Fixed Windows build [skip ci]

.github/workflows/build.yml

@@ -8,8 +8,6 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - postgres: 17
-            os: ubuntu-22.04
           - postgres: 16
             os: ubuntu-22.04
           - postgres: 15
@@ -23,7 +21,7 @@ jobs:
           - postgres: 11
             os: ubuntu-20.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: ${{ matrix.postgres }}
@@ -45,7 +43,7 @@ jobs:
     runs-on: macos-latest
     if: ${{ !startsWith(github.ref_name, 'windows') }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: 14
@@ -67,7 +65,7 @@ jobs:
     runs-on: windows-latest
     if: ${{ !startsWith(github.ref_name, 'mac') }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: 14

CHANGELOG.md

@@ -1,11 +1,7 @@
-## 0.6.0 (unreleased)
+## 0.5.1 (unreleased)
 
-- Added support for inline filtering with HNSW
+- Added check for MVCC-compliant snapshot for HNSW index scans
-
+- Improved performance of index scans for IVFFlat after updates and deletes
-## 0.5.1 (2023-10-10)
-
-- Improved performance of HNSW index builds
-- Added check for MVCC-compliant snapshot for index scans
 
 ## 0.5.0 (2023-08-28)
 

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.5.1",
+	"version": "0.5.0",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.5.1",
+			"version": "0.5.0",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,10 +1,10 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.5.0
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
-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
+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/tinyint.o src/vector.o
-HEADERS = src/vector.h
+HEADERS = src/tinyint.h 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
+EXTVERSION = 0.5.0
 
-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
+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\tinyint.obj src\vector.obj
-HEADERS = src\vector.h
+HEADERS = src\tinyint.h 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)

README.md

@@ -18,7 +18,7 @@ Compile and install the extension (supports Postgres 11+)
 
 ```sh
 cd /tmp
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -26,7 +26,7 @@ make install # may need sudo
 
 See the [installation notes](#installation-notes) if you run into issues
 
-You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
+You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres)
 
 ## Getting Started
 
@@ -215,23 +215,6 @@ SELECT ...
 COMMIT;
 ```
 
-### Indexing Progress
-
-Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
-
-```sql
-SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
-```
-
-The phases for IVFFlat are:
-
-1. `initializing`
-2. `performing k-means`
-3. `assigning tuples`
-4. `loading tuples`
-
-Note: `%` is only populated during the `loading tuples` phase
-
 ## HNSW
 
 An HNSW index creates a multilayer graph. It has slower build times and uses more memory than IVFFlat, but has better query performance (in terms of speed-recall tradeoff). There’s no training step like IVFFlat, so the index can be created without any data in the table.
@@ -288,18 +271,22 @@ SELECT ...
 COMMIT;
 ```
 
-### Indexing Progress
+## Indexing Progress
 
 Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
 
 ```sql
-SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
+SELECT phase, tuples_done, tuples_total FROM pg_stat_progress_create_index;
 ```
 
-The phases for HNSW are:
+The phases are:
 
 1. `initializing`
-2. `loading tuples`
+2. `performing k-means` - IVFFlat only
+3. `assigning tuples` - IVFFlat only
+4. `loading tuples`
+
+Note: `tuples_done` and `tuples_total` are only populated during the `loading tuples` phase
 
 ## Filtering
 
@@ -315,12 +302,6 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
 CREATE INDEX ON items (category_id);
 ```
 
-Or a composite HNSW index for approximate search (added in 0.6.0)
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops, category_id);
-```
-
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
 
 ```sql
@@ -336,15 +317,13 @@ CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(cate
 
 ## Hybrid Search
 
-Use together with Postgres [full-text search](https://www.postgresql.org/docs/current/textsearch-intro.html) for hybrid search.
+Use together with Postgres [full-text search](https://www.postgresql.org/docs/current/textsearch-intro.html) for hybrid search ([Python example](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search.py)).
 
 ```sql
 SELECT id, content FROM items, plainto_tsquery('hello search') query
     WHERE textsearch @@ query ORDER BY ts_rank_cd(textsearch, query) DESC LIMIT 5;
 ```
 
-You can use [Reciprocal Rank Fusion](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search_rrf.py) or a [cross-encoder](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search.py) to combine results.
-
 ## Performance
 
 Use `EXPLAIN ANALYZE` to debug performance.
@@ -381,7 +360,6 @@ Use pgvector from any language with a Postgres client. You can even generate and
 
 Language | Libraries / Examples
 --- | ---
-C | [pgvector-c](https://github.com/pgvector/pgvector-c)
 C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
 C# | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
 Crystal | [pgvector-crystal](https://github.com/pgvector/pgvector-crystal)
@@ -389,11 +367,10 @@ Dart | [pgvector-dart](https://github.com/pgvector/pgvector-dart)
 Elixir | [pgvector-elixir](https://github.com/pgvector/pgvector-elixir)
 Go | [pgvector-go](https://github.com/pgvector/pgvector-go)
 Haskell | [pgvector-haskell](https://github.com/pgvector/pgvector-haskell)
-Java, Kotlin, Groovy, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
+Java, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
-JavaScript, TypeScript | [pgvector-node](https://github.com/pgvector/pgvector-node)
 Julia | [pgvector-julia](https://github.com/pgvector/pgvector-julia)
 Lua | [pgvector-lua](https://github.com/pgvector/pgvector-lua)
-Nim | [pgvector-nim](https://github.com/pgvector/pgvector-nim)
+Node.js | [pgvector-node](https://github.com/pgvector/pgvector-node)
 Perl | [pgvector-perl](https://github.com/pgvector/pgvector-perl)
 PHP | [pgvector-php](https://github.com/pgvector/pgvector-php)
 Python | [pgvector-python](https://github.com/pgvector/pgvector-python)
@@ -401,7 +378,6 @@ R | [pgvector-r](https://github.com/pgvector/pgvector-r)
 Ruby | [pgvector-ruby](https://github.com/pgvector/pgvector-ruby), [Neighbor](https://github.com/ankane/neighbor)
 Rust | [pgvector-rust](https://github.com/pgvector/pgvector-rust)
 Swift | [pgvector-swift](https://github.com/pgvector/pgvector-swift)
-Zig | [pgvector-zig](https://github.com/pgvector/pgvector-zig)
 
 ## Frequently Asked Questions
 
@@ -417,55 +393,6 @@ Yes, pgvector uses the write-ahead log (WAL), which allows for replication and p
 
 You’ll need to use [dimensionality reduction](https://en.wikipedia.org/wiki/Dimensionality_reduction) at the moment.
 
-#### Can I store vectors with different dimensions in the same column?
-
-You can use `vector` as the type (instead of `vector(3)`).
-
-```sql
-CREATE TABLE embeddings (model_id bigint, item_id bigint, embedding vector, PRIMARY KEY (model_id, item_id));
-```
-
-However, you can only create indexes on rows with the same number of dimensions (using [expression](https://www.postgresql.org/docs/current/indexes-expressional.html) and [partial](https://www.postgresql.org/docs/current/indexes-partial.html) indexing):
-
-```sql
-CREATE INDEX ON embeddings USING hnsw ((embedding::vector(3)) vector_l2_ops) WHERE (model_id = 123);
-```
-
-and query with:
-
-```sql
-SELECT * FROM embeddings WHERE model_id = 123 ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
-```
-
-#### Can I store vectors with more precision?
-
-You can use the `double precision[]` or `numeric[]` type to store vectors with more precision.
-
-```sql
-CREATE TABLE items (id bigserial PRIMARY KEY, embedding double precision[]);
-
--- use {} instead of [] for Postgres arrays
-INSERT INTO items (embedding) VALUES ('{1,2,3}'), ('{4,5,6}');
-```
-
-Optionally, add a [check constraint](https://www.postgresql.org/docs/current/ddl-constraints.html) to ensure data can be converted to the `vector` type and has the expected dimensions.
-
-```sql
-ALTER TABLE items ADD CHECK (vector_dims(embedding::vector) = 3);
-```
-
-Use [expression indexing](https://www.postgresql.org/docs/current/indexes-expressional.html) to index (at a lower precision):
-
-```sql
-CREATE INDEX ON items USING hnsw ((embedding::vector(3)) vector_l2_ops);
-```
-
-and query with:
-
-```sql
-SELECT * FROM items ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
-```
-
 ## Troubleshooting
 
 #### Why isn’t a query using an index?
@@ -479,8 +406,6 @@ SELECT ...
 COMMIT;
 ```
 
-Also, if the table is small, a table scan may be faster.
-
 #### Why isn’t a query using a parallel table scan?
 
 The planner doesn’t consider [out-of-line storage](https://www.postgresql.org/docs/current/storage-toast.html) in cost estimates, which can make a serial scan look cheaper. You can reduce the cost of a parallel scan for a query with:
@@ -584,7 +509,7 @@ Then use `nmake` to build:
 
 ```cmd
 set "PGROOT=C:\Program Files\PostgreSQL\15"
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
@@ -605,7 +530,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --build-arg PG_MAJOR=15 -t myuser/pgvector .
 ```
@@ -670,7 +595,7 @@ pgvector is available on [these providers](https://github.com/pgvector/pgvector/
 
