Examples with MatrixIndexes org.apache.sysml.runtime.matrix.data.MatrixIndexes used on opensource projects

Example 6 with MatrixIndexes

use of org.apache.sysml.runtime.matrix.data.MatrixIndexes in project incubator-systemml by apache.

the class ReorgSPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) throws DMLRuntimeException {
    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 col = 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);
        // extract column (if necessary) and sort 
        out = in1;
        if (!singleCol) {
            out = out.filter(new IsBlockInRange(1, mcIn.getRows(), col, col, mcIn)).mapValues(new ExtractColumn((int) UtilFunctions.computeCellInBlock(col, mcIn.getColsPerBlock())));
        }
        //actual index/data sort operation
        if (ixret) {
            //sort indexes 
            out = RDDSortUtils.sortIndexesByVal(out, !desc, mcIn.getRows(), mcIn.getRowsPerBlock());
        } else if (singleCol && !desc) {
            //sort single-column matrix
            out = RDDSortUtils.sortByVal(out, mcIn.getRows(), mcIn.getRowsPerBlock());
        } else {
            //sort multi-column matrix
            if (!_bSortIndInMem)
                out = RDDSortUtils.sortDataByVal(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), mcIn.getRowsPerBlock(), mcIn.getColsPerBlock());
            else
                out = RDDSortUtils.sortDataByValMemSort(out, in1, !desc, mcIn.getRows(), mcIn.getCols(), mcIn.getRowsPerBlock(), mcIn.getColsPerBlock(), sec, (ReorgOperator) _optr);
        }
    } else {
        throw new DMLRuntimeException("Error: Incorrect opcode in ReorgSPInstruction:" + opcode);
    }
    //store output rdd handle
    updateReorgMatrixCharacteristics(sec);
    sec.setRDDHandleForVariable(output.getName(), out);
    sec.addLineageRDD(output.getName(), input1.getName());
}

Example 7 with MatrixIndexes

use of org.apache.sysml.runtime.matrix.data.MatrixIndexes in project incubator-systemml by apache.

