-
Notifications
You must be signed in to change notification settings - Fork 237
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'branch-23.10' into gpucoredump
- Loading branch information
Showing
200 changed files
with
5,514 additions
and
2,072 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
84 changes: 84 additions & 0 deletions
84
...c/main/databricks/scala/com/nvidia/spark/rapids/delta/GpuDeltaParquetFileFormatBase.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,84 @@ | ||
| /* | ||
| * Copyright (c) 2023, NVIDIA CORPORATION. | ||
| * | ||
| * Licensed 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 com.nvidia.spark.rapids.delta | ||
|
|
||
| import com.databricks.sql.transaction.tahoe.{DeltaColumnMapping, DeltaColumnMappingMode, NoMapping} | ||
| import com.nvidia.spark.rapids.{GpuMetric, GpuParquetMultiFilePartitionReaderFactory, GpuReadParquetFileFormat} | ||
| import org.apache.hadoop.conf.Configuration | ||
|
|
||
| import org.apache.spark.broadcast.Broadcast | ||
| import org.apache.spark.sql.SparkSession | ||
| import org.apache.spark.sql.catalyst.InternalRow | ||
| import org.apache.spark.sql.connector.read.PartitionReaderFactory | ||
| import org.apache.spark.sql.execution.datasources.PartitionedFile | ||
| import org.apache.spark.sql.rapids.GpuFileSourceScanExec | ||
| import org.apache.spark.sql.sources.Filter | ||
| import org.apache.spark.sql.types.StructType | ||
| import org.apache.spark.util.SerializableConfiguration | ||
|
|
||
| abstract class GpuDeltaParquetFileFormatBase extends GpuReadParquetFileFormat { | ||
| val columnMappingMode: DeltaColumnMappingMode | ||
| val referenceSchema: StructType | ||
|
|
||
| def prepareSchema(inputSchema: StructType): StructType = { | ||
| DeltaColumnMapping.createPhysicalSchema(inputSchema, referenceSchema, columnMappingMode) | ||
| } | ||
|
|
||
| override def createMultiFileReaderFactory( | ||
| broadcastedConf: Broadcast[SerializableConfiguration], | ||
| pushedFilters: Array[Filter], | ||
| fileScan: GpuFileSourceScanExec): PartitionReaderFactory = { | ||
| GpuParquetMultiFilePartitionReaderFactory( | ||
| fileScan.conf, | ||
| broadcastedConf, | ||
| prepareSchema(fileScan.relation.dataSchema), | ||
| prepareSchema(fileScan.requiredSchema), | ||
| prepareSchema(fileScan.readPartitionSchema), | ||
| pushedFilters, | ||
| fileScan.rapidsConf, | ||
| fileScan.allMetrics, | ||
| fileScan.queryUsesInputFile, | ||
| fileScan.alluxioPathsMap) | ||
| } | ||
|
|
||
| override def buildReaderWithPartitionValuesAndMetrics( | ||
| sparkSession: SparkSession, | ||
| dataSchema: StructType, | ||
| partitionSchema: StructType, | ||
| requiredSchema: StructType, | ||
| filters: Seq[Filter], | ||
| options: Map[String, String], | ||
| hadoopConf: Configuration, | ||
| metrics: Map[String, GpuMetric], | ||
| alluxioPathReplacementMap: Option[Map[String, String]]) | ||
| : PartitionedFile => Iterator[InternalRow] = { | ||
| super.buildReaderWithPartitionValuesAndMetrics( | ||
| sparkSession, | ||
| prepareSchema(dataSchema), | ||
| prepareSchema(partitionSchema), | ||
| prepareSchema(requiredSchema), | ||
| filters, | ||
| options, | ||
| hadoopConf, | ||
| metrics, | ||
| alluxioPathReplacementMap) | ||
| } | ||
|
|
||
| override def supportFieldName(name: String): Boolean = { | ||
| if (columnMappingMode != NoMapping) true else super.supportFieldName(name) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
84 changes: 84 additions & 0 deletions
84
...mon/src/main/delta-io/scala/com/nvidia/spark/rapids/delta/GpuDeltaParquetFileFormat.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,84 @@ | ||
| /* | ||
| * Copyright (c) 2023, NVIDIA CORPORATION. | ||
| * | ||
| * Licensed 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 com.nvidia.spark.rapids.delta | ||
|
|
||
| import com.nvidia.spark.rapids.{GpuMetric, GpuParquetMultiFilePartitionReaderFactory, GpuReadParquetFileFormat} | ||
| import org.apache.hadoop.conf.Configuration | ||
|
|
||
| import org.apache.spark.broadcast.Broadcast | ||
| import org.apache.spark.sql.SparkSession | ||
| import org.apache.spark.sql.catalyst.InternalRow | ||
| import org.apache.spark.sql.connector.read.PartitionReaderFactory | ||
| import org.apache.spark.sql.delta.{DeltaColumnMapping, DeltaColumnMappingMode, NoMapping} | ||
| import org.apache.spark.sql.execution.datasources.PartitionedFile | ||
| import org.apache.spark.sql.rapids.GpuFileSourceScanExec | ||
| import org.apache.spark.sql.sources.Filter | ||
| import org.apache.spark.sql.types.StructType | ||
| import org.apache.spark.util.SerializableConfiguration | ||
|
|
||
| trait GpuDeltaParquetFileFormat extends GpuReadParquetFileFormat { | ||
| val columnMappingMode: DeltaColumnMappingMode | ||
| val referenceSchema: StructType | ||
|
|
||
| def prepareSchema(inputSchema: StructType): StructType = { | ||
| DeltaColumnMapping.createPhysicalSchema(inputSchema, referenceSchema, columnMappingMode) | ||
| } | ||
|
|
||
| override def createMultiFileReaderFactory( | ||
| broadcastedConf: Broadcast[SerializableConfiguration], | ||
| pushedFilters: Array[Filter], | ||
| fileScan: GpuFileSourceScanExec): PartitionReaderFactory = { | ||
| GpuParquetMultiFilePartitionReaderFactory( | ||
| fileScan.conf, | ||
| broadcastedConf, | ||
| prepareSchema(fileScan.relation.dataSchema), | ||
| prepareSchema(fileScan.requiredSchema), | ||
| prepareSchema(fileScan.readPartitionSchema), | ||
| pushedFilters, | ||
| fileScan.rapidsConf, | ||
| fileScan.allMetrics, | ||
| fileScan.queryUsesInputFile, | ||
| fileScan.alluxioPathsMap) | ||
| } | ||
|
|
||
| override def buildReaderWithPartitionValuesAndMetrics( | ||
| sparkSession: SparkSession, | ||
| dataSchema: StructType, | ||
| partitionSchema: StructType, | ||
| requiredSchema: StructType, | ||
| filters: Seq[Filter], | ||
| options: Map[String, String], | ||
| hadoopConf: Configuration, | ||
| metrics: Map[String, GpuMetric], | ||
| alluxioPathReplacementMap: Option[Map[String, String]]) | ||
| : PartitionedFile => Iterator[InternalRow] = { | ||
| super.buildReaderWithPartitionValuesAndMetrics( | ||
| sparkSession, | ||
| prepareSchema(dataSchema), | ||
| prepareSchema(partitionSchema), | ||
| prepareSchema(requiredSchema), | ||
| filters, | ||
| options, | ||
| hadoopConf, | ||
| metrics, | ||
| alluxioPathReplacementMap) | ||
| } | ||
|
|
||
| override def supportFieldName(name: String): Boolean = { | ||
| if (columnMappingMode != NoMapping) true else super.supportFieldName(name) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.