Repository: spark Updated Branches: refs/heads/master d7f2c1986 -> 5b8b324f3
[SPARK-6303][SQL] Remove unnecessary Average in GeneratedAggregate Because `Average` is a `PartialAggregate`, we never get a `Average` node when reaching `HashAggregation` to prepare `GeneratedAggregate`. That is why in SQLQuerySuite there is already a test for `avg` with codegen. And it works. But we can find a case in `GeneratedAggregate` to deal with `Average`. Based on the above, we actually never execute this case. So we can remove this case from `GeneratedAggregate`. Author: Liang-Chi Hsieh <vii...@gmail.com> Closes #4996 from viirya/add_average_codegened and squashes the following commits: 621c12f [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into add_average_codegened 368cfbc [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into add_average_codegened 74926d1 [Liang-Chi Hsieh] Add Average in canBeCodeGened lists. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/5b8b324f Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/5b8b324f Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/5b8b324f Branch: refs/heads/master Commit: 5b8b324f33e857b95de65031334846a7ca26fa60 Parents: d7f2c19 Author: Liang-Chi Hsieh <vii...@gmail.com> Authored: Mon Apr 13 18:15:29 2015 -0700 Committer: Michael Armbrust <mich...@databricks.com> Committed: Mon Apr 13 18:15:29 2015 -0700 ---------------------------------------------------------------------- .../sql/execution/GeneratedAggregate.scala | 45 -------------------- 1 file changed, 45 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/5b8b324f/sql/core/src/main/scala/org/apache/spark/sql/execution/GeneratedAggregate.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/GeneratedAggregate.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/GeneratedAggregate.scala index 95176e4..b510cf0 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/GeneratedAggregate.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/GeneratedAggregate.scala @@ -153,51 +153,6 @@ case class GeneratedAggregate( AggregateEvaluation(currentSum :: Nil, initialValue :: Nil, updateFunction :: Nil, result) - case a @ Average(expr) => - val calcType = - expr.dataType match { - case DecimalType.Fixed(_, _) => - DecimalType.Unlimited - case _ => - expr.dataType - } - - val currentCount = AttributeReference("currentCount", LongType, nullable = false)() - val currentSum = AttributeReference("currentSum", calcType, nullable = false)() - val initialCount = Literal(0L) - val initialSum = Cast(Literal(0L), calcType) - - // If we're evaluating UnscaledValue(x), we can do Count on x directly, since its - // UnscaledValue will be null if and only if x is null; helps with Average on decimals - val toCount = expr match { - case UnscaledValue(e) => e - case _ => expr - } - - val updateCount = If(IsNotNull(toCount), Add(currentCount, Literal(1L)), currentCount) - val updateSum = Coalesce(Add(Cast(expr, calcType), currentSum) :: currentSum :: Nil) - - val result = - expr.dataType match { - case DecimalType.Fixed(_, _) => - If(EqualTo(currentCount, Literal(0L)), - Literal.create(null, a.dataType), - Cast(Divide( - Cast(currentSum, DecimalType.Unlimited), - Cast(currentCount, DecimalType.Unlimited)), a.dataType)) - case _ => - If(EqualTo(currentCount, Literal(0L)), - Literal.create(null, a.dataType), - Divide(Cast(currentSum, a.dataType), Cast(currentCount, a.dataType))) - } - - AggregateEvaluation( - currentCount :: currentSum :: Nil, - initialCount :: initialSum :: Nil, - updateCount :: updateSum :: Nil, - result - ) - case m @ Max(expr) => val currentMax = AttributeReference("currentMax", expr.dataType, nullable = true)() val initialValue = Literal.create(null, expr.dataType) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
