Packages

case class GpuFloatMax(child: Expression) extends GpuMax with GpuReplaceWindowFunction with Product with Serializable

Max aggregation for FloatType and DoubleType to handle Nans.

In Spark, Nan is the max float value, however in cuDF, the calculation involving Nan is undefined. We design a workaround method here to match the Spark's behaviour. The high level idea is that, in the projection stage, we create another column isNan. If any value in this column is true, return Nan, Else, return what GpuBasicMax returns.

Linear Supertypes
GpuReplaceWindowFunction, GpuMax, Serializable, Serializable, GpuRunningWindowFunction, GpuAggregateWindowFunction, GpuWindowFunction, GpuUnboundToUnboundWindowWithFixer, GpuBatchedRunningWindowWithFixer, GpuAggregateFunction, GpuUnevaluable, ShimExpression, GpuExpression, Expression, TreeNode[Expression], Product, Equals, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. GpuFloatMax
  2. GpuReplaceWindowFunction
  3. GpuMax
  4. Serializable
  5. Serializable
  6. GpuRunningWindowFunction
  7. GpuAggregateWindowFunction
  8. GpuWindowFunction
  9. GpuUnboundToUnboundWindowWithFixer
  10. GpuBatchedRunningWindowWithFixer
  11. GpuAggregateFunction
  12. GpuUnevaluable
  13. ShimExpression
  14. GpuExpression
  15. Expression
  16. TreeNode
  17. Product
  18. Equals
  19. AnyRef
  20. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new GpuFloatMax(child: Expression)

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. lazy val aggBufferAttributes: Seq[AttributeReference]

    This is the contract with the outside world.

    This is the contract with the outside world. It describes what the output of postUpdate should look like, and what the input to preMerge looks like. It also describes what the output of postMerge must look like.

    Definition Classes
    GpuMax → GpuAggregateFunction
  5. def apply(number: Int): TreeNode[_]
    Definition Classes
    TreeNode
  6. def argString(maxFields: Int): String
    Definition Classes
    TreeNode
  7. def asCode: String
    Definition Classes
    TreeNode
  8. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  9. def canFixUp: Boolean

    Checks whether the running window can be fixed up.

    Checks whether the running window can be fixed up. This should be called before newFixer(), to check whether the fixer would work.

    Definition Classes
    GpuBatchedRunningWindowWithFixer
  10. lazy val canonicalized: Expression
    Definition Classes
    GpuExpression → Expression
  11. def checkInputDataTypes(): TypeCheckResult
    Definition Classes
    GpuMax → Expression
  12. val child: Expression
  13. def children: Seq[Expression]
    Definition Classes
    GpuMax → TreeNode
  14. def childrenResolved: Boolean
    Definition Classes
    Expression
  15. def clone(): Expression
    Definition Classes
    TreeNode → AnyRef
  16. def collect[B](pf: PartialFunction[Expression, B]): Seq[B]
    Definition Classes
    TreeNode
  17. def collectFirst[B](pf: PartialFunction[Expression, B]): Option[B]
    Definition Classes
    TreeNode
  18. def collectLeaves(): Seq[Expression]
    Definition Classes
    TreeNode
  19. final def columnarEval(batch: ColumnarBatch): GpuColumnVector

    Returns the result of evaluating this expression on the entire ColumnarBatch.

    Returns the result of evaluating this expression on the entire ColumnarBatch. The result of calling this is a GpuColumnVector.

    By convention any GpuColumnVector returned by columnarEval is owned by the caller and will need to be closed by them. This can happen by putting it into a ColumnarBatch and closing the batch or by closing the vector directly if it is a temporary value.

    Definition Classes
    GpuUnevaluable → GpuExpression
  20. final def columnarEvalAny(batch: ColumnarBatch): Any

    Returns the result of evaluating this expression on the entire ColumnarBatch.