 ## Upgrading
 
-[Install](#installation) the latest version (use the same method as the original installation). Then in each database you want to upgrade, run:
+Install the latest version. Then in each database you want to upgrade, run:
 
 ```sql
 ALTER EXTENSION vector UPDATE;
@@ -718,7 +643,6 @@ Thanks to:
 - [k-means++: The Advantage of Careful Seeding](https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf)
 - [Concept Decompositions for Large Sparse Text Data using Clustering](https://www.cs.utexas.edu/users/inderjit/public_papers/concept_mlj.pdf)
 - [Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs](https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf)
-- [HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints](https://arxiv.org/pdf/2207.07940.pdf)
 
 ## History
 

sql/vector--0.5.0--0.5.1.sql

@@ -1,2 +1,67 @@
 -- complain if script is sourced in psql, rather than via CREATE EXTENSION
 \echo Use "ALTER EXTENSION vector UPDATE TO '0.5.1'" to load this file. \quit
+
+-- tinyint
+
+CREATE TYPE tinyint;
+
+CREATE FUNCTION tinyint_in(cstring, oid, integer) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_out(tinyint) RETURNS cstring
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_recv(internal, oid, integer) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_send(tinyint) RETURNS bytea
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE TYPE tinyint (
+	INPUT     = tinyint_in,
+	OUTPUT    = tinyint_out,
+	RECEIVE   = tinyint_recv,
+	SEND      = tinyint_send,
+	INTERNALLENGTH = 1,
+	PASSEDBYVALUE,
+	ALIGNMENT = char
+);
+
+CREATE FUNCTION integer_to_tinyint(integer, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION numeric_to_tinyint(numeric, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE CAST (integer AS tinyint)
+	WITH FUNCTION integer_to_tinyint(integer, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (numeric AS tinyint)
+	WITH FUNCTION numeric_to_tinyint(numeric, integer, boolean) AS IMPLICIT;
+
+CREATE FUNCTION l2_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION cosine_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_negative_inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR <-> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = l2_distance,
+	COMMUTATOR = '<->'
+);
+
+CREATE OPERATOR <#> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = tinyint_negative_inner_product,
+	COMMUTATOR = '<#>'
+);
+
+CREATE OPERATOR <=> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = cosine_distance,
+	COMMUTATOR = '<=>'
+);

sql/vector--0.5.1--0.6.0.sql

@@ -1,18 +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 FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION hnsw_attribute_distance(bigint, bigint) RETURNS float8
-	AS 'MODULE_PATHNAME', 'hnsw_int8_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 = (integer, integer),
-	FUNCTION 3 hnsw_attribute_distance(integer, integer);
-
-CREATE OPERATOR CLASS vector_bigint_ops
-	DEFAULT FOR TYPE bigint USING hnsw AS
-	OPERATOR 2 = (bigint, bigint),
-	FUNCTION 3 hnsw_attribute_distance(bigint, bigint);

sql/vector.sql

@@ -291,20 +291,67 @@ CREATE OPERATOR CLASS vector_cosine_ops
 	FUNCTION 1 vector_negative_inner_product(vector, vector),
 	FUNCTION 2 vector_norm(vector);
 
--- hnsw attributes
+-- tinyint
 
-CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
+CREATE TYPE tinyint;
-	AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
-CREATE FUNCTION hnsw_attribute_distance(bigint, bigint) RETURNS float8
+CREATE FUNCTION tinyint_in(cstring, oid, integer) RETURNS tinyint
-	AS 'MODULE_PATHNAME', 'hnsw_int8_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
-CREATE OPERATOR CLASS vector_integer_ops
+CREATE FUNCTION tinyint_out(tinyint) RETURNS cstring
-	DEFAULT FOR TYPE integer USING hnsw AS
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-	OPERATOR 2 = (integer, integer),
-	FUNCTION 3 hnsw_attribute_distance(integer, integer);
 
-CREATE OPERATOR CLASS vector_bigint_ops
+CREATE FUNCTION tinyint_recv(internal, oid, integer) RETURNS tinyint
-	DEFAULT FOR TYPE bigint USING hnsw AS
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-	OPERATOR 2 = (bigint, bigint),
+
-	FUNCTION 3 hnsw_attribute_distance(bigint, bigint);
+CREATE FUNCTION tinyint_send(tinyint) RETURNS bytea
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE TYPE tinyint (
+	INPUT     = tinyint_in,
+	OUTPUT    = tinyint_out,
+	RECEIVE   = tinyint_recv,
+	SEND      = tinyint_send,
+	INTERNALLENGTH = 1,
+	PASSEDBYVALUE,
+	ALIGNMENT = char
+);
+
+CREATE FUNCTION integer_to_tinyint(integer, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION numeric_to_tinyint(numeric, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE CAST (integer AS tinyint)
+	WITH FUNCTION integer_to_tinyint(integer, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (numeric AS tinyint)
+	WITH FUNCTION numeric_to_tinyint(numeric, integer, boolean) AS IMPLICIT;
+
+CREATE FUNCTION l2_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION cosine_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_negative_inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR <-> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = l2_distance,
+	COMMUTATOR = '<->'
+);
+
+CREATE OPERATOR <#> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = tinyint_negative_inner_product,
+	COMMUTATOR = '<#>'
+);
+
+CREATE OPERATOR <=> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = cosine_distance,
+	COMMUTATOR = '<=>'
+);

src/hnsw.c

@@ -167,7 +167,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
 	amroutine->amstrategies = 0;
-	amroutine->amsupport = 3;
+	amroutine->amsupport = 2;
 #if PG_VERSION_NUM >= 130000
 	amroutine->amoptsprocnum = 0;
 #endif
@@ -175,7 +175,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->amcanorderbyop = true;
 	amroutine->amcanbackward = false;	/* can change direction mid-scan */
 	amroutine->amcanunique = false;
-	amroutine->amcanmulticol = true;
+	amroutine->amcanmulticol = false;
 	amroutine->amoptionalkey = true;
 	amroutine->amsearcharray = false;
 	amroutine->amsearchnulls = false;
@@ -222,31 +222,3 @@ hnswhandler(PG_FUNCTION_ARGS)
 
 	PG_RETURN_POINTER(amroutine);
 }
-
-/*
- * Get the distance between two int4 attributes
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int4_attribute_distance);
-Datum
-hnsw_int4_attribute_distance(PG_FUNCTION_ARGS)
-{
-	int32		a = PG_GETARG_INT32(0);
-	int32		b = PG_GETARG_INT32(1);
-	double		distance = ((double) a) - ((double) b);
-
-	PG_RETURN_FLOAT8(distance);
-}
-
-/*
- * Get the distance between two int8 attributes
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int8_attribute_distance);
-Datum
-hnsw_int8_attribute_distance(PG_FUNCTION_ARGS)
-{
-	int64		a = PG_GETARG_INT64(0);
-	int64		b = PG_GETARG_INT64(1);
-	double		distance = ((double) a) - ((double) b);
-
-	PG_RETURN_FLOAT8(distance);
-}

src/hnsw.h

@@ -19,7 +19,6 @@
 /* Support functions */
 #define HNSW_DISTANCE_PROC 1
 #define HNSW_NORM_PROC 2
-#define HNSW_ATTRIBUTE_DISTANCE_PROC 3
 
 #define HNSW_VERSION	1
 #define HNSW_MAGIC_NUMBER 0xA953A953
@@ -60,7 +59,7 @@
 
 #define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))
 
-#define HNSW_ELEMENT_TUPLE_SIZE(size)	MAXALIGN(offsetof(HnswElementTupleData, data) + (size))
+#define HNSW_ELEMENT_TUPLE_SIZE(_dim)	MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
 #define HNSW_NEIGHBOR_TUPLE_SIZE(level, m)	MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))
 
 #define HnswPageGetOpaque(page)	((HnswPageOpaque) PageGetSpecialPointer(page))
@@ -104,8 +103,7 @@ typedef struct HnswElementData
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Datum		value;
+	Vector	   *vec;
-	IndexTuple	itup;
 }			HnswElementData;
 
 typedef HnswElementData * HnswElement;
@@ -114,13 +112,11 @@ typedef struct HnswCandidate
 {
 	HnswElement element;
 	float		distance;
-	bool		closer;
 }			HnswCandidate;
 
 typedef struct HnswNeighborArray
 {
 	int			length;
-	bool		closerSet;
 	HnswCandidate *items;
 }			HnswNeighborArray;
 
@@ -156,18 +152,17 @@ typedef struct HnswBuildState
 	double		reltuples;
 
 	/* Support functions */
-	FmgrInfo  **procinfos;
+	FmgrInfo   *procinfo;
 	FmgrInfo   *normprocinfo;
-	Oid		   *collations;
+	Oid			collation;
 
 	/* Variables */
 	List	   *elements;
 	HnswElement entryPoint;
 	double		ml;
 	int			maxLevel;
-	long		memoryLeft;
+	double		maxInMemoryElements;
 	bool		flushed;
-	bool		useIndexTuple;
 	Vector	   *normvec;
 
 	/* Memory */
@@ -207,7 +202,7 @@ typedef struct HnswElementTupleData
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
 	uint16		unused2;
-	Vector		data;
+	Vector		vec;
 }			HnswElementTupleData;
 
 typedef HnswElementTupleData * HnswElementTuple;
@@ -229,9 +224,9 @@ typedef struct HnswScanOpaqueData
 	MemoryContext tmpCtx;
 
 	/* Support functions */
-	FmgrInfo  **procinfos;
+	FmgrInfo   *procinfo;
 	FmgrInfo   *normprocinfo;
-	Oid		   *collations;
+	Oid			collation;
 }			HnswScanOpaqueData;
 
 typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -249,8 +244,8 @@ typedef struct HnswVacuumState
 	int			efConstruction;
 
 	/* Support functions */
-	FmgrInfo  **procinfos;
+	FmgrInfo   *procinfo;
-	Oid		   *collations;
+	Oid			collation;
 
 	/* Variables */
 	HTAB	   *deleted;
@@ -272,27 +267,26 @@ 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, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, int m, bool loadVec, HnswElement skipElement, bool inMemory);
+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);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
 void		HnswFreeElement(HnswElement element);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfos, Oid *collations, int m, int efConstruction, bool existing, bool inMemory);
+void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
-HnswElement HnswFindDuplicate(HnswElement e, Relation index);
+HnswElement HnswFindDuplicate(HnswElement e);
-HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, FmgrInfo **procinfos, Oid *collations, bool loadVec, bool inMemory);
