Search in sources :

Example 1 with IsBlockInList

use of org.apache.sysml.runtime.instructions.spark.functions.IsBlockInList in project incubator-systemml by apache.

the class ReorgSPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    String opcode = getOpcode();
    // get input rdd handle
    JavaPairRDD<MatrixIndexes, MatrixBlock> in1 = sec.getBinaryBlockRDDHandleForVariable(input1.getName());
    JavaPairRDD<MatrixIndexes, MatrixBlock> out = null;
    MatrixCharacteristics mcIn = sec.getMatrixCharacteristics(input1.getName());
    if (// TRANSPOSE
    opcode.equalsIgnoreCase("r'")) {
        // execute transpose reorg operation
        out = in1.mapToPair(new ReorgMapFunction(opcode));
    } else if (// REVERSE
    opcode.equalsIgnoreCase("rev")) {
        // execute reverse reorg operation
        out = in1.flatMapToPair(new RDDRevFunction(mcIn));
        if (mcIn.getRows() % mcIn.getRowsPerBlock() != 0)
            out = RDDAggregateUtils.mergeByKey(out, false);
    } else if (// DIAG
    opcode.equalsIgnoreCase("rdiag")) {
        if (mcIn.getCols() == 1) {
            // diagV2M
            out = in1.flatMapToPair(new RDDDiagV2MFunction(mcIn));
        } else {
            // diagM2V
            // execute diagM2V operation
            out = in1.filter(new FilterDiagBlocksFunction()).mapToPair(new ReorgMapFunction(opcode));
        }
    } else if (// ORDER
    opcode.equalsIgnoreCase("rsort")) {
        // Sort by column 'col' in ascending/descending order and return either index/value
        // get parameters
        long[] cols = _col.getDataType().isMatrix() ? DataConverter.convertToLongVector(ec.getMatrixInput(_col.getName())) : new long[] { ec.getScalarInput(_col.getName(), _col.getValueType(), _col.isLiteral()).getLongValue() };
        boolean desc = ec.getScalarInput(_desc.getName(), _desc.getValueType(), _desc.isLiteral()).getBooleanValue();
        boolean ixret = ec.getScalarInput(_ixret.getName(), _ixret.getValueType(), _ixret.isLiteral()).getBooleanValue();
        boolean singleCol = (mcIn.getCols() == 1);
        out = in1;
        if (cols.length > mcIn.getColsPerBlock())
            LOG.warn("Unsupported sort with number of order-by columns large than blocksize: " + cols.length);
        if (singleCol || cols.length == 1) {
            // extract column (if necessary) and sort
            if (!singleCol)
                out = out.filter(new IsBlockInRange(1, mcIn.getRows(), cols[0], cols[0], mcIn)).mapValues(new ExtractColumn((int) UtilFunctions.computeCellInBlock(cols[0], mcIn.getColsPerBlock())));
            // actual index/data sort operation
            if (// sort indexes
            ixret)
                out = RDDSortUtils.sortIndexesByVal(out, !desc, mcIn.getRows(), mcIn.getRowsPerBlock());
            else if (// sort single-column matrix
            singleCol && !desc)
                out = RDDSortUtils.sortByVal(out, mcIn.getRows(), mcIn.getRowsPerBlock());
            else if (// sort multi-column matrix w/ rewrite
            !_bSortIndInMem)
                out = RDDSortUtils.sortDataByVal(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), mcIn.getRowsPerBlock(), mcIn.getColsPerBlock());
            else
                // sort multi-column matrix
                out = RDDSortUtils.sortDataByValMemSort(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), mcIn.getRowsPerBlock(), mcIn.getColsPerBlock(), sec, (ReorgOperator) _optr);
        } else {
            // extract columns (if necessary)
            if (cols.length < mcIn.getCols())
                out = out.filter(new IsBlockInList(cols, mcIn)).mapToPair(new ExtractColumns(cols, mcIn));
            // append extracted columns (if necessary)
            if (mcIn.getCols() > mcIn.getColsPerBlock())
                out = RDDAggregateUtils.mergeByKey(out);
            // actual index/data sort operation
            if (// sort indexes
            ixret)
                out = RDDSortUtils.sortIndexesByVals(out, !desc, mcIn.getRows(), (long) cols.length, mcIn.getRowsPerBlock());
            else if (// sort single-column matrix
            cols.length == mcIn.getCols() && !desc)
                out = RDDSortUtils.sortByVals(out, mcIn.getRows(), cols.length, mcIn.getRowsPerBlock());
            else
                // sort multi-column matrix
                out = RDDSortUtils.sortDataByVals(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), cols.length, mcIn.getRowsPerBlock(), mcIn.getColsPerBlock());
        }
    } else {
        throw new DMLRuntimeException("Error: Incorrect opcode in ReorgSPInstruction:" + opcode);
    }
    // store output rdd handle
    if (opcode.equalsIgnoreCase("rsort") && _col.getDataType().isMatrix())
        sec.releaseMatrixInput(_col.getName());
    updateReorgMatrixCharacteristics(sec);
    sec.setRDDHandleForVariable(output.getName(), out);
    sec.addLineageRDD(output.getName(), input1.getName());
}
Also used : MatrixBlock(org.apache.sysml.runtime.matrix.data.MatrixBlock) MatrixIndexes(org.apache.sysml.runtime.matrix.data.MatrixIndexes) IsBlockInRange(org.apache.sysml.runtime.instructions.spark.functions.IsBlockInRange) ReorgOperator(org.apache.sysml.runtime.matrix.operators.ReorgOperator) MatrixCharacteristics(org.apache.sysml.runtime.matrix.MatrixCharacteristics) DMLRuntimeException(org.apache.sysml.runtime.DMLRuntimeException) FilterDiagBlocksFunction(org.apache.sysml.runtime.instructions.spark.functions.FilterDiagBlocksFunction) SparkExecutionContext(org.apache.sysml.runtime.controlprogram.context.SparkExecutionContext) ReorgMapFunction(org.apache.sysml.runtime.instructions.spark.functions.ReorgMapFunction) IsBlockInList(org.apache.sysml.runtime.instructions.spark.functions.IsBlockInList)

