mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 20:15:46 +08:00
Compare commits
4 Commits
ivfflat-st
...
tinyint
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d977caa47d | ||
|
|
cc87960109 | ||
|
|
c6d1d8bc2c | ||
|
|
4914511cf6 |
8
.github/workflows/build.yml
vendored
8
.github/workflows/build.yml
vendored
@@ -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
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
## 0.5.1 (2023-10-10)
|
||||
## 0.5.1 (unreleased)
|
||||
|
||||
- Improved performance of HNSW index builds
|
||||
- Added check for MVCC-compliant snapshot for index scans
|
||||
- Added check for MVCC-compliant snapshot for HNSW index scans
|
||||
- Improved performance of index scans for IVFFlat after updates and deletes
|
||||
|
||||
## 0.5.0 (2023-08-28)
|
||||
|
||||
|
||||
@@ -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"
|
||||
}
|
||||
},
|
||||
|
||||
6
Makefile
6
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
|
||||
HEADERS = src/vector.h
|
||||
OBJS = src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/tinyint.o src/vector.o
|
||||
HEADERS = src/tinyint.h src/vector.h
|
||||
|
||||
TESTS = $(wildcard test/sql/*.sql)
|
||||
REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))
|
||||
|
||||
@@ -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
|
||||
HEADERS = src\vector.h
|
||||
OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\tinyint.obj src\vector.obj
|
||||
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)
|
||||
@@ -56,7 +56,7 @@ install:
|
||||
copy $(EXTENSION).control "$(SHAREDIR)\extension"
|
||||
copy sql\$(EXTENSION)--*.sql "$(SHAREDIR)\extension"
|
||||
mkdir "$(INCLUDEDIR_SERVER)\extension\$(EXTENSION)"
|
||||
copy $(HEADERS) "$(INCLUDEDIR_SERVER)\extension\$(EXTENSION)"
|
||||
for %f in ($(HEADERS)) do copy %f "$(INCLUDEDIR_SERVER)\extension\$(EXTENSION)"
|
||||
|
||||
installcheck:
|
||||
"$(BINDIR)\pg_regress" --bindir="$(BINDIR)" $(REGRESS_OPTS) $(REGRESS)
|
||||
|
||||
@@ -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
|
||||
@@ -509,7 +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
|
||||
@@ -530,7 +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 .
|
||||
```
|
||||
|
||||
@@ -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 = '<=>'
|
||||
);
|
||||
|
||||
@@ -290,3 +290,68 @@ CREATE OPERATOR CLASS vector_cosine_ops
|
||||
OPERATOR 1 <=> (vector, vector) FOR ORDER BY float_ops,
|
||||
FUNCTION 1 vector_negative_inner_product(vector, vector),
|
||||
FUNCTION 2 vector_norm(vector);
|
||||
|
||||
-- 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 = '<=>'
|
||||
);
|
||||
|
||||
@@ -112,13 +112,11 @@ typedef struct HnswCandidate
|
||||
{
|
||||
HnswElement element;
|
||||
float distance;
|
||||
bool closer;
|
||||
} HnswCandidate;
|
||||
|
||||
typedef struct HnswNeighborArray
|
||||
{
|
||||
int length;
|
||||
bool closerSet;
|
||||
HnswCandidate *items;
|
||||
} HnswNeighborArray;
|
||||
|
||||
|
||||
115
src/hnswutils.c
115
src/hnswutils.c
@@ -139,7 +139,6 @@ HnswInitNeighbors(HnswElement element, int m)
|
||||
a = &element->neighbors[lc];
|
||||
a->length = 0;
|
||||
a->items = palloc(sizeof(HnswCandidate) * lm);
|
||||
a->closerSet = false;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -693,34 +692,6 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
|
||||
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
|
||||
*/
|
||||
@@ -777,77 +748,33 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
|
||||
* Algorithm 4 from paper
|
||||
*/
|
||||
static List *
|
||||
SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, 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 */
|
||||
if (mustCalculate)
|
||||
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
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, procinfo, collation);
|
||||
closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
|
||||
if (!e->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, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
}
|
||||
}
|
||||
else if (e == newCandidate)
|
||||
{
|
||||
e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
|
||||
if (e->closer)
|
||||
if (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);
|
||||
@@ -901,6 +828,28 @@ 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
|
||||
*/
|
||||
@@ -954,12 +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, ¤tNeighbors->items[i]);
|
||||
c = lappend(c, &hc2);
|
||||
list_sort(c, CompareCandidateDistances);
|
||||
|
||||
SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);
|
||||
SelectNeighbors(c, m, lc, procinfo, collation, &pruned);
|
||||
|
||||
/* Should not happen */
|
||||
if (pruned == NULL)
|
||||
@@ -1058,12 +1008,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
|
||||
else
|
||||
lw = w;
|
||||
|
||||
/*
|
||||
* 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, procinfo, collation, element, NULL, NULL, false);
|
||||
neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, NULL);
|
||||
|
||||
