Skip to content

[SPARK-22704][SQL] Least and Greatest use less global variables #19899

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

Closed
wants to merge 8 commits into from
Closed

[SPARK-22704][SQL] Least and Greatest use less global variables #19899

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
bd3b4c7
initial commit
kiszk Dec 5, 2017
d322931
remove print
kiszk Dec 5, 2017
facaf1c
address review comments
kiszk Dec 6, 2017
d467192
address review comments
kiszk Dec 6, 2017
e9a2202
address review comments
kiszk Dec 6, 2017
47fcdc2
address review comments
kiszk Dec 6, 2017
e5aa90e
address review comment
kiszk Dec 6, 2017
e1ed6c1
fix build failure
kiszk Dec 6, 2017
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
94 changes: 62 additions & 32 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -602,23 +602,38 @@ case class Least(children: Seq[Expression]) extends Expression {

override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
val evalChildren = children.map(_.genCode(ctx))
ctx.addMutableState(ctx.JAVA_BOOLEAN, ev.isNull)
ctx.addMutableState(ctx.javaType(dataType), ev.value)
def updateEval(eval: ExprCode): String = {
val tmpIsNull = ctx.freshName("leastTmpIsNull")
ctx.addMutableState(ctx.JAVA_BOOLEAN, tmpIsNull)
val evals = evalChildren.map(eval =>
s"""
${eval.code}
if (!${eval.isNull} && (${ev.isNull} ||
${ctx.genGreater(dataType, ev.value, eval.value)})) {
${ev.isNull} = false;
${ev.value} = ${eval.value};
}
"""
}
val codes = ctx.splitExpressionsWithCurrentInputs(evalChildren.map(updateEval))
ev.copy(code = s"""
${ev.isNull} = true;
${ev.value} = ${ctx.defaultValue(dataType)};
$codes""")
|${eval.code}
|if (!${eval.isNull} && ($tmpIsNull ||
| ${ctx.genGreater(dataType, ev.value, eval.value)})) {
| $tmpIsNull = false;
| ${ev.value} = ${eval.value};
|}
""".stripMargin
)

val resultType = ctx.javaType(dataType)
val codes = ctx.splitExpressionsWithCurrentInputs(
expressions = evals,
funcName = "least",
extraArguments = Seq(resultType -> ev.value),
returnType = resultType,
makeSplitFunction = body =>
s"""
|$body
|return ${ev.value};
""".stripMargin,
foldFunctions = _.map(funcCall => s"${ev.value} = $funcCall;").mkString("\n"))
ev.copy(code =
s"""
|$tmpIsNull = true;
|${ctx.javaType(dataType)} ${ev.value} = ${ctx.defaultValue(dataType)};
|$codes
|final boolean ${ev.isNull} = $tmpIsNull;
""".stripMargin)
}
}

Expand Down Expand Up @@ -668,22 +683,37 @@ case class Greatest(children: Seq[Expression]) extends Expression {

override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
val evalChildren = children.map(_.genCode(ctx))
ctx.addMutableState(ctx.JAVA_BOOLEAN, ev.isNull)
ctx.addMutableState(ctx.javaType(dataType), ev.value)
def updateEval(eval: ExprCode): String = {
val tmpIsNull = ctx.freshName("greatestTmpIsNull")
ctx.addMutableState(ctx.JAVA_BOOLEAN, tmpIsNull)
val evals = evalChildren.map(eval =>
s"""
${eval.code}
if (!${eval.isNull} && (${ev.isNull} ||
${ctx.genGreater(dataType, eval.value, ev.value)})) {
${ev.isNull} = false;
${ev.value} = ${eval.value};
}
"""
}
val codes = ctx.splitExpressionsWithCurrentInputs(evalChildren.map(updateEval))
ev.copy(code = s"""
${ev.isNull} = true;
${ev.value} = ${ctx.defaultValue(dataType)};
$codes""")
|${eval.code}
|if (!${eval.isNull} && ($tmpIsNull ||
| ${ctx.genGreater(dataType, eval.value, ev.value)})) {
| $tmpIsNull = false;
| ${ev.value} = ${eval.value};
|}
""".stripMargin
)

val resultType = ctx.javaType(dataType)
val codes = ctx.splitExpressionsWithCurrentInputs(
expressions = evals,
funcName = "greatest",
extraArguments = Seq(resultType -> ev.value),
returnType = resultType,
makeSplitFunction = body =>
s"""
|$body
|return ${ev.value};
""".stripMargin,
foldFunctions = _.map(funcCall => s"${ev.value} = $funcCall;").mkString("\n"))
ev.copy(code =
s"""
|$tmpIsNull = true;
|${ctx.javaType(dataType)} ${ev.value} = ${ctx.defaultValue(dataType)};
|$codes
|final boolean ${ev.isNull} = $tmpIsNull;
""".stripMargin)
}
}
11 changes: 11 additions & 0 deletions .../src/test/scala/org/apache/spark/sql/catalyst/expressions/ArithmeticExpressionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ import org.apache.spark.SparkFunSuite
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.TypeCheckFailure
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.expressions.codegen.CodegenContext
import org.apache.spark.sql.types._

class ArithmeticExpressionSuite extends SparkFunSuite with ExpressionEvalHelper {
Expand Down Expand Up @@ -343,4 +344,14 @@ class ArithmeticExpressionSuite extends SparkFunSuite with ExpressionEvalHelper
checkEvaluation(Least(inputsExpr), "s" * 1, EmptyRow)
checkEvaluation(Greatest(inputsExpr), "s" * N, EmptyRow)
}

test("SPARK-22704: Least and greatest use less global variables") {
val ctx1 = new CodegenContext()
Least(Seq(Literal(1), Literal(1))).genCode(ctx1)
assert(ctx1.mutableStates.size == 1)

val ctx2 = new CodegenContext()
Greatest(Seq(Literal(1), Literal(1))).genCode(ctx2)
assert(ctx2.mutableStates.size == 1)
}
}