Removed unused functions

Co-authored-by: Heikki Linnakangas <heikki.linnakangas@iki.fi>

.github/workflows/build.yml

@@ -20,6 +20,8 @@ jobs:
             os: ubuntu-20.04
           - postgres: 12
             os: ubuntu-20.04
+          - postgres: 11
+            os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1

CHANGELOG.md

@@ -1,6 +1,9 @@
 ## 0.5.2 (unreleased)
 
+- Improved performance of HNSW
 - Added support for on-disk parallel index builds for HNSW
+- Reduced WAL generation for HNSW index builds
+- Fixed `invalid memory alloc request size` error with HNSW index build
 
 ## 0.5.1 (2023-10-10)
 

Makefile

@@ -3,8 +3,8 @@ EXTVERSION = 0.5.1
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
-OBJS = src/half.o src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/vector.o
-HEADERS = src/half.h src/vector.h
+OBJS = src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/vector.o
+HEADERS = src/vector.h
 
 TESTS = $(wildcard test/sql/*.sql)
 REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))

Makefile.win

@@ -1,8 +1,8 @@
 EXTENSION = vector
 EXTVERSION = 0.5.1
 
-OBJS = src\half.obj src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
-HEADERS = src\half.h src\vector.h
+OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
+HEADERS = src\vector.h
 
 REGRESS = btree cast copy functions input ivfflat_cosine ivfflat_ip ivfflat_l2 ivfflat_options ivfflat_unlogged
 REGRESS_OPTS = --inputdir=test --load-extension=$(EXTENSION)

sql/vector--0.5.1--0.6.0.sql

@@ -1,82 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "ALTER EXTENSION vector UPDATE TO '0.6.0'" to load this file. \quit
-
-CREATE TYPE half;
-
-CREATE FUNCTION half_in(cstring, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_out(half) RETURNS cstring
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_recv(internal, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_send(half) RETURNS bytea
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE TYPE half (
-	INPUT     = half_in,
-	OUTPUT    = half_out,
-	RECEIVE   = half_recv,
-	SEND      = half_send,
-	INTERNALLENGTH = 2,
-	PASSEDBYVALUE,
-	ALIGNMENT = int2
-);
-
-CREATE FUNCTION l2_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION cosine_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l1_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l1_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_l2_squared_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_negative_inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION float4_to_half(real, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION integer_to_half(integer, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION numeric_to_half(numeric, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE CAST (real AS half)
-	WITH FUNCTION float4_to_half(real, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (integer AS half)
-	WITH FUNCTION integer_to_half(integer, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (numeric AS half)
-	WITH FUNCTION numeric_to_half(numeric, integer, boolean) AS IMPLICIT;
-
-CREATE OPERATOR <-> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = l2_distance,
-	COMMUTATOR = '<->'
-);
-
-CREATE OPERATOR <#> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = half_negative_inner_product,
-	COMMUTATOR = '<#>'
-);
-
-CREATE OPERATOR <=> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance,
-	COMMUTATOR = '<=>'
-);
-
-CREATE OPERATOR CLASS half_l2_ops
-	FOR TYPE half[] USING hnsw AS
-	OPERATOR 1 <-> (half[], half[]) FOR ORDER BY float_ops,
-	FUNCTION 1 half_l2_squared_distance(half[], half[]);

sql/vector.sql

@@ -290,97 +290,3 @@ CREATE OPERATOR CLASS vector_cosine_ops
 	OPERATOR 1 <=> (vector, vector) FOR ORDER BY float_ops,
 	FUNCTION 1 vector_negative_inner_product(vector, vector),
 	FUNCTION 2 vector_norm(vector);
-
--- half type
-
-CREATE TYPE half;
-
-CREATE FUNCTION half_in(cstring, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_out(half) RETURNS cstring
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_recv(internal, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_send(half) RETURNS bytea
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE TYPE half (
-	INPUT     = half_in,
-	OUTPUT    = half_out,
-	RECEIVE   = half_recv,
-	SEND      = half_send,
-	INTERNALLENGTH = 2,
-	PASSEDBYVALUE,
-	ALIGNMENT = int2
-);
-
--- half functions
-
-CREATE FUNCTION l2_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION cosine_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l1_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l1_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- half private functions
-
-CREATE FUNCTION half_l2_squared_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_negative_inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- half cast functions
-
-CREATE FUNCTION float4_to_half(real, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION integer_to_half(integer, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION numeric_to_half(numeric, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- half casts
-
-CREATE CAST (real AS half)
-	WITH FUNCTION float4_to_half(real, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (integer AS half)
-	WITH FUNCTION integer_to_half(integer, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (numeric AS half)
-	WITH FUNCTION numeric_to_half(numeric, integer, boolean) AS IMPLICIT;
-
--- half operators
-
-CREATE OPERATOR <-> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = l2_distance,
-	COMMUTATOR = '<->'
-);
-
-CREATE OPERATOR <#> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = half_negative_inner_product,
-	COMMUTATOR = '<#>'
-);
-
-CREATE OPERATOR <=> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance,
-	COMMUTATOR = '<=>'
-);
-
--- half opclasses
-
-CREATE OPERATOR CLASS half_l2_ops
-	FOR TYPE half[] USING hnsw AS
-	OPERATOR 1 <-> (half[], half[]) FOR ORDER BY float_ops,
-	FUNCTION 1 half_l2_squared_distance(half[], half[]);