AddConnections(element, neighbors, lm, lc);
|
||||
|
||||
|
||||
@@ -287,7 +287,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
|
||||
#else
|
||||
TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc);
|
||||
#endif
|
||||
TupleDesc tupdesc = IvfflatTupleDesc(index);
|
||||
TupleDesc tupdesc = RelationGetDescr(index);
|
||||
|
||||
UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
|
||||
|
||||
@@ -339,8 +339,6 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
|
||||
/* Set the start and insert pages */
|
||||
IvfflatUpdateList(index, buildstate->listInfo[i], insertPage, InvalidBlockNumber, startPage, forkNum);
|
||||
}
|
||||
|
||||
FreeTupleDesc(tupdesc);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@@ -246,6 +246,8 @@ typedef struct IvfflatScanOpaqueData
|
||||
int probes;
|
||||
int dimensions;
|
||||
bool first;
|
||||
Buffer buf;
|
||||
ItemPointerData heaptid;
|
||||
|
||||
/* Sorting */
|
||||
Tuplesortstate *sortstate;
|
||||
@@ -287,7 +289,6 @@ void IvfflatInitPage(Buffer buf, Page page);
|
||||
void IvfflatInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
|
||||
void IvfflatInit(void);
|
||||
PGDLLEXPORT void IvfflatParallelBuildMain(dsm_segment *seg, shm_toc *toc);
|
||||
TupleDesc IvfflatTupleDesc(Relation index);
|
||||
|
||||
/* Index access methods */
|
||||
IndexBuildResult *ivfflatbuild(Relation heap, Relation index, IndexInfo *indexInfo);
|
||||
|
||||
@@ -94,7 +94,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
|
||||
originalInsertPage = insertPage;
|
||||
|
||||
/* Form tuple */
|
||||
itup = index_form_tuple(IvfflatTupleDesc(index), &value, isnull);
|
||||
itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
|
||||
itup->t_tid = *heap_tid;
|
||||
|
||||
/* Get tuple size */
|
||||
|
||||
@@ -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);
|
||||
|
||||
|
||||
@@ -4,10 +4,6 @@
|
||||
#include "storage/bufmgr.h"
|
||||
#include "vector.h"
|
||||
|
||||
#if PG_VERSION_NUM < 130000
|
||||
#define TYPSTORAGE_PLAIN 'p'
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Allocate a vector array
|
||||
*/
|
||||
@@ -242,17 +238,3 @@ IvfflatUpdateList(Relation index, ListInfo listInfo,
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Get the tuple descriptor
|
||||
*/
|
||||
TupleDesc
|
||||
IvfflatTupleDesc(Relation index)
|
||||
{
|
||||
TupleDesc tupdesc = CreateTupleDescCopyConstr(RelationGetDescr(index));
|
||||
|
||||
/* Prevent compression */
|
||||
TupleDescAttr(tupdesc, 0)->attstorage = TYPSTORAGE_PLAIN;
|
||||
|
||||
return tupdesc;
|
||||
}
|
||||
|
||||
294
src/tinyint.c
Normal file
294
src/tinyint.c
Normal file
@@ -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);
|
||||
}
|
||||
8
src/tinyint.h
Normal file
8
src/tinyint.h
Normal file
@@ -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
|
||||
@@ -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
|
||||
|
||||
148
test/expected/tinyint.out
Normal file
148
test/expected/tinyint.out
Normal file
@@ -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)
|
||||
|
||||
@@ -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]', '[0,1]');
|
||||
SELECT l2_distance('[1,2]', '[3]');
|
||||
SELECT l2_distance('[3e38]', '[-3e38]');
|
||||
SELECT l2_distance('[0,0]'::vector, '[3,4]');
|
||||
SELECT l2_distance('[0,0]'::vector, '[0,1]');
|
||||
SELECT l2_distance('[1,2]'::vector, '[3]');
|
||||
SELECT l2_distance('[3e38]'::vector, '[-3e38]');
|
||||
|
||||
SELECT inner_product('[1,2]', '[3,4]');
|
||||
SELECT inner_product('[1,2]', '[3]');
|
||||
SELECT inner_product('[3e38]', '[3e38]');
|
||||
SELECT inner_product('[1,2]'::vector, '[3,4]');
|
||||
SELECT inner_product('[1,2]'::vector, '[3]');
|
||||
SELECT inner_product('[3e38]'::vector, '[3e38]');
|
||||
|
||||
SELECT cosine_distance('[1,2]', '[2,4]');
|
||||
SELECT cosine_distance('[1,2]', '[0,0]');
|
||||
SELECT cosine_distance('[1,1]', '[1,1]');
|
||||
SELECT cosine_distance('[1,0]', '[0,2]');
|
||||
SELECT cosine_distance('[1,1]', '[-1,-1]');
|
||||
SELECT cosine_distance('[1,2]', '[3]');
|
||||
SELECT cosine_distance('[1,1]', '[1.1,1.1]');
|
||||
SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
|
||||
SELECT cosine_distance('[3e38]', '[3e38]');
|
||||
SELECT cosine_distance('[1,2]'::vector, '[2,4]');
|
||||
SELECT cosine_distance('[1,2]'::vector, '[0,0]');
|
||||
SELECT cosine_distance('[1,1]'::vector, '[1,1]');
|
||||
SELECT cosine_distance('[1,0]'::vector, '[0,2]');
|
||||
SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
|
||||
SELECT cosine_distance('[1,2]'::vector, '[3]');
|
||||
SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
|
||||
SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
|
||||
SELECT cosine_distance('[3e38]'::vector, '[3e38]');
|
||||
|
||||
SELECT l1_distance('[0,0]', '[3,4]');
|
||||
SELECT l1_distance('[0,0]', '[0,1]');
|
||||
|
||||
34
test/sql/tinyint.sql
Normal file
34
test/sql/tinyint.sql
Normal file
@@ -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[];
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user