    Returns the result of evaluating this expression on the entire ColumnarBatch. The result of calling this may be a single GpuColumnVector or a scalar value. Scalar values typically happen if they are a part of the expression i.e. col("a") + 100. In this case the 100 is a literal that Add would have to be able to handle.

    By convention any AutoCloseable returned by columnarEvalAny is owned by the caller and will need to be closed by them.

    Definition Classes
    GpuUnevaluable → GpuExpression
  21. lazy val containsChild: Set[TreeNode[_]]
    Definition Classes
    TreeNode
  22. def convertToAst(numFirstTableColumns: Int): AstExpression

    Build an equivalent representation of this expression in a cudf AST.

    Build an equivalent representation of this expression in a cudf AST.

    numFirstTableColumns

    number of columns in the leftmost input table. Spark places the columns of all inputs in a single sequence, while cudf AST uses an explicit table reference to make column indices unique. This parameter helps translate input column references from Spark's single sequence into cudf's separate sequences.

    returns

    top node of the equivalent AST

    Definition Classes
    GpuExpression
  23. def copyTagsFrom(other: Expression): Unit
    Definition Classes
    TreeNode
  24. val dataType: DataType
    Definition Classes
    GpuFloatMax → GpuMax → Expression
  25. lazy val deterministic: Boolean
    Definition Classes
    Expression
  26. def disableCoalesceUntilInput(): Boolean

    Override this if your expression cannot allow combining of data from multiple files into a single batch before it operates on them.

    Override this if your expression cannot allow combining of data from multiple files into a single batch before it operates on them. These are for things like getting the input file name. Which for spark is stored in a thread local variable which means we have to jump through some hoops to make this work.

    Definition Classes
    GpuExpression
  27. def disableTieredProjectCombine: Boolean

    If this returns true then tiered project will stop looking to combine expressions when this is seen.

    If this returns true then tiered project will stop looking to combine expressions when this is seen.

    Definition Classes
    GpuExpression
  28. final def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode
    Definition Classes
    GpuExpression → Expression
  29. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  30. final def eval(input: InternalRow = null): Any
    Definition Classes
    GpuExpression → Expression
  31. lazy val evaluateExpression: Expression

    This takes the output of postMerge computes the final result of the aggregation.

    This takes the output of postMerge computes the final result of the aggregation.

    Definition Classes
    GpuMax → GpuAggregateFunction
    Note

    evaluateExpression is bound to aggBufferAttributes, so the references used in evaluateExpression must also be used in aggBufferAttributes.

  32. def fastEquals(other: TreeNode[_]): Boolean
    Definition Classes
    TreeNode
  33. def filteredInputProjection(filter: Expression): Seq[Expression]
    Definition Classes
    GpuAggregateFunction
  34. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  35. def find(f: (Expression) ⇒ Boolean): Option[Expression]
    Definition Classes
    TreeNode
  36. def flatArguments: Iterator[Any]
    Attributes
    protected
    Definition Classes
    Expression
  37. def flatMap[A](f: (Expression) ⇒ TraversableOnce[A]): Seq[A]
    Definition Classes
    TreeNode
  38. final def foldable: Boolean

    An aggregate function is not foldable.

    An aggregate function is not foldable.

    Definition Classes
    GpuAggregateFunction → Expression
  39. def foreach(f: (Expression) ⇒ Unit): Unit
    Definition Classes
    TreeNode
  40. def foreachUp(f: (Expression) ⇒ Unit): Unit
    Definition Classes
    TreeNode
  41. def genCode(ctx: CodegenContext): ExprCode
    Definition Classes
    Expression
  42. def generateTreeString(depth: Int, lastChildren: Seq[Boolean], append: (String) ⇒ Unit, verbose: Boolean, prefix: String, addSuffix: Boolean, maxFields: Int, printNodeId: Boolean, indent: Int): Unit
    Definition Classes
    TreeNode
  43. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  44. def getMinPeriods: Int

    Get "min-periods" value, i.e.