Example 2 with IsBlockInList

use of org.apache.sysml.runtime.instructions.spark.functions.IsBlockInList in project systemml by apache.

the class ReorgSPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    String opcode = getOpcode();
    // get input rdd handle
    JavaPairRDD<MatrixIndexes, MatrixBlock> in1 = sec.getBinaryBlockRDDHandleForVariable(input1.getName());
    JavaPairRDD<MatrixIndexes, MatrixBlock> out = null;
    MatrixCharacteristics mcIn = sec.getMatrixCharacteristics(input1.getName());
    if (// TRANSPOSE
    opcode.equalsIgnoreCase("r'")) {
        // execute transpose reorg operation
        out = in1.mapToPair(new ReorgMapFunction(opcode));
    } else if (// REVERSE
    opcode.equalsIgnoreCase("rev")) {
        // execute reverse reorg operation
        out = in1.flatMapToPair(new RDDRevFunction(mcIn));
        if (mcIn.getRows() % mcIn.getRowsPerBlock() != 0)
            out = RDDAggregateUtils.mergeByKey(out, false);
    } else if (// DIAG
    opcode.equalsIgnoreCase("rdiag")) {
        if (mcIn.getCols() == 1) {
            // diagV2M
            out = in1.flatMapToPair(new RDDDiagV2MFunction(mcIn));
        } else {
            // diagM2V
            // execute diagM2V operation
            out = in1.filter(new FilterDiagBlocksFunction()).mapToPair(new ReorgMapFunction(opcode));
        }
    } else if (// ORDER
    opcode.equalsIgnoreCase("rsort")) {
        // Sort by column 'col' in ascending/descending order and return either index/value
        // get parameters
        long[] cols = _col.getDataType().isMatrix() ? DataConverter.convertToLongVector(ec.getMatrixInput(_col.getName())) : new long[] { ec.getScalarInput(_col.getName(), _col.getValueType(), _col.isLiteral()).getLongValue() };
        boolean desc = ec.getScalarInput(_desc.getName(), _desc.getValueType(), _desc.isLiteral()).getBooleanValue();
        boolean ixret = ec.getScalarInput(_ixret.getName(), _ixret.getValueType(), _ixret.isLiteral()).getBooleanValue();
        boolean singleCol = (mcIn.getCols() == 1);
        out = in1;
        if (cols.length > mcIn.getColsPerBlock())
            LOG.warn("Unsupported sort with number of order-by columns large than blocksize: " + cols.length);
        if (singleCol || cols.length == 1) {
            // extract column (if necessary) and sort
            if (!singleCol)
                out = out.filter(new IsBlockInRange(1, mcIn.getRows(), cols[0], cols[0], mcIn)).mapValues(new ExtractColumn((int) UtilFunctions.computeCellInBlock(cols[0], mcIn.getColsPerBlock())));
            // actual index/data sort operation
            if (// sort indexes
            ixret)
                out = RDDSortUtils.sortIndexesByVal(out, !desc, mcIn.getRows(), mcIn.getRowsPerBlock());
            else if (// sort single-column matrix
            singleCol && !desc)
                out = RDDSortUtils.sortByVal(out, mcIn.getRows(), mcIn.getRowsPerBlock());
            else if (// sort multi-column matrix w/ rewrite
            !_bSortIndInMem)
                out = RDDSortUtils.sortDataByVal(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), mcIn.getRowsPerBlock(), mcIn.getColsPerBlock());
            else
                // sort multi-column matrix
