Added TAP test [skip ci]

sql/vector.sql

@@ -266,9 +266,6 @@ COMMENT ON ACCESS METHOD hnsw IS 'hnsw index access method';
 CREATE FUNCTION ivfflat_halfvec_support(internal) RETURNS internal
 	AS 'MODULE_PATHNAME' LANGUAGE C;
 
-CREATE FUNCTION ivfflat_minivec_support(internal) RETURNS internal
-	AS 'MODULE_PATHNAME' LANGUAGE C;
-
 CREATE FUNCTION ivfflat_bit_support(internal) RETURNS internal
 	AS 'MODULE_PATHNAME' LANGUAGE C;
 
@@ -751,9 +748,6 @@ CREATE FUNCTION minivec_l2_squared_distance(minivec, minivec) RETURNS float8
 CREATE FUNCTION minivec_negative_inner_product(minivec, minivec) RETURNS float8
 	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
-CREATE FUNCTION minivec_spherical_distance(minivec, minivec) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
 -- minivec cast functions
 
 CREATE FUNCTION minivec(minivec, integer, boolean) RETURNS minivec
@@ -893,30 +887,6 @@ CREATE OPERATOR CLASS minivec_ops
 	OPERATOR 5 > ,
 	FUNCTION 1 minivec_cmp(minivec, minivec);
 
-CREATE OPERATOR CLASS minivec_l2_ops
-	FOR TYPE minivec USING ivfflat AS
-	OPERATOR 1 <-> (minivec, minivec) FOR ORDER BY float_ops,
-	FUNCTION 1 minivec_l2_squared_distance(minivec, minivec),
-	FUNCTION 3 l2_distance(minivec, minivec),
-	FUNCTION 5 ivfflat_minivec_support(internal);
-
-CREATE OPERATOR CLASS minivec_ip_ops
-	FOR TYPE minivec USING ivfflat AS
-	OPERATOR 1 <#> (minivec, minivec) FOR ORDER BY float_ops,
-	FUNCTION 1 minivec_negative_inner_product(minivec, minivec),
-	FUNCTION 3 minivec_spherical_distance(minivec, minivec),
-	FUNCTION 4 l2_norm(minivec),
-	FUNCTION 5 ivfflat_minivec_support(internal);
-
-CREATE OPERATOR CLASS minivec_cosine_ops
-	FOR TYPE minivec USING ivfflat AS
-	OPERATOR 1 <=> (minivec, minivec) FOR ORDER BY float_ops,
-	FUNCTION 1 cosine_distance(minivec, minivec),
-	FUNCTION 2 l2_norm(minivec),
-	FUNCTION 3 minivec_spherical_distance(minivec, minivec),
-	FUNCTION 4 l2_norm(minivec),
-	FUNCTION 5 ivfflat_minivec_support(internal);
-
 CREATE OPERATOR CLASS minivec_l2_ops
 	FOR TYPE minivec USING hnsw AS
 	OPERATOR 1 <-> (minivec, minivec) FOR ORDER BY float_ops,
@@ -932,7 +902,7 @@ CREATE OPERATOR CLASS minivec_ip_ops
 CREATE OPERATOR CLASS minivec_cosine_ops
 	FOR TYPE minivec USING hnsw AS
 	OPERATOR 1 <=> (minivec, minivec) FOR ORDER BY float_ops,
-	FUNCTION 1 cosine_distance(minivec, minivec),
+	FUNCTION 1 minivec_negative_inner_product(minivec, minivec),
 	FUNCTION 2 l2_norm(minivec),
 	FUNCTION 3 hnsw_minivec_support(internal);
 

src/hnswutils.c

@@ -159,9 +159,6 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 Datum
 HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
 {
-	if (!typeInfo->normalize)
-		return value;
-
 	return DirectFunctionCall1Coll(typeInfo->normalize, collation, value);
 }
 
@@ -1385,8 +1382,7 @@ hnsw_minivec_support(PG_FUNCTION_ARGS)
 {
 	static const HnswTypeInfo typeInfo = {
 		.maxDimensions = HNSW_MAX_DIM * 4,
-		/* Do not normalize to maximize precision */
+		.normalize = minivec_l2_normalize,
-		.normalize = NULL,
 		.checkValue = NULL
 	};
 

src/ivfutils.c

@@ -7,7 +7,6 @@
 #include "halfutils.h"
 #include "halfvec.h"
 #include "ivfflat.h"
-#include "minivec.h"
 #include "storage/bufmgr.h"
 
