Parth Chandra created SPARK-38254:
-------------------------------------
Summary: Improve vectorized loop for Packed encodings
Key: SPARK-38254
URL: https://issues.apache.org/jira/browse/SPARK-38254
Project: Spark
Issue Type: Improvement
Components: SQL
Affects Versions: 3.2.1
Reporter: Parth Chandra
In
[https://github.com/apache/spark/blob/439975590cf4f21c2a548a2ac6231eb234e1a2f3/sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedRleValuesReader.java#L239]
the vectorized reader is called one row at a time instead of calling multiple
rows at a time. This loses the benefit of a vectorized reader and should be
improved.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
