jackylee-ch commented on code in PR #8967: URL: https://github.com/apache/incubator-gluten/pull/8967#discussion_r1991622188
########## backends-velox/src/main/scala/org/apache/gluten/extension/HashAggregateIgnoreNullKeysRule.scala: ########## @@ -0,0 +1,89 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.gluten.extension + +import org.apache.gluten.config.VeloxConfig +import org.apache.gluten.execution._ + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.catalyst.plans.Inner +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.execution.adaptive.ShuffleQueryStageExec +import org.apache.spark.sql.execution.exchange.ShuffleExchangeLike +import org.apache.spark.sql.execution.joins.BaseJoinExec + +/** + * To identify aggregates that the groupby key is used as inner join keys. In this case, we can set + * ignoreNullKeys to true when convert to velox's AggregateNode. + */ +case class HashAggregateIgnoreNullKeysRule(session: SparkSession) extends Rule[SparkPlan] { + override def apply(plan: SparkPlan): SparkPlan = { + if ( + !session.conf.get(VeloxConfig.VELOX_PROPAGATE_IGNORE_NULL_KEYS_ENABLED.key, "true").toBoolean Review Comment: nit: use `VeloxConfig.get.enablePropagateIgnoreNullKeys` ########## backends-velox/src/main/scala/org/apache/gluten/extension/HashAggregateIgnoreNullKeysRule.scala: ########## @@ -0,0 +1,89 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.gluten.extension + +import org.apache.gluten.config.VeloxConfig +import org.apache.gluten.execution._ + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.catalyst.plans.Inner +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.execution.adaptive.ShuffleQueryStageExec +import org.apache.spark.sql.execution.exchange.ShuffleExchangeLike +import org.apache.spark.sql.execution.joins.BaseJoinExec + +/** + * To identify aggregates that the groupby key is used as inner join keys. In this case, we can set + * ignoreNullKeys to true when convert to velox's AggregateNode. + */ +case class HashAggregateIgnoreNullKeysRule(session: SparkSession) extends Rule[SparkPlan] { + override def apply(plan: SparkPlan): SparkPlan = { + if ( + !session.conf.get(VeloxConfig.VELOX_PROPAGATE_IGNORE_NULL_KEYS_ENABLED.key, "true").toBoolean + ) { + return plan + } + plan.transformUp { + case join: BaseJoinExec if join.joinType == Inner => + val newLeftChild = setIgnoreKeysIfAggregateOnJoinKeys(join.left, join.leftKeys) + val newRightChild = setIgnoreKeysIfAggregateOnJoinKeys(join.right, join.rightKeys) + if (!newLeftChild.fastEquals(join.left) || !newRightChild.fastEquals(join.right)) { + join.withNewChildren(Seq(newLeftChild, newRightChild)) + } else { + join + } + case p => p + } + } + + private def setIgnoreKeysIfAggregateOnJoinKeys( + plan: SparkPlan, + joinKeys: Seq[Expression]): SparkPlan = { + def transformDown: SparkPlan => SparkPlan = { Review Comment: Why we need a function here? can we directly use `setIgnoreKeysIfAggregateOnJoinKeys`? ########## backends-velox/src/main/scala/org/apache/gluten/extension/HashAggregateIgnoreNullKeysRule.scala: ########## @@ -0,0 +1,89 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.gluten.extension + +import org.apache.gluten.config.VeloxConfig +import org.apache.gluten.execution._ + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.catalyst.plans.Inner +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.execution.adaptive.ShuffleQueryStageExec +import org.apache.spark.sql.execution.exchange.ShuffleExchangeLike +import org.apache.spark.sql.execution.joins.BaseJoinExec + +/** + * To identify aggregates that the groupby key is used as inner join keys. In this case, we can set + * ignoreNullKeys to true when convert to velox's AggregateNode. + */ +case class HashAggregateIgnoreNullKeysRule(session: SparkSession) extends Rule[SparkPlan] { + override def apply(plan: SparkPlan): SparkPlan = { + if ( + !session.conf.get(VeloxConfig.VELOX_PROPAGATE_IGNORE_NULL_KEYS_ENABLED.key, "true").toBoolean + ) { + return plan + } + plan.transformUp { + case join: BaseJoinExec if join.joinType == Inner => + val newLeftChild = setIgnoreKeysIfAggregateOnJoinKeys(join.left, join.leftKeys) + val newRightChild = setIgnoreKeysIfAggregateOnJoinKeys(join.right, join.rightKeys) + if (!newLeftChild.fastEquals(join.left) || !newRightChild.fastEquals(join.right)) { + join.withNewChildren(Seq(newLeftChild, newRightChild)) + } else { + join + } + case p => p + } + } + + private def setIgnoreKeysIfAggregateOnJoinKeys( + plan: SparkPlan, + joinKeys: Seq[Expression]): SparkPlan = { + def transformDown: SparkPlan => SparkPlan = { + case agg: FlushableHashAggregateExecTransformer => Review Comment: nit: use `HashAggregateExecTransformer` ########## backends-velox/src/main/scala/org/apache/gluten/extension/HashAggregateIgnoreNullKeysRule.scala: ########## @@ -0,0 +1,89 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.gluten.extension + +import org.apache.gluten.config.VeloxConfig +import org.apache.gluten.execution._ + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.catalyst.plans.Inner +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.execution.adaptive.ShuffleQueryStageExec +import org.apache.spark.sql.execution.exchange.ShuffleExchangeLike +import org.apache.spark.sql.execution.joins.BaseJoinExec + +/** + * To identify aggregates that the groupby key is used as inner join keys. In this case, we can set + * ignoreNullKeys to true when convert to velox's AggregateNode. + */ +case class HashAggregateIgnoreNullKeysRule(session: SparkSession) extends Rule[SparkPlan] { + override def apply(plan: SparkPlan): SparkPlan = { + if ( + !session.conf.get(VeloxConfig.VELOX_PROPAGATE_IGNORE_NULL_KEYS_ENABLED.key, "true").toBoolean + ) { + return plan + } + plan.transformUp { + case join: BaseJoinExec if join.joinType == Inner => + val newLeftChild = setIgnoreKeysIfAggregateOnJoinKeys(join.left, join.leftKeys) + val newRightChild = setIgnoreKeysIfAggregateOnJoinKeys(join.right, join.rightKeys) + if (!newLeftChild.fastEquals(join.left) || !newRightChild.fastEquals(join.right)) { Review Comment: nit: change it to `if (newLeftChild.fastEquals(join.left) && newRightChild.fastEquals(join.right))` for better understanding. -- 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]