                out = RDDSortUtils.sortDataByValMemSort(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), mcIn.getRowsPerBlock(), mcIn.getColsPerBlock(), sec, (ReorgOperator) _optr);
        } else {
            // extract columns (if necessary)
            if (cols.length < mcIn.getCols())
                out = out.filter(new IsBlockInList(cols, mcIn)).mapToPair(new ExtractColumns(cols, mcIn));
            // append extracted columns (if necessary)
            if (mcIn.getCols() > mcIn.getColsPerBlock())
                out = RDDAggregateUtils.mergeByKey(out);
            // actual index/data sort operation
            if (// sort indexes
            ixret)
                out = RDDSortUtils.sortIndexesByVals(out, !desc, mcIn.getRows(), (long) cols.length, mcIn.getRowsPerBlock());
            else if (// sort single-column matrix
            cols.length == mcIn.getCols() && !desc)
                out = RDDSortUtils.sortByVals(out, mcIn.getRows(), cols.length, mcIn.getRowsPerBlock());
            else
                // sort multi-column matrix
                out = RDDSortUtils.sortDataByVals(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), cols.length, mcIn.getRowsPerBlock(), mcIn.getColsPerBlock());
        }
    } else {
        throw new DMLRuntimeException("Error: Incorrect opcode in ReorgSPInstruction:" + opcode);
    }
    // store output rdd handle
    if (opcode.equalsIgnoreCase("rsort") && _col.getDataType().isMatrix())
        sec.releaseMatrixInput(_col.getName());
    updateReorgMatrixCharacteristics(sec);
    sec.setRDDHandleForVariable(output.getName(), out);
    sec.addLineageRDD(output.getName(), input1.getName());
}
Also used : MatrixBlock(org.apache.sysml.runtime.matrix.data.MatrixBlock) MatrixIndexes(org.apache.sysml.runtime.matrix.data.MatrixIndexes) IsBlockInRange(org.apache.sysml.runtime.instructions.spark.functions.IsBlockInRange) ReorgOperator(org.apache.sysml.runtime.matrix.operators.ReorgOperator) MatrixCharacteristics(org.apache.sysml.runtime.matrix.MatrixCharacteristics) DMLRuntimeException(org.apache.sysml.runtime.DMLRuntimeException) FilterDiagBlocksFunction(org.apache.sysml.runtime.instructions.spark.functions.FilterDiagBlocksFunction) SparkExecutionContext(org.apache.sysml.runtime.controlprogram.context.SparkExecutionContext) ReorgMapFunction(org.apache.sysml.runtime.instructions.spark.functions.ReorgMapFunction) IsBlockInList(org.apache.sysml.runtime.instructions.spark.functions.IsBlockInList)

Aggregations

DMLRuntimeException (org.apache.sysml.runtime.DMLRuntimeException)2 SparkExecutionContext (org.apache.sysml.runtime.controlprogram.context.SparkExecutionContext)2 FilterDiagBlocksFunction (org.apache.sysml.runtime.instructions.spark.functions.FilterDiagBlocksFunction)2 IsBlockInList (org.apache.sysml.runtime.instructions.spark.functions.IsBlockInList)2 IsBlockInRange (org.apache.sysml.runtime.instructions.spark.functions.IsBlockInRange)2 ReorgMapFunction (org.apache.sysml.runtime.instructions.spark.functions.ReorgMapFunction)2 MatrixCharacteristics (org.apache.sysml.runtime.matrix.MatrixCharacteristics)2 MatrixBlock (org.apache.sysml.runtime.matrix.data.MatrixBlock)2 MatrixIndexes (org.apache.sysml.runtime.matrix.data.MatrixIndexes)2 ReorgOperator (org.apache.sysml.runtime.matrix.operators.ReorgOperator)2