+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		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 **procinfos, Oid *collations, HnswElement e, int m, bool checkExisting);
+void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
-void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
+void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
-void		HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec);
+void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTuple);
+void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
-void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo **procinfos, Oid *collations, bool inMemory);
+void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
-void		HnswElementSetData(HnswElement element, Relation index, Datum value, Datum *values, bool *isnull);
 
 /* Index access methods */
 IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);
@@ -309,6 +303,5 @@ IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
 void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
-FmgrInfo  **HnswInitProcinfos(Relation index);
 
 #endif

src/hnswbuild.c

@@ -8,7 +8,6 @@
 #include "lib/pairingheap.h"
 #include "nodes/pg_list.h"
 #include "storage/bufmgr.h"
-#include "utils/datum.h"
 #include "utils/memutils.h"
 
 #if PG_VERSION_NUM >= 140000
@@ -106,8 +105,8 @@ CreateElementPages(HnswBuildState * buildstate)
 {
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
-	bool		useIndexTuple = buildstate->useIndexTuple;
+	int			dimensions = buildstate->dimensions;
-	Size		etupAllocSize;
+	Size		etupSize;
 	Size		maxSize;
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
@@ -118,11 +117,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	ListCell   *lc;
 
 	/* Calculate sizes */
-	etupAllocSize = BLCKSZ;
 	maxSize = HNSW_MAX_SIZE;
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 
 	/* Allocate once */
-	etup = palloc0(etupAllocSize);
+	etup = palloc0(etupSize);
 	ntup = palloc0(BLCKSZ);
 
 	/* Prepare first page */
@@ -134,24 +133,15 @@ CreateElementPages(HnswBuildState * buildstate)
 	foreach(lc, buildstate->elements)
 	{
 		HnswElement element = lfirst(lc);
-		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
 
-		/* Zero memory for each element */
+		HnswSetElementTuple(etup, element);
-		MemSet(etup, 0, etupAllocSize);
 
 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(element->itup) : VARSIZE_ANY(DatumGetPointer(element->value)));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
-		/* Initial size check */
-		if (etupSize > etupAllocSize)
-			elog(ERROR, "index tuple too large");
-
-		HnswSetElementTuple(etup, element, useIndexTuple);
-
 		/* 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);
@@ -274,15 +264,13 @@ FlushPages(HnswBuildState * buildstate)
  * Insert tuple
  */
 static bool
-InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, HnswBuildState * buildstate, HnswElement * dup, MemoryContext outerCtx)
+InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState * buildstate, HnswElement * dup)
 {
-	FmgrInfo  **procinfos = buildstate->procinfos;
+	FmgrInfo   *procinfo = buildstate->procinfo;
-	Oid		   *collations = buildstate->collations;
+	Oid			collation = buildstate->collation;
 	HnswElement entryPoint = buildstate->entryPoint;
 	int			efConstruction = buildstate->efConstruction;
 	int			m = buildstate->m;
-	bool		inMemory = true;
-	MemoryContext oldCtx;
 
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -290,20 +278,18 @@ InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, Hn
 	/* Normalize if needed */
 	if (buildstate->normprocinfo != NULL)
 	{
-		if (!HnswNormValue(buildstate->normprocinfo, collations[0], &value, buildstate->normvec))
+		if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
 			return false;
 	}
 
 	/* Copy value to element so accessible outside of memory context */
-	oldCtx = MemoryContextSwitchTo(outerCtx);
+	memcpy(element->vec, DatumGetVector(value), VECTOR_SIZE(buildstate->dimensions));
-	HnswElementSetData(element, index, value, values, isnull);
-	MemoryContextSwitchTo(oldCtx);
 
 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, false, inMemory);
+	HnswInsertElement(element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
 
 	/* Look for duplicate */
-	*dup = HnswFindDuplicate(element, index);
+	*dup = HnswFindDuplicate(element);
 
 	/* Update neighbors if needed */
 	if (*dup == NULL)
@@ -314,7 +300,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, Hn
 			HnswNeighborArray *neighbors = &element->neighbors[lc];
 
 			for (int i = 0; i < neighbors->length; i++)
-				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, index, procinfos, collations, inMemory);
+				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, NULL, procinfo, collation);
 		}
 	}
 
@@ -327,21 +313,6 @@ InsertTuple(Relation index, Datum *values, bool *isnull, HnswElement element, Hn
 	return *dup == NULL;
 }
 
-/*
- * Get the memory used by an element
- */
-static long
-HnswElementMemory(HnswElement e, int m)
-{
-	long		elementSize = sizeof(HnswElementData);
-
-	elementSize += sizeof(HnswNeighborArray) * (e->level + 1);
-	elementSize += sizeof(HnswCandidate) * (m * (e->level + 2));
-	elementSize += sizeof(ItemPointerData);
-	elementSize += IndexTupleSize(e->itup);
-	return elementSize;
-}
-
 /*
  * Callback for table_index_build_scan
  */
@@ -363,7 +334,7 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	if (buildstate->memoryLeft <= 0)
+	if (buildstate->indtuples >= buildstate->maxInMemoryElements)
 	{
 		if (!buildstate->flushed)
 		{
@@ -389,12 +360,13 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 
 	/* Allocate necessary memory outside of memory context */
 	element = HnswInitElement(tid, buildstate->m, buildstate->ml, buildstate->maxLevel);
+	element->vec = palloc(VECTOR_SIZE(buildstate->dimensions));
 
 	/* Use memory context since detoast can allocate */
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Insert tuple */
-	inserted = InsertTuple(index, values, isnull, element, buildstate, &dup, oldCtx);
+	inserted = InsertTuple(index, values, element, buildstate, &dup);
 
 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -402,21 +374,31 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 
 	/* Add outside memory context */
 	if (dup != NULL)
-	{
 		HnswAddHeapTid(dup, tid);
-		buildstate->memoryLeft -= sizeof(ItemPointerData);
-	}
 
 	/* Add to buildstate or free */
 	if (inserted)
-	{
 		buildstate->elements = lappend(buildstate->elements, element);
-		buildstate->memoryLeft -= HnswElementMemory(element, buildstate->m);
-	}
 	else
 		HnswFreeElement(element);
 }
 
+/*
+ * Get the max number of elements that fit into maintenance_work_mem
+ */
+static double
+HnswGetMaxInMemoryElements(int m, double ml, int dimensions)
+{
+	Size		elementSize = sizeof(HnswElementData);
+	double		avgLevel = -log(0.5) * ml;
+
+	elementSize += sizeof(HnswNeighborArray) * (avgLevel + 1);
+	elementSize += sizeof(HnswCandidate) * (m * (avgLevel + 2));
+	elementSize += sizeof(ItemPointerData);
+	elementSize += VECTOR_SIZE(dimensions);
+	return (maintenance_work_mem * 1024L) / elementSize;
+}
+
 /*
  * Initialize the build state
  */
@@ -432,19 +414,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->efConstruction = HnswGetEfConstruction(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
 
-	/* TODO See if needed */
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 2)
-		elog(ERROR, "index cannot have more than two columns");
-
-	if (!OidIsValid(index_getprocid(index, 1, HNSW_DISTANCE_PROC)))
-		elog(ERROR, "first column must be a vector");
-
-	for (int i = 1; i < IndexRelationGetNumberOfKeyAttributes(index); i++)
-	{
-		if (!OidIsValid(index_getprocid(index, i + 1, HNSW_ATTRIBUTE_DISTANCE_PROC)))
-			elog(ERROR, "column %d cannot be a vector", i + 1);
-	}
-
 	/* Require column to have dimensions to be indexed */
 	if (buildstate->dimensions < 0)
 		elog(ERROR, "column does not have dimensions");
@@ -459,17 +428,16 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->indtuples = 0;
 
 	/* Get support functions */
-	buildstate->procinfos = HnswInitProcinfos(index);
+	buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	buildstate->collations = index->rd_indcollation;
+	buildstate->collation = index->rd_indcollation[0];
 
 	buildstate->elements = NIL;
 	buildstate->entryPoint = NULL;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
-	buildstate->memoryLeft = maintenance_work_mem * 1024L;
+	buildstate->maxInMemoryElements = HnswGetMaxInMemoryElements(buildstate->m, buildstate->ml, buildstate->dimensions);
 	buildstate->flushed = false;
-	buildstate->useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;
 
 	/* Reuse for each tuple */
 	buildstate->normvec = InitVector(buildstate->dimensions);
@@ -485,7 +453,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 static void
 FreeBuildState(HnswBuildState * buildstate)
 {
-	pfree(buildstate->procinfos);
 	pfree(buildstate->normvec);
 	MemoryContextDelete(buildstate->tmpCtx);
 }

src/hnswinsert.c

@@ -123,16 +123,16 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	Size		minCombinedSize;
 	HnswElementTuple etup;
 	BlockNumber currentPage = insertPage;
+	int			dimensions = e->vec->dim;
 	HnswNeighborTuple ntup;
 	Buffer		nbuf;
 	Page		npage;
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(e->itup) : VARSIZE_ANY(DatumGetPointer(e->value)));
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -140,7 +140,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(etup, e, useIndexTuple);
+	HnswSetElementTuple(etup, e);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
@@ -302,7 +302,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
  * Update neighbors
  */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e, int m, bool checkExisting)
+HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -334,7 +334,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo **procinfos, Oid *collations, H
 			 */
 
 			/* Select neighbors */
-			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfos, collations, false);