 /*
@@ -71,9 +70,6 @@ IvfflatOptionalProcInfo(Relation index, uint16 procnum)
 Datum
 IvfflatNormValue(const IvfflatTypeInfo * typeInfo, Oid collation, Datum value)
 {
-	if (!typeInfo->normalize)
-		return value;
-
 	return DirectFunctionCall1Coll(typeInfo->normalize, collation, value);
 }
 
@@ -235,7 +231,6 @@ IvfflatUpdateList(Relation index, ListInfo listInfo,
 
 PGDLLEXPORT Datum l2_normalize(PG_FUNCTION_ARGS);
 PGDLLEXPORT Datum halfvec_l2_normalize(PG_FUNCTION_ARGS);
-PGDLLEXPORT Datum minivec_l2_normalize(PG_FUNCTION_ARGS);
 PGDLLEXPORT Datum sparsevec_l2_normalize(PG_FUNCTION_ARGS);
 
 static Size
@@ -250,12 +245,6 @@ HalfvecItemSize(int dimensions)
 	return HALFVEC_SIZE(dimensions);
 }
 
-static Size
-MinivecItemSize(int dimensions)
-{
-	return MINIVEC_SIZE(dimensions);
-}
-
 static Size
 BitItemSize(int dimensions)
 {
@@ -286,18 +275,6 @@ HalfvecUpdateCenter(Pointer v, int dimensions, float *x)
 		vec->x[k] = Float4ToHalfUnchecked(x[k]);
 }
 
-static void
-MinivecUpdateCenter(Pointer v, int dimensions, float *x)
-{
-	MiniVector *vec = (MiniVector *) v;
-
-	SET_VARSIZE(vec, MINIVEC_SIZE(dimensions));
-	vec->dim = dimensions;
-
-	for (int k = 0; k < dimensions; k++)
-		vec->x[k] = Float4ToFp8Unchecked(x[k]);
-}
-
 static void
 BitUpdateCenter(Pointer v, int dimensions, float *x)
 {
@@ -332,15 +309,6 @@ HalfvecSumCenter(Pointer v, float *x)
 		x[k] += HalfToFloat4(vec->x[k]);
 }
 
-static void
-MinivecSumCenter(Pointer v, float *x)
-{
-	MiniVector *vec = (MiniVector *) v;
-
-	for (int k = 0; k < vec->dim; k++)
-		x[k] += Fp8ToFloat4(vec->x[k]);
-}
-
 static void
 BitSumCenter(Pointer v, float *x)
 {
@@ -389,22 +357,6 @@ ivfflat_halfvec_support(PG_FUNCTION_ARGS)
 	PG_RETURN_POINTER(&typeInfo);
 };
 
-FUNCTION_PREFIX PG_FUNCTION_INFO_V1(ivfflat_minivec_support);
-Datum
-ivfflat_minivec_support(PG_FUNCTION_ARGS)
-{
-	static const IvfflatTypeInfo typeInfo = {
-		.maxDimensions = IVFFLAT_MAX_DIM * 4,
-		/* Do not normalize to maximize precision */
-		.normalize = NULL,
-		.itemSize = MinivecItemSize,
-		.updateCenter = MinivecUpdateCenter,
-		.sumCenter = MinivecSumCenter
-	};
-
-	PG_RETURN_POINTER(&typeInfo);
-};
-
 FUNCTION_PREFIX PG_FUNCTION_INFO_V1(ivfflat_bit_support);
 Datum
 ivfflat_bit_support(PG_FUNCTION_ARGS)

src/minivec.c

@@ -652,6 +652,7 @@ MinivecL1Distance(int dim, fp8 * ax, fp8 * bx)
 {
 	float		distance = 0.0;
 
+	/* Auto-vectorized */
 	for (int i = 0; i < dim; i++)
 		distance += fabsf(Fp8ToFloat4(ax[i]) - Fp8ToFloat4(bx[i]));
 
