org.apache.sysds.runtime.instructions.spark.utils

Class SparkUtils

java.lang.Object

org.apache.sysds.runtime.instructions.spark.utils.SparkUtils

public class SparkUtils
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
static org.apache.spark.storage.StorageLevel	DEFAULT_TMP

Constructor Summary

Constructors

Constructor and Description
SparkUtils()

Method Summary

Modifier and Type	Method and Description
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell>	cacheBinaryCellRDD(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> input)
static DataCharacteristics	computeDataCharacteristics(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> input) Utility to compute dimensions and non-zeros in a given RDD of binary cells.
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	copyBinaryBlockMatrix(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in) Creates a partitioning-preserving deep copy of the input matrix RDD, where the indexes and values are copied.
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	copyBinaryBlockMatrix(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, boolean deep) Creates a partitioning-preserving copy of the input matrix RDD.
static org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock>	copyBinaryBlockTensor(org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock> in) Creates a partitioning-preserving deep copy of the input tensor RDD, where the indexes and values are copied.
static org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock>	copyBinaryBlockTensor(org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock> in, boolean deep) Creates a partitioning-preserving copy of the input tensor RDD.
static List<scala.Tuple2<Long,FrameBlock>>	fromIndexedFrameBlock(List<Pair<Long,FrameBlock>> in)
static scala.Tuple2<Long,FrameBlock>	fromIndexedFrameBlock(Pair<Long,FrameBlock> in)
static scala.Tuple2<MatrixIndexes,MatrixBlock>	fromIndexedMatrixBlock(IndexedMatrixValue in)
static List<scala.Tuple2<MatrixIndexes,MatrixBlock>>	fromIndexedMatrixBlock(List<IndexedMatrixValue> in)
static Pair<MatrixIndexes,MatrixBlock>	fromIndexedMatrixBlockToPair(IndexedMatrixValue in)
static List<Pair<MatrixIndexes,MatrixBlock>>	fromIndexedMatrixBlockToPair(List<IndexedMatrixValue> in)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	getEmptyBlockRDD(org.apache.spark.api.java.JavaSparkContext sc, DataCharacteristics mc) Creates an RDD of empty blocks according to the given matrix characteristics.
static long	getNonZeros(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> input)
static int	getNumPreferredPartitions(DataCharacteristics dc)
static int	getNumPreferredPartitions(DataCharacteristics dc, org.apache.spark.api.java.JavaPairRDD<?,?> in)
static String	getPrefixFromSparkDebugInfo(String line)
static String	getStartLineFromSparkDebugInfo(String line)
static boolean	isHashPartitioned(org.apache.spark.api.java.JavaPairRDD<?,?> in) Indicates if the input RDD is hash partitioned, i.e., it has a partitioner of type org.apache.spark.HashPartitioner.
static Pair<Long,FrameBlock>	toIndexedFrameBlock(scala.Tuple2<Long,FrameBlock> in)
static List<Pair<Long,Long>>	toIndexedLong(List<scala.Tuple2<Long,Long>> in)
static IndexedMatrixValue	toIndexedMatrixBlock(MatrixIndexes ix, MatrixBlock mb)
static IndexedMatrixValue	toIndexedMatrixBlock(scala.Tuple2<MatrixIndexes,MatrixBlock> in)
static IndexedTensorBlock	toIndexedTensorBlock(TensorIndexes ix, TensorBlock mb)
static IndexedTensorBlock	toIndexedTensorBlock(scala.Tuple2<TensorIndexes,TensorBlock> in)

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_TMP

public static final org.apache.spark.storage.StorageLevel DEFAULT_TMP

Constructor Detail

SparkUtils

public SparkUtils()

Method Detail

toIndexedMatrixBlock

public static IndexedMatrixValue toIndexedMatrixBlock(scala.Tuple2<MatrixIndexes,MatrixBlock> in)

toIndexedMatrixBlock

public static IndexedMatrixValue toIndexedMatrixBlock(MatrixIndexes ix,
                                                      MatrixBlock mb)

toIndexedTensorBlock

public static IndexedTensorBlock toIndexedTensorBlock(scala.Tuple2<TensorIndexes,TensorBlock> in)

toIndexedTensorBlock

public static IndexedTensorBlock toIndexedTensorBlock(TensorIndexes ix,
                                                      TensorBlock mb)

fromIndexedMatrixBlock

public static scala.Tuple2<MatrixIndexes,MatrixBlock> fromIndexedMatrixBlock(IndexedMatrixValue in)

