
 
+## Scaling
+
+Scale pgvector the same way you scale Postgres.
+
+Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring).
+
+Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus) or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py)).
+
 ## Languages
 
 Use pgvector from any language with a Postgres client. You can even generate and store vectors in one language and query them in another.
@@ -875,8 +878,6 @@ No, but like other index types, you’ll likely see better performance if they d
 SELECT pg_size_pretty(pg_relation_size('index_name'));
 ```
 
-Use [half-precision indexing](#half-precision-indexing) or [binary quantization](#binary-quantization) for smaller indexes.
-
 ## Troubleshooting
 
 #### Why isn’t a query using an index?

src/bitutils.c

@@ -169,7 +169,7 @@ BitJaccardDistanceAvx512Popcount(uint32 bytes, unsigned char *ax, unsigned char
 #endif
 
 TARGET_XSAVE static bool
-SupportsAvx512Popcount(void)
+SupportsAvx512Popcount()
 {
 	unsigned int exx[4] = {0, 0, 0, 0};
 

src/hnsw.c

@@ -13,7 +13,6 @@
 #include "hnsw.h"
 #include "miscadmin.h"
 #include "nodes/pg_list.h"
-#include "storage/lwlock.h"
 #include "utils/float.h"
 #include "utils/guc.h"
 #include "utils/relcache.h"
@@ -258,11 +257,6 @@ hnswvalidate(Oid opclassoid)
 	return true;
 }
 
-static void
-hnswunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
-{
-}
-
 /*
  * Define index handler
  *
@@ -284,7 +278,6 @@ hnswhandler(PG_FUNCTION_ARGS)
 		.amconsistentequality = false,
 		.amconsistentordering = false,
 		.amcanbackward = false,
-		.amcanmarkpos = false,
 		.amcanunique = false,
 		.amcanmulticol = false,
 		.amoptionalkey = true,
@@ -317,14 +310,11 @@ hnswhandler(PG_FUNCTION_ARGS)
 		.amadjustmembers = NULL,
 		.ambeginscan = hnswbeginscan,
 		.amrescan = hnswrescan,
-		.amgettuple = NULL,
+		.amgettuple = hnswgettuple,
-		.amgetbatch = hnswgetbatch,
-		.amunguardbatch = hnswunguardbatch,
-		.amkillitemsbatch = NULL,
-		.amgettransform = NULL,
 		.amgetbitmap = NULL,
 		.amendscan = hnswendscan,
-		.amposreset = NULL,
+		.ammarkpos = NULL,
+		.amrestrpos = NULL,
 		.amestimateparallelscan = NULL,
 		.aminitparallelscan = NULL,
 		.amparallelrescan = NULL,

src/hnsw.h

@@ -10,10 +10,6 @@
 #include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #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/sampling.h"
 #include "vector.h"
@@ -465,7 +461,7 @@ IndexBulkDeleteResult *hnswbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResu
 IndexBulkDeleteResult *hnswvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
 IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
 void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
-IndexScanBatch hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir);
+bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
 static inline HnswNeighborArray *

src/hnswbuild.c

@@ -54,7 +54,6 @@
 #include "nodes/execnodes.h"
 #include "optimizer/optimizer.h"
 #include "storage/bufmgr.h"
-#include "storage/condition_variable.h"
 #include "tcop/tcopprot.h"
 #include "utils/datum.h"
 #include "utils/memutils.h"
@@ -803,11 +802,7 @@ HnswParallelScanAndInsert(Relation heapRel, Relation indexRel, HnswShared * hnsw
 	buildstate.hnswarea = hnswarea;
 	InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
 	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,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);

src/hnswinsert.c

@@ -6,7 +6,6 @@
 #include "nodes/execnodes.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
-#include "storage/lwlock.h"
 #include "utils/datum.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"

src/hnswscan.c

@@ -3,7 +3,6 @@
 #include <limits.h>
 
 #include "access/genam.h"
-#include "access/indexbatch.h"
 #include "access/relscan.h"
 #include "hnsw.h"
 #include "lib/pairingheap.h"
@@ -136,11 +135,6 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	double		maxMemory;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
-	scan->maxitemsbatch = hnsw_ef_search * HNSW_HEAPTIDS;
-	/* unused but must be > 0 */
-	scan->batch_index_opaque_static = MAXALIGN(1);
-	scan->batch_index_opaque_dyn = 0;
-	scan->batch_tuples_workspace = 0;
 
 	so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
 	so->typeInfo = HnswGetTypeInfo(index);
@@ -190,13 +184,12 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
 }
 
 /*
- * Fetch the next batch in the given scan
+ * Fetch the next tuple in the given scan
  */
-IndexScanBatch
+bool
-hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
+hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
-	IndexScanBatch batch = indexam_util_alloc_batch(scan);
 	MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
 
 	/*
@@ -252,7 +245,6 @@ hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
 		HnswSearchCandidate *sc;
 		HnswElement element;
 		ItemPointer heaptid;
-		int			nitems = 0;
 
 		if (list_length(so->w) == 0)
 		{
@@ -298,8 +290,6 @@ hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
 				break;
 		}
 
-		while (list_length(so->w) != 0)
-		{
 		sc = llast(so->w);
 		element = HnswPtrAccess(base, sc->element);
 
@@ -328,34 +318,16 @@ hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
 			so->previousDistance = sc->distance;
 		}
 
-			batch->items[nitems].tableTid = *heaptid;
-			batch->items[nitems].indexOffset = -1;
-			batch->items[nitems].tupleOffset = 0;
-			nitems++;
-
-			/* Keep batch size flexible */
-			if (nitems == scan->maxitemsbatch)
-				break;
-		}
-
-		/* Needed for strict iterative scans */
-		if (nitems == 0)
-			continue;
-
 		MemoryContextSwitchTo(oldCtx);
 
+		scan->xs_heaptid = *heaptid;
 		scan->xs_recheck = false;
 		scan->xs_recheckorderby = false;
-
+		return true;
-		batch->firstItem = 0;
-		batch->lastItem = nitems - 1;
-		batch->dir = ForwardScanDirection;
-		return batch;
 	}
 
 	MemoryContextSwitchTo(oldCtx);
-	indexam_util_release_batch(scan, batch);
+	return false;
-	return NULL;
 }
 
 /*

src/ivfbuild.c

@@ -22,7 +22,6 @@
 #include "nodes/execnodes.h"
 #include "optimizer/optimizer.h"
 #include "storage/bufmgr.h"
-#include "storage/condition_variable.h"
 #include "tcop/tcopprot.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
@@ -63,13 +62,15 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 	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 (!IvfflatCheckNorm(buildstate->kmeansnormprocinfo, buildstate->collation, value))
 			return;
+
+		value = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
 	}
 
 	if (samples->length < targsamples)
@@ -80,7 +81,7 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 	else
 	{
 		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)
 		{
@@ -96,9 +97,6 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 
 		buildstate->rowstoskip -= 1;
 	}
-
-	/* Increment after reservoir_get_next_S */
-	buildstate->samplerows += 1;
 }
 
 /*
@@ -135,7 +133,6 @@ SampleRows(IvfflatBuildState * buildstate)
 	int			targsamples = buildstate->samples->maxlen;
 	BlockNumber totalblocks = RelationGetNumberOfBlocks(buildstate->heap);
 
-	buildstate->samplerows = 0;
 	buildstate->rowstoskip = -1;
 
 	BlockSampler_Init(&buildstate->bs, totalblocks, targsamples, RandomInt());
@@ -145,24 +142,8 @@ SampleRows(IvfflatBuildState * buildstate)
 	{
 		BlockNumber targblock = BlockSampler_Next(&buildstate->bs);
 
-		/* Set anyvisible to false like table_index_build_scan */
 		table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-									 false, false, 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));
-		}
 	}
 }
 
@@ -393,9 +374,6 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -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);
 
@@ -457,7 +435,7 @@ ComputeCenters(IvfflatBuildState * buildstate)
 	buildstate->samples = VectorArrayInit(numSamples, buildstate->dimensions, buildstate->centers->itemsize);
 	if (buildstate->heap != NULL)
 	{
-		IvfflatBench("sample rows", SampleRows(buildstate));
+		SampleRows(buildstate);
 
 		if (buildstate->samples->length < buildstate->lists)
 		{
@@ -672,11 +650,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
 	buildstate.sortstate = ivfspool->sortstate;
 	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,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);

src/ivfflat.c

@@ -175,11 +175,6 @@ ivfflatvalidate(Oid opclassoid)
 	return true;
 }
 
-static void
-ivfflatunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
-{
-}
-
 /*
  * Define index handler
  *
@@ -201,7 +196,6 @@ ivfflathandler(PG_FUNCTION_ARGS)
 		.amconsistentequality = false,
 		.amconsistentordering = false,
 		.amcanbackward = false,
-		.amcanmarkpos = false,
 		.amcanunique = false,
 		.amcanmulticol = false,
 		.amoptionalkey = true,
@@ -234,14 +228,11 @@ ivfflathandler(PG_FUNCTION_ARGS)
 		.amadjustmembers = NULL,
 		.ambeginscan = ivfflatbeginscan,
 		.amrescan = ivfflatrescan,
-		.amgettuple = NULL,
+		.amgettuple = ivfflatgettuple,
-		.amgetbatch = ivfflatgetbatch,
-		.amunguardbatch = ivfflatunguardbatch,
