Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/17436#discussion_r151725539
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala
---
@@ -75,9 +77,14 @@ class VectorizedHashMapGenerator(
}
}.mkString("\n").concat(";")
+ val columnVector = if (!conf.offHeapColumnVectorEnabled) {
+ "OnHeapColumnVector"
+ } else {
+ "OffHeapColumnVector"
+ }
s"""
- | private
org.apache.spark.sql.execution.vectorized.OnHeapColumnVector[] batchVectors;
- | private
org.apache.spark.sql.execution.vectorized.OnHeapColumnVector[] bufferVectors;
--- End diff --
I see. `"spark.sql.codegen.aggregate.map.vectorized.enable" = true` only in
benchmark or test cases.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