src/half.c

@@ -1,599 +0,0 @@
-#include "postgres.h"
-
-#include <math.h>
-
-#include "common/shortest_dec.h"
-#include "fmgr.h"
-#include "half.h"
-#include "lib/stringinfo.h"
-#include "libpq/pqformat.h"
-#include "utils/array.h"
-#include "utils/builtins.h"
-#include "utils/float.h"
-#include "utils/numeric.h"
-
-#if PG_VERSION_NUM < 120003
-static pg_noinline void
-float_overflow_error(void)
-{
-	ereport(ERROR,
-			(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-			 errmsg("value out of range: overflow")));
-}
-
-static pg_noinline void
-float_underflow_error(void)
-{
-	ereport(ERROR,
-			(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-			 errmsg("value out of range: underflow")));
-}
-#endif
-
-/*
- * Check if array is a vector
- */
-static void
-CheckArrayIsVector(ArrayType *array)
-{
-	if (ARR_NDIM(array) > 1)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("array must be 1-D")));
-
-	if (ARR_HASNULL(array) && array_contains_nulls(array))
-		ereport(ERROR,
-				(errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED),
-				 errmsg("array must not contain nulls")));
-}
-
-/*
- * Check if dimensions are the same
- */
-static int
-CheckDims(ArrayType *a, ArrayType *b)
-{
-	int			dima;
-	int			dimb;
-
-	CheckArrayIsVector(a);
-	CheckArrayIsVector(b);
-
-	dima = ARR_DIMS(a)[0];
-	dimb = ARR_DIMS(b)[0];
-
-	if (dima != dimb)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("different dimensions %d and %d", dima, dimb)));
-
-	return dima;
-}
-
-/*
- * Return the datum representation for a half
- */
-static inline Datum
-HalfGetDatum(half X)
-{
-	union
-	{
-		half		value;
-		int16		retval;
-	}			myunion;
-
-	myunion.value = X;
-	return Int16GetDatum(myunion.retval);
-}
-
-/*
- * Return the half value of a datum
- */
-static inline half
-DatumGetHalf(Datum X)
-{
-	union
-	{
-		int16		value;
-		half		retval;
-	}			myunion;
-
-	myunion.value = DatumGetInt16(X);
-	return myunion.retval;
-}
-
-/*
- * Append a half to a StringInfo buffer
- */
-static half
-pq_getmsghalf(StringInfo msg)
-{
-	union
-	{
-		half		h;
-		uint16		i;
-	}			swap;
-
-	/* TODO Likely use float4 for clients */
-	swap.i = pq_getmsgint(msg, 2);
-	return swap.h;
-}
-
-/*
- * Get a half from a message buffer
- */
-static void
-pq_sendhalf(StringInfo buf, half h)
-{
-	union
-	{
-		half		h;
-		uint16		i;
-	}			swap;
-
-	/* TODO Likely use float4 for clients */
-	swap.h = h;
-	pq_sendint16(buf, swap.i);
-}
-
-/*
- * Convert a half to a float4
- */
-static float
-HalfToFloat4(half num)
-{
-#ifdef FLT16_SUPPORT
-	return (float) num;
-#else
-	/* TODO Improve performance */
-	/* TODO Check endianness */
-	uint16		bin = *((uint16 *) &num);
-	uint32		exponent = (bin & 0x7C00) >> 10;
-	uint32		mantissa = bin & 0x03FF;
-
-	/* Sign */
-	uint32		result = (bin & 0x8000) << 16;
-
-	if (exponent == 31)
-	{
-		if (mantissa == 0)
-		{
-			/* Infinite */
-			result |= 0x7F800000;
-		}
-		else
-		{
-			/* NaN */
-			result |= 0x7FC00000;
-			result |= mantissa << 13;
-		}
-	}
-	else if (exponent == 0)
-	{
-		/* Subnormal */
-		if (mantissa != 0)
-		{
-			exponent = -14;
-
-			for (int i = 0; i < 10; i++)
-			{
-				mantissa <<= 1;
-				exponent -= 1;
-
-				if ((mantissa >> 10) % 2 == 1)
-				{
-					mantissa &= 0x03ff;
-					break;
-				}
-			}
-
-			result |= (exponent + 127) << 23;
-			result |= mantissa << 13;
-		}
-	}
-	else
-	{
-		/* Normal */
-		result |= (exponent - 15 + 127) << 23;
-		result |= mantissa << 13;
-	}
-
-	return *((float *) &result);
-#endif
-}
-
-/*
- * Convert a float4 to a half
- */
-static half
-Float4ToHalfUnchecked(float num)
-{
-#ifdef FLT16_SUPPORT
-	return (_Float16) num;
-#else
-	/* TODO Improve performance */
-	/* TODO Check endianness */
-	uint32		bin = *((uint32 *) &num);
-	int			exponent = (bin & 0x7F800000) >> 23;
-	int			mantissa = bin & 0x007FFFFF;
-
-	/* Sign */
-	uint16		result = (bin & 0x80000000) >> 16;
-
-	if (isinf(num))
-	{
-		/* Infinite */
-		result |= 0x7C00;
-	}
-	else if (isnan(num))
-	{
-		/* NaN */
-		result |= 0x7E00;
-		result |= mantissa >> 13;
-	}
-	else if (exponent > 98)
-	{
-		int			m;
-		int			gr;
-		int			s;
-
-		exponent -= 127;
-		s = mantissa & 0x00000FFF;
-
-		/* Subnormal */
-		if (exponent < -14)
-		{
-			int			diff = -exponent - 14;
-
-			mantissa >>= diff;
-			mantissa += 1 << (23 - diff);
-			s |= mantissa & 0x00000FFF;
-		}
-
-		m = mantissa >> 13;
-
-		/* Round */
-		gr = (mantissa >> 12) % 4;
-		if (gr == 3 || (gr == 1 && s != 0))
-			m += 1;
-
-		if (m == 1024)
-		{
-			m = 0;
-			exponent += 1;
-		}
-
-		if (exponent > 15)
-		{
-			/* Infinite */
-			result |= 0x7C00;
-		}
-		else
-		{
-			if (exponent >= -14)
-				result |= (exponent + 15) << 10;
-
-			result |= m;
-		}
-	}
-
-	return *((half *) & result);
-#endif
-}
-
-/*
- * Convert a float4 to a half
- */
-static half
-Float4ToHalf(float num)
-{
-	half		result = Float4ToHalfUnchecked(num);
-
-	/* TODO Perform checks without HalfToFloat4 */
-	if (unlikely(isinf(HalfToFloat4(result))) && !isinf(num))
-		float_overflow_error();
-	if (unlikely(HalfToFloat4(result) == 0.0f) && num != 0.0)
-		float_underflow_error();
-
-	return result;
-}
-
-/*
- * Convert textual representation to internal representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_in);
-Datum
-half_in(PG_FUNCTION_ARGS)
-{
-	char	   *num = PG_GETARG_CSTRING(0);
-	char	   *orig_num;
-	float		val;
-	char	   *endptr;
-
-	orig_num = num;
-
-	/* Skip leading whitespace */
-	while (*num != '\0' && isspace((unsigned char) *num))
-		num++;
-
-	/*
-	 * Check for an empty-string input to begin with, to avoid the vagaries of
-	 * strtof() on different platforms.
-	 */
-	if (*num == '\0')
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("invalid input syntax for type %s: \"%s\"",
-						"half", orig_num)));
-
-	val = strtof(num, &endptr);
-
-	if (val < -HALF_MAX || val > HALF_MAX)
-		ereport(ERROR,
-				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-				 errmsg("\"%s\" is out of range for type %s",
-						orig_num, "half")));
-
-	/* Skip trailing whitespace */
-	while (*endptr != '\0' && isspace((unsigned char) *endptr))
-		endptr++;
-
-	/* If there is any junk left at the end of the string, bail out */
-	if (*endptr != '\0')
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("invalid input syntax for type %s: \"%s\"",
-						"half", orig_num)));
-
-	PG_RETURN_HALF(Float4ToHalf(val));
-}
-
-/*
- * Convert internal representation to textual representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_out);
-Datum
-half_out(PG_FUNCTION_ARGS)
-{
-	float		num = HalfToFloat4(PG_GETARG_HALF(0));
-	char	   *ascii = (char *) palloc(32);
-	int			ndig = FLT_DIG + extra_float_digits;
-
-	if (extra_float_digits > 0)
-	{
-		float_to_shortest_decimal_buf(num, ascii);
-		PG_RETURN_CSTRING(ascii);
-	}
-
-	(void) pg_strfromd(ascii, 32, ndig, num);
-	PG_RETURN_CSTRING(ascii);
-}
-
-/*
- * Convert external binary representation to internal representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_recv);
-Datum
-half_recv(PG_FUNCTION_ARGS)
-{
-	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
-
-	PG_RETURN_HALF(pq_getmsghalf(buf));
-}
-
-/*
- * Convert internal representation to the external binary representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_send);
-Datum
-half_send(PG_FUNCTION_ARGS)
-{
-	half		arg1 = PG_GETARG_HALF(0);
-	StringInfoData buf;
-
-	pq_begintypsend(&buf);
-	pq_sendhalf(&buf, arg1);
-	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
-}
-
-/*
- * Convert integer to half
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(integer_to_half);
-Datum
-integer_to_half(PG_FUNCTION_ARGS)
-{
-	int32		i = PG_GETARG_INT32(0);
-
-	/* TODO Figure out correct error */
-	float		f = (float) i;
-	half		h = Float4ToHalf(f);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Convert numeric to half
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(numeric_to_half);
-Datum
-numeric_to_half(PG_FUNCTION_ARGS)
-{
-	Numeric		num = PG_GETARG_NUMERIC(0);
-	float		f = DatumGetFloat4(DirectFunctionCall1(numeric_float4, NumericGetDatum(num)));
-	half		h = Float4ToHalf(f);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Convert float4 to half
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(float4_to_half);
-Datum
-float4_to_half(PG_FUNCTION_ARGS)
-{
-	float		f = PG_GETARG_FLOAT4(0);
-	half		h = Float4ToHalf(f);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Get the L2 distance between half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_l2_distance);
-Datum
-half_l2_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		float		diff = HalfToFloat4(ax[i]) - HalfToFloat4(bx[i]);
-
-		distance += diff * diff;
-	}
-
-	PG_RETURN_FLOAT8(sqrt((double) distance));
-}
-
-/*
- * Get the L2 squared distance between half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_l2_squared_distance);
-Datum
-half_l2_squared_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		float		diff = HalfToFloat4(ax[i]) - HalfToFloat4(bx[i]);
-
-		distance += diff * diff;
-	}
-
-	PG_RETURN_FLOAT8((double) distance);
-}
-
-/*
- * Get the inner product of two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_inner_product);
-Datum
-half_inner_product(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += HalfToFloat4(ax[i]) * HalfToFloat4(bx[i]);
-
-	PG_RETURN_FLOAT8((double) distance);
-}
-
-/*
- * Get the negative inner product of two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_negative_inner_product);
-Datum
-half_negative_inner_product(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += HalfToFloat4(ax[i]) * HalfToFloat4(bx[i]);
-
-	PG_RETURN_FLOAT8((double) distance * -1);
-}
-
-/*
- * Get the cosine distance between two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_cosine_distance);
-Datum
-half_cosine_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	float		norma = 0.0;
-	float		normb = 0.0;
-	double		similarity;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		float		axi = HalfToFloat4(ax[i]);
-		float		bxi = HalfToFloat4(bx[i]);
-
-		distance += axi * bxi;
-		norma += axi * axi;
-		normb += bxi * bxi;
-	}
-
-	/* Use sqrt(a * b) over sqrt(a) * sqrt(b) */
-	similarity = (double) distance / sqrt((double) norma * (double) normb);
-
-#ifdef _MSC_VER
-	/* /fp:fast may not propagate NaN */
-	if (isnan(similarity))
-		PG_RETURN_FLOAT8(NAN);
-#endif
-
-	/* Keep in range */
-	if (similarity > 1)
-		similarity = 1;
-	else if (similarity < -1)
-		similarity = -1;
-
-	PG_RETURN_FLOAT8(1 - similarity);
-}
-
-/*
- * Get the L1 distance between two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_l1_distance);
-Datum
-half_l1_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += fabsf(HalfToFloat4(ax[i]) - HalfToFloat4(bx[i]));
-
-	PG_RETURN_FLOAT8((double) distance);
-}