@@ -696,6 +697,7 @@ minivec_l2_norm(PG_FUNCTION_ARGS)
 	fp8		   *ax = a->x;
 	double		norm = 0.0;
 
+	/* Auto-vectorized */
 	for (int i = 0; i < a->dim; i++)
 	{
 		double		axi = (double) Fp8ToFloat4(ax[i]);
@@ -722,6 +724,7 @@ minivec_l2_normalize(PG_FUNCTION_ARGS)
 	result = InitMiniVector(a->dim);
 	rx = result->x;
 
+	/* Auto-vectorized */
 	for (int i = 0; i < a->dim; i++)
 		norm += (double) Fp8ToFloat4(ax[i]) * (double) Fp8ToFloat4(ax[i]);
 
@@ -763,8 +766,15 @@ minivec_add(PG_FUNCTION_ARGS)
 	result = InitMiniVector(a->dim);
 	rx = result->x;
 
+	/* Auto-vectorized */
 	for (int i = 0, imax = a->dim; i < imax; i++)
+	{
+#ifdef FLT16_SUPPORT
+		rx[i] = ax[i] + bx[i];
+#else
 		rx[i] = Float4ToFp8Unchecked(Fp8ToFloat4(ax[i]) + Fp8ToFloat4(bx[i]));
+#endif
+	}
 
 	/* Check for overflow */
 	for (int i = 0, imax = a->dim; i < imax; i++)
@@ -795,8 +805,15 @@ minivec_sub(PG_FUNCTION_ARGS)
 	result = InitMiniVector(a->dim);
 	rx = result->x;
 
+	/* Auto-vectorized */
 	for (int i = 0, imax = a->dim; i < imax; i++)
+	{
+#ifdef FLT16_SUPPORT
+		rx[i] = ax[i] - bx[i];
+#else
 		rx[i] = Float4ToFp8Unchecked(Fp8ToFloat4(ax[i]) - Fp8ToFloat4(bx[i]));
+#endif
+	}
 
 	/* Check for overflow */
 	for (int i = 0, imax = a->dim; i < imax; i++)
@@ -827,8 +844,15 @@ minivec_mul(PG_FUNCTION_ARGS)
 	result = InitMiniVector(a->dim);
 	rx = result->x;
 
+	/* Auto-vectorized */
 	for (int i = 0, imax = a->dim; i < imax; i++)
+	{
+#ifdef FLT16_SUPPORT
+		rx[i] = ax[i] * bx[i];
+#else
 		rx[i] = Float4ToFp8Unchecked(Fp8ToFloat4(ax[i]) * Fp8ToFloat4(bx[i]));
+#endif
+	}
 
 	/* Check for overflow and underflow */
 	for (int i = 0, imax = a->dim; i < imax; i++)