fromIndexedMatrixBlock

public static List<scala.Tuple2<MatrixIndexes,MatrixBlock>> fromIndexedMatrixBlock(List<IndexedMatrixValue> in)

fromIndexedMatrixBlockToPair

public static Pair<MatrixIndexes,MatrixBlock> fromIndexedMatrixBlockToPair(IndexedMatrixValue in)

fromIndexedMatrixBlockToPair

public static List<Pair<MatrixIndexes,MatrixBlock>> fromIndexedMatrixBlockToPair(List<IndexedMatrixValue> in)

fromIndexedFrameBlock

public static scala.Tuple2<Long,FrameBlock> fromIndexedFrameBlock(Pair<Long,FrameBlock> in)

fromIndexedFrameBlock

public static List<scala.Tuple2<Long,FrameBlock>> fromIndexedFrameBlock(List<Pair<Long,FrameBlock>> in)

toIndexedLong

public static List<Pair<Long,Long>> toIndexedLong(List<scala.Tuple2<Long,Long>> in)

toIndexedFrameBlock

public static Pair<Long,FrameBlock> toIndexedFrameBlock(scala.Tuple2<Long,FrameBlock> in)

isHashPartitioned

public static boolean isHashPartitioned(org.apache.spark.api.java.JavaPairRDD<?,?> in)

Indicates if the input RDD is hash partitioned, i.e., it has a partitioner of type org.apache.spark.HashPartitioner.

Parameters:

in - input JavaPairRDD

Returns:

true if input is hash partitioned

getNumPreferredPartitions

public static int getNumPreferredPartitions(DataCharacteristics dc,
                                            org.apache.spark.api.java.JavaPairRDD<?,?> in)

getNumPreferredPartitions

public static int getNumPreferredPartitions(DataCharacteristics dc)

copyBinaryBlockMatrix

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> copyBinaryBlockMatrix(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in)

Creates a partitioning-preserving deep copy of the input matrix RDD, where the indexes and values are copied.

Parameters:

in - matrix as JavaPairRDD<MatrixIndexes,MatrixBlock>

Returns:

matrix as JavaPairRDD<MatrixIndexes,MatrixBlock>

copyBinaryBlockMatrix

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> copyBinaryBlockMatrix(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                                                     boolean deep)

Creates a partitioning-preserving copy of the input matrix RDD. If a deep copy is requested, indexes and values are copied, otherwise they are simply passed through.

Parameters:

in - matrix as JavaPairRDD<MatrixIndexes,MatrixBlock>

deep - if true, perform deep copy

Returns:

matrix as JavaPairRDD<MatrixIndexes,MatrixBlock>

copyBinaryBlockTensor

public static org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock> copyBinaryBlockTensor(org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock> in)

Creates a partitioning-preserving deep copy of the input tensor RDD, where the indexes and values are copied.

Parameters:

in - tensor as JavaPairRDD<TensorIndexes,HomogTensor>

Returns:

tensor as JavaPairRDD<TensorIndexes,HomogTensor>

copyBinaryBlockTensor

public static org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock> copyBinaryBlockTensor(org.apache.spark.api.java.JavaPairRDD<TensorIndexes,BasicTensorBlock> in,
                                                                                                          boolean deep)

Creates a partitioning-preserving copy of the input tensor RDD. If a deep copy is requested, indexes and values are copied, otherwise they are simply passed through.

Parameters:

in - tensor as JavaPairRDD<TensorIndexes,HomogTensor>

deep - if true, perform deep copy

Returns:

tensor as JavaPairRDD<TensorIndexes,HomogTensor>

getStartLineFromSparkDebugInfo

public static String getStartLineFromSparkDebugInfo(String line)

getPrefixFromSparkDebugInfo

public static String getPrefixFromSparkDebugInfo(String line)

getEmptyBlockRDD

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> getEmptyBlockRDD(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                DataCharacteristics mc)

Creates an RDD of empty blocks according to the given matrix characteristics. This is done in a scalable manner by parallelizing block ranges and generating empty blocks in a distributed manner, under awareness of preferred output partition sizes.

Parameters:

sc - spark context

mc - matrix characteristics

Returns:

pair rdd of empty matrix blocks

cacheBinaryCellRDD

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> cacheBinaryCellRDD(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> input)

computeDataCharacteristics

public static DataCharacteristics computeDataCharacteristics(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> input)

Utility to compute dimensions and non-zeros in a given RDD of binary cells.

Parameters:

input - matrix as JavaPairRDD<MatrixIndexes, MatrixCell>

Returns:

matrix characteristics

getNonZeros

public static long getNonZeros(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> input)