    Get "min-periods" value, i.e. the minimum number of periods/rows above which a non-null value is returned for the function. Otherwise, null is returned.

    returns

    Non-negative value for min-periods.

    Definition Classes
    GpuWindowFunction
  45. def getTagValue[T](tag: TreeNodeTag[T]): Option[T]
    Definition Classes
    TreeNode
  46. def groupByScanAggregation(isRunningBatched: Boolean): Seq[AggAndReplace[GroupByScanAggregation]]

    Get the aggregations to perform on the results of groupByScanInputProjection.

    Get the aggregations to perform on the results of groupByScanInputProjection. The aggregations will be zipped with the values to produce the output.

    isRunningBatched

    is this for a batched running window that will use a fixer or not?

    returns

    the aggregations to perform as a group by scan.

    Definition Classes
    GpuMax → GpuRunningWindowFunction
  47. def groupByScanInputProjection(isRunningBatched: Boolean): Seq[Expression]

    Get the input projections for a group by scan.

    Get the input projections for a group by scan. This corresponds to a running window with a partition by clause. The partition keys will be used as the grouping keys.

    isRunningBatched

    is this for a batched running window that will use a fixer or not?

    returns

    the input expressions that will be aggregated using the result from groupByScanAggregation

    Definition Classes
    GpuMax → GpuRunningWindowFunction
  48. def hasSideEffects: Boolean

    Could evaluating this expression cause side-effects, such as throwing an exception?

    Could evaluating this expression cause side-effects, such as throwing an exception?

    Definition Classes
    GpuExpression
  49. def hashCode(): Int
    Definition Classes
    TreeNode → AnyRef → Any
  50. lazy val initialValues: Seq[GpuLiteral]

    These are values that spark calls initial because it uses them to initialize the aggregation buffer, and returns them in case of an empty aggregate when there are no expressions.

    These are values that spark calls initial because it uses them to initialize the aggregation buffer, and returns them in case of an empty aggregate when there are no expressions.

    In our case they are only used in a very specific case: the empty input reduction case. In this case we don't have input to reduce, but we do have reduction functions, so each reduction function's initialValues is invoked to populate a single row of output.

    Definition Classes
    GpuMax → GpuAggregateFunction
  51. def innerChildren: Seq[TreeNode[_]]
    Definition Classes
    TreeNode
  52. lazy val inputProjection: Seq[Expression]

    Using the child reference, define the shape of input batches sent to the update expressions

    Using the child reference, define the shape of input batches sent to the update expressions

    Definition Classes
    GpuFloatMax → GpuMax → GpuAggregateFunction
    Note

    this can be thought of as "pre" update: as update consumes its output in order

  53. def isGroupByScanSupported: Boolean

    Should a group by scan be run or not.

    Should a group by scan be run or not. This should never return false unless this is also an instance of GpuAggregateWindowFunction so the window code can fall back to it for computation.

    Definition Classes
    GpuMax → GpuRunningWindowFunction
  54. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  55. def isScanSupported: Boolean

    Should a scan be run or not.

    Should a scan be run or not. This should never return false unless this is also an instance of GpuAggregateWindowFunction so the window code can fall back to it for computation.

    Definition Classes
    GpuMax → GpuRunningWindowFunction
  56. def jsonFields: List[JField]
    Attributes
    protected
    Definition Classes
    TreeNode
  57. def makeCopy(newArgs: Array[AnyRef]): Expression
    Definition Classes
    TreeNode
  58. def map[A](f: (Expression) ⇒ A): Seq[A]
    Definition Classes
    TreeNode
  59. def mapChildren(f: (Expression) ⇒ Expression): Expression
    Definition Classes
    TreeNode
  60. def mapProductIterator[B](f: (Any) ⇒ B)(implicit arg0: ClassTag[B]): Array[B]
    Attributes
    protected
    Definition Classes
    TreeNode
  61. lazy val mergeAggregates: Seq[CudfAggregate]

    merge: second half of the aggregation.

    merge: second half of the aggregation. Also used to merge multiple batches in the update or merge stages. These cuDF aggregates consume the output of preMerge. The sequence of CudfAggregate must match the shape of aggBufferAttributes, and care must be taken to ensure that each cuDF aggregate is able to work with the corresponding input (i.e. aggBufferAttributes[i] is the input to mergeAggregates[i]). If a transformation is required, preMerge can be used to mutate the batches before they arrive at mergeAggregates.

    Definition Classes
    GpuFloatMax → GpuMax → GpuAggregateFunction
  62. lazy val mergeIsNan: CudfAggregate
    Attributes
    protected
  63. lazy val mergeMaxVal: CudfMax
    Attributes
    protected
  64. val nan: Any
    Attributes
    protected
  65. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  66. def newFixer(): BatchedRunningWindowFixer

    Get a new class that can be used to fix up batched running window operations.

    Get a new class that can be used to fix up batched running window operations.

    Definition Classes
    GpuMax → GpuBatchedRunningWindowWithFixer
  67. def newUnboundedToUnboundedFixer: BatchedUnboundedToUnboundedWindowFixer
    Definition Classes
    GpuMax → GpuUnboundToUnboundWindowWithFixer
  68. def nodeName: String
    Definition Classes
    TreeNode
  69. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  70. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  71. def nullable: Boolean
    Definition Classes
    GpuMax → Expression
  72. def numberedTreeString: String
    Definition Classes
    TreeNode
  73. val origin: Origin
    Definition Classes
    TreeNode
  74. def otherCopyArgs: Seq[AnyRef]
    Attributes
    protected
    Definition Classes
    TreeNode
  75. def p(number: Int): Expression
    Definition Classes
    TreeNode
  76. lazy val postMerge: Seq[Expression]
    Definition Classes
    GpuFloatMax → GpuAggregateFunction
  77. final lazy val postMergeAttr: Seq[AttributeReference]

    This is the last aggregation step, which optionally changes the result of the mergeAggregate.

    This is the last aggregation step, which optionally changes the result of the mergeAggregate. postMergeAttr: matches the order (and types) of mergeAggregates postMerge: binds to postMergeAttr and defines an expression that results in what Spark expects from the merge. We set this to postMergeAttr by default, for the pass through case (like in postUpdate). GpuM2 is the exception, where postMerge mutates the result of the mergeAggregates to output what Spark expects.

    Definition Classes
    GpuAggregateFunction
  78. lazy val postUpdate: Seq[Expression]
    Definition Classes
    GpuFloatMax → GpuAggregateFunction
  79. final lazy val postUpdateAttr: Seq[AttributeReference]

    This is the last step in the update phase.

    This is the last step in the update phase. It can optionally modify the result of the cuDF update aggregates, or be a pass-through. postUpdateAttr: matches the order (and types) of updateAggregates postUpdate: binds to postUpdateAttr and defines an expression that results in what Spark expects from the update. By default this is postUpdateAttr, as it should match the shape of the Spark agg buffer leaving cuDF, but in the M2 and Count cases we overwrite it, because the cuDF shape isn't what Spark expects.

    Definition Classes
    GpuAggregateFunction
  80. lazy val preMerge: Seq[Expression]

    This step is the first step into the merge phase.

    This step is the first step into the merge phase. It can optionally modify the result of the postUpdate before it goes into the cuDF merge aggregation. preMerge: modify a partial batch to match the input required by a merge aggregate

    This always binds to aggBufferAttributes as that is the inbound schema for this aggregate from Spark. If it is set to aggBufferAttributes by default so the bind behaves like a pass through in most cases.

    Definition Classes
    GpuFloatMax → GpuAggregateFunction
  81. def prettyJson: String
    Definition Classes
    TreeNode
  82. def prettyName: String
    Definition Classes
    Expression
  83. def references: AttributeSet
    Definition Classes
    Expression
  84. lazy val resolved: Boolean
    Definition Classes
    Expression
  85. lazy val retryable: Boolean

    true means this expression can be used inside a retry block, otherwise false.

    true means this expression can be used inside a retry block, otherwise false. An expression is retryable when

    • it is deterministic, or
    • when being non-deterministic, it is a Retryable and its children are all retryable.
    Definition Classes
    GpuExpression
  86. def scanAggregation(isRunningBatched: Boolean): Seq[AggAndReplace[ScanAggregation]]

    Get the aggregations to perform on the results of scanInputProjection.

    Get the aggregations to perform on the results of scanInputProjection. The aggregations will be zipped with the values to produce the output.

    isRunningBatched

    is this for a batched running window that will use a fixer or not?

    returns

    the aggregations to perform as a group by scan.

    Definition Classes
    GpuMax → GpuRunningWindowFunction
  87. def scanCombine(isRunningBatched: Boolean, cols: Seq[ColumnVector]): ColumnVector

    Provides a way to combine the result of multiple aggregations into a final value.

    Provides a way to combine the result of multiple aggregations into a final value. By default it requires that there is a single aggregation and works as just a pass through.

    isRunningBatched

    is this for a batched running window that will use a fixer or not?

    cols

    the columns to be combined

    returns

    the result of combining these together.

    Definition Classes
    GpuRunningWindowFunction
  88. def scanInputProjection(isRunningBatched: Boolean): Seq[Expression]

    Get the input projections for a scan.

    Get the input projections for a scan. This corresponds to a running window without a partition by clause.

    isRunningBatched

    is this for a batched running window that will use a fixer or not?

    returns

    the input expressions that will be aggregated using the result from scanAggregation

    Definition Classes
    GpuMax → GpuRunningWindowFunction
  89. val selfNonDeterministic: Boolean

    Whether an expression itself is non-deterministic when its "deterministic" is false, no matter whether it has any non-deterministic children.

    Whether an expression itself is non-deterministic when its "deterministic" is false, no matter whether it has any non-deterministic children. An expression is actually a tree, and deterministic being false means there is at least one tree node is non-deterministic, but we need to know the exact nodes which are non-deterministic to check if it implements the Retryable.

    Default to false because Spark checks only children by default in Expression. So it is non-deterministic iff it has non-deterministic children.

    NOTE When overriding "deterministic", this should be taken care of.

    Definition Classes
    GpuExpression
  90. def semanticEquals(other: Expression): Boolean
    Definition Classes
    Expression
  91. def semanticHash(): Int
    Definition Classes
    Expression
  92. def setTagValue[T](tag: TreeNodeTag[T], value: T): Unit
    Definition Classes
    TreeNode
  93. def shouldReplaceWindow(spec: GpuWindowSpecDefinition): Boolean

    Return true if windowReplacement should be called to replace this GpuWindowFunction with something else.

    Return true if windowReplacement should be called to replace this GpuWindowFunction with something else.

    Definition Classes
    GpuFloatMax → GpuReplaceWindowFunction
  94. def simpleString(maxFields: Int): String
    Definition Classes
    Expression → TreeNode
  95. def simpleStringWithNodeId(): String
    Definition Classes
    Expression → TreeNode
  96. def sql(isDistinct: Boolean): String
    Definition Classes
    GpuAggregateFunction
  97. def sql: String
    Definition Classes
    Expression
  98. def stringArgs: Iterator[Any]
    Attributes
    protected
    Definition Classes
    TreeNode
  99. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  100. def toAggString(isDistinct: Boolean): String

    String representation used in explain plans.

    String representation used in explain plans.

    Definition Classes
    GpuAggregateFunction
  101. def toJSON: String
    Definition Classes
    TreeNode
  102. def toString(): String
    Definition Classes
    Expression → TreeNode → AnyRef → Any
  103. def transform(rule: PartialFunction[Expression, Expression]): Expression
    Definition Classes
    TreeNode
  104. def transformDown(rule: PartialFunction[Expression, Expression]): Expression
    Definition Classes
    TreeNode
  105. def transformUp(rule: PartialFunction[Expression, Expression]): Expression
    Definition Classes
    TreeNode
  106. def treeString(append: (String) ⇒ Unit, verbose: Boolean, addSuffix: Boolean, maxFields: Int, printOperatorId: Boolean): Unit
    Definition Classes
    TreeNode
  107. final def treeString(verbose: Boolean, addSuffix: Boolean, maxFields: Int, printOperatorId: Boolean): String
    Definition Classes
    TreeNode
  108. final def treeString: String
    Definition Classes
    TreeNode
  109. def unsetTagValue[T](tag: TreeNodeTag[T]): Unit
    Definition Classes
    TreeNode
  110. lazy val updateAggregates: Seq[CudfAggregate]

    update: first half of the aggregation The sequence of CudfAggregate must match the shape of inputProjections, and care must be taken to ensure that each cuDF aggregate is able to work with the corresponding inputProjection (i.e.

    update: first half of the aggregation The sequence of CudfAggregate must match the shape of inputProjections, and care must be taken to ensure that each cuDF aggregate is able to work with the corresponding inputProjection (i.e. inputProjection[i] is the input to updateAggregates[i]).

    Definition Classes
    GpuFloatMax → GpuMax → GpuAggregateFunction
  111. lazy val updateIsNan: CudfAggregate
    Attributes
    protected
  112. lazy val updateMaxVal: CudfMax
    Attributes
    protected
  113. final def verboseString(maxFields: Int): String
    Definition Classes
    Expression → TreeNode
  114. def verboseStringWithSuffix(maxFields: Int): String
    Definition Classes
    TreeNode
  115. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  116. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  117. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  118. def windowAggregation(inputs: Seq[(ColumnVector, Int)]): RollingAggregationOnColumn

    Create the aggregation operation to perform for Windowing.

    Create the aggregation operation to perform for Windowing. The input to this method is a sequence of (index, ColumnVector) that corresponds one to one with what was returned by windowInputProjection. The index is the index into the Table for the corresponding ColumnVector. Some aggregations need extra values.

    Definition Classes
    GpuMax → GpuAggregateWindowFunction
  119. lazy val windowInputProjection: Seq[Expression]

    Using child references, define the shape of the vectors sent to the window operations

    Using child references, define the shape of the vectors sent to the window operations

    Definition Classes
    GpuMax → GpuAggregateWindowFunction
  120. def windowOutput(result: ColumnVector): ColumnVector

    Do a final pass over the window aggregation output.

    Do a final pass over the window aggregation output. This lets us cast the result to a desired type or check for overflow. This is not used for GpuRunningWindowFunction. There you can use scanCombine.

    Definition Classes
    GpuAggregateWindowFunction
  121. def windowReplacement(spec: GpuWindowSpecDefinition): Expression

    Return a new single expression that can replace the existing aggregation in window calculations.

    Return a new single expression that can replace the existing aggregation in window calculations. Please note that this requires that there are no nested window operations. For example you cannot do a SUM of AVERAGES with this currently. That support may be added in the future.

    Definition Classes
    GpuFloatMax → GpuReplaceWindowFunction
  122. def withNewChildren(newChildren: Seq[Expression]): Expression
    Definition Classes
    TreeNode

Inherited from GpuReplaceWindowFunction

Inherited from GpuMax

Inherited from Serializable

Inherited from Serializable

Inherited from GpuRunningWindowFunction

Inherited from GpuAggregateWindowFunction

Inherited from GpuWindowFunction

Inherited from GpuUnboundToUnboundWindowWithFixer

Inherited from GpuBatchedRunningWindowWithFixer

Inherited from GpuAggregateFunction

Inherited from GpuUnevaluable

Inherited from ShimExpression

Inherited from GpuExpression

Inherited from Expression

Inherited from TreeNode[Expression]

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped