Examples with Transform org.apache.sysml.lops.Transform used on opensource projects

Example 1 with Transform

use of org.apache.sysml.lops.Transform in project incubator-systemml by apache.

the class QuaternaryOp method constructMRLopsWeightedDivMM.

private void constructMRLopsWeightedDivMM(WDivMMType wtype) throws HopsException, LopsException {
    //NOTE: the common case for wdivmm are factors U/V with a rank of 10s to 100s; the current runtime only
    //supports single block outer products (U/V rank <= blocksize, i.e., 1000 by default); we enforce this
    //by applying the hop rewrite for Weighted DivMM only if this constraint holds. 
    Hop W = getInput().get(0);
    Hop U = getInput().get(1);
    Hop V = getInput().get(2);
    Hop X = getInput().get(3);
    //MR operator selection, part1
    //size U
    double m1Size = OptimizerUtils.estimateSize(U.getDim1(), U.getDim2());
    //size V
    double m2Size = OptimizerUtils.estimateSize(V.getDim1(), V.getDim2());
    boolean isMapWdivmm = ((!wtype.hasFourInputs() || wtype.hasScalar()) && m1Size + m2Size < OptimizerUtils.getRemoteMemBudgetMap(true));
    if (//broadcast
    !FORCE_REPLICATION && isMapWdivmm) {
        //partitioning of U
        boolean needPartU = !U.dimsKnown() || U.getDim1() * U.getDim2() > DistributedCacheInput.PARTITION_SIZE;
        Lop lU = U.constructLops();
        if (needPartU) {
            //requires partitioning
            lU = new DataPartition(lU, DataType.MATRIX, ValueType.DOUBLE, (m1Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
            lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), getRowsInBlock(), getColsInBlock(), U.getNnz());
            setLineNumbers(lU);
        }
        //partitioning of V
        boolean needPartV = !V.dimsKnown() || V.getDim1() * V.getDim2() > DistributedCacheInput.PARTITION_SIZE;
        Lop lV = V.constructLops();
        if (needPartV) {
            //requires partitioning
            lV = new DataPartition(lV, DataType.MATRIX, ValueType.DOUBLE, (m2Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
            lV.getOutputParameters().setDimensions(V.getDim1(), V.getDim2(), getRowsInBlock(), getColsInBlock(), V.getNnz());
            setLineNumbers(lV);
        }
        //map-side wdivmm always with broadcast
        Lop wdivmm = new WeightedDivMM(W.constructLops(), lU, lV, X.constructLops(), DataType.MATRIX, ValueType.DOUBLE, wtype, ExecType.MR);
        setOutputDimensions(wdivmm);
        setLineNumbers(wdivmm);
        setLops(wdivmm);
    } else //general case
    {
        //MR operator selection part 2 (both cannot happen for wdivmm, otherwise mapwdivmm)
        boolean cacheU = !FORCE_REPLICATION && (m1Size < OptimizerUtils.getRemoteMemBudgetReduce());
        boolean cacheV = !FORCE_REPLICATION && ((!cacheU && m2Size < OptimizerUtils.getRemoteMemBudgetReduce()) || (cacheU && m1Size + m2Size < OptimizerUtils.getRemoteMemBudgetReduce()));
        Group grpW = new Group(W.constructLops(), Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
        grpW.getOutputParameters().setDimensions(W.getDim1(), W.getDim2(), W.getRowsInBlock(), W.getColsInBlock(), W.getNnz());
        setLineNumbers(grpW);
        Lop grpX = X.constructLops();
        if (wtype.hasFourInputs() && (X.getDataType() != DataType.SCALAR))
            grpX = new Group(grpX, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
        grpX.getOutputParameters().setDimensions(X.getDim1(), X.getDim2(), X.getRowsInBlock(), X.getColsInBlock(), X.getNnz());
        setLineNumbers(grpX);
        Lop lU = null;
        if (cacheU) {
            //partitioning of U for read through distributed cache
            boolean needPartU = !U.dimsKnown() || U.getDim1() * U.getDim2() > DistributedCacheInput.PARTITION_SIZE;
            lU = U.constructLops();
            if (needPartU) {
                //requires partitioning
                lU = new DataPartition(lU, DataType.MATRIX, ValueType.DOUBLE, (m1Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
                lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), getRowsInBlock(), getColsInBlock(), U.getNnz());
                setLineNumbers(lU);
            }
        } else {
            //replication of U for shuffle to target block
            //ncol of t(V) -> nrow of V determines num replicates
            Lop offset = createOffsetLop(V, false);
            lU = new RepMat(U.constructLops(), offset, true, V.getDataType(), V.getValueType());
            lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), U.getRowsInBlock(), U.getColsInBlock(), U.getNnz());
            setLineNumbers(lU);
            Group grpU = new Group(lU, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
            grpU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), U.getRowsInBlock(), U.getColsInBlock(), -1);
            setLineNumbers(grpU);
            lU = grpU;
        }
        Lop lV = null;
        if (cacheV) {
            //partitioning of V for read through distributed cache
            boolean needPartV = !V.dimsKnown() || V.getDim1() * V.getDim2() > DistributedCacheInput.PARTITION_SIZE;
            lV = V.constructLops();
            if (needPartV) {
                //requires partitioning
                lV = new DataPartition(lV, DataType.MATRIX, ValueType.DOUBLE, (m2Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
                lV.getOutputParameters().setDimensions(V.getDim1(), V.getDim2(), getRowsInBlock(), getColsInBlock(), V.getNnz());
                setLineNumbers(lV);
            }
        } else {
            //replication of t(V) for shuffle to target block
            Transform ltV = new Transform(V.constructLops(), HopsTransf2Lops.get(ReOrgOp.TRANSPOSE), getDataType(), getValueType(), ExecType.MR);
            ltV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), V.getNnz());
            setLineNumbers(ltV);
            //nrow of U determines num replicates
            Lop offset = createOffsetLop(U, false);
            lV = new RepMat(ltV, offset, false, V.getDataType(), V.getValueType());
            lV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), V.getNnz());
            setLineNumbers(lV);
            Group grpV = new Group(lV, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
            grpV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), -1);
            setLineNumbers(grpV);
            lV = grpV;
        }
        //reduce-side wdivmm w/ or without broadcast
        Lop wdivmm = new WeightedDivMMR(grpW, lU, lV, grpX, DataType.MATRIX, ValueType.DOUBLE, wtype, cacheU, cacheV, ExecType.MR);
        setOutputDimensions(wdivmm);
        setLineNumbers(wdivmm);
        setLops(wdivmm);
    }
    //in contrast to to wsloss/wsigmoid, wdivmm requires partial aggregation (for the final mm)
    Group grp = new Group(getLops(), Group.OperationTypes.Sort, getDataType(), getValueType());
    setOutputDimensions(grp);
    setLineNumbers(grp);
    Aggregate agg1 = new Aggregate(grp, HopsAgg2Lops.get(AggOp.SUM), getDataType(), getValueType(), ExecType.MR);
    // aggregation uses kahanSum but the inputs do not have correction values
    agg1.setupCorrectionLocation(CorrectionLocationType.NONE);
    setOutputDimensions(agg1);
    setLineNumbers(agg1);
    setLops(agg1);
}

