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

[SPARK-32258][SQL] NormalizeFloatingNumbers directly normalizes IF/CaseWhen/Coalesce child expressions #29061

Closed
wants to merge 5 commits into from
Closed

[SPARK-32258][SQL] NormalizeFloatingNumbers directly normalizes IF/CaseWhen/Coalesce child expressions #29061

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
f1652aa
NormalizeFloatingNumbers can directly normalize on certain children
viirya Jul 9, 2020
ba0ea32
Change test name.
viirya Jul 9, 2020
5046337
Remove unused import and add jira number.
viirya Jul 10, 2020
78b8667
Address comment.
viirya Jul 12, 2020
d5dce7c
Remove unused code.
viirya Jul 12, 2020
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
8 changes: 7 additions & 1 deletion ...yst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NormalizeFloatingNumbers.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.expressions.{Alias, And, ArrayTransform, CreateArray, CreateMap, CreateNamedStruct, CreateStruct, EqualTo, ExpectsInputTypes, Expression, GetStructField, If, IsNull, KnownFloatingPointNormalized, LambdaFunction, Literal, NamedLambdaVariable, UnaryExpression}
import org.apache.spark.sql.catalyst.expressions.{Alias, And, ArrayTransform, CaseWhen, CreateArray, CreateMap, CreateNamedStruct, CreateStruct, EqualTo, ExpectsInputTypes, Expression, GetStructField, If, IsNull, KnownFloatingPointNormalized, LambdaFunction, Literal, NamedLambdaVariable, UnaryExpression}
import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, ExprCode}
import org.apache.spark.sql.catalyst.planning.ExtractEquiJoinKeys
import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, Subquery, Window}
Expand Down Expand Up @@ -116,6 +116,12 @@ object NormalizeFloatingNumbers extends Rule[LogicalPlan] {
case CreateMap(children, useStringTypeWhenEmpty) =>
CreateMap(children.map(normalize), useStringTypeWhenEmpty)

case If(cond, trueValue, falseValue) =>
dongjoon-hyun marked this conversation as resolved.
Show resolved Hide resolved
If(cond, normalize(trueValue), normalize(falseValue))

case CaseWhen(branches, elseVale) =>
dongjoon-hyun marked this conversation as resolved.
Show resolved Hide resolved
CaseWhen(branches.map(br => (br._1, normalize(br._2))), elseVale.map(normalize))

dongjoon-hyun marked this conversation as resolved.
Show resolved Hide resolved
case _ if expr.dataType == FloatType || expr.dataType == DoubleType =>
Copy link
Contributor

Choose a reason for hiding this comment

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

Shall we put these new cases after this case? The main goal of this optimization is to avoid constructing a new CreateStruct during normalization. If it's just a float/double type If/CashWhen/Coalesce, it's actually an overhead to duplicate the normalization work in each child.

Copy link
Member Author

Choose a reason for hiding this comment

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

Okay.

KnownFloatingPointNormalized(NormalizeNaNAndZero(expr))

Expand Down
35 changes: 34 additions & 1 deletion ...st/scala/org/apache/spark/sql/catalyst/optimizer/NormalizeFloatingPointNumbersSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.expressions.{And, IsNull, KnownFloatingPointNormalized}
import org.apache.spark.sql.catalyst.expressions.{And, CaseWhen, If, IsNull, KnownFloatingPointNormalized}
viirya marked this conversation as resolved.
Show resolved Hide resolved
import org.apache.spark.sql.catalyst.plans.PlanTest
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules.RuleExecutor
Expand Down Expand Up @@ -91,5 +91,38 @@ class NormalizeFloatingPointNumbersSuite extends PlanTest {

comparePlans(doubleOptimized, correctAnswer)
}

test("normalize the children of If") {
viirya marked this conversation as resolved.
Show resolved Hide resolved
val cond = If(a > 0.1D, a, a + 0.2D) === b
val query = testRelation1.join(testRelation2, condition = Some(cond))
val optimized = Optimize.execute(query)
val doubleOptimized = Optimize.execute(optimized)

val joinCond = If(a > 0.1D,
KnownFloatingPointNormalized(NormalizeNaNAndZero(a)),
KnownFloatingPointNormalized(NormalizeNaNAndZero(a + 0.2D))) ===
KnownFloatingPointNormalized(NormalizeNaNAndZero(b))
val correctAnswer = testRelation1.join(testRelation2, condition = Some(joinCond))

comparePlans(doubleOptimized, correctAnswer)
}

test("normalize the children of CaseWhen") {
val cond = CaseWhen(
Seq((a > 0.1D, a), (a > 0.2D, a + 0.2D)),
Some(a + 0.3D)) === b
val query = testRelation1.join(testRelation2, condition = Some(cond))
val optimized = Optimize.execute(query)
val doubleOptimized = Optimize.execute(optimized)

val joinCond = CaseWhen(
Seq((a > 0.1D, KnownFloatingPointNormalized(NormalizeNaNAndZero(a))),
(a > 0.2D, KnownFloatingPointNormalized(NormalizeNaNAndZero(a + 0.2D)))),
Some(KnownFloatingPointNormalized(NormalizeNaNAndZero(a + 0.3D)))) ===
KnownFloatingPointNormalized(NormalizeNaNAndZero(b))
val correctAnswer = testRelation1.join(testRelation2, condition = Some(joinCond))

comparePlans(doubleOptimized, correctAnswer)
}
}