+			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfo, collation);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
@@ -405,9 +405,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	ItemId		itemid;
+	Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(dup->vec->dim);
 	HnswElementTuple etup;
-	Size		etupSize;
 	int			i;
 
 	/* Read page */
@@ -417,9 +416,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	page = GenericXLogRegisterBuffer(state, buf, 0);
 
 	/* Find space */
-	itemid = PageGetItemId(page, dup->offno);
+	etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, dup->offno));
-	etup = (HnswElementTuple) PageGetItem(page, itemid);
-	etupSize = ItemIdGetLength(itemid);
 	for (i = 0; i < HNSW_HEAPTIDS; i++)
 	{
 		if (!ItemPointerIsValid(&etup->heaptids[i]))
@@ -452,7 +449,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
  * Write changes to disk
  */
 static void
-WriteElement(Relation index, FmgrInfo **procinfos, Oid *collations, 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)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
@@ -471,7 +468,7 @@ WriteElement(Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfos, collations, element, m, false);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
 
 	/* Update metapage if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -490,8 +487,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
-	FmgrInfo  **procinfos = HnswInitProcinfos(index);
+	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	Oid		   *collations = index->rd_indcollation;
+	Oid			collation = index->rd_indcollation[0];
 	HnswElement dup;
 	LOCKMODE	lockmode = ShareLock;
 
@@ -502,7 +499,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 	if (normprocinfo != NULL)
 	{
-		if (!HnswNormValue(normprocinfo, collations[0], &value, NULL))
+		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
 			return false;
 	}
 
@@ -518,7 +515,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 
 	/* Create an element */
 	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	HnswElementSetData(element, index, value, values, isnull);
+	element->vec = DatumGetVector(value);
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -535,13 +532,13 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	}
 
 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, false, false);
+	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
 	/* Look for duplicate */
-	dup = HnswFindDuplicate(element, index);
+	dup = HnswFindDuplicate(element);
 
 	/* Write to disk */
-	WriteElement(index, procinfos, collations, element, m, efConstruction, dup, entryPoint);
+	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);

src/hnswscan.c

@@ -15,13 +15,12 @@ GetScanItems(IndexScanDesc scan, Datum q)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
-	FmgrInfo  **procinfos = so->procinfos;
+	FmgrInfo   *procinfo = so->procinfo;
-	Oid		   *collations = so->collations;
+	Oid			collation = so->collation;
 	List	   *ep;
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
-	ScanKeyData *keyData = scan->keyData;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -29,15 +28,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, NULL, keyData, index, procinfos, collations, false, false));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, NULL, keyData, ep, 1, lc, index, procinfos, collations, m, false, NULL, false);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, NULL, keyData, ep, hnsw_ef_search, 0, index, procinfos, collations, m, false, NULL, false);
+	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
 }
 
 /*
@@ -84,7 +83,7 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Fine if normalization fails */
 		if (so->normprocinfo != NULL)
-			HnswNormValue(so->normprocinfo, so->collations[0], &value, NULL);
+			HnswNormValue(so->normprocinfo, so->collation, &value, NULL);
 	}
 
 	return value;
@@ -108,9 +107,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 									   ALLOCSET_DEFAULT_SIZES);
 
 	/* Set support functions */
-	so->procinfos = HnswInitProcinfos(index);
+	so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	so->collations = index->rd_indcollation;
+	so->collation = index->rd_indcollation[0];
 
 	scan->opaque = so;
 
@@ -207,9 +206,6 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		scan->xs_ctup.t_self = *heaptid;
 #endif
 
-		/* TODO Check during scan */
-		scan->xs_recheck = scan->numberOfKeys > 0;
-
 		scan->xs_recheckorderby = false;
 		return true;
 	}
@@ -226,7 +222,6 @@ hnswendscan(IndexScanDesc scan)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
-	pfree(so->procinfos);
 	MemoryContextDelete(so->tmpCtx);
 
 	pfree(so);

src/hnswutils.c

@@ -4,13 +4,8 @@
 
 #include "hnsw.h"
 #include "storage/bufmgr.h"
-#include "utils/datum.h"
 #include "vector.h"
 
-#if PG_VERSION_NUM < 130000
-#define TYPSTORAGE_PLAIN 'p'
-#endif
-
 /*
  * Get the max number of connections in an upper layer for each element in the index
  */
@@ -51,22 +46,6 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 	return index_getprocinfo(index, 1, procnum);
 }
 
-/*
- * Init procs
- */
-FmgrInfo  **
-HnswInitProcinfos(Relation index)
-{
-	int			keyAttributes = IndexRelationGetNumberOfKeyAttributes(index);
-	FmgrInfo  **procinfos = palloc(keyAttributes * sizeof(FmgrInfo *));
-
-	procinfos[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	for (int i = 1; i < keyAttributes; i++)
-		procinfos[i] = index_getprocinfo(index, i + 1, HNSW_ATTRIBUTE_DISTANCE_PROC);
-
-	return procinfos;
-}
-
 /*
  * Divide by the norm
  *
@@ -160,7 +139,6 @@ HnswInitNeighbors(HnswElement element, int m)
 		a = &element->neighbors[lc];
 		a->length = 0;
 		a->items = palloc(sizeof(HnswCandidate) * lm);
-		a->closerSet = false;
 	}
 }
 
@@ -194,7 +172,6 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
 
 	element->level = level;
 	element->deleted = 0;
-	element->itup = NULL;
 
 	HnswInitNeighbors(element, m);
 
@@ -209,8 +186,7 @@ HnswFreeElement(HnswElement element)
 {
 	HnswFreeNeighbors(element);
 	list_free_deep(element->heaptids);
-	if (element->itup)
+	pfree(element->vec);
-		pfree(element->itup);
 	pfree(element);
 }
 
@@ -237,8 +213,7 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	element->blkno = blkno;
 	element->offno = offno;
 	element->neighbors = NULL;
-	element->value = PointerGetDatum(NULL);
+	element->vec = NULL;
-	element->itup = NULL;
 	return element;
 }
 
@@ -336,7 +311,7 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
  * Set element tuple, except for neighbor info
  */
 void
-HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTuple)
+HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
 {
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
@@ -348,11 +323,7 @@ HnswSetElementTuple(HnswElementTuple etup, HnswElement element, bool useIndexTup
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-
+	memcpy(&etup->vec, element->vec, VECTOR_SIZE(element->vec->dim));
-	if (useIndexTuple)
-		memcpy(&etup->data, element->itup, IndexTupleSize(element->itup));
-	else
-		memcpy(&etup->data, DatumGetPointer(element->value), VARSIZE_ANY(DatumGetPointer(element->value)));
 }
 
 /*
@@ -453,7 +424,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m)
  * Load an element from a tuple
  */
 void
-HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index)
+HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec)
 {
 	element->level = etup->level;
 	element->deleted = etup->deleted;
@@ -475,149 +446,16 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 
 	if (loadVec)
 	{
-		if (IndexRelationGetNumberOfAttributes(index) > 1)
+		element->vec = palloc(VECTOR_SIZE(etup->vec.dim));
-		{
+		memcpy(element->vec, &etup->vec, VECTOR_SIZE(etup->vec.dim));
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			element->itup = CopyIndexTuple((IndexTuple) &etup->data);
-			element->value = index_getattr(element->itup, 1, tupdesc, &unused);
-		}
-		else
-		{
-			Vector	   *vec = palloc(VARSIZE_ANY(&etup->data));
-
-			memcpy(vec, &etup->data, VARSIZE_ANY(&etup->data));
-			element->value = PointerGetDatum(vec);
-		}
 	}
 }
 
-/*
- * Get the tuple descriptor
- */
-static TupleDesc
-HnswTupleDesc(Relation index)
-{
-	TupleDesc	tupdesc = CreateTupleDescCopyConstr(RelationGetDescr(index));
-
-	/* Prevent compression */
-	TupleDescAttr(tupdesc, 0)->attstorage = TYPSTORAGE_PLAIN;
-
-	return tupdesc;
-}
-
-/*
- * Set element data
- */
-void
-HnswElementSetData(HnswElement element, Relation index, Datum value, Datum *values, bool *isnull)
-{
-	/* TODO Create once per index build */
-	TupleDesc	tupdesc = HnswTupleDesc(index);
-	bool		unused;
-	Datum		tmp;
-
-	tmp = values[0];
-	values[0] = value;
-	element->itup = index_form_tuple(tupdesc, values, isnull);
-	values[0] = tmp;
-
-	element->value = index_getattr(element->itup, 1, tupdesc, &unused);
-
-	FreeTupleDesc(tupdesc);
-}
-
-/*
- * Get the attribute distance
- */
-static inline double
-AttributeDistance(double e)
-{
-	/* TODO Better bias */
-	/* must be >> max(w * g) + 1 / log10(2) */
-	double		bias = 4.32;
-
-	return e > 0 ? bias - 1.0 / log10(e + 1) : 0;
-}
-
-/*
- * Get the distance
- */
-static double
-GetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations)
-{
-	double		g = DatumGetFloat8(FunctionCall2Coll(procinfos[0], collations[0], q, vec));
-
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
-	{
-		double		w = 0.25;
-		double		e = 0.0;
-		TupleDesc	tupdesc = RelationGetDescr(index);
-
-		if (keyData)
-		{
-			/* TODO need to pass length of key data */
-			int			keyCount = 1;
-
-			for (int i = 0; i < keyCount; i++)
-			{
-				ScanKey		key = &keyData[i];
-				bool		isnull;
-				Datum		value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
-				bool		attnull = key->sk_flags & SK_ISNULL;
-
-				if (isnull || attnull)
-				{
-					if (isnull != attnull)
-						e += 1000;
-				}
-				else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
-				{
-					double		ei = fabs(DatumGetFloat8(FunctionCall2Coll(procinfos[key->sk_attno - 1], collations[key->sk_attno - 1], value, key->sk_argument)));
-
-					if (ei > 0)
-						e += ei;