src/minivec.h

@@ -1,6 +1,8 @@
 #ifndef MINIVEC_H
 #define MINIVEC_H
 
+#include <float.h>
+
 #define MINIVEC_MAX_DIM 16000
 
 #define fp8 uint8
@@ -44,19 +46,10 @@ Fp8IsZero(fp8 num)
 static inline float
 Fp8ToFloat4(fp8 num)
 {
-	/* Lookup table for non-sign bits */
+	float		lookup[128] = {0, 0.00195312, 0.00390625, 0.00585938, 0.0078125, 0.00976562, 0.0117188, 0.0136719, 0.015625, 0.0175781, 0.0195312, 0.0214844, 0.0234375, 0.0253906, 0.0273438, 0.0292969, 0.03125, 0.0351562, 0.0390625, 0.0429688, 0.046875, 0.0507812, 0.0546875, 0.0585938, 0.0625, 0.0703125, 0.078125, 0.0859375, 0.09375, 0.101562, 0.109375, 0.117188, 0.125, 0.140625, 0.15625, 0.171875, 0.1875, 0.203125, 0.21875, 0.234375, 0.25, 0.28125, 0.3125, 0.34375, 0.375, 0.40625, 0.4375, 0.46875, 0.5, 0.5625, 0.625, 0.6875, 0.75, 0.8125, 0.875, 0.9375, 1, 1.125, 1.25, 1.375, 1.5, 1.625, 1.75, 1.875, 2, 2.25, 2.5, 2.75, 3, 3.25, 3.5, 3.75, 4, 4.5, 5, 5.5, 6, 6.5, 7, 7.5, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 20, 22, 24, 26, 28, 30, 32, 36, 40, 44, 48, 52, 56, 60, 64, 72, 80, 88, 96, 104, 112, 120, 128, 144, 160, 176, 192, 208, 224, 240, 256, 288, 320, 352, 384, 416, 448, NAN};
-	/* Uses uint32 for correctness */
+	float		v = lookup[num & 0x7F];
-	uint32		lookup[128] = {0, 989855744, 998244352, 1002438656, 1006632960, 1008730112, 1010827264, 1012924416, 1015021568, 1016070144, 1017118720, 1018167296, 1019215872, 1020264448, 1021313024, 1022361600, 1023410176, 1024458752, 1025507328, 1026555904, 1027604480, 1028653056, 1029701632, 1030750208, 1031798784, 1032847360, 1033895936, 1034944512, 1035993088, 1037041664, 1038090240, 1039138816, 1040187392, 1041235968, 1042284544, 1043333120, 1044381696, 1045430272, 1046478848, 1047527424, 1048576000, 1049624576, 1050673152, 1051721728, 1052770304, 1053818880, 1054867456, 1055916032, 1056964608, 1058013184, 1059061760, 1060110336, 1061158912, 1062207488, 1063256064, 1064304640, 1065353216, 1066401792, 1067450368, 1068498944, 1069547520, 1070596096, 1071644672, 1072693248, 1073741824, 1074790400, 1075838976, 1076887552, 1077936128, 1078984704, 1080033280, 1081081856, 1082130432, 1083179008, 1084227584, 1085276160, 1086324736, 1087373312, 1088421888, 1089470464, 1090519040, 1091567616, 1092616192, 1093664768, 1094713344, 1095761920, 1096810496, 1097859072, 1098907648, 1099956224, 1101004800, 1102053376, 1103101952, 1104150528, 1105199104, 1106247680, 1107296256, 1108344832, 1109393408, 1110441984, 1111490560, 1112539136, 1113587712, 1114636288, 1115684864, 1116733440, 1117782016, 1118830592, 1119879168, 1120927744, 1121976320, 1123024896, 1124073472, 1125122048, 1126170624, 1127219200, 1128267776, 1129316352, 1130364928, 1131413504, 1132462080, 1133510656, 1134559232, 1135607808, 1136656384, 1137704960, 1138753536, 2146435072};
 
-	union
+	return (num & 0x80) == 0x80 ? -v : v;
-	{
-		float		f;
-		uint32		i;
-	}			swap;
-
-	swap.i = lookup[num & 0x7F];
-
-	return (num & 0x80) == 0x80 ? -swap.f : swap.f;
 }
 
 /*
@@ -69,15 +62,15 @@ Float4ToFp8Unchecked(float num)
 	{
 		float		f;
 		uint32		i;
-	}			swap;
+	}			swapfloat;
 
 	uint32		bin;
 	int			exponent;
 	int			mantissa;
 	uint8		result;
 
-	swap.f = num;
+	swapfloat.f = num;
-	bin = swap.i;
+	bin = swapfloat.i;
 	exponent = (bin & 0x7F800000) >> 23;
 	mantissa = bin & 0x007FFFFF;
 
@@ -89,14 +82,14 @@ Float4ToFp8Unchecked(float num)
 		/* NaN */
 		result |= 0x7F;
 	}
-	else if (exponent > 114)
+	else if (exponent > 116)
 	{
 		int			m;
 		int			gr;
 		int			s;
 
 		exponent -= 127;
-		s = mantissa & 0x0007FFFF;
+		s = mantissa & 0x000FFFFF;
 
 		/* Subnormal */
 		if (exponent < -6)
@@ -105,7 +98,7 @@ Float4ToFp8Unchecked(float num)
 
 			mantissa >>= diff;
 			mantissa += 1 << (23 - diff);
-			s |= mantissa & 0x0007FFFF;
+			s |= mantissa & 0x000FFFFF;
 		}
 
 		m = mantissa >> 20;
@@ -128,7 +121,7 @@ Float4ToFp8Unchecked(float num)
 		}
 		else
 		{
-			if (exponent >= -6)
+			if (exponent >= -7)
 				result |= (exponent + 7) << 3;
 
 			result |= m;
@@ -146,7 +139,7 @@ Float4ToFp8(float num)
 {
 	fp8			result = Float4ToFp8Unchecked(num);
 