Example 2 with Transform

use of org.apache.sysml.lops.Transform in project incubator-systemml by apache.

the class QuaternaryOp method constructMRLopsWeightedCeMM.

private void constructMRLopsWeightedCeMM(WCeMMType wtype) throws HopsException, LopsException {
    //NOTE: the common case for wcemm are factors U/V with a rank of 10s to 100s; the current runtime only
    //supports single block outer products (U/V rank <= blocksize, i.e., 1000 by default); we enforce this
    //by applying the hop rewrite for Weighted Cross Entropy only if this constraint holds. 
    Hop X = getInput().get(0);
    Hop U = getInput().get(1);
    Hop V = getInput().get(2);
    Hop eps = getInput().get(3);
    //MR operator selection, part1
    //size U
    double m1Size = OptimizerUtils.estimateSize(U.getDim1(), U.getDim2());
    //size V
    double m2Size = OptimizerUtils.estimateSize(V.getDim1(), V.getDim2());
    boolean isMapWcemm = (m1Size + m2Size < OptimizerUtils.getRemoteMemBudgetMap(true));
    if (//broadcast
    !FORCE_REPLICATION && isMapWcemm) {
        //partitioning of U
        boolean needPartU = !U.dimsKnown() || U.getDim1() * U.getDim2() > DistributedCacheInput.PARTITION_SIZE;
        Lop lU = U.constructLops();
        if (needPartU) {
            //requires partitioning
            lU = new DataPartition(lU, DataType.MATRIX, ValueType.DOUBLE, (m1Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
            lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), getRowsInBlock(), getColsInBlock(), U.getNnz());
            setLineNumbers(lU);
        }
        //partitioning of V
        boolean needPartV = !V.dimsKnown() || V.getDim1() * V.getDim2() > DistributedCacheInput.PARTITION_SIZE;
        Lop lV = V.constructLops();
        if (needPartV) {
            //requires partitioning
            lV = new DataPartition(lV, DataType.MATRIX, ValueType.DOUBLE, (m2Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
            lV.getOutputParameters().setDimensions(V.getDim1(), V.getDim2(), getRowsInBlock(), getColsInBlock(), V.getNnz());
            setLineNumbers(lV);
        }
        //map-side wcemm always with broadcast
        Lop wcemm = new WeightedCrossEntropy(X.constructLops(), lU, lV, eps.constructLops(), DataType.MATRIX, ValueType.DOUBLE, wtype, ExecType.MR);
        wcemm.getOutputParameters().setDimensions(1, 1, X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(wcemm);
        Group grp = new Group(wcemm, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
        grp.getOutputParameters().setDimensions(1, 1, X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(grp);
        Aggregate agg1 = new Aggregate(grp, HopsAgg2Lops.get(AggOp.SUM), DataType.MATRIX, ValueType.DOUBLE, ExecType.MR);
        // aggregation uses kahanSum 
        agg1.setupCorrectionLocation(CorrectionLocationType.NONE);
        agg1.getOutputParameters().setDimensions(1, 1, X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(agg1);
        UnaryCP unary1 = new UnaryCP(agg1, HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR), getDataType(), getValueType());
        unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
        setLineNumbers(unary1);
        setLops(unary1);
    } else //general case
    {
        //MR operator selection part 2
        boolean cacheU = !FORCE_REPLICATION && (m1Size < OptimizerUtils.getRemoteMemBudgetReduce());
        boolean cacheV = !FORCE_REPLICATION && ((!cacheU && m2Size < OptimizerUtils.getRemoteMemBudgetReduce()) || (cacheU && m1Size + m2Size < OptimizerUtils.getRemoteMemBudgetReduce()));
        Group grpX = new Group(X.constructLops(), Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
        grpX.getOutputParameters().setDimensions(X.getDim1(), X.getDim2(), X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(grpX);
        Lop lU = null;
        if (cacheU) {
            //partitioning of U for read through distributed cache