src/half.h

@@ -1,28 +0,0 @@
-#ifndef HALF_H
-#define HALF_H
-
-#define __STDC_WANT_IEC_60559_TYPES_EXT__
-
-#include <float.h>
-
-/* _Float16 and __fp16 are not supported on x86_64 with GCC 11 */
-#if defined(__is_identifier)
-#if __is_identifier(_Float16)
-#define FLT16_SUPPORT
-#endif
-#elif defined(FLT16_MAX)
-#define FLT16_SUPPORT
-#endif
-
-#ifdef FLT16_SUPPORT
-#define half _Float16
-#define HALF_MAX FLT16_MAX
-#else
-#define half uint16
-#define HALF_MAX 65504
-#endif
-
-#define PG_GETARG_HALF(n)  DatumGetHalf(PG_GETARG_DATUM(n))
-#define PG_RETURN_HALF(x)  return HalfGetDatum(x)
-
-#endif

src/hnsw.h

@@ -104,6 +104,7 @@ typedef struct HnswElementData
 	List	   *heaptids;
 	uint8		level;
 	uint8		deleted;
+	uint32		hash;
 	HnswNeighborArray *neighbors;
 	BlockNumber blkno;
 	OffsetNumber offno;
@@ -303,7 +304,7 @@ typedef struct HnswVacuumState
 	Oid			collation;
 
 	/* Variables */
-	HTAB	   *deleted;
+	struct tidhash_hash *deleted;
 	BufferAccessStrategy bas;
 	HnswNeighborTuple ntup;
 	HnswElementData highestPoint;
@@ -317,10 +318,8 @@ int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
 FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
 bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
-void		HnswCommitBuffer(Buffer buf, GenericXLogState *state);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
-void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 void		HnswInit(void);
 List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
@@ -331,12 +330,12 @@ HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
 void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
 HnswElement HnswFindDuplicate(HnswElement e);
 HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
+void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 void		HnswInitNeighbors(HnswElement element, int m);
-bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel);
-void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
+bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building);
+void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
 void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
 void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
@@ -360,4 +359,31 @@ void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
+/* Hash tables */
+typedef struct TidHashEntry
+{
+	ItemPointerData tid;
+	char		status;
+}			TidHashEntry;
+
+#define SH_PREFIX tidhash
+#define SH_ELEMENT_TYPE TidHashEntry
+#define SH_KEY_TYPE ItemPointerData
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
+typedef struct PointerHashEntry
+{
+	uintptr_t	ptr;
+	char		status;
+}			PointerHashEntry;
+
+#define SH_PREFIX pointerhash
+#define SH_ELEMENT_TYPE PointerHashEntry
+#define SH_KEY_TYPE uintptr_t
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
 #endif

src/hnswbuild.c

@@ -56,6 +56,8 @@
 #define PARALLEL_KEY_HNSW_SHARED		UINT64CONST(0xA000000000000001)
 #define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000002)
 