-	if (unlikely(Fp8IsNan(result)) && !isinf(num))
+	if (unlikely(Fp8IsNan(result)) && !isnan(num))
 	{
 		char	   *buf = palloc(FLOAT_SHORTEST_DECIMAL_LEN);
 

test/expected/ivfflat_minivec.out

@@ -1,84 +0,0 @@
-SET enable_seqscan = off;
--- L2
-CREATE TABLE t (val minivec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val minivec_l2_ops) WITH (lists = 1);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,2,4]
- [1,1,1]
- [0,0,0]
-(4 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <-> (SELECT NULL::minivec)) t2;
- count 
--------
-     4
-(1 row)
-
-SELECT COUNT(*) FROM t;
- count 
--------
-     5
-(1 row)
-
-TRUNCATE t;
-NOTICE:  ivfflat index created with little data
-DETAIL:  This will cause low recall.
-HINT:  Drop the index until the table has more data.
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
- val 
------
-(0 rows)
-
-DROP TABLE t;
--- inner product
-CREATE TABLE t (val minivec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val minivec_ip_ops) WITH (lists = 1);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <#> '[3,3,3]';
-   val   
----------
- [1,2,4]
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(4 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <#> (SELECT NULL::minivec)) t2;
- count 
--------
-     4
-(1 row)
-
-DROP TABLE t;
--- cosine
-CREATE TABLE t (val minivec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val minivec_cosine_ops) WITH (lists = 1);
-INSERT INTO t (val) VALUES ('[1,2,4]');
-SELECT * FROM t ORDER BY val <=> '[3,3,3]';
-   val   
----------
- [1,1,1]
- [1,2,3]
- [1,2,4]
-(3 rows)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
- count 
--------
-     3
-(1 row)
-
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::minivec)) t2;
- count 
--------
-     3
-(1 row)
-
-DROP TABLE t;

test/sql/ivfflat_minivec.sql

@@ -1,45 +0,0 @@
-SET enable_seqscan = off;
-
--- L2
-
-CREATE TABLE t (val minivec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val minivec_l2_ops) WITH (lists = 1);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <-> (SELECT NULL::minivec)) t2;
-SELECT COUNT(*) FROM t;
-
-TRUNCATE t;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-DROP TABLE t;
-
--- inner product
-
-CREATE TABLE t (val minivec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val minivec_ip_ops) WITH (lists = 1);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <#> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <#> (SELECT NULL::minivec)) t2;
-
-DROP TABLE t;
-
--- cosine
-
-CREATE TABLE t (val minivec(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val minivec_cosine_ops) WITH (lists = 1);
-
-INSERT INTO t (val) VALUES ('[1,2,4]');
-
-SELECT * FROM t ORDER BY val <=> '[3,3,3]';
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
-SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::minivec)) t2;
-
-DROP TABLE t;

test/t/033_comparison.pl

@@ -40,10 +40,6 @@ for (1 .. 50)
 	$actual = $node->safe_psql("postgres", "SELECT halfvec_cmp(v::halfvec, '$query'::real[]::halfvec) FROM tst");
 	is($expected, $actual);
 
-	# Test minivec
-	$actual = $node->safe_psql("postgres", "SELECT minivec_cmp(v::minivec, '$query'::real[]::minivec) FROM tst");
-	is($expected, $actual);
-
 	# Test sparsevec
 	$actual = $node->safe_psql("postgres", "SELECT sparsevec_cmp(v::vector::sparsevec, '$query'::real[]::vector::sparsevec) FROM tst");
 	is($expected, $actual);

test/t/034_distance_functions.pl

@@ -45,10 +45,6 @@ for my $function (@functions)
 		my $actual = $node->safe_psql("postgres", "SELECT $function(v::halfvec, '$query'::vector::halfvec) FROM tst");
 		is($expected, $actual, "halfvec $function");
 
