lgbo-ustc commented on issue #7311:
URL:
https://github.com/apache/incubator-gluten/issues/7311#issuecomment-2369991391
Some example queries
```sql
select n_regionkey, count(distinct(n_name)), sum(distinct(n_nationkey)) from
tpch_pq.nation group by n_regionkey with cube;
```
```
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[n_regionkey#45L, spark_grouping_id#44L],
functions=[count(spark_catalog.tpch_pq.nation.n_name#47),
sum(spark_catalog.tpch_pq.nation.n_nationkey#48L)])
+- Exchange hashpartitioning(n_regionkey#45L, spark_grouping_id#44L, 5),
ENSURE_REQUIREMENTS, [plan_id=273]
+- HashAggregate(keys=[n_regionkey#45L, spark_grouping_id#44L],
functions=[partial_count(spark_catalog.tpch_pq.nation.n_name#47) FILTER (WHERE
(gid#46 = 1)), partial_sum(spark_catalog.tpch_pq.nation.n_nationkey#48L) FILTER
(WHERE (gid#46 = 2))])
+- HashAggregate(keys=[n_regionkey#45L, spark_grouping_id#44L,
spark_catalog.tpch_pq.nation.n_name#47,
spark_catalog.tpch_pq.nation.n_nationkey#48L, gid#46], functions=[])
+- Exchange hashpartitioning(n_regionkey#45L,
spark_grouping_id#44L, spark_catalog.tpch_pq.nation.n_name#47,
spark_catalog.tpch_pq.nation.n_nationkey#48L, gid#46, 5), ENSURE_REQUIREMENTS,
[plan_id=269]
+- HashAggregate(keys=[n_regionkey#45L,
spark_grouping_id#44L, spark_catalog.tpch_pq.nation.n_name#47,
spark_catalog.tpch_pq.nation.n_nationkey#48L, gid#46], functions=[])
+- Expand [[n_regionkey#45L, spark_grouping_id#44L,
n_name#1, null, 1], [n_regionkey#45L, spark_grouping_id#44L, null,
n_nationkey#0L, 2]], [n_regionkey#45L, spark_grouping_id#44L,
spark_catalog.tpch_pq.nation.n_name#47,
spark_catalog.tpch_pq.nation.n_nationkey#48L, gid#46]
+- Expand [[n_nationkey#0L, n_name#1, n_regionkey#2L,
0], [n_nationkey#0L, n_name#1, null, 1]], [n_nationkey#0L, n_name#1,
n_regionkey#45L, spark_grouping_id#44L]
+- FileScan parquet
tpch_pq.nation[n_nationkey#0L,n_name#1,n_regionkey#2L] Batched: true,
DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1
paths)[file:/home/workspace/docker/local_gluten/tpch_pq_data/nat...,
PartitionFilters: [], PushedFilters: [], ReadSchema:
struct<n_nationkey:bigint,n_name:string,n_regionkey:bigint>
```
```sql
select n_regionkey, count(distinct(n_name)), sum(distinct(n_nationkey)) from
tpch_pq.nation group by n_regionkey
```
```
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[n_regionkey#2L],
functions=[count(spark_catalog.tpch_pq.nation.n_name#65),
sum(spark_catalog.tpch_pq.nation.n_nationkey#66L)])
+- Exchange hashpartitioning(n_regionkey#2L, 5), ENSURE_REQUIREMENTS,
[plan_id=310]
+- HashAggregate(keys=[n_regionkey#2L],
functions=[partial_count(spark_catalog.tpch_pq.nation.n_name#65) FILTER (WHERE
(gid#64 = 1)), partial_sum(spark_catalog.tpch_pq.nation.n_nationkey#66L) FILTER
(WHERE (gid#64 = 2))])
+- HashAggregate(keys=[n_regionkey#2L,
spark_catalog.tpch_pq.nation.n_name#65,
spark_catalog.tpch_pq.nation.n_nationkey#66L, gid#64], functions=[])
+- Exchange hashpartitioning(n_regionkey#2L,
spark_catalog.tpch_pq.nation.n_name#65,
spark_catalog.tpch_pq.nation.n_nationkey#66L, gid#64, 5), ENSURE_REQUIREMENTS,
[plan_id=306]
+- HashAggregate(keys=[n_regionkey#2L,
spark_catalog.tpch_pq.nation.n_name#65,
spark_catalog.tpch_pq.nation.n_nationkey#66L, gid#64], functions=[])
+- Expand [[n_regionkey#2L, n_name#1, null, 1],
[n_regionkey#2L, null, n_nationkey#0L, 2]], [n_regionkey#2L,
spark_catalog.tpch_pq.nation.n_name#65,
spark_catalog.tpch_pq.nation.n_nationkey#66L, gid#64]
+- FileScan parquet
tpch_pq.nation[n_nationkey#0L,n_name#1,n_regionkey#2L] Batched: true,
DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1
paths)[file:/home/workspace/docker/local_gluten/tpch_pq_data/nat...,
PartitionFilters: [], PushedFilters: [], ReadSchema:
struct<n_nationkey:bigint,n_name:string,n_regionkey:bigint>
```
```sql
select n_regionkey, count(distinct(n_name)) from tpch_pq.nation group by
n_regionkey
```
```
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[n_regionkey#2L], functions=[count(distinct n_name#1)])
+- Exchange hashpartitioning(n_regionkey#2L, 5), ENSURE_REQUIREMENTS,
[plan_id=342]
+- HashAggregate(keys=[n_regionkey#2L],
functions=[partial_count(distinct n_name#1)])
+- HashAggregate(keys=[n_regionkey#2L, n_name#1], functions=[])
+- Exchange hashpartitioning(n_regionkey#2L, n_name#1, 5),
ENSURE_REQUIREMENTS, [plan_id=338]
+- HashAggregate(keys=[n_regionkey#2L, n_name#1],
functions=[])
+- FileScan parquet
tpch_pq.nation[n_name#1,n_regionkey#2L] Batched: true, DataFilters: [], Format:
Parquet, Location: InMemoryFileIndex(1
paths)[file:/home/workspace/docker/local_gluten/tpch_pq_data/nat...,
PartitionFilters: [], PushedFilters: [], ReadSchema:
struct<n_name:string,n_regionkey:bigint>
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