+#define LIST_MAX_LENGTH ((1 << 26) - 1)
+
 /*
  * Create the metapage
  */
@@ -66,11 +68,11 @@ CreateMetaPage(HnswBuildState * buildstate)
 	ForkNumber	forkNum = buildstate->forkNum;
 	Buffer		buf;
 	Page		page;
-	GenericXLogState *state;
 	HnswMetaPage metap;
 
 	buf = HnswNewBuffer(index, forkNum);
-	HnswInitRegisterPage(index, &buf, &page, &state);
+	page = BufferGetPage(buf);
+	HnswInitPage(buf, page);
 
 	/* Set metapage data */
 	metap = HnswPageGetMeta(page);
@@ -86,14 +88,14 @@ CreateMetaPage(HnswBuildState * buildstate)
 	((PageHeader) page)->pd_lower =
 		((char *) metap + sizeof(HnswMetaPageData)) - (char *) page;
 
-	HnswCommitBuffer(buf, state);
+	UnlockReleaseBuffer(buf);
 }
 
 /*
  * Add a new page
  */
 static void
-HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum)
+HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
 {
 	/* Add a new page */
 	Buffer		newbuf = HnswNewBuffer(index, forkNum);
@@ -102,7 +104,6 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 	HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
 
 	/* Commit */
-	GenericXLogFinish(*state);
 	UnlockReleaseBuffer(*buf);
 
 	/* Can take a while, so ensure we can interrupt */
@@ -113,8 +114,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 
 	/* Prepare new page */
 	*buf = newbuf;
-	*state = GenericXLogStart(index);
-	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
+	*page = BufferGetPage(*buf);
 	HnswInitPage(*buf, *page);
 }
 
@@ -133,7 +133,6 @@ CreateElementPages(HnswBuildState * buildstate)
 	BlockNumber insertPage;
 	Buffer		buf;
 	Page		page;
-	GenericXLogState *state;
 	ListCell   *lc;
 
 	/* Calculate sizes */
@@ -146,8 +145,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 	/* Prepare first page */
 	buf = HnswNewBuffer(index, forkNum);
-	state = GenericXLogStart(index);
-	page = GenericXLogRegisterBuffer(state, buf, GENERIC_XLOG_FULL_IMAGE);
+	page = BufferGetPage(buf);
 	HnswInitPage(buf, page);
 
 	foreach(lc, buildstate->elements)
@@ -173,7 +171,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
-			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, forkNum);
 
 		/* Calculate offsets */
 		element->blkno = BufferGetBlockNumber(buf);
@@ -197,7 +195,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 		/* Add new page if needed */
 		if (PageGetFreeSpace(page) < ntupSize)
-			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, forkNum);
 
 		/* Add placeholder for neighbors */
 		if (PageAddItem(page, (Item) ntup, ntupSize, InvalidOffsetNumber, false, false) != element->neighborOffno)
@@ -207,10 +205,9 @@ CreateElementPages(HnswBuildState * buildstate)
 	insertPage = BufferGetBlockNumber(buf);
 
 	/* Commit */
-	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
-	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum);
+	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum, true);
 
 	pfree(etup);
 	pfree(ntup);
@@ -236,7 +233,6 @@ CreateNeighborPages(HnswBuildState * buildstate)
 		HnswElement e = lfirst(lc);
 		Buffer		buf;
 		Page		page;
-		GenericXLogState *state;
 		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 
 		/* Can take a while, so ensure we can interrupt */
@@ -245,8 +241,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
 
 		buf = ReadBufferExtended(index, forkNum, e->neighborPage, RBM_NORMAL, NULL);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		state = GenericXLogStart(index);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
+		page = BufferGetPage(buf);
 
 		HnswSetNeighborTuple(ntup, e, m);
 
@@ -254,7 +249,6 @@ CreateNeighborPages(HnswBuildState * buildstate)
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 		/* Commit */
-		GenericXLogFinish(state);
 		UnlockReleaseBuffer(buf);
 	}
 
@@ -381,21 +375,22 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	if (buildstate->memoryLeft <= 0)
+	if (buildstate->flushed || buildstate->memoryLeft <= 0 || list_length(buildstate->elements) == LIST_MAX_LENGTH)
 	{
 		if (!buildstate->flushed)
 		{
-			ereport(NOTICE,
-					(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
-					 errdetail("Building will take significantly more time."),
-					 errhint("Increase maintenance_work_mem to speed up builds.")));
+			if (buildstate->memoryLeft <= 0)
+				ereport(NOTICE,
+						(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
+						 errdetail("Building will take significantly more time."),
+						 errhint("Increase maintenance_work_mem to speed up builds.")));
 
 			FlushPages(buildstate);
 		}
 
 		oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
-		if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap))
+		if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap, true))
 		{
 			if (buildstate->hnswshared)
 			{
@@ -462,8 +457,8 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
 
 	/* Require column to have dimensions to be indexed */
-	// if (buildstate->dimensions < 0)
-	// 	elog(ERROR, "column does not have dimensions");
+	if (buildstate->dimensions < 0)
+		elog(ERROR, "column does not have dimensions");
 
 	if (buildstate->dimensions > HNSW_MAX_DIM)
 		elog(ERROR, "column cannot have more than %d dimensions for hnsw index", HNSW_MAX_DIM);
@@ -877,6 +872,22 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 		HnswEndParallel(buildstate->hnswleader);
 }
 
+#if PG_VERSION_NUM < 110008
+void
+log_newpage_range(Relation rel, ForkNumber forkNum, BlockNumber startblk, BlockNumber endblk, bool page_std)
+{
+	for (BlockNumber blkno = startblk; blkno < endblk; blkno++)
+	{
+		Buffer		buf = ReadBufferExtended(rel, forkNum, blkno, RBM_NORMAL, NULL);
+
+		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
+		MarkBufferDirty(buf);
+		log_newpage_buffer(buf, page_std);
+		UnlockReleaseBuffer(buf);
+	}
+}
+#endif
+
 /*
  * Build the index
  */
@@ -892,6 +903,9 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
 	if (!buildstate->flushed)
 		FlushPages(buildstate);
 
+	if (RelationNeedsWAL(index))
+		log_newpage_range(index, forkNum, 0, RelationGetNumberOfBlocks(index), true);
+
 	FreeBuildState(buildstate);
 }
 

src/hnswinsert.c

@@ -92,7 +92,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
  * Add a new page
  */
 static void
-HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page)
+HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page, bool building)
 {
 	/* Add a new page */
 	LockRelationForExtension(index, ExclusiveLock);
@@ -100,7 +100,11 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
 	UnlockRelationForExtension(index, ExclusiveLock);
 