-		# Test minivec
-		$actual = $node->safe_psql("postgres", "SELECT $function(v::minivec, '$query'::vector::minivec) FROM tst");
-		is($expected, $actual, "minivec $function");
-
 		# Test sparsevec
 		$actual = $node->safe_psql("postgres", "SELECT $function(v::sparsevec, '$query'::vector::sparsevec) FROM tst");
 		is($expected, $actual, "sparsevec $function");

test/t/037_inputs.pl

@@ -12,8 +12,8 @@ $node->start;
 # Create extension
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 
-my @types = ("vector", "halfvec", "minivec", "sparsevec");
+my @types = ("vector", "halfvec", "sparsevec");
-my @inputs = ("[1.23,4.56,7.89]", "[1.23,4.56,7.89]", "[1.23,4.56,7.89]", "{1:1.23,2:4.56,3:7.89}/3");
+my @inputs = ("[1.23,4.56,7.89]", "[1.23,4.56,7.89]", "{1:1.23,2:4.56,3:7.89}/3");
 my @subs = (" ", " ", ",", ":", "-", "1", "9", "\0", "2147483648", "-2147483649");
 
 for my $i (0 .. $#types)

test/t/039_hnsw_minivec_build_recall.pl

@@ -95,6 +95,10 @@ for my $i (0 .. $#operators)
 
 	# Test approximate results
 	my $min = 0.98;
+	if ($operator eq '<=>')
+	{
+		$min = 0.65;
+	}
 	test_recall($min, $operator);
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");

test/t/040_hnsw_minivec_insert_recall.pl

@@ -1,113 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my $dim = 10;
-my $array_sql = join(",", ('2 * random() * random()') x $dim);
-
-sub test_recall
-{
-	my ($min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i serial, v minivec($dim));");
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, rand());
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-}
-
-# Check each index type
-my @operators = ("<->", "<#>", "<=>", "<+>");
-my @opclasses = ("minivec_l2_ops", "minivec_ip_ops", "minivec_cosine_ops", "minivec_l1_ops");
-
-for my $i (0 .. $#operators)
-{
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	# Add index
-	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v $opclass);");
-
-	# Use concurrent inserts
-	$node->pgbench(
-		"--no-vacuum --client=10 --transactions=1000",
-		0,
-		[qr{actually processed}],
-		[qr{^$}],
-		"concurrent INSERTs",
-		{
-			"040_hnsw_minivec_insert_recall_$opclass" => "INSERT INTO tst (v) VALUES (ARRAY[$array_sql]);"
-		}
-	);
-
-	# Get exact results
-	@expected = ();
-	foreach (@queries)
-	{
-		my $res = $node->safe_psql("postgres", qq(
-			SET enable_indexscan = off;
-			SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;
-		));
-		push(@expected, $res);
-	}
-
-	# Test approximate results
-	my $min = 0.98;
-	test_recall($min, $operator);
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-	$node->safe_psql("postgres", "TRUNCATE tst;");
-}
-
-done_testing();

test/t/041_hnsw_minivec_vacuum_recall.pl

@@ -1,97 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-
-sub test_recall
-{
-	my ($min, $ef_search, $test_name) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET hnsw.ef_search = $ef_search;
-		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SET hnsw.ef_search = $ef_search;
-			SELECT i FROM tst ORDER BY v <-> '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $test_name);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v minivec(3));");
-$node->safe_psql("postgres", "ALTER TABLE tst SET (autovacuum_enabled = false);");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) i;"
-);
-
-# Add index
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v minivec_l2_ops) WITH (m = 4, ef_construction = 8);");
-
-# Delete data
-$node->safe_psql("postgres", "DELETE FROM tst WHERE i > 2500;");
-
-# Generate queries
-for (1 .. 20)
-{
-	my $r1 = rand();
-	my $r2 = rand();
-	my $r3 = rand();
-	push(@queries, "[$r1,$r2,$r3]");
-}
-
-# Get exact results
-@expected = ();
-foreach (@queries)
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_indexscan = off;
-		SELECT i FROM tst ORDER BY v <-> '$_' LIMIT $limit;
-	));
-	push(@expected, $res);
-}
-
-test_recall(0.18, $limit, "before vacuum");
-test_recall(0.93, 100, "before vacuum");
-
-# TODO Test concurrent inserts with vacuum
-$node->safe_psql("postgres", "VACUUM tst;");
-
-test_recall(0.95, $limit, "after vacuum");
-
-done_testing();

