Skip to content

Commit

Permalink
Initial benchmark
Browse files Browse the repository at this point in the history
  • Loading branch information
mwiewior committed Dec 1, 2024
1 parent f15b9ef commit dd1a7ea
Show file tree
Hide file tree
Showing 5 changed files with 967 additions and 0 deletions.
18 changes: 18 additions & 0 deletions benchmark/queries/0-1.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
SET sequila.prefer_interval_join TO true;
SET datafusion.execution.target_partitions=1;
SET sequila.interval_join_algorithm TO coitrees;
SET datafusion.optimizer.repartition_joins TO false;
SET datafusion.execution.coalesce_batches TO false;

CREATE EXTERNAL TABLE a
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/chainRn4/*parquet';

CREATE EXTERNAL TABLE b
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/fBrain-DS14718/*parquet';

select count(1) from a join b
on a.contig = b.contig
and a.pos_end > b.pos_start
and a.pos_start < b.pos_end;
18 changes: 18 additions & 0 deletions benchmark/queries/0-3.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
SET sequila.prefer_interval_join TO true;
SET datafusion.execution.target_partitions=1;
SET sequila.interval_join_algorithm TO coitrees;
SET datafusion.optimizer.repartition_joins TO false;
SET datafusion.execution.coalesce_batches TO false;

CREATE EXTERNAL TABLE a
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/chainRn4/*parquet';

CREATE EXTERNAL TABLE b
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/chainOrnAna1/*parquet';

select count(1) from a join b
on a.contig = b.contig
and a.pos_end > b.pos_start
and a.pos_start < b.pos_end;
18 changes: 18 additions & 0 deletions benchmark/queries/0-8.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
SET sequila.prefer_interval_join TO true;
SET datafusion.execution.target_partitions=1;
SET sequila.interval_join_algorithm TO coitrees;
SET datafusion.optimizer.repartition_joins TO false;
SET datafusion.execution.coalesce_batches TO false;

CREATE EXTERNAL TABLE a
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/chainRn4/*parquet';

CREATE EXTERNAL TABLE b
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/ex-rna/*parquet';

select count(1) from a join b
on a.contig = b.contig
and a.pos_end > b.pos_start
and a.pos_start < b.pos_end;
18 changes: 18 additions & 0 deletions benchmark/queries/7-8.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
SET sequila.prefer_interval_join TO true;
SET datafusion.execution.target_partitions=1;
SET sequila.interval_join_algorithm TO coitrees;
SET datafusion.optimizer.repartition_joins TO false;
SET datafusion.execution.coalesce_batches TO false;

CREATE EXTERNAL TABLE a
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/ex-anno/*parquet';

CREATE EXTERNAL TABLE b
STORED AS PARQUET
LOCATION '/Users/mwiewior/research/git/openstack-bdg-runners/ansible/roles/gha_runner/files/databio/ex-rna/*parquet';

select count(1) from a join b
on a.contig = b.contig
and a.pos_end > b.pos_start
and a.pos_start < b.pos_end;
Loading

0 comments on commit dd1a7ea

Please sign in to comment.