            boolean needPartU = !U.dimsKnown() || U.getDim1() * U.getDim2() > DistributedCacheInput.PARTITION_SIZE;
            lU = U.constructLops();
            if (needPartU) {
                //requires partitioning
                lU = new DataPartition(lU, DataType.MATRIX, ValueType.DOUBLE, (m1Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
                lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), getRowsInBlock(), getColsInBlock(), U.getNnz());
                setLineNumbers(lU);
            }
        } else {
            //replication of U for shuffle to target block
            //ncol of t(V) -> nrow of V determines num replicates
            Lop offset = createOffsetLop(V, false);
            lU = new RepMat(U.constructLops(), offset, true, V.getDataType(), V.getValueType());
            lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), U.getRowsInBlock(), U.getColsInBlock(), U.getNnz());
            setLineNumbers(lU);
            Group grpU = new Group(lU, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
            grpU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), U.getRowsInBlock(), U.getColsInBlock(), -1);
            setLineNumbers(grpU);
            lU = grpU;
        }
        Lop lV = null;
        if (cacheV) {
            //partitioning of V for read through distributed cache
            boolean needPartV = !V.dimsKnown() || V.getDim1() * V.getDim2() > DistributedCacheInput.PARTITION_SIZE;
            lV = V.constructLops();
            if (needPartV) {
                //requires partitioning
                lV = new DataPartition(lV, DataType.MATRIX, ValueType.DOUBLE, (m2Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
                lV.getOutputParameters().setDimensions(V.getDim1(), V.getDim2(), getRowsInBlock(), getColsInBlock(), V.getNnz());
                setLineNumbers(lV);
            }
        } else {
            //replication of t(V) for shuffle to target block
            Transform ltV = new Transform(V.constructLops(), HopsTransf2Lops.get(ReOrgOp.TRANSPOSE), getDataType(), getValueType(), ExecType.MR);
            ltV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), V.getNnz());
            setLineNumbers(ltV);
            //nrow of U determines num replicates
            Lop offset = createOffsetLop(U, false);
            lV = new RepMat(ltV, offset, false, V.getDataType(), V.getValueType());
            lV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), V.getNnz());
            setLineNumbers(lV);
            Group grpV = new Group(lV, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
            grpV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), -1);
            setLineNumbers(grpV);
            lV = grpV;
        }
        //reduce-side wcemm w/ or without broadcast
        Lop wcemm = new WeightedCrossEntropyR(grpX, lU, lV, eps.constructLops(), DataType.MATRIX, ValueType.DOUBLE, wtype, cacheU, cacheV, ExecType.MR);
        wcemm.getOutputParameters().setDimensions(1, 1, X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(wcemm);
        Group grp = new Group(wcemm, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
        grp.getOutputParameters().setDimensions(1, 1, X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(grp);
        Aggregate agg1 = new Aggregate(grp, HopsAgg2Lops.get(AggOp.SUM), DataType.MATRIX, ValueType.DOUBLE, ExecType.MR);
        // aggregation uses kahanSum 
        agg1.setupCorrectionLocation(CorrectionLocationType.NONE);
        agg1.getOutputParameters().setDimensions(1, 1, X.getRowsInBlock(), X.getColsInBlock(), -1);
        setLineNumbers(agg1);
        UnaryCP unary1 = new UnaryCP(agg1, HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR), getDataType(), getValueType());
        unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
        setLineNumbers(unary1);
        setLops(unary1);
    }
}