-					else
-						/* Distance is zero for inequality */
-						e += 1000;
-				}
-			}
-
-			return w * g + AttributeDistance(e);
-		}
-		else if (qtup)
-		{
-			int			keyCount = IndexRelationGetNumberOfKeyAttributes(index) - 1;
-
-			for (int i = 0; i < keyCount; i++)
-			{
-				bool		isnull;
-				bool		attnull;
-				Datum		value = index_getattr(itup, i + 2, tupdesc, &isnull);
-				Datum		value2 = index_getattr(qtup, i + 2, tupdesc, &attnull);
-
-				if (isnull || attnull)
-				{
-					if (isnull != attnull)
-						e += 1000;
-				}
-				else
-					e += fabs(DatumGetFloat8(FunctionCall2Coll(procinfos[i + 1], collations[i + 1], value, value2)));
-			}
-
-			return w * g + AttributeDistance(e);
-		}
-	}
-
-	return g;
-}
-
 /*
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec)
+HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	Buffer		buf;
 	Page		page;
@@ -633,27 +471,11 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup,
 	Assert(HnswIsElementTuple(etup));
 
 	/* Load element */
-	HnswLoadElementFromTuple(element, etup, true, loadVec, index);
+	HnswLoadElementFromTuple(element, etup, true, loadVec);
 
 	/* Calculate distance */
 	if (distance != NULL)
-	{
+		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->vec)));
-		IndexTuple	itup = NULL;
-		Datum		value;
-
-		if (IndexRelationGetNumberOfAttributes(index) > 1)
-		{
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			itup = (IndexTuple) &etup->data;
-			value = index_getattr(itup, 1, tupdesc, &unused);
-		}
-		else
-			value = PointerGetDatum(&etup->data);
-
-		*distance = GetDistance(itup, value, *q, qtup, keyData, index, procinfos, collations);
-	}
 
 	UnlockReleaseBuffer(buf);
 }
@@ -662,24 +484,24 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, IndexTuple qtup,
  * Get the distance for a candidate
  */
 static float
-GetCandidateDistance(HnswCandidate * hc, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations)
+GetCandidateDistance(HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
 {
-	return GetDistance(hc->element->itup, hc->element->value, q, qtup, keyData, index, procinfos, collations);
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, PointerGetDatum(hc->element->vec)));
 }
 
 /*
  * Create a candidate for the entry point
  */
 HnswCandidate *
-HnswEntryCandidate(HnswElement entryPoint, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfos, Oid *collations, bool loadVec, bool inMemory)
+HnswEntryCandidate(HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	HnswCandidate *hc = palloc(sizeof(HnswCandidate));
 
 	hc->element = entryPoint;
-	if (inMemory)
+	if (index == NULL)
-		hc->distance = GetCandidateDistance(hc, q, qtup, keyData, index, procinfos, collations);
+		hc->distance = GetCandidateDistance(hc, q, procinfo, collation);
 	else
-		HnswLoadElement(hc->element, &hc->distance, &q, qtup, keyData, index, procinfos, collations, loadVec);
+		HnswLoadElement(hc->element, &hc->distance, &q, index, procinfo, collation, loadVec);
 	return hc;
 }
 
@@ -729,9 +551,9 @@ CreatePairingHeapNode(HnswCandidate * c)
  * Add to visited
  */
 static inline void
-AddToVisited(HTAB *v, HnswCandidate * hc, bool inMemory, bool *found)
+AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
 {
-	if (inMemory)
+	if (index == NULL)
 		hash_search(v, &hc->element, HASH_ENTER, found);
 	else
 	{
@@ -746,7 +568,7 @@ AddToVisited(HTAB *v, HnswCandidate * hc, bool inMemory, bool *found)
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, int m, bool loadVec, HnswElement skipElement, bool inMemory)
+HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
 {
 	ListCell   *lc2;
 
@@ -758,7 +580,7 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 	HTAB	   *v;
 
 	/* Create hash table */
-	if (inMemory)
+	if (index == NULL)
 	{
 		hash_ctl.keysize = sizeof(HnswElement *);
 		hash_ctl.entrysize = sizeof(HnswElement *);
@@ -777,7 +599,7 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
 
-		AddToVisited(v, hc, inMemory, NULL);
+		AddToVisited(v, hc, index, NULL);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -811,7 +633,7 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 			HnswCandidate *e = &neighborhood->items[i];
 			bool		visited;
 
-			AddToVisited(v, e, inMemory, &visited);
+			AddToVisited(v, e, index, &visited);
 
 			if (!visited)
 			{
@@ -819,10 +641,10 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 
 				f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
 
-				if (inMemory)
+				if (index == NULL)
-					eDistance = GetCandidateDistance(e, q, qtup, keyData, index, procinfos, collations);
+					eDistance = GetCandidateDistance(e, q, procinfo, collation);
 				else
-					HnswLoadElement(e->element, &eDistance, &q, qtup, keyData, index, procinfos, collations, loadVec);
+					HnswLoadElement(e->element, &eDistance, &q, index, procinfo, collation, inserting);
 
 				Assert(!e->element->deleted);
 
@@ -870,39 +692,11 @@ HnswSearchLayer(Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef
 	return w;
 }
 
-/*
- * Compare candidate distances
- */
-static int
-#if PG_VERSION_NUM >= 130000
-CompareCandidateDistances(const ListCell *a, const ListCell *b)
-#else
-CompareCandidateDistances(const void *a, const void *b)
-#endif
-{
-	HnswCandidate *hca = lfirst((ListCell *) a);
-	HnswCandidate *hcb = lfirst((ListCell *) b);
-
-	if (hca->distance < hcb->distance)
-		return 1;
-
-	if (hca->distance > hcb->distance)
-		return -1;
-
-	if (hca->element < hcb->element)
-		return 1;
-
-	if (hca->element > hcb->element)
-		return -1;
-
-	return 0;
-}
-
 /*
  * Calculate the distance between elements
  */
 static float
-HnswGetCachedDistance(HnswElement a, HnswElement b, int lc, Relation index, FmgrInfo **procinfos, Oid *collations)
+HnswGetDistance(HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid collation)
 {
 	/* Look for cached distance */
 	if (a->neighbors != NULL)
@@ -927,21 +721,21 @@ HnswGetCachedDistance(HnswElement a, HnswElement b, int lc, Relation index, Fmgr
 		}
 	}
 
-	return GetDistance(a->itup, a->value, b->value, b->itup, NULL, index, procinfos, collations);
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(a->vec), PointerGetDatum(b->vec)));
 }
 
 /*
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(HnswCandidate * e, List *r, int lc, Relation index, FmgrInfo **procinfos, Oid *collations)
+CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid collation)
 {
 	ListCell   *lc2;
 
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
-		float		distance = HnswGetCachedDistance(e->element, ri->element, lc, index, procinfos, collations);
+		float		distance = HnswGetDistance(e->element, ri->element, lc, procinfo, collation);
 
 		if (distance <= e->distance)
 			return false;
@@ -954,77 +748,33 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, Relation index, FmgrInfo
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oid *collations, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswCandidate * *pruned)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
 	pairingheap *wd;
-	bool		mustCalculate = !e2->neighbors[lc].closerSet;
-	List	   *added = NIL;
-	bool		removedAny = false;
 
 	if (list_length(w) <= m)
 		return w;
 
 	wd = pairingheap_allocate(CompareNearestCandidates, NULL);
 
-	/* Ensure order of candidates is deterministic for closer caching */
-	if (sortCandidates)
-		list_sort(w, CompareCandidateDistances);
-
 	while (list_length(w) > 0 && list_length(r) < m)
 	{
 		/* Assumes w is already ordered desc */
 		HnswCandidate *e = llast(w);
+		bool		closer;
 
 		w = list_delete_last(w);
 
-		/* Use previous state of r and wd to skip work when possible */
+		closer = CheckElementCloser(e, r, lc, procinfo, collation);
-		if (mustCalculate)
-			e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
-		else if (list_length(added) > 0)
-		{
-			/*
-			 * If the current candidate was closer, we only need to compare it
-			 * with the other candidates that we have added.
-			 */
-			if (e->closer)
-			{
-				e->closer = CheckElementCloser(e, added, lc, index, procinfos, collations);
 
-				if (!e->closer)
+		if (closer)
-					removedAny = true;
-			}
-			else
-			{
-				/*
-				 * If we have removed any candidates from closer, a candidate
-				 * that was not closer earlier might now be.
-				 */
-				if (removedAny)
-				{
-					e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
-					if (e->closer)
-						added = lappend(added, e);
-				}
-			}
-		}
-		else if (e == newCandidate)
-		{
-			e->closer = CheckElementCloser(e, r, lc, index, procinfos, collations);
-			if (e->closer)
-				added = lappend(added, e);
-		}
-
-		if (e->closer)
 			r = lappend(r, e);
 		else
 			pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
 	}
 
-	/* Cached value can only be used in future if sorted deterministically */
-	e2->neighbors[lc].closerSet = sortCandidates;
-
 	/* Keep pruned connections */
 	while (!pairingheap_is_empty(wd) && list_length(r) < m)
 		r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
@@ -1045,20 +795,16 @@ SelectNeighbors(List *c, int m, int lc, Relation index, FmgrInfo **procinfos, Oi
  * Find duplicate element
  */
 HnswElement
-HnswFindDuplicate(HnswElement e, Relation index)
+HnswFindDuplicate(HnswElement e)
 {
 	HnswNeighborArray *neighbors = &e->neighbors[0];
 
-	/* TODO Implement */
-	if (IndexRelationGetNumberOfAttributes(index) > 1)
-		return NULL;
-
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 
 		/* Exit early since ordered by distance */
-		if (!datumIsEqual(e->value, neighbor->element->value, false, -1))
+		if (vector_cmp_internal(e->vec, neighbor->element->vec) != 0)
 			break;
 
 		/* Check for space */
@@ -1082,11 +828,33 @@ AddConnections(HnswElement element, List *neighbors, int m, int lc)
 		a->items[a->length++] = *((HnswCandidate *) lfirst(lc2));
 }
 
+/*
+ * Compare candidate distances
+ */
+static int
+#if PG_VERSION_NUM >= 130000
+CompareCandidateDistances(const ListCell *a, const ListCell *b)
+#else
+CompareCandidateDistances(const void *a, const void *b)
+#endif
+{
+	HnswCandidate *hca = lfirst((ListCell *) a);