test/t/042_hnsw_minivec_duplicates.pl

@@ -1,58 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-# Initialize node
-my $node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (v minivec(3));");
-
-sub insert_vectors
-{
-	for my $i (1 .. 20)
-	{
-		$node->safe_psql("postgres", "INSERT INTO tst VALUES ('[1,1,1]');");
-	}
-}
-
-sub test_duplicates
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET hnsw.ef_search = 1;
-		SELECT COUNT(*) FROM (SELECT * FROM tst ORDER BY v <-> '[1,1,1]') t;
-	));
-	is($res, 10);
-}
-
-# Test duplicates with build
-insert_vectors();
-$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v minivec_l2_ops);");
-test_duplicates();
-
-# Reset
-$node->safe_psql("postgres", "TRUNCATE tst;");
-
-# Test duplicates with inserts
-insert_vectors();
-test_duplicates();
-
-# Test fallback path for inserts
-$node->pgbench(
-	"--no-vacuum --client=5 --transactions=100",
-	0,
-	[qr{actually processed}],
-	[qr{^$}],
-	"concurrent INSERTs",
-	{
-		"042_hnsw_minivec_duplicates" => "INSERT INTO tst VALUES ('[1,1,1]');"
-	}
-);
-
-done_testing();

test/t/043_ivfflat_minivec_build_recall.pl

@@ -1,154 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my $dim = 10;
-my $array_sql = join(",", ('random()') x $dim);
-
-sub test_recall
-{
-	my ($probes, $min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET ivfflat.probes = $probes;
-		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan using idx on tst/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SET ivfflat.probes = $probes;
-			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-
-		my @expected_ids = split("\n", $expected[$i]);
-		my %expected_set = map { $_ => 1 } @expected_ids;
-
-		foreach (@actual_ids)
-		{
-			if (exists($expected_set{$_}))
-			{
-				$correct++;
-			}
-		}
-
-		$total += $limit;
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v minivec($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, rand());
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-}
-
-# Check each index type
-my @operators = ("<->", "<#>", "<=>");
-my @opclasses = ("minivec_l2_ops", "minivec_ip_ops", "minivec_cosine_ops");
-
-for my $i (0 .. $#operators)
-{
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	# Get exact results
-	@expected = ();
-	foreach (@queries)
-	{
-		my $res = $node->safe_psql("postgres", qq(
-			WITH top AS (
-				SELECT v $operator '$_' AS distance FROM tst ORDER BY distance LIMIT $limit
-			)
-			SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
-		));
-		push(@expected, $res);
-	}
-
-	# Build index serially
-	$node->safe_psql("postgres", qq(
-		SET max_parallel_maintenance_workers = 0;
-		CREATE INDEX idx ON tst USING ivfflat (v $opclass);
-	));
-
-	# Test approximate results
-	if ($operator ne "<#>")
-	{
-		# TODO Fix test (uniform random vectors all have similar inner product)
-		test_recall(1, 0.33, $operator);
-		test_recall(10, 0.93, $operator);
-	}
-
-	# Test probes equals lists
-	if ($operator eq "<=>")
-	{
-		test_recall(100, 0.98, $operator);
-	}
-	else
-	{
-		test_recall(100, 1.00, $operator);
-	}
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-
-	# Build index in parallel
-	my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
-		SET client_min_messages = DEBUG;
-		SET min_parallel_table_scan_size = 1;
-		CREATE INDEX idx ON tst USING ivfflat (v $opclass);
-	));
-	is($ret, 0, $stderr);
-	like($stderr, qr/using \d+ parallel workers/);
-
-	# Test approximate results
-	if ($operator ne "<#>")
-	{
-		# TODO Fix test (uniform random vectors all have similar inner product)
-		test_recall(1, 0.33, $operator);
-		test_recall(10, 0.93, $operator);
-	}
-
-	# Test probes equals lists
-	if ($operator eq "<=>")
-	{
-		test_recall(100, 0.98, $operator);
-	}
-	else
-	{
-		test_recall(100, 1.00, $operator);
-	}
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-}
-
-done_testing();