Example 3 with Transform

use of org.apache.sysml.lops.Transform in project incubator-systemml by apache.

the class AggBinaryOp method constructSparkLopsMapMMWithLeftTransposeRewrite.

private Lop constructSparkLopsMapMMWithLeftTransposeRewrite() throws HopsException, LopsException {
    //guaranteed to exists
    Hop X = getInput().get(0).getInput().get(0);
    Hop Y = getInput().get(1);
    //right vector transpose
    Lop tY = new Transform(Y.constructLops(), OperationTypes.Transpose, getDataType(), getValueType(), ExecType.CP);
    tY.getOutputParameters().setDimensions(Y.getDim2(), Y.getDim1(), getRowsInBlock(), getColsInBlock(), Y.getNnz());
    setLineNumbers(tY);
    //matrix mult spark
    boolean needAgg = requiresAggregation(MMultMethod.MAPMM_R);
    SparkAggType aggtype = getSparkMMAggregationType(needAgg);
    _outputEmptyBlocks = !OptimizerUtils.allowsToFilterEmptyBlockOutputs(this);
    Lop mult = new MapMult(tY, X.constructLops(), getDataType(), getValueType(), false, false, _outputEmptyBlocks, aggtype);
    mult.getOutputParameters().setDimensions(Y.getDim2(), X.getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
    setLineNumbers(mult);
    //result transpose (dimensions set outside)
    Lop out = new Transform(mult, OperationTypes.Transpose, getDataType(), getValueType(), ExecType.CP);
    return out;
}

Example 4 with Transform

use of org.apache.sysml.lops.Transform in project incubator-systemml by apache.

the class AggBinaryOp method constructMRLopsMapMMWithLeftTransposeRewrite.