+	HnswCandidate *hcb = lfirst((ListCell *) b);
+
+	if (hca->distance < hcb->distance)
+		return 1;
+
+	if (hca->distance > hcb->distance)
+		return -1;
+
+	return 0;
+}
+
 /*
  * Update connections
  */
 void
-HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo **procinfos, Oid *collations, bool inMemory)
+HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
 {
 	HnswNeighborArray *currentNeighbors = &hc->element->neighbors[lc];
 
@@ -1109,20 +877,18 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		HnswCandidate *pruned = NULL;
 
 		/* Load elements on insert */
-		if (!inMemory)
+		if (index != NULL)
 		{
-			Datum		q = hc->element->value;
+			Datum		q = PointerGetDatum(hc->element->vec);
-			IndexTuple	qtup = hc->element->itup;
-			ScanKeyData *keyData = NULL;
 
 			for (int i = 0; i < currentNeighbors->length; i++)
 			{
 				HnswCandidate *hc3 = &currentNeighbors->items[i];
 
-				if (DatumGetPointer(hc3->element->value) == NULL)
+				if (hc3->element->vec == NULL)
-					HnswLoadElement(hc3->element, &hc3->distance, &q, qtup, keyData, index, procinfos, collations, true);
+					HnswLoadElement(hc3->element, &hc3->distance, &q, index, procinfo, collation, true);
 				else
-					hc3->distance = GetCandidateDistance(hc3, q, qtup, keyData, index, procinfos, collations);
+					hc3->distance = GetCandidateDistance(hc3, q, procinfo, collation);
 
 				/* Prune element if being deleted */
 				if (list_length(hc3->element->heaptids) == 0)
@@ -1137,12 +903,13 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		{
 			List	   *c = NIL;
 
-			/* Add candidates */
+			/* Add and sort candidates */
 			for (int i = 0; i < currentNeighbors->length; i++)
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);
+			list_sort(c, CompareCandidateDistances);
 
-			SelectNeighbors(c, m, lc, index, procinfos, collations, hc->element, &hc2, &pruned, true);
+			SelectNeighbors(c, m, lc, procinfo, collation, &pruned);
 
 			/* Should not happen */
 			if (pruned == NULL)
@@ -1194,15 +961,13 @@ RemoveElements(List *w, HnswElement skipElement)
  * Algorithm 1 from paper
  */
 void
-HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfos, Oid *collations, int m, int efConstruction, bool existing, bool inMemory)
+HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	Datum		q = element->value;
+	Datum		q = PointerGetDatum(element->vec);
-	IndexTuple	qtup = element->itup;
-	ScanKeyData *keyData = NULL;
 	HnswElement skipElement = existing ? element : NULL;
 
 	/* No neighbors if no entry point */
@@ -1210,13 +975,13 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, qtup, keyData, index, procinfos, collations, true, inMemory));
+	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, true));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(q, qtup, keyData, ep, 1, lc, index, procinfos, collations, m, true, skipElement, inMemory);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
 		ep = w;
 	}
 
@@ -1234,21 +999,16 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		List	   *neighbors;
 		List	   *lw;
 
-		w = HnswSearchLayer(q, qtup, keyData, ep, efConstruction, lc, index, procinfos, collations, m, true, skipElement, inMemory);
+		w = HnswSearchLayer(q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */
-		if (!inMemory)
+		if (index != NULL)
 			lw = RemoveElements(w, skipElement);
 		else
 			lw = w;
 
-		/*
+		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, NULL);
-		 * Candidates are sorted, but not deterministically. Could set
-		 * sortCandidates to true for in-memory builds to enable closer
-		 * caching, but there does not seem to be a difference in performance.
-		 */
-		neighbors = SelectNeighbors(lw, lm, lc, index, procinfos, collations, element, NULL, NULL, false);
 
 		AddConnections(element, neighbors, lm, lc);
 

src/hnswvacuum.c

@@ -62,8 +62,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 		/* Iterate over nodes */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			int			idx = 0;
 			bool		itemUpdated = false;
 
@@ -94,7 +93,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 
 				if (itemUpdated)
 				{
-					Size		etupSize = ItemIdGetLength(itemid);
+					Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
 
 					/* Mark rest as invalid */
 					for (int i = idx; i < HNSW_HEAPTIDS; i++)
@@ -195,8 +194,8 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	GenericXLogState *state;
 	int			m = vacuumstate->m;
 	int			efConstruction = vacuumstate->efConstruction;
-	FmgrInfo  **procinfos = vacuumstate->procinfos;
+	FmgrInfo   *procinfo = vacuumstate->procinfo;
-	Oid		   *collations = vacuumstate->collations;
+	Oid			collation = vacuumstate->collation;
 	BufferAccessStrategy bas = vacuumstate->bas;
 	HnswNeighborTuple ntup = vacuumstate->ntup;
 	Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
@@ -210,7 +209,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptids = NIL;
 
 	/* Add element to graph, skipping itself */
-	HnswInsertElement(element, entryPoint, index, procinfos, collations, m, efConstruction, true, false);
+	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, true);
 
 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
@@ -231,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfos, collations, element, m, true);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
 }
 
 /*
@@ -258,7 +257,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, NULL, NULL, index, vacuumstate->procinfos, vacuumstate->collations, true);
+		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
 
 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -296,7 +295,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * is outdated, this can remove connections at higher levels in
 			 * the graph until they are repaired, but this should be fine.
 			 */
-			HnswLoadElement(entryPoint, NULL, NULL, NULL, NULL, index, vacuumstate->procinfos, vacuumstate->collations, true);
+			HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -372,7 +371,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 
 			/* Create an element */
 			element = HnswInitElementFromBlock(blkno, offno);
-			HnswLoadElementFromTuple(element, etup, false, true, index);
+			HnswLoadElementFromTuple(element, etup, false, true);
 
 			elements = lappend(elements, element);
 		}
@@ -442,7 +441,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	BlockNumber insertPage = InvalidBlockNumber;
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index);
 
 	/*
 	 * Wait for index scans to complete. Scans before this point may contain
@@ -479,8 +477,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 		/* Update element and neighbors together */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			HnswNeighborTuple ntup;
 			Size		etupSize;
 			Size		ntupSize;
@@ -508,7 +505,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 				continue;
 
 			/* Calculate sizes */
-			etupSize = ItemIdGetLength(itemid);
+			etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
 			ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(etup->level, vacuumstate->m);
 
 			/* Get neighbor page */
@@ -531,18 +528,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 
 			/* Overwrite element */
 			etup->deleted = 1;
-			if (useIndexTuple)
+			MemSet(&etup->vec.x, 0, etup->vec.dim * sizeof(float));
-			{
-				IndexTuple	itup = (IndexTuple) &etup->data;
-
-				MemSet(itup, 0, IndexTupleSize(itup));
-			}
-			else
-			{
-				Vector	   *vec = (Vector *) (&etup->data);
-
-				MemSet(vec, 0, VARSIZE_ANY(vec));
-			}
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)
@@ -598,8 +584,8 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->callback_state = callback_state;
 	vacuumstate->efConstruction = HnswGetEfConstruction(index);
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
-	vacuumstate->procinfos = HnswInitProcinfos(index);
+	vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	vacuumstate->collations = index->rd_indcollation;
+	vacuumstate->collation = index->rd_indcollation[0];
 	vacuumstate->ntup = palloc0(BLCKSZ);
 	vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 												"Hnsw vacuum temporary context",
@@ -623,7 +609,6 @@ FreeVacuumState(HnswVacuumState * vacuumstate)
 {
 	hash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
-	pfree(vacuumstate->procinfos);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);
 }

src/ivfflat.h

@@ -246,6 +246,8 @@ typedef struct IvfflatScanOpaqueData
 	int			probes;
 	int			dimensions;
 	bool		first;
+	Buffer		buf;
+	ItemPointerData heaptid;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;

src/ivfscan.c

@@ -143,6 +143,10 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				bool		isnull;
 				ItemId		itemid = PageGetItemId(page, offno);
 
+				/* Skip dead tuples */
+				if (scan->ignore_killed_tuples && ItemIdIsDead(itemid))
+					continue;
+
 				itup = (IndexTuple) PageGetItem(page, itemid);
 				datum = index_getattr(itup, 1, tupdesc, &isnull);
 
@@ -157,6 +161,8 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				slot->tts_isnull[0] = false;
 				slot->tts_values[1] = PointerGetDatum(&itup->t_tid);
 				slot->tts_isnull[1] = false;
+				slot->tts_values[2] = Int32GetDatum((int) searchPage);
+				slot->tts_isnull[2] = false;
 				ExecStoreVirtualTuple(slot);
 
 				tuplesort_puttupleslot(so->sortstate, slot);
@@ -181,6 +187,55 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	tuplesort_performsort(so->sortstate);
 }
 
+/*
+ * Mark prior tuple as dead
+ */
+static void
+MarkPriorTupleDead(IndexScanDesc scan)
+{
+	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	Buffer		buf = so->buf;
+	Page		page;
+	OffsetNumber maxoffno;
+
+	/* Safety check */
+	if (!BufferIsValid(so->buf) || !ItemPointerIsValid(&so->heaptid))
+		return;
+
+	/* Only a shared locked is needed for ItemIdMarkDead */
+	LockBuffer(buf, BUFFER_LOCK_SHARE);
+	page = BufferGetPage(buf);
+	maxoffno = PageGetMaxOffsetNumber(page);
+
+	for (OffsetNumber offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
+	{