 	/* Init new page */
-	*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
+	if (building)
+		*npage = BufferGetPage(*nbuf);
+	else
+		*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
+
 	HnswInitPage(*nbuf, *npage);
 
 	/* Update previous buffer */
@@ -111,7 +115,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
  * Add to element and neighbor pages
  */
 static void
-WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage)
+WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -151,8 +155,16 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		buf = ReadBuffer(index, currentPage);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
-		state = GenericXLogStart(index);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
+		if (building)
+		{
+			state = NULL;
+			page = BufferGetPage(buf);
+		}
+		else
+		{
+			state = GenericXLogStart(index);
+			page = GenericXLogRegisterBuffer(state, buf, 0);
+		}
 
 		/* Keep track of first page where element at level 0 can fit */
 		if (!BlockNumberIsValid(newInsertPage) && PageGetFreeSpace(page) >= minCombinedSize)
@@ -172,7 +184,12 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (HnswFreeOffset(index, buf, page, e, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
 		{
 			if (nbuf != buf)
-				npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			{
+				if (building)
+					npage = BufferGetPage(nbuf);
+				else
+					npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			}
 
 			break;
 		}
@@ -181,7 +198,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		/* Skip if both tuples can fit on the same page */
 		if (combinedSize > maxSize && PageGetFreeSpace(page) >= etupSize && !BlockNumberIsValid(HnswPageGetOpaque(page)->nextblkno))
 		{
-			HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+			HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			break;
 		}
 
@@ -190,7 +207,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (BlockNumberIsValid(currentPage))
 		{
 			/* Move to next page */
-			GenericXLogAbort(state);
+			if (!building)
+				GenericXLogAbort(state);
 			UnlockReleaseBuffer(buf);
 		}
 		else
@@ -198,22 +216,31 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 			Buffer		newbuf;
 			Page		newpage;
 
-			HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
+			HnswInsertAppendPage(index, &newbuf, &newpage, state, page, building);
 
 			/* Commit */
-			GenericXLogFinish(state);
+			if (!building)
+				GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
 			UnlockReleaseBuffer(buf);
 
 			/* Prepare new buffer */
-			state = GenericXLogStart(index);
 			buf = newbuf;
-			page = GenericXLogRegisterBuffer(state, buf, 0);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Create new page for neighbors if needed */
 			if (PageGetFreeSpace(page) < combinedSize)
-				HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+				HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			else
 			{
 				nbuf = buf;
@@ -267,7 +294,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	}
 
 	/* Commit */
-	GenericXLogFinish(state);
+	if (!building)
+		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 	if (nbuf != buf)
 		UnlockReleaseBuffer(nbuf);
@@ -301,7 +329,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
  * Update neighbors
  */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
+HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -342,8 +370,16 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			/* Register page */
 			buf = ReadBuffer(index, hc->element->neighborPage);
 			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-			state = GenericXLogStart(index);
-			page = GenericXLogRegisterBuffer(state, buf, 0);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Get tuple */
 			itemid = PageGetItemId(page, offno);
@@ -385,9 +421,10 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 					elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 				/* Commit */
-				GenericXLogFinish(state);
+				if (!building)
+					GenericXLogFinish(state);
 			}
-			else
+			else if (!building)
 				GenericXLogAbort(state);
 
 			UnlockReleaseBuffer(buf);
@@ -399,7 +436,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
  * Add a heap TID to an existing element
  */
 static bool
-HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
+HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -412,8 +449,16 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* Read page */
 	buf = ReadBuffer(index, dup->blkno);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	state = GenericXLogStart(index);
-	page = GenericXLogRegisterBuffer(state, buf, 0);
+	if (building)
+	{
+		state = NULL;
+		page = BufferGetPage(buf);
+	}
+	else
+	{
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
+	}
 
 	/* Find space */
 	itemid = PageGetItemId(page, dup->offno);
@@ -428,7 +473,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* Either being deleted or we lost our chance to another backend */
 	if (i == 0 || i == HNSW_HEAPTIDS)
 	{
-		GenericXLogAbort(state);
+		if (!building)
+			GenericXLogAbort(state);
 		UnlockReleaseBuffer(buf);
 		return false;
 	}
@@ -441,7 +487,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 	/* Commit */
-	GenericXLogFinish(state);
+	if (!building)
+		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
 	return true;
@@ -451,37 +498,37 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
  * Write changes to disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
+WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Try to add to existing page */
 	if (dup != NULL)
 	{
-		if (HnswAddDuplicate(index, element, dup))
+		if (HnswAddDuplicate(index, element, dup, building))
 			return;
 	}
 
 	/* Write element and neighbor tuples */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage);
+	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
-		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
 
 	/* Update metapage if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
-		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, building);
 }
 
 /*
  * Insert a tuple into the index
  */
 bool
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
 {
 	Datum		value;
 	FmgrInfo   *normprocinfo;
@@ -540,7 +587,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	dup = HnswFindDuplicate(element);
 
 	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
+	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -574,7 +621,7 @@ hnswinsert(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid,
 	oldCtx = MemoryContextSwitchTo(insertCtx);
 
 	/* Insert tuple */
-	HnswInsertTuple(index, values, isnull, heap_tid, heap);
+	HnswInsertTuple(index, values, isnull, heap_tid, heap, false);
 
 	/* Delete memory context */
 	MemoryContextSwitchTo(oldCtx);

src/hnswutils.c

@@ -7,6 +7,89 @@
 #include "utils/datum.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 130000
+#include "common/hashfn.h"
+#else
+#include "utils/hashutils.h"
+#endif
+
+#if PG_VERSION_NUM < 170000
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+#endif
+
+/* TID hash table */
+static uint32
+hash_tid(ItemPointerData tid)
+{
+	union
+	{
+		uint64		i;
+		ItemPointerData tid;
+	}			x;
+
+	/* Initialize unused bytes */
+	x.i = 0;
+	x.tid = tid;
+
+	return murmurhash64(x.i);
+}
+
+#define SH_PREFIX		tidhash
+#define SH_ELEMENT_TYPE	TidHashEntry
+#define SH_KEY_TYPE		ItemPointerData
+#define	SH_KEY			tid
+#define SH_HASH_KEY(tb, key)	hash_tid(key)
+#define SH_EQUAL(tb, a, b)		ItemPointerEquals(&a, &b)
+#define	SH_SCOPE		extern
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+/* Needed to include simplehash.h twice */
+#if PG_VERSION_NUM < 120000
+#undef SH_EQUAL
+#define sh_log2 pointerhash_sh_log2
+#define sh_pow2 pointerhash_sh_pow2
+#endif
+
+/* Pointer hash table */
+static uint32
+hash_pointer(uintptr_t ptr)
+{
+#if SIZEOF_VOID_P == 8
+	return murmurhash64((uint64) ptr);
+#else
+	return murmurhash32((uint32) ptr);
+#endif
+}
+
+#define SH_PREFIX		pointerhash
+#define SH_ELEMENT_TYPE	PointerHashEntry
+#define SH_KEY_TYPE		uintptr_t
+#define	SH_KEY			ptr
+#define SH_HASH_KEY(tb, key)	hash_pointer(key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define	SH_SCOPE		extern
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+typedef union
+{
+	pointerhash_hash *pointers;
+	tidhash_hash *tids;
+}			visited_hash;
+
 /*
  * Get the max number of connections in an upper layer for each element in the index
  */
@@ -101,27 +184,6 @@ HnswInitPage(Buffer buf, Page page)
 	HnswPageGetOpaque(page)->page_id = HNSW_PAGE_ID;
 }
 