private Lop constructMRLopsMapMMWithLeftTransposeRewrite() throws HopsException, LopsException {
    //guaranteed to exists
    Hop X = getInput().get(0).getInput().get(0);
    Hop Y = getInput().get(1);
    //right vector transpose CP
    Lop tY = new Transform(Y.constructLops(), OperationTypes.Transpose, getDataType(), getValueType(), ExecType.CP);
    tY.getOutputParameters().setDimensions(Y.getDim2(), Y.getDim1(), getRowsInBlock(), getColsInBlock(), Y.getNnz());
    setLineNumbers(tY);
    //matrix mult
    // If number of columns is smaller than block size then explicit aggregation is not required.
    // i.e., entire matrix multiplication can be performed in the mappers.
    boolean needAgg = (X.getDim1() <= 0 || X.getDim1() > X.getRowsInBlock());
    //R disregarding transpose rewrite
    boolean needPart = requiresPartitioning(MMultMethod.MAPMM_R, true);
    //pre partitioning
    Lop dcinput = null;
    if (needPart) {
        ExecType etPart = (OptimizerUtils.estimateSizeExactSparsity(Y.getDim2(), Y.getDim1(), OptimizerUtils.getSparsity(Y.getDim2(), Y.getDim1(), Y.getNnz())) < OptimizerUtils.getLocalMemBudget()) ? ExecType.CP : //operator selection
        ExecType.MR;
        dcinput = new DataPartition(tY, DataType.MATRIX, ValueType.DOUBLE, etPart, PDataPartitionFormat.COLUMN_BLOCK_WISE_N);
        dcinput.getOutputParameters().setDimensions(Y.getDim2(), Y.getDim1(), getRowsInBlock(), getColsInBlock(), Y.getNnz());
        setLineNumbers(dcinput);
    } else
        dcinput = tY;
    MapMult mapmult = new MapMult(dcinput, X.constructLops(), getDataType(), getValueType(), false, needPart, false);
    mapmult.getOutputParameters().setDimensions(Y.getDim2(), X.getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
    setLineNumbers(mapmult);
    //post aggregation 
    Lop mult = null;
    if (needAgg) {
        Group grp = new Group(mapmult, Group.OperationTypes.Sort, getDataType(), getValueType());
        grp.getOutputParameters().setDimensions(Y.getDim2(), X.getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
        setLineNumbers(grp);
        Aggregate agg1 = new Aggregate(grp, HopsAgg2Lops.get(outerOp), getDataType(), getValueType(), ExecType.MR);
        agg1.getOutputParameters().setDimensions(Y.getDim2(), X.getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
        setLineNumbers(agg1);
        agg1.setupCorrectionLocation(CorrectionLocationType.NONE);
        mult = agg1;
    } else
        mult = mapmult;
    //result transpose CP 
    Lop out = new Transform(mult, OperationTypes.Transpose, getDataType(), getValueType(), ExecType.CP);
    out.getOutputParameters().setDimensions(X.getDim2(), Y.getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
    return out;
}

Example 5 with Transform

use of org.apache.sysml.lops.Transform in project incubator-systemml by apache.

the class QuaternaryOp method constructMRLopsWeightedUMM.