+		ItemId		itemid = PageGetItemId(page, offno);
+		IndexTuple	itup = (IndexTuple) PageGetItem(page, itemid);
+
+		/*
+		 * Find tuple. Since buffer has been pinned, tuple cannot have been
+		 * vacuumed (and heap TID reused).
+		 */
+		if (ItemPointerEquals(&itup->t_tid, &so->heaptid))
+		{
+			/*
+			 * Make sure tuple has not already been marked dead to avoid extra
+			 * WAL if wal_log_hints or data checksums enabled
+			 */
+			if (!ItemIdIsDead(itemid))
+			{
+				ItemIdMarkDead(itemid);
+				MarkBufferDirtyHint(buf, true);
+			}
+
+			break;
+		}
+	}
+
+	/* Unlock buffer */
+	LockBuffer(buf, BUFFER_LOCK_UNLOCK);
+}
+
 /*
  * Prepare for an index scan
  */
@@ -206,7 +261,9 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 		probes = lists;
 
 	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
+	so->buf = InvalidBuffer;
 	so->first = true;
+	ItemPointerSetInvalid(&so->heaptid);
 	so->probes = probes;
 	so->dimensions = dimensions;
 
@@ -217,12 +274,13 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 
 	/* Create tuple description for sorting */
 #if PG_VERSION_NUM >= 120000
-	so->tupdesc = CreateTemplateTupleDesc(2);
+	so->tupdesc = CreateTemplateTupleDesc(3);
 #else
-	so->tupdesc = CreateTemplateTupleDesc(2, false);
+	so->tupdesc = CreateTemplateTupleDesc(3, false);
 #endif
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 3, "indexblkno", INT4OID, -1, 0);
 
 	/* Prep sort */
 	so->sortstate = tuplesort_begin_heap(so->tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, work_mem, NULL, false);
@@ -254,6 +312,7 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 #endif
 
 	so->first = true;
+	ItemPointerSetInvalid(&so->heaptid);
 	pairingheap_reset(so->listQueue);
 
 	if (keys && scan->numberOfKeys > 0)
@@ -288,11 +347,6 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (scan->orderByData == NULL)
 			elog(ERROR, "cannot scan ivfflat index without order");
 
-		/* Requires MVCC-compliant snapshot as not able to pin during sorting */
-		/* https://www.postgresql.org/docs/current/index-locking.html */
-		if (!IsMVCCSnapshot(scan->xs_snapshot))
-			elog(ERROR, "non-MVCC snapshots are not supported with ivfflat");
-
 		if (scan->orderByData->sk_flags & SK_ISNULL)
 			value = PointerGetDatum(InitVector(so->dimensions));
 		else
@@ -316,10 +370,17 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (value != scan->orderByData->sk_argument)
 			pfree(DatumGetPointer(value));
 	}
+	else
+	{
+		/* Mark prior tuple as dead */
+		if (scan->kill_prior_tuple)
+			MarkPriorTupleDead(scan);
+	}
 
 	if (tuplesort_gettupleslot(so->sortstate, true, false, so->slot, NULL))
 	{
 		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
+		BlockNumber indexblkno = DatumGetInt32(slot_getattr(so->slot, 3, &so->isnull));
 
 #if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
@@ -327,6 +388,21 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		scan->xs_ctup.t_self = *heaptid;
 #endif
 
+		/* Keep track of info needed to mark tuple as dead */
+		so->heaptid = *heaptid;
+
+		/* Unpin buffer */
+		if (BufferIsValid(so->buf))
+			ReleaseBuffer(so->buf);
+
+		/*
+		 * An index scan must maintain a pin on the index page holding the
+		 * item last returned by amgettuple
+		 *
+		 * https://www.postgresql.org/docs/current/index-locking.html
+		 */
+		so->buf = ReadBuffer(scan->indexRelation, indexblkno);
+
 		scan->xs_recheckorderby = false;
 		return true;
 	}
@@ -342,6 +418,10 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
+	/* Release pin */
+	if (BufferIsValid(so->buf))
+		ReleaseBuffer(so->buf);
+
 	pairingheap_free(so->listQueue);
 	tuplesort_end(so->sortstate);
 

src/tinyint.c

@@ -0,0 +1,294 @@
+#include "postgres.h"
+
+#include <math.h>
+#include <stdint.h>
+
+#include "fmgr.h"
+#include "lib/stringinfo.h"
+#include "libpq/pqformat.h"
+#include "tinyint.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/numeric.h"
+
+/*
+ * Check if array is a vector
+ */
+static bool
+ArrayIsVector(ArrayType *a)
+{
+	return ARR_NDIM(a) == 1 && !array_contains_nulls(a);
+}
+
+/*
+ * Check if dimensions are the same
+ */
+static int
+CheckDims(ArrayType *a, ArrayType *b)
+{
+	int			dima;
+	int			dimb;
+
+	if (!ArrayIsVector(a) || !ArrayIsVector(b))
+		return 0;
+
+	dima = ARR_DIMS(a)[0];
+	dimb = ARR_DIMS(b)[0];
+
+	if (dima != dimb)
+		return 0;
+
+	return dima;
+}
+
+/*
+ * Check range
+ */
+static void
+CheckRange(long i)
+{
+	if (i < INT8_MIN || i > INT8_MAX)
+		ereport(ERROR,
+				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
+				 errmsg("value \"%ld\" is out of range for type tinyint", i)));
+}
+
+/*
+ * Convert textual representation to internal representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_in);
+Datum
+tinyint_in(PG_FUNCTION_ARGS)
+{
+	char	   *s = PG_GETARG_CSTRING(0);
+	const char *ptr = s;
+	long		i;
+	char	   *end;
+
+	/* skip leading spaces */
+	while (*ptr != '\0' && isspace((unsigned char) *ptr))
+		ptr++;
+
+	if (*ptr == '\0')
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("invalid input syntax for type tinyint: \"%s\"", s)));
+
+	i = strtol(ptr, &end, 10);
+	ptr = end;
+
+	if (i < INT8_MIN || i > INT8_MAX)
+		ereport(ERROR,
+				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
+				 errmsg("value \"%s\" is out of range for type tinyint", s)));
+
+	/* allow trailing whitespace, but not other trailing chars */
+	while (*ptr != '\0' && isspace((unsigned char) *ptr))
+		ptr++;
+
+	if (*ptr != '\0')
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("invalid input syntax for type tinyint: \"%s\"", s)));
+
+	PG_RETURN_INT8(i);
+}
+
+/*
+ * Convert internal representation to textual representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_out);
+Datum
+tinyint_out(PG_FUNCTION_ARGS)
+{
+	int8		num = PG_GETARG_INT8(0);
+	char	   *result = (char *) palloc(5);	/* sign, 3 digits, '\0' */
+
+	pg_ltoa((int32) num, result);
+	PG_RETURN_CSTRING(result);
+}
+
+/*
+ * Convert external binary representation to internal representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_recv);
+Datum
+tinyint_recv(PG_FUNCTION_ARGS)
+{
+	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
+
+	PG_RETURN_INT8((int8) pq_getmsgint(buf, sizeof(int8)));
+}
+
+/*
+ * Convert internal representation to the external binary representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_send);
+Datum
+tinyint_send(PG_FUNCTION_ARGS)
+{
+	int8		arg1 = PG_GETARG_INT8(0);
+	StringInfoData buf;
+
+	pq_begintypsend(&buf);
+	pq_sendint8(&buf, arg1);
+	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
+}
+
+/*
+ * Convert integer to tinyint
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(integer_to_tinyint);
+Datum
+integer_to_tinyint(PG_FUNCTION_ARGS)
+{
+	int32		i = PG_GETARG_INT32(0);
+
+	CheckRange(i);
+
+	PG_RETURN_INT8(i);
+}
+
+/*
+ * Convert numeric to tinyint
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(numeric_to_tinyint);
+Datum
+numeric_to_tinyint(PG_FUNCTION_ARGS)
+{
+	Numeric		num = PG_GETARG_NUMERIC(0);
+	int32		i = numeric_int4_opt_error(num, NULL);
+
+	CheckRange(i);
+
+	PG_RETURN_INT8(i);
+}
+
+/*
+ * Get the L2 distance between tinyint arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_l2_distance);
+Datum
+tinyint_l2_distance(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8    *ax = (int8 *) ARR_DATA_PTR(a);
+	int8    *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+	{
+		double		diff = ax[i] - bx[i];
+
+		distance += diff * diff;
+	}
+
+	PG_RETURN_FLOAT8(sqrt(distance));
+}
+
+/*
+ * Get the inner product of two tinyint arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_inner_product);
+Datum
+tinyint_inner_product(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8	   *ax = (int8 *) ARR_DATA_PTR(a);
+	int8	   *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+		distance += ax[i] * bx[i];
+
+	PG_RETURN_FLOAT8(distance);
+}
+
+/*
+ * Get the negative inner product of two tinyint arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_negative_inner_product);
+Datum
+tinyint_negative_inner_product(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8	   *ax = (int8 *) ARR_DATA_PTR(a);
+	int8	   *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+		distance += ax[i] * bx[i];
+
+	PG_RETURN_FLOAT8(distance * -1);
+}
+
+/*
+ * Get the cosine distance between two float2 arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_cosine_distance);
+Datum
+tinyint_cosine_distance(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8   *ax = (int8 *) ARR_DATA_PTR(a);
+	int8   *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	double		norma = 0.0;
+	double		normb = 0.0;
+	double		similarity;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+	{
+		float		axi = ax[i];
+		float		bxi = bx[i];
+
+		distance += axi * bxi;
+		norma += axi * axi;
+		normb += bxi * bxi;
+	}
+
+	/* Use sqrt(a * b) over sqrt(a) * sqrt(b) */
+	similarity = distance / sqrt(norma * 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);
+}

src/tinyint.h

@@ -0,0 +1,8 @@
+#ifndef TINYINT_H
+#define TINYINT_H
+
+#define DatumGetInt8(X) ((int8) (X))
+#define PG_GETARG_INT8(n)	 DatumGetInt8(PG_GETARG_DATUM(n))
+#define PG_RETURN_INT8(x)	 return Int8GetDatum(x)
+
+#endif

src/vector.c

@@ -89,7 +89,7 @@ CheckDim(int dim)
 }
 
 /*
- * Ensure finite element
+ * Ensure finite elements
  */
 static inline void
 CheckElement(float value)
@@ -437,18 +437,17 @@ vector_send(PG_FUNCTION_ARGS)
 
 /*
  * Convert vector to vector
- * This is needed to check the type modifier
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(vector);
 Datum
 vector(PG_FUNCTION_ARGS)
 {
-	Vector	   *vec = PG_GETARG_VECTOR_P(0);
+	Vector	   *arg = PG_GETARG_VECTOR_P(0);
 	int32		typmod = PG_GETARG_INT32(1);
 
-	CheckExpectedDim(typmod, vec->dim);
+	CheckExpectedDim(typmod, arg->dim);
 
-	PG_RETURN_POINTER(vec);
+	PG_RETURN_POINTER(arg);
 }
 
 /*
@@ -465,6 +464,7 @@ array_to_vector(PG_FUNCTION_ARGS)
 	bool		typbyval;
 	char		typalign;
 	Datum	   *elemsp;
+	bool	   *nullsp;
 	int			nelemsp;
 
 	if (ARR_NDIM(array) > 1)
@@ -478,7 +478,7 @@ array_to_vector(PG_FUNCTION_ARGS)