-/*
- * Init and register page
- */
-void
-HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state)
-{
-	*state = GenericXLogStart(index);
-	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
-	HnswInitPage(*buf, *page);
-}
-
-/*
- * Commit buffer
- */
-void
-HnswCommitBuffer(Buffer buf, GenericXLogState *state)
-{
-	GenericXLogFinish(state);
-	UnlockReleaseBuffer(buf);
-}
-
 /*
  * Allocate neighbors
  */
@@ -296,7 +358,7 @@ HnswUpdateMetaPageInfo(Page page, int updateEntry, HnswElement entryPoint, Block
  * Update the metapage
  */
 void
-HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum)
+HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -304,12 +366,22 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 
 	buf = ReadBufferExtended(index, forkNum, HNSW_METAPAGE_BLKNO, RBM_NORMAL, NULL);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	state = GenericXLogStart(index);
-	page = GenericXLogRegisterBuffer(state, buf, 0);
+	if (building)
+	{
+		state = NULL;
+		page = BufferGetPage(buf);
+	}
+	else
+	{
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
+	}
 
 	HnswUpdateMetaPageInfo(page, updateEntry, entryPoint, insertPage);
 
-	HnswCommitBuffer(buf, state);
+	if (!building)
+		GenericXLogFinish(state);
+	UnlockReleaseBuffer(buf);
 }
 
 /*
@@ -553,16 +625,22 @@ CreatePairingHeapNode(HnswCandidate * c)
  * Add to visited
  */
 static inline void
-AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(visited_hash v, HnswCandidate * hc, Relation index, bool *found)
 {
 	if (index == NULL)
-		hash_search(v, &hc->element, HASH_ENTER, found);
+	{
+#if PG_VERSION_NUM >= 130000
+		pointerhash_insert_hash(v.pointers, (uintptr_t) hc->element, hc->element->hash, found);
+#else
+		pointerhash_insert(v.pointers, (uintptr_t) hc->element, found);
+#endif
+	}
 	else
 	{
 		ItemPointerData indextid;
 
 		ItemPointerSet(&indextid, hc->element->blkno, hc->element->offno);
-		hash_search(v, &indextid, HASH_ENTER, found);
+		tidhash_insert(v.tids, indextid, found);
 	}
 }
 
@@ -578,30 +656,21 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
 	pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
 	int			wlen = 0;
-	HASHCTL		hash_ctl;
-	HTAB	   *v;
+	visited_hash v;
 
 	/* Create hash table */
 	if (index == NULL)
-	{
-		hash_ctl.keysize = sizeof(HnswElement *);
-		hash_ctl.entrysize = sizeof(HnswElement *);
-	}
+		v.pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
 	else
-	{
-		hash_ctl.keysize = sizeof(ItemPointerData);
-		hash_ctl.entrysize = sizeof(ItemPointerData);
-	}
-
-	hash_ctl.hcxt = CurrentMemoryContext;
-	v = hash_create("hnsw visited", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+		v.tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
 
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
+		bool		found;
 
-		AddToVisited(v, hc, index, NULL);
+		AddToVisited(v, hc, index, &found);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -1021,6 +1090,12 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 	Datum		q = element->value;
 	HnswElement skipElement = existing ? element : NULL;
 
+#if PG_VERSION_NUM >= 130000
+	/* Precompute hash */
+	if (index == NULL)
+		element->hash = hash_pointer((uintptr_t) element);
+#endif
+
 	/* No neighbors if no entry point */
 	if (entryPoint == NULL)
 		return;

src/hnswvacuum.c

@@ -12,12 +12,9 @@
  * Check if deleted list contains an index TID
  */
 static bool
-DeletedContains(HTAB *deleted, ItemPointer indextid)
+DeletedContains(tidhash_hash * deleted, ItemPointer indextid)
 {
-	bool		found;
-
-	hash_search(deleted, indextid, HASH_FIND, &found);
-	return found;
+	return tidhash_lookup(deleted, *indextid) != NULL;
 }
 
 /*
@@ -110,11 +107,13 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 			if (!ItemPointerIsValid(&etup->heaptids[0]))
 			{
 				ItemPointerData ip;
+				bool		found;
 
 				/* Add to deleted list */
 				ItemPointerSet(&ip, blkno, offno);
 
-				(void) hash_search(vacuumstate->deleted, &ip, HASH_ENTER, NULL);
+				tidhash_insert(vacuumstate->deleted, ip, &found);
+				Assert(!found);
 			}
 			else if (etup->level > highestLevel && !(entryPoint != NULL && blkno == entryPoint->blkno && offno == entryPoint->offno))
 			{
@@ -231,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -287,7 +286,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * point is outdated and empty, the entry point will be empty
 			 * until an element is repaired.
 			 */
-			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM);
+			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM, false);
 		}
 		else
 		{
@@ -420,7 +419,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 			 * was replaced and highest point was outdated.
 			 */
 			if (entryPoint == NULL || element->level > entryPoint->level)
-				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, false);
 
 			/* Release lock */
 			UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -565,7 +564,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	}
 
 	/* Update insert page last, after everything has been marked as deleted */
-	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM);
+	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM, false);
 }
 
 /*
@@ -575,7 +574,6 @@ static void
 InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
 {
 	Relation	index = info->index;
-	HASHCTL		hash_ctl;
 
 	if (stats == NULL)
 		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
@@ -597,10 +595,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
 
 	/* Create hash table */
-	hash_ctl.keysize = sizeof(ItemPointerData);
-	hash_ctl.entrysize = sizeof(ItemPointerData);
-	hash_ctl.hcxt = CurrentMemoryContext;
-	vacuumstate->deleted = hash_create("hnswbulkdelete indextids", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+	vacuumstate->deleted = tidhash_create(CurrentMemoryContext, 256, NULL);
 }
 
