Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix CustomShuffleReader replacement when decimal types enabled #1685

Merged
merged 5 commits into from
Feb 10, 2021
Merged

Fix CustomShuffleReader replacement when decimal types enabled #1685

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
62ac42e
fix CustomShuffleReader replacement error when decimal enabled
sperlingxx Feb 8, 2021
f88b954
fix typo
sperlingxx Feb 8, 2021
23d61d4
update
sperlingxx Feb 9, 2021
88bae86
update supported_ops
sperlingxx Feb 9, 2021
b72778f
fix supported_ops.md
sperlingxx Feb 10, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOverrides.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2610,7 +2610,7 @@ object GpuOverrides {
),
exec[CustomShuffleReaderExec](
"A wrapper of shuffle query stage",
ExecChecks(TypeSig.commonCudfTypes, TypeSig.all),
ExecChecks(TypeSig.commonCudfTypes + TypeSig.DECIMAL, TypeSig.all),
(exec, conf, p, r) =>
new SparkPlanMeta[CustomShuffleReaderExec](exec, conf, p, r) {
override def tagPlanForGpu(): Unit = {
Expand Down
18 changes: 14 additions & 4 deletions tests/src/test/scala/com/nvidia/spark/rapids/AdaptiveQueryExecSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ import org.apache.spark.sql.execution.joins.SortMergeJoinExec
import org.apache.spark.sql.functions.{col, when}
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

2021 copyrights

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed.

import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.rapids.execution.{GpuCustomShuffleReaderExec, GpuShuffledHashJoinBase}
import org.apache.spark.sql.types.{DecimalType, IntegerType, StructField, StructType}

object AdaptiveQueryExecSuite {
val TEST_FILES_ROOT: File = TestUtils.getTempDir(this.getClass.getSimpleName)
Expand Down Expand Up @@ -272,6 +273,7 @@ class AdaptiveQueryExecSuite
val conf = new SparkConf()
.set(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key, "true")
.set(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key, "-1")
.set(RapidsConf.DECIMAL_TYPE_ENABLED.key, "true")

withGpuSparkSession(spark => {
setupTestData(spark)
Expand Down Expand Up @@ -309,6 +311,7 @@ class AdaptiveQueryExecSuite
.set(SQLConf.ADVISORY_PARTITION_SIZE_IN_BYTES.key, "50")
// disable DemoteBroadcastHashJoin rule from removing BHJ due to empty partitions
.set(SQLConf.NON_EMPTY_PARTITION_RATIO_FOR_BROADCAST_JOIN.key, "0")
.set(RapidsConf.DECIMAL_TYPE_ENABLED.key, "true")

withGpuSparkSession(spark => {
setupTestData(spark)
Expand Down Expand Up @@ -340,6 +343,7 @@ class AdaptiveQueryExecSuite
.set(SQLConf.NON_EMPTY_PARTITION_RATIO_FOR_BROADCAST_JOIN.key, "0")
.set(SQLConf.SHUFFLE_PARTITIONS.key, "5")
.set(RapidsConf.ENABLE_CAST_STRING_TO_INTEGER.key, "true")
.set(RapidsConf.DECIMAL_TYPE_ENABLED.key, "true")

withGpuSparkSession(spark => {
setupTestData(spark)
Expand Down Expand Up @@ -468,10 +472,16 @@ class AdaptiveQueryExecSuite

/** Ported from org.apache.spark.sql.test.SQLTestData */
private def testData2(spark: SparkSession) {
import spark.implicits._
val df = Seq[(Int, Int)]((1, 1), (1, 2), (2, 1), (2, 2), (3, 1), (3, 2))
.toDF("a", "b")
.repartition(col("a"))
import scala.collection.JavaConverters._
val df = spark.createDataFrame(
List(
Row(1, BigDecimal(1)), Row(1, BigDecimal(2)), Row(2, BigDecimal(1)),
Row(2, BigDecimal(2)), Row(3, BigDecimal(1)), Row(3, BigDecimal(2))
).asJava,
StructType(Array(
StructField("a", IntegerType),
StructField("b", DecimalType(18, 0))))
).repartition(col("a"))
registerAsParquetTable(spark, df, "testData2")
}

Expand Down