the class QuaternarySPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) throws DMLRuntimeException {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    QuaternaryOperator qop = (QuaternaryOperator) _optr;
    //tracking of rdds and broadcasts (for lineage maintenance)
    ArrayList<String> rddVars = new ArrayList<String>();
    ArrayList<String> bcVars = new ArrayList<String>();
    JavaPairRDD<MatrixIndexes, MatrixBlock> in = sec.getBinaryBlockRDDHandleForVariable(input1.getName());
    JavaPairRDD<MatrixIndexes, MatrixBlock> out = null;
    MatrixCharacteristics inMc = sec.getMatrixCharacteristics(input1.getName());
    long rlen = inMc.getRows();
    long clen = inMc.getCols();
    int brlen = inMc.getRowsPerBlock();
    int bclen = inMc.getColsPerBlock();
    //(map/redwsloss, map/redwcemm); safe because theses ops produce a scalar
    if (qop.wtype1 != null || qop.wtype4 != null) {
        in = in.filter(new FilterNonEmptyBlocksFunction());
    }
    //map-side only operation (one rdd input, two broadcasts)
    if (WeightedSquaredLoss.OPCODE.equalsIgnoreCase(getOpcode()) || WeightedSigmoid.OPCODE.equalsIgnoreCase(getOpcode()) || WeightedDivMM.OPCODE.equalsIgnoreCase(getOpcode()) || WeightedCrossEntropy.OPCODE.equalsIgnoreCase(getOpcode()) || WeightedUnaryMM.OPCODE.equalsIgnoreCase(getOpcode())) {
        PartitionedBroadcast<MatrixBlock> bc1 = sec.getBroadcastForVariable(input2.getName());
        PartitionedBroadcast<MatrixBlock> bc2 = sec.getBroadcastForVariable(input3.getName());
        //partitioning-preserving mappartitions (key access required for broadcast loopkup)
        //only wdivmm changes keys
        boolean noKeyChange = (qop.wtype3 == null || qop.wtype3.isBasic());
        out = in.mapPartitionsToPair(new RDDQuaternaryFunction1(qop, bc1, bc2), noKeyChange);
        rddVars.add(input1.getName());
        bcVars.add(input2.getName());
        bcVars.add(input3.getName());
    } else //reduce-side operation (two/three/four rdd inputs, zero/one/two broadcasts)
    {
        PartitionedBroadcast<MatrixBlock> bc1 = _cacheU ? sec.getBroadcastForVariable(input2.getName()) : null;
        PartitionedBroadcast<MatrixBlock> bc2 = _cacheV ? sec.getBroadcastForVariable(input3.getName()) : null;
        JavaPairRDD<MatrixIndexes, MatrixBlock> inU = (!_cacheU) ? sec.getBinaryBlockRDDHandleForVariable(input2.getName()) : null;
        JavaPairRDD<MatrixIndexes, MatrixBlock> inV = (!_cacheV) ? sec.getBinaryBlockRDDHandleForVariable(input3.getName()) : null;
        JavaPairRDD<MatrixIndexes, MatrixBlock> inW = (qop.hasFourInputs() && !_input4.isLiteral()) ? sec.getBinaryBlockRDDHandleForVariable(_input4.getName()) : null;
        //preparation of transposed and replicated U
        if (inU != null)
            inU = inU.flatMapToPair(new ReplicateBlocksFunction(clen, bclen, true));
        //preparation of transposed and replicated V
        if (inV != null)
            inV = inV.mapToPair(new TransposeFactorIndexesFunction()).flatMapToPair(new ReplicateBlocksFunction(rlen, brlen, false));
        //functions calls w/ two rdd inputs		
        if (inU != null && inV == null && inW == null)
            out = in.join(inU).mapToPair(new RDDQuaternaryFunction2(qop, bc1, bc2));
        else if (inU == null && inV != null && inW == null)
            out = in.join(inV).mapToPair(new RDDQuaternaryFunction2(qop, bc1, bc2));
        else if (inU == null && inV == null && inW != null)
            out = in.join(inW).mapToPair(new RDDQuaternaryFunction2(qop, bc1, bc2));
        else //function calls w/ three rdd inputs
        if (inU != null && inV != null && inW == null)
            out = in.join(inU).join(inV).mapToPair(new RDDQuaternaryFunction3(qop, bc1, bc2));
        else if (inU != null && inV == null && inW != null)
            out = in.join(inU).join(inW).mapToPair(new RDDQuaternaryFunction3(qop, bc1, bc2));
        else if (inU == null && inV != null && inW != null)
            out = in.join(inV).join(inW).mapToPair(new RDDQuaternaryFunction3(qop, bc1, bc2));
        else if (inU == null && inV == null && inW == null) {
            out = in.mapPartitionsToPair(new RDDQuaternaryFunction1(qop, bc1, bc2), false);
        } else
            //function call w/ four rdd inputs
            //need keys in case of wdivmm 
            out = in.join(inU).join(inV).join(inW).mapToPair(new RDDQuaternaryFunction4(qop));
        //keep variable names for lineage maintenance
        if (inU == null)
            bcVars.add(input2.getName());
        else
            rddVars.add(input2.getName());
        if (inV == null)
            bcVars.add(input3.getName());
        else
            rddVars.add(input3.getName());
        if (inW != null)
            rddVars.add(_input4.getName());
    }
    //output handling, incl aggregation
    if (//map/redwsloss, map/redwcemm
    qop.wtype1 != null || qop.wtype4 != null) {
        //full aggregate and cast to scalar
        MatrixBlock tmp = RDDAggregateUtils.sumStable(out);
        DoubleObject ret = new DoubleObject(tmp.getValue(0, 0));
        sec.setVariable(output.getName(), ret);
    } else //map/redwsigmoid, map/redwdivmm, map/redwumm 
    {
        //aggregation if required (map/redwdivmm)
        if (qop.wtype3 != null && !qop.wtype3.isBasic())
            out = RDDAggregateUtils.sumByKeyStable(out, false);
        //put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        //maintain lineage information for output rdd
        for (String rddVar : rddVars) sec.addLineageRDD(output.getName(), rddVar);
        for (String bcVar : bcVars) sec.addLineageBroadcast(output.getName(), bcVar);
        //update matrix characteristics
        updateOutputMatrixCharacteristics(sec, qop);
    }
}

Example 8 with MatrixIndexes

use of org.apache.sysml.runtime.matrix.data.MatrixIndexes in project incubator-systemml by apache.

the class RandSPInstruction method generateSequence.

private void generateSequence(SparkExecutionContext sec) throws DMLRuntimeException {
    //sanity check valid increment
    if (seq_incr == 0) {
        throw new DMLRuntimeException("ERROR: While performing seq(" + seq_from + "," + seq_to + "," + seq_incr + ")");
    }
    //handle default 1 to -1 for special case of from>to
    seq_incr = LibMatrixDatagen.updateSeqIncr(seq_from, seq_to, seq_incr);
    if (LOG.isTraceEnabled())
        LOG.trace("Process RandSPInstruction seq with seqFrom=" + seq_from + ", seqTo=" + seq_to + ", seqIncr" + seq_incr);