-		.amkillitemsbatch = NULL,
-		.amgettransform = NULL,
 		.amgetbitmap = NULL,
 		.amendscan = ivfflatendscan,
-		.amposreset = NULL,
+		.ammarkpos = NULL,
+		.amrestrpos = NULL,
 		.amestimateparallelscan = NULL,
 		.aminitparallelscan = NULL,
 		.amparallelrescan = NULL,

src/ivfflat.h

@@ -9,7 +9,6 @@
 #include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
-#include "storage/condition_variable.h"
 #include "utils/sampling.h"
 #include "utils/tuplesort.h"
 #include "vector.h"
@@ -214,8 +213,7 @@ typedef struct IvfflatBuildState
 	/* Sampling */
 	BlockSamplerData bs;
 	ReservoirStateData rstate;
-	double		samplerows;
+	int			rowstoskip;
-	double		rowstoskip;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -344,7 +342,7 @@ IndexBulkDeleteResult *ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteR
 IndexBulkDeleteResult *ivfflatvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
 IndexScanDesc ivfflatbeginscan(Relation index, int nkeys, int norderbys);
 void		ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
-IndexScanBatch ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir);
+bool		ivfflatgettuple(IndexScanDesc scan, ScanDirection dir);
 void		ivfflatendscan(IndexScanDesc scan);
 
 #endif

src/ivfscan.c

@@ -3,7 +3,6 @@
 #include <float.h>
 
 #include "access/genam.h"
-#include "access/indexbatch.h"
 #include "access/itup.h"
 #include "access/relscan.h"
 #include "access/tupdesc.h"
@@ -262,11 +261,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	MemoryContext oldCtx;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
-	scan->maxitemsbatch = 1000;
-	/* unused but must be > 0 */
-	scan->batch_index_opaque_static = MAXALIGN(1);
-	scan->batch_index_opaque_dyn = 0;
-	scan->batch_tuples_workspace = 0;
 
 	/* Get lists and dimensions from metapage */
 	IvfflatGetMetaPageInfo(index, &lists, &dimensions);
@@ -304,9 +298,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->tupdesc = CreateTemplateTupleDesc(2);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
-#if PG_VERSION_NUM >= 190000
-	TupleDescFinalize(so->tupdesc);
-#endif
 
 	/* Prep sort */
 	so->sortstate = InitScanSortState(so->tupdesc);
@@ -354,16 +345,14 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 }
 
 /*
- * Fetch the next batch in the given scan
+ * Fetch the next tuple in the given scan
  */
-IndexScanBatch
+bool
-ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
+ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
-	IndexScanBatch batch = indexam_util_alloc_batch(scan);
 	ItemPointer heaptid;
 	bool		isnull;
-	int			nitems = 0;
 
 	/*
 	 * Index can be used to scan backward, but Postgres doesn't support
@@ -401,37 +390,17 @@ ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir
 	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
 		if (so->listIndex == so->maxProbes)
-		{
+			return false;
-			indexam_util_release_batch(scan, batch);
-			return NULL;
-		}
 
 		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
 	}
 
-	for (;;)
-	{
 	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
 
-		batch->items[nitems].tableTid = *heaptid;
+	scan->xs_heaptid = *heaptid;
-		batch->items[nitems].indexOffset = -1;
-		batch->items[nitems].tupleOffset = 0;
-		nitems++;
-
-		if (nitems == scan->maxitemsbatch)
-			break;
-
-		if (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
-			break;
-	}
-
 	scan->xs_recheck = false;
 	scan->xs_recheckorderby = false;
-
+	return true;
-	batch->firstItem = 0;
-	batch->lastItem = nitems - 1;
-	batch->dir = ForwardScanDirection;
-	return batch;
 }
 
 /*

src/sparsevec.c

@@ -182,10 +182,10 @@ sparsevec_isspace(char ch)
 static int
 CompareIndices(const void *a, const void *b)
 {
-	if (((const SparseInputElement *) a)->index < ((const SparseInputElement *) b)->index)
+	if (((SparseInputElement *) a)->index < ((SparseInputElement *) b)->index)
 		return -1;
 
-	if (((const SparseInputElement *) a)->index > ((const SparseInputElement *) b)->index)
+	if (((SparseInputElement *) a)->index > ((SparseInputElement *) b)->index)
 		return 1;
 
 	return 0;
@@ -895,28 +895,24 @@ SparsevecInnerProduct(SparseVector * a, SparseVector * b)
 	float	   *ax = SPARSEVEC_VALUES(a);
 	float	   *bx = SPARSEVEC_VALUES(b);
 	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];
-
-		for (int j = bpos; j < b->nnz; j++)
-		{
 		int			bi = b->indices[j];
 
-			/* Only update when the same index */
 		if (ai == bi)
+		{
 			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;