 /*
@@ -609,7 +604,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 static void
 FreeVacuumState(HnswVacuumState * vacuumstate)
 {
-	hash_destroy(vacuumstate->deleted);
+	tidhash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);

src/vector.c

@@ -724,7 +724,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 }
 
 /*
- * Get the L1 distance between vectors
+ * Get the L1 distance between two vectors
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(l1_distance);
 Datum
@@ -903,8 +903,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_lt);
 Datum
 vector_lt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
 }
@@ -916,8 +916,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_le);
 Datum
 vector_le(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
 }
@@ -929,8 +929,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_eq);
 Datum
 vector_eq(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
 }
@@ -942,8 +942,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ne);
 Datum
 vector_ne(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
 }
@@ -955,8 +955,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ge);
 Datum
 vector_ge(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
 }
@@ -968,8 +968,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_gt);
 Datum
 vector_gt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
 }
@@ -981,8 +981,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_cmp);
 Datum
 vector_cmp(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_INT32(vector_cmp_internal(a, b));
 }

test/expected/copy.out

@@ -1,15 +1,15 @@
-CREATE TABLE t (val vector(3), val2 half[]);
-INSERT INTO t (val, val2) VALUES ('[0,0,0]', '{0,0,0}'), ('[1,2,3]', '{1,2,3}'), ('[1,1,1]', '{1,1,1}'), (NULL, NULL);
-CREATE TABLE t2 (val vector(3), val2 half[]);
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
+CREATE TABLE t2 (val vector(3));
 \copy t TO 'results/data.bin' WITH (FORMAT binary)
 \copy t2 FROM 'results/data.bin' WITH (FORMAT binary)
 SELECT * FROM t2 ORDER BY val;
-   val   |  val2   
----------+---------
- [0,0,0] | {0,0,0}
- [1,1,1] | {1,1,1}
- [1,2,3] | {1,2,3}
-         | 
+   val   
+---------
+ [0,0,0]
+ [1,1,1]
+ [1,2,3]
+ 
 (4 rows)
 
 DROP TABLE t;

test/expected/functions.out

@@ -54,105 +54,105 @@ SELECT vector_norm('[3e37,4e37]')::real;
        5e+37
 (1 row)
 
-SELECT l2_distance('[0,0]'::vector, '[3,4]');
+SELECT l2_distance('[0,0]', '[3,4]');
  l2_distance 
 -------------
            5
 (1 row)
 
-SELECT l2_distance('[0,0]'::vector, '[0,1]');
+SELECT l2_distance('[0,0]', '[0,1]');
  l2_distance 
 -------------
            1
 (1 row)
 
-SELECT l2_distance('[1,2]'::vector, '[3]');
+SELECT l2_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l2_distance('[3e38]'::vector, '[-3e38]');
+SELECT l2_distance('[3e38]', '[-3e38]');
  l2_distance 
 -------------
     Infinity
 (1 row)
 
-SELECT inner_product('[1,2]'::vector, '[3,4]');
+SELECT inner_product('[1,2]', '[3,4]');
  inner_product 
 ---------------
             11
 (1 row)
 
-SELECT inner_product('[1,2]'::vector, '[3]');
+SELECT inner_product('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT inner_product('[3e38]'::vector, '[3e38]');
+SELECT inner_product('[3e38]', '[3e38]');
  inner_product 
 ---------------
       Infinity
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[2,4]');
+SELECT cosine_distance('[1,2]', '[2,4]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[0,0]');
+SELECT cosine_distance('[1,2]', '[0,0]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[1,1]');
+SELECT cosine_distance('[1,1]', '[1,1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,0]'::vector, '[0,2]');
+SELECT cosine_distance('[1,0]', '[0,2]');
  cosine_distance 
 -----------------
                1
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
+SELECT cosine_distance('[1,1]', '[-1,-1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[3]');
+SELECT cosine_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
+SELECT cosine_distance('[1,1]', '[1.1,1.1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[3e38]'::vector, '[3e38]');
+SELECT cosine_distance('[3e38]', '[3e38]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT l1_distance('[0,0]'::vector, '[3,4]');
+SELECT l1_distance('[0,0]', '[3,4]');
  l1_distance 
 -------------
            7
 (1 row)
 
-SELECT l1_distance('[0,0]'::vector, '[0,1]');
+SELECT l1_distance('[0,0]', '[0,1]');
  l1_distance 
 -------------
            1
 (1 row)
 
-SELECT l1_distance('[1,2]'::vector, '[3]');
+SELECT l1_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l1_distance('[3e38]'::vector, '[-3e38]');
+SELECT l1_distance('[3e38]', '[-3e38]');
  l1_distance 
 -------------
     Infinity

test/expected/half.out

@@ -1,182 +0,0 @@
-SELECT '1.5'::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '65504'::half;
- half  
--------
- 65504
-(1 row)
-
-SELECT '65505'::half;
-ERROR:  "65505" is out of range for type half
-LINE 1: SELECT '65505'::half;
-               ^
-SELECT '-65504'::half;
-  half  
---------
- -65504
-(1 row)
-
-SELECT '-65505'::half;
-ERROR:  "-65505" is out of range for type half
-LINE 1: SELECT '-65505'::half;
-               ^
-SELECT ''::half;
-ERROR:  invalid input syntax for type half: ""
-LINE 1: SELECT ''::half;
-               ^
-SELECT ' '::half;
-ERROR:  invalid input syntax for type half: " "
-LINE 1: SELECT ' '::half;
-               ^
-SELECT '-'::half;
-ERROR:  invalid input syntax for type half: "-"
-LINE 1: SELECT '-'::half;
-               ^
-SELECT ' 1.5'::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '1.5 '::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '1.5a'::half;
-ERROR:  invalid input syntax for type half: "1.5a"
-LINE 1: SELECT '1.5a'::half;
-               ^
-SELECT '{1,2,3}'::half[];
-  half   
----------
- {1,2,3}
-(1 row)
-
-SELECT '65505'::integer::half;
- half  
--------
- 65504
-(1 row)
-
-SELECT 'NaN'::real::half;
- half 
-------
- NaN
-(1 row)
-
-SELECT 'Infinity'::real::half;
-   half   
-----------
- Infinity
-(1 row)
-
-SELECT l2_distance('{0,0}'::half[], '{3,4}'::half[]);
- l2_distance 
--------------
-           5
-(1 row)
-
-SELECT l2_distance('{0,0}'::half[], '{0,1}'::half[]);
- l2_distance 
--------------
-           1
-(1 row)
-
-SELECT l2_distance('{1,2}'::half[], '{3}'::half[]);
-ERROR:  different dimensions 2 and 1
-SELECT '{0,0}'::half[] <-> '{3,4}'::half[];
- ?column? 
-----------
-        5
-(1 row)
-
-SELECT inner_product('{1,2}'::half[], '{3,4}'::half[]);
- inner_product 
----------------
-            11
-(1 row)
-
-SELECT inner_product('{1,2}'::half[], '{3}'::half[]);
-ERROR:  different dimensions 2 and 1
-SELECT inner_product('{65504}'::half[], '{65504}'::half[]);
- inner_product 
----------------
-    4290774016
-(1 row)
-
-SELECT '{1,2}'::half[] <#> '{3,4}'::half[];
- ?column? 
-----------
-      -11
-(1 row)
-
-SELECT cosine_distance('{1,2}'::half[], '{2,4}'::half[]);
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('{1,2}'::half[], '{0,0}'::half[]);
- cosine_distance 
------------------
-             NaN
-(1 row)
-
-SELECT cosine_distance('{1,1}'::half[], '{1,1}'::half[]);
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('{1,0}'::half[], '{0,2}'::half[]);
- cosine_distance 
------------------
-               1
-(1 row)
-
-SELECT cosine_distance('{1,1}'::half[], '{-1,-1}'::half[]);
- cosine_distance 
------------------
-               2
-(1 row)
-
-SELECT cosine_distance('{1,2}'::half[], '{3}'::half[]);
-ERROR:  different dimensions 2 and 1
-SELECT cosine_distance('{1,1}'::half[], '{1.1,1.1}'::half[]);
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('{1,1}'::half[], '{-1.1,-1.1}'::half[]);
- cosine_distance 
------------------
-               2
-(1 row)
-
-SELECT '{1,2}'::half[] <=> '{2,4}'::half[];
- ?column? 
-----------
-        0
-(1 row)
-
-SELECT l1_distance('{0,0}'::half[], '{3,4}');
- l1_distance 
--------------
-           7
-(1 row)
-
-SELECT l1_distance('{0,0}'::half[], '{0,1}');
- l1_distance 
--------------
-           1
-(1 row)
-
-SELECT l1_distance('{1,2}'::half[], '{3}');
-ERROR:  different dimensions 2 and 1