 				 errmsg("array must not contain nulls")));
 
 	get_typlenbyvalalign(ARR_ELEMTYPE(array), &typlen, &typbyval, &typalign);
-	deconstruct_array(array, ARR_ELEMTYPE(array), typlen, typbyval, typalign, &elemsp, NULL, &nelemsp);
+	deconstruct_array(array, ARR_ELEMTYPE(array), typlen, typbyval, typalign, &elemsp, &nullsp, &nelemsp);
 
 	CheckDim(nelemsp);
 	CheckExpectedDim(typmod, nelemsp);
@@ -512,12 +512,6 @@ array_to_vector(PG_FUNCTION_ARGS)
 				 errmsg("unsupported array type")));
 	}
 
-	/*
-	 * Free allocation from deconstruct_array. Do not free individual elements
-	 * when pass-by-reference since they point to original array.
-	 */
-	pfree(elemsp);
-
 	/* Check elements */
 	for (int i = 0; i < result->dim; i++)
 		CheckElement(result->x[i]);

test/expected/functions.out

@@ -54,85 +54,85 @@ SELECT vector_norm('[3e37,4e37]')::real;
        5e+37
 (1 row)
 
-SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]'::vector, '[3,4]');
  l2_distance 
 -------------
            5
 (1 row)
 
-SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[0,0]'::vector, '[0,1]');
  l2_distance 
 -------------
            1
 (1 row)
 
-SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l2_distance('[3e38]', '[-3e38]');
+SELECT l2_distance('[3e38]'::vector, '[-3e38]');
  l2_distance 
 -------------
     Infinity
 (1 row)
 
-SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]'::vector, '[3,4]');
  inner_product 
 ---------------
             11
 (1 row)
 
-SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT inner_product('[3e38]', '[3e38]');
+SELECT inner_product('[3e38]'::vector, '[3e38]');
  inner_product 
 ---------------
       Infinity
 (1 row)
 
-SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]'::vector, '[2,4]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,2]'::vector, '[0,0]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,1]'::vector, '[1,1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,0]'::vector, '[0,2]');
  cosine_distance 
 -----------------
                1
 (1 row)
 
-SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[3e38]', '[3e38]');
+SELECT cosine_distance('[3e38]'::vector, '[3e38]');
  cosine_distance 
 -----------------
              NaN

test/expected/tinyint.out

@@ -0,0 +1,148 @@
+SELECT '127'::tinyint;
+ tinyint 
+---------
+ 127
+(1 row)
+
+SELECT '128'::tinyint;
+ERROR:  value "128" is out of range for type tinyint
+LINE 1: SELECT '128'::tinyint;
+               ^
+SELECT '-128'::tinyint;
+ tinyint 
+---------
+ -128
+(1 row)
+
+SELECT '-129'::tinyint;
+ERROR:  value "-129" is out of range for type tinyint
+LINE 1: SELECT '-129'::tinyint;
+               ^
+SELECT ''::tinyint;
+ERROR:  invalid input syntax for type tinyint: ""
+LINE 1: SELECT ''::tinyint;
+               ^
+SELECT ' 1'::tinyint;
+ tinyint 
+---------
+ 1
+(1 row)
+
+SELECT '1 '::tinyint;
+ tinyint 
+---------
+ 1
+(1 row)
+
+SELECT '1a'::tinyint;
+ERROR:  invalid input syntax for type tinyint: "1a"
+LINE 1: SELECT '1a'::tinyint;
+               ^
+SELECT '{1,2,3}'::tinyint[];
+ tinyint 
+---------
+ {1,2,3}
+(1 row)
+
+SELECT '128'::numeric::tinyint;
+ERROR:  value "128" is out of range for type tinyint
+SELECT 'NaN'::numeric::tinyint;
+ERROR:  cannot convert NaN to integer
+SELECT l2_distance('{0,0}'::tinyint[], '{3,4}'::tinyint[]);
+ l2_distance 
+-------------
+           5
+(1 row)
+
+SELECT l2_distance('{0,0}'::tinyint[], '{0,1}'::tinyint[]);
+ l2_distance 
+-------------
+           1
+(1 row)
+
+SELECT l2_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+ l2_distance 
+-------------
+            
+(1 row)
+
+SELECT l2_distance('{3e38}'::tinyint[], '{-3e38}'::tinyint[]);
+ERROR:  invalid input syntax for type tinyint: "3e38"
+LINE 1: SELECT l2_distance('{3e38}'::tinyint[], '{-3e38}'::tinyint[]...
+                           ^
+SELECT '{0,0}'::tinyint[] <-> '{3,4}'::tinyint[];
+ ?column? 
+----------
+        5
+(1 row)
+
+SELECT inner_product('{1,2}'::tinyint[], '{3,4}'::tinyint[]);
+ inner_product 
+---------------
+            11
+(1 row)
+
+SELECT inner_product('{1,2}'::tinyint[], '{3}'::tinyint[]);
+ inner_product 
+---------------
+              
+(1 row)
+
+SELECT inner_product('{127}'::tinyint[], '{127}'::tinyint[]);
+ inner_product 
+---------------
+         16129
+(1 row)
+
+SELECT '{1,2}'::tinyint[] <#> '{3,4}'::tinyint[];
+ ?column? 
+----------
+      -11
+(1 row)
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{2,4}'::tinyint[]);
+ cosine_distance 
+-----------------
+               0
+(1 row)
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{0,0}'::tinyint[]);
+ cosine_distance 
+-----------------
+             NaN
+(1 row)
+
+SELECT cosine_distance('{1,1}'::tinyint[], '{1,1}'::tinyint[]);
+ cosine_distance 
+-----------------
+               0
+(1 row)
+
+SELECT cosine_distance('{1,0}'::tinyint[], '{0,2}'::tinyint[]);
+ cosine_distance 
+-----------------
+               1
+(1 row)
+
+SELECT cosine_distance('{1,1}'::tinyint[], '{-1,-1}'::tinyint[]);
+ cosine_distance 
+-----------------
+               2
+(1 row)
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+ cosine_distance 
+-----------------
+                
+(1 row)
+
+SELECT cosine_distance('{3e38}'::tinyint[], '{3e38}'::tinyint[]);
+ERROR:  invalid input syntax for type tinyint: "3e38"
+LINE 1: SELECT cosine_distance('{3e38}'::tinyint[], '{3e38}'::tinyin...
+                               ^
+SELECT '{1,2}'::tinyint[] <=> '{2,4}'::tinyint[];
+ ?column? 
+----------
+        0
+(1 row)
+

test/sql/functions.sql

@@ -13,24 +13,24 @@ SELECT vector_norm('[3,4]');
 SELECT vector_norm('[0,1]');
 SELECT vector_norm('[3e37,4e37]')::real;
 
-SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]'::vector, '[3,4]');
-SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[0,0]'::vector, '[0,1]');
-SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[1,2]'::vector, '[3]');
-SELECT l2_distance('[3e38]', '[-3e38]');
+SELECT l2_distance('[3e38]'::vector, '[-3e38]');
 
-SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]'::vector, '[3,4]');
-SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[1,2]'::vector, '[3]');
-SELECT inner_product('[3e38]', '[3e38]');
+SELECT inner_product('[3e38]'::vector, '[3e38]');
 
-SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]'::vector, '[2,4]');
-SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,2]'::vector, '[0,0]');
-SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,1]'::vector, '[1,1]');
-SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,0]'::vector, '[0,2]');
-SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
-SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,2]'::vector, '[3]');
-SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
-SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
-SELECT cosine_distance('[3e38]', '[3e38]');
+SELECT cosine_distance('[3e38]'::vector, '[3e38]');
 
 SELECT l1_distance('[0,0]', '[3,4]');
 SELECT l1_distance('[0,0]', '[0,1]');

test/sql/tinyint.sql

@@ -0,0 +1,34 @@
+SELECT '127'::tinyint;
+SELECT '128'::tinyint;
+SELECT '-128'::tinyint;
+SELECT '-129'::tinyint;
+
+SELECT ''::tinyint;
+SELECT ' 1'::tinyint;
+SELECT '1 '::tinyint;
+SELECT '1a'::tinyint;
+
+SELECT '{1,2,3}'::tinyint[];
+
+SELECT '128'::numeric::tinyint;
+SELECT 'NaN'::numeric::tinyint;
+
+SELECT l2_distance('{0,0}'::tinyint[], '{3,4}'::tinyint[]);
+SELECT l2_distance('{0,0}'::tinyint[], '{0,1}'::tinyint[]);
+SELECT l2_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+SELECT l2_distance('{3e38}'::tinyint[], '{-3e38}'::tinyint[]);
+SELECT '{0,0}'::tinyint[] <-> '{3,4}'::tinyint[];
+
+SELECT inner_product('{1,2}'::tinyint[], '{3,4}'::tinyint[]);
+SELECT inner_product('{1,2}'::tinyint[], '{3}'::tinyint[]);
+SELECT inner_product('{127}'::tinyint[], '{127}'::tinyint[]);
+SELECT '{1,2}'::tinyint[] <#> '{3,4}'::tinyint[];
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{2,4}'::tinyint[]);
+SELECT cosine_distance('{1,2}'::tinyint[], '{0,0}'::tinyint[]);
+SELECT cosine_distance('{1,1}'::tinyint[], '{1,1}'::tinyint[]);
+SELECT cosine_distance('{1,0}'::tinyint[], '{0,2}'::tinyint[]);
+SELECT cosine_distance('{1,1}'::tinyint[], '{-1,-1}'::tinyint[]);
+SELECT cosine_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+SELECT cosine_distance('{3e38}'::tinyint[], '{3e38}'::tinyint[]);
+SELECT '{1,2}'::tinyint[] <=> '{2,4}'::tinyint[];

test/t/019_hnsw_filtering.pl

@@ -1,107 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @cs = ();
-my @expected;
-my $limit = 20;
-my $dim = 3;
-my $array_sql = join(",", ('random()') x $dim);
-my $nc = 50;
-
-sub test_recall
-{
-	my ($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 WHERE c = $cs[0] ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Cond/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT i FROM tst WHERE c = $cs[$i] 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 vector($dim), c int8);");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 20000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, rand());
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-	push(@cs, int(rand() * $nc));
-}
-
-# Get exact results
-@expected = ();
-for my $i (0 .. $#queries)
-{
-	my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <-> '$queries[$i]' LIMIT $limit;");
-	push(@expected, $res);
-}
-
-# Add index
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c);");
-
-# Test recall
-test_recall(0.99, '<->');
-
-# Test vacuum
-$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
-$node->safe_psql("postgres", "VACUUM tst;");
-
-# Test columns
-my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_l2_ops);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c);");
-like($stderr, qr/index cannot have more than two columns/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, v vector_l2_ops);");
-like($stderr, qr/column 2 cannot be a vector/);
-
-done_testing();

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat and hnsw access methods'
-default_version = '0.5.1'
+default_version = '0.5.0'
 module_pathname = '$libdir/vector'
 relocatable = true