Github user hvanhovell commented on a diff in the pull request:
https://github.com/apache/spark/pull/18958#discussion_r133421918
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala
---
@@ -89,14 +91,23 @@ class VectorizedHashMapGenerator(
| $generatedAggBufferSchema
|
| public $generatedClassName() {
- | batch =
org.apache.spark.sql.execution.vectorized.ColumnarBatch.allocate(schema,
- | org.apache.spark.memory.MemoryMode.ON_HEAP, capacity);
- | // TODO: Possibly generate this projection in HashAggregate
directly
- | aggregateBufferBatch =
org.apache.spark.sql.execution.vectorized.ColumnarBatch.allocate(
- | aggregateBufferSchema,
org.apache.spark.memory.MemoryMode.ON_HEAP, capacity);
- | for (int i = 0 ; i < aggregateBufferBatch.numCols(); i++) {
- | aggregateBufferBatch.setColumn(i,
batch.column(i+${groupingKeys.length}));
+ | batchVectors = new org.apache.spark.sql.execution.vectorized
+ | .OnHeapColumnVector[schema.fields().length];
+ | for (int i = 0; i < schema.fields().length; i++) {
+ | batchVectors[i] = new
org.apache.spark.sql.execution.vectorized.OnHeapColumnVector(
+ | capacity, schema.fields()[i].dataType());
+ | }
+ | batch = new
org.apache.spark.sql.execution.vectorized.ColumnarBatch(
+ | schema, batchVectors, capacity);
+ |
+ | bufferVectors = new org.apache.spark.sql.execution.vectorized
+ | .OnHeapColumnVector[aggregateBufferSchema.fields().length];
+ | for (int i = 0; i < aggregateBufferSchema.fields().length;
i++) {
+ | bufferVectors[i] = batchVectors[i + ${groupingKeys.length}];
| }
+ | // TODO: Possibly generate this projection in HashAggregate
directly
--- End diff --
Can you elaborate?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
