Package org.apache.sysds.lops

Class MapMult

java.lang.Object

org.apache.sysds.lops.Lop

org.apache.sysds.lops.MapMult

public class MapMult
extends Lop

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	MapMult.CacheType

Nested classes/interfaces inherited from class org.apache.sysds.lops.Lop

Lop.SimpleInstType, Lop.Type, Lop.VisitStatus

Field Summary

Fields

Modifier and Type	Field	Description
static String	OPCODE

Fields inherited from class org.apache.sysds.lops.Lop

_beginColumn, _beginLine, _endColumn, _endLine, _filename, CP_CHILD_THREAD, CP_ROOT_THREAD_ID, DATATYPE_PREFIX, FILE_SEPARATOR, FRAME_VAR_NAME_PREFIX, INSTRUCTION_DELIMITOR, LITERAL_PREFIX, MATRIX_VAR_NAME_PREFIX, NAME_VALUE_SEPARATOR, OPERAND_DELIMITOR, PROCESS_PREFIX, SCALAR_VAR_NAME_PREFIX, UPDATE_INPLACE_PREFIX, VALUETYPE_PREFIX, VARIABLE_NAME_PLACEHOLDER

Constructor Summary

Constructors

Constructor	Description
MapMult(Lop input1, Lop input2, Types.DataType dt, Types.ValueType vt, boolean rightCache, boolean partitioned, boolean emptyBlocks, AggBinaryOp.SparkAggType aggtype)	Constructor to setup a partial Matrix-Vector Multiplication for Spark

Method Summary

Modifier and Type	Method	Description
AggBinaryOp.SparkAggType	getAggType()	Method to get aggregate type if applicable.
Lop	getBroadcastInput()	Method to get the input to be broadcast.
String	getInstructions(String input1, String input2, String output)	Method should be overridden if needed
String	toString()	Method to have Lops print their state.

Methods inherited from class org.apache.sysds.lops.Lop

activatePrefetch, addInput, addOutput, addToDag, createReachable, getBeginColumn, getBeginLine, getComputeEstimate, getDataType, getEndColumn, getEndLine, getExecType, getFederatedOutput, getFilename, getID, getInput, getInputs, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getInstructions, getLevel, getNnz, getNumCols, getNumRows, getOutputMemoryEstimate, getOutputParameters, getOutputs, getPrivacyConstraint, getProducesIntermediateOutput, getReachable, getSimpleInstructionType, getTotalMemoryEstimate, getType, getValueType, getVisited, isAllOutputsCP, isAllOutputsGPU, isAsynchronousOp, isDataExecLocation, isExecCP, isExecGPU, isExecSpark, isVariable, isVisited, prefetchActivated, prepInputOperand, prepInputOperand, prepOperand, prepOperand, prepOutputOperand, prepOutputOperand, prepOutputOperand, prepScalarInputOperand, prepScalarInputOperand, prepScalarLabel, prepScalarOperand, printErrorLocation, removeConsumer, removeInput, removeOutput, replaceAllInputs, replaceAllOutputs, replaceInput, resetVisitStatus, setAllPositions, setAsynchronous, setBeginColumn, setBeginLine, setComputeEstimate, setConsumerCount, setDataType, setEndColumn, setEndLine, setExecType, setFederatedOutput, setFilename, setMemoryEstimates, setNewID, setPrivacyConstraint, setValueType, setVisited, setVisited

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

OPCODE

public static final String OPCODE

See Also:

Constant Field Values

Constructor Detail

MapMult

public MapMult(Lop input1,
               Lop input2,
               Types.DataType dt,
               Types.ValueType vt,
               boolean rightCache,
               boolean partitioned,
               boolean emptyBlocks,
               AggBinaryOp.SparkAggType aggtype)

Constructor to setup a partial Matrix-Vector Multiplication for Spark

Parameters:

input1 - low-level operator 1

input2 - low-level operator 2

dt - data type

vt - value type

rightCache - true if right cache, false if left cache

partitioned - true if partitioned, false if not partitioned

emptyBlocks - true if output empty blocks

aggtype - spark aggregation type

Method Detail

getAggType

public AggBinaryOp.SparkAggType getAggType()

Description copied from class: Lop

Method to get aggregate type if applicable. This method is overridden by the Lops with aggregate types (e.g. MapMult)

Overrides:

getAggType in class Lop

Returns:

SparkAggType

getBroadcastInput

public Lop getBroadcastInput()

Description copied from class: Lop

Method to get the input to be broadcast. This method is overridden by the Lops which require broadcasts (e.g. AppendM)

Overrides:

getBroadcastInput in class Lop

Returns:

An input Lop or Null

toString

public String toString()

Description copied from class: Lop

Method to have Lops print their state. This is for debugging purposes.

Specified by:

toString in class Lop

getInstructions

public String getInstructions(String input1,
                              String input2,
                              String output)

Description copied from class: Lop

Method should be overridden if needed

Overrides:

getInstructions in class Lop

Parameters:

input1 - input 1

input2 - input 2

output - output

Returns:

instructions as string