test/sql/copy.sql

@@ -1,7 +1,7 @@
-CREATE TABLE t (val vector(3), val2 half[]);
-INSERT INTO t (val, val2) VALUES ('[0,0,0]', '{0,0,0}'), ('[1,2,3]', '{1,2,3}'), ('[1,1,1]', '{1,1,1}'), (NULL, NULL);
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
 
-CREATE TABLE t2 (val vector(3), val2 half[]);
+CREATE TABLE t2 (val vector(3));
 
 \copy t TO 'results/data.bin' WITH (FORMAT binary)
 \copy t2 FROM 'results/data.bin' WITH (FORMAT binary)

test/sql/functions.sql

@@ -13,29 +13,29 @@ SELECT vector_norm('[3,4]');
 SELECT vector_norm('[0,1]');
 SELECT vector_norm('[3e37,4e37]')::real;
 
-SELECT l2_distance('[0,0]'::vector, '[3,4]');
-SELECT l2_distance('[0,0]'::vector, '[0,1]');
-SELECT l2_distance('[1,2]'::vector, '[3]');
-SELECT l2_distance('[3e38]'::vector, '[-3e38]');
+SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[3e38]', '[-3e38]');
 
-SELECT inner_product('[1,2]'::vector, '[3,4]');
-SELECT inner_product('[1,2]'::vector, '[3]');
-SELECT inner_product('[3e38]'::vector, '[3e38]');
+SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[3e38]', '[3e38]');
 
-SELECT cosine_distance('[1,2]'::vector, '[2,4]');
-SELECT cosine_distance('[1,2]'::vector, '[0,0]');
-SELECT cosine_distance('[1,1]'::vector, '[1,1]');
-SELECT cosine_distance('[1,0]'::vector, '[0,2]');
-SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
-SELECT cosine_distance('[1,2]'::vector, '[3]');
-SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
-SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
-SELECT cosine_distance('[3e38]'::vector, '[3e38]');
+SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[3e38]', '[3e38]');
 
-SELECT l1_distance('[0,0]'::vector, '[3,4]');
-SELECT l1_distance('[0,0]'::vector, '[0,1]');
-SELECT l1_distance('[1,2]'::vector, '[3]');
-SELECT l1_distance('[3e38]'::vector, '[-3e38]');
+SELECT l1_distance('[0,0]', '[3,4]');
+SELECT l1_distance('[0,0]', '[0,1]');
+SELECT l1_distance('[1,2]', '[3]');
+SELECT l1_distance('[3e38]', '[-3e38]');
 
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]']) v;
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]', NULL]) v;

test/sql/half.sql

@@ -1,42 +0,0 @@
-SELECT '1.5'::half;
-SELECT '65504'::half;
-SELECT '65505'::half;
-SELECT '-65504'::half;
-SELECT '-65505'::half;
-
-SELECT ''::half;
-SELECT ' '::half;
-SELECT '-'::half;
-SELECT ' 1.5'::half;
-SELECT '1.5 '::half;
-SELECT '1.5a'::half;
-
-SELECT '{1,2,3}'::half[];
-
-SELECT '65505'::integer::half;
-SELECT 'NaN'::real::half;
-SELECT 'Infinity'::real::half;
-
-SELECT l2_distance('{0,0}'::half[], '{3,4}'::half[]);
-SELECT l2_distance('{0,0}'::half[], '{0,1}'::half[]);
-SELECT l2_distance('{1,2}'::half[], '{3}'::half[]);
-SELECT '{0,0}'::half[] <-> '{3,4}'::half[];
-
-SELECT inner_product('{1,2}'::half[], '{3,4}'::half[]);
-SELECT inner_product('{1,2}'::half[], '{3}'::half[]);
-SELECT inner_product('{65504}'::half[], '{65504}'::half[]);
-SELECT '{1,2}'::half[] <#> '{3,4}'::half[];
-
-SELECT cosine_distance('{1,2}'::half[], '{2,4}'::half[]);
-SELECT cosine_distance('{1,2}'::half[], '{0,0}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{1,1}'::half[]);
-SELECT cosine_distance('{1,0}'::half[], '{0,2}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{-1,-1}'::half[]);
-SELECT cosine_distance('{1,2}'::half[], '{3}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{1.1,1.1}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{-1.1,-1.1}'::half[]);
-SELECT '{1,2}'::half[] <=> '{2,4}'::half[];
-
-SELECT l1_distance('{0,0}'::half[], '{3,4}');
-SELECT l1_distance('{0,0}'::half[], '{0,1}');
-SELECT l1_distance('{1,2}'::half[], '{3}');

test/t/019_hnsw_half.pl

@@ -1,93 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-
-sub test_recall
-{
-	my ($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 = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v half[3]);");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()]::numeric[]::half[] FROM generate_series(1, 10000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my $r1 = rand();
-	my $r2 = rand();
-	my $r3 = rand();
-	push(@queries, "{$r1,$r2,$r3}");
-}
-
-# Check each index type
-my @operators = ("<->");
-my @opclasses = ("half_l2_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", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
-		push(@expected, $res);
-	}
-
-	# Add index
-	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
-
-	my $min = $operator eq "<#>" ? 0.80 : 0.99;
-	test_recall($min, $operator);
-}
-
-done_testing();