private void constructMRLopsWeightedUMM(WUMMType wtype) throws HopsException, LopsException {
    //NOTE: the common case for wumm are factors U/V with a rank of 10s to 100s; the current runtime only
    //supports single block outer products (U/V rank <= blocksize, i.e., 1000 by default); we enforce this
    //by applying the hop rewrite for Weighted UnaryMM  only if this constraint holds. 
    Unary.OperationTypes uop = _uop != null ? HopsOpOp1LopsU.get(_uop) : _sop == OpOp2.POW ? Unary.OperationTypes.POW2 : Unary.OperationTypes.MULTIPLY2;
    Hop X = getInput().get(0);
    Hop U = getInput().get(1);
    Hop V = getInput().get(2);
    //MR operator selection, part1
    //size U
    double m1Size = OptimizerUtils.estimateSize(U.getDim1(), U.getDim2());
    //size V
    double m2Size = OptimizerUtils.estimateSize(V.getDim1(), V.getDim2());
    boolean isMapWumm = (m1Size + m2Size < OptimizerUtils.getRemoteMemBudgetMap(true));
    if (//broadcast
    !FORCE_REPLICATION && isMapWumm) {
        //partitioning of U
        boolean needPartU = !U.dimsKnown() || U.getDim1() * U.getDim2() > DistributedCacheInput.PARTITION_SIZE;
        Lop lU = U.constructLops();
        if (needPartU) {
            //requires partitioning
            lU = new DataPartition(lU, DataType.MATRIX, ValueType.DOUBLE, (m1Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
            lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), getRowsInBlock(), getColsInBlock(), U.getNnz());
            setLineNumbers(lU);
        }
        //partitioning of V
        boolean needPartV = !V.dimsKnown() || V.getDim1() * V.getDim2() > DistributedCacheInput.PARTITION_SIZE;
        Lop lV = V.constructLops();
        if (needPartV) {
            //requires partitioning
            lV = new DataPartition(lV, DataType.MATRIX, ValueType.DOUBLE, (m2Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
            lV.getOutputParameters().setDimensions(V.getDim1(), V.getDim2(), getRowsInBlock(), getColsInBlock(), V.getNnz());
            setLineNumbers(lV);
        }
        //map-side wumm always with broadcast
        Lop wumm = new WeightedUnaryMM(X.constructLops(), lU, lV, DataType.MATRIX, ValueType.DOUBLE, wtype, uop, ExecType.MR);
        setOutputDimensions(wumm);
        setLineNumbers(wumm);
        setLops(wumm);
    //in contrast to wsloss no aggregation required 
    } else //general case
    {
        //MR operator selection part 2
        boolean cacheU = !FORCE_REPLICATION && (m1Size < OptimizerUtils.getRemoteMemBudgetReduce());
        boolean cacheV = !FORCE_REPLICATION && ((!cacheU && m2Size < OptimizerUtils.getRemoteMemBudgetReduce()) || (cacheU && m1Size + m2Size < OptimizerUtils.getRemoteMemBudgetReduce()));
        Group grpX = new Group(X.constructLops(), Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
        grpX.getOutputParameters().setDimensions(X.getDim1(), X.getDim2(), X.getRowsInBlock(), X.getColsInBlock(), X.getNnz());
        setLineNumbers(grpX);
        Lop lU = null;
        if (cacheU) {
            //partitioning of U for read through distributed cache
            boolean needPartU = !U.dimsKnown() || U.getDim1() * U.getDim2() > DistributedCacheInput.PARTITION_SIZE;
            lU = U.constructLops();
            if (needPartU) {
                //requires partitioning
                lU = new DataPartition(lU, DataType.MATRIX, ValueType.DOUBLE, (m1Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
                lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), getRowsInBlock(), getColsInBlock(), U.getNnz());
                setLineNumbers(lU);
            }
        } else {
            //replication of U for shuffle to target block
            //ncol of t(V) -> nrow of V determines num replicates
            Lop offset = createOffsetLop(V, false);
            lU = new RepMat(U.constructLops(), offset, true, V.getDataType(), V.getValueType());
            lU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), U.getRowsInBlock(), U.getColsInBlock(), U.getNnz());
            setLineNumbers(lU);
            Group grpU = new Group(lU, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
            grpU.getOutputParameters().setDimensions(U.getDim1(), U.getDim2(), U.getRowsInBlock(), U.getColsInBlock(), -1);
            setLineNumbers(grpU);
            lU = grpU;
        }
        Lop lV = null;
        if (cacheV) {
            //partitioning of V for read through distributed cache
            boolean needPartV = !V.dimsKnown() || V.getDim1() * V.getDim2() > DistributedCacheInput.PARTITION_SIZE;
            lV = V.constructLops();
            if (needPartV) {
                //requires partitioning
                lV = new DataPartition(lV, DataType.MATRIX, ValueType.DOUBLE, (m2Size > OptimizerUtils.getLocalMemBudget()) ? ExecType.MR : ExecType.CP, PDataPartitionFormat.ROW_BLOCK_WISE_N);
                lV.getOutputParameters().setDimensions(V.getDim1(), V.getDim2(), getRowsInBlock(), getColsInBlock(), V.getNnz());
                setLineNumbers(lV);
            }
        } else {
            //replication of t(V) for shuffle to target block
            Transform ltV = new Transform(V.constructLops(), HopsTransf2Lops.get(ReOrgOp.TRANSPOSE), getDataType(), getValueType(), ExecType.MR);
            ltV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), V.getNnz());
            setLineNumbers(ltV);
            //nrow of U determines num replicates
            Lop offset = createOffsetLop(U, false);
            lV = new RepMat(ltV, offset, false, V.getDataType(), V.getValueType());
            lV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), V.getNnz());
            setLineNumbers(lV);
            Group grpV = new Group(lV, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
            grpV.getOutputParameters().setDimensions(V.getDim2(), V.getDim1(), V.getColsInBlock(), V.getRowsInBlock(), -1);
            setLineNumbers(grpV);
            lV = grpV;
        }
        //reduce-side wumm w/ or without broadcast
        Lop wumm = new WeightedUnaryMMR(grpX, lU, lV, DataType.MATRIX, ValueType.DOUBLE, wtype, uop, cacheU, cacheV, ExecType.MR);
        setOutputDimensions(wumm);
        setLineNumbers(wumm);
        setLops(wumm);
    //in contrast to wsloss no aggregation required 	
    }
}