Class BlockPartitioner
- java.lang.Object
-
- org.apache.spark.Partitioner
-
- org.apache.sysds.runtime.instructions.spark.data.BlockPartitioner
-
- All Implemented Interfaces:
Serializable,scala.Serializable
public class BlockPartitioner extends org.apache.spark.PartitionerDefault partitioner used for all binary block rdd operations in order to enable sufficient local aggregation independent of the aggregation direction (row/col-wise). Especially, on large squared matrices (as common for factorization or graph algorithms), this is crucial for performance.- See Also:
- Serialized Form
-
-
Constructor Summary
Constructors Constructor Description BlockPartitioner(DataCharacteristics mc, int numParts)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description booleanequals(Object obj)intgetPartition(Object arg0)inthashCode()intnumPartitions()
-
-
-
Constructor Detail
-
BlockPartitioner
public BlockPartitioner(DataCharacteristics mc, int numParts)
-
-
Method Detail
-
getPartition
public int getPartition(Object arg0)
- Specified by:
getPartitionin classorg.apache.spark.Partitioner
-
numPartitions
public int numPartitions()
- Specified by:
numPartitionsin classorg.apache.spark.Partitioner
-
-