Class BinaryOp

All Implemented Interfaces:
ParseInfo

public class BinaryOp extends MultiThreadedHop
Binary (cell operations): aij + bij Properties: Symbol: *, -, +, ... 2 Operands Semantic: align indices (sort), then perform operation
  • Field Details

  • Constructor Details

  • Method Details

    • getOp

      public Types.OpOp2 getOp()
    • setOp

      public void setOp(Types.OpOp2 iop)
    • setOuterVectorOperation

      public void setOuterVectorOperation(boolean flag)
    • isOuter

      public boolean isOuter()
    • isInplace

      public boolean isInplace()
    • isGPUEnabled

      public boolean isGPUEnabled()
      Description copied from class: Hop
      In memory-based optimizer mode (see OptimizerUtils.isMemoryBasedOptLevel()), the exectype is determined by checking this method as well as memory budget of this Hop. Please see findExecTypeByMemEstimate for more detail. This method is necessary because not all operator are supported efficiently on GPU (for example: operations on frames and scalar as well as operations such as table).
      Specified by:
      isGPUEnabled in class Hop
      Returns:
      true if the Hop is eligible for GPU Exectype.
    • isMultiThreadedOpType

      public boolean isMultiThreadedOpType()
      Specified by:
      isMultiThreadedOpType in class MultiThreadedHop
    • constructLops

      public Lop constructLops()
      Specified by:
      constructLops in class Hop
    • getOpString

      public String getOpString()
      Specified by:
      getOpString in class Hop
    • allowsAllExecTypes

      public boolean allowsAllExecTypes()
      Specified by:
      allowsAllExecTypes in class Hop
    • constructSPAppendLop

      public static Lop constructSPAppendLop(Hop left, Hop right, Types.DataType dt, Types.ValueType vt, boolean cbind, Hop current)
    • footprintInMapper

      public static double footprintInMapper(long m1_dim1, long m1_dim2, long m2_dim1, long m2_dim2, long m1_rpb, long m1_cpb)
      Estimates the memory footprint of MapMult operation depending on which input is put into distributed cache. This function is called by optFindAppendMethod() to decide the execution strategy, as well as by piggybacking to decide the number of Map-side instructions to put into a single GMR job.
      Parameters:
      m1_dim1 - ?
      m1_dim2 - ?
      m2_dim1 - ?
      m2_dim2 - ?
      m1_rpb - ?
      m1_cpb - ?
      Returns:
      memory footprint estimate
    • requiresReplication

      public static boolean requiresReplication(Hop left, Hop right)
    • refreshSizeInformation

      public void refreshSizeInformation()
      Description copied from class: Hop
      Update the output size information for this hop.
      Specified by:
      refreshSizeInformation in class Hop
    • clone

      public Object clone() throws CloneNotSupportedException
      Specified by:
      clone in class Hop
      Throws:
      CloneNotSupportedException
    • compare

      public boolean compare(Hop that)
      Specified by:
      compare in class Hop
    • supportsMatrixScalarOperations

      public boolean supportsMatrixScalarOperations()
    • isPPredOperation

      public boolean isPPredOperation()
    • getComplementPPredOperation

      public Types.OpOp2 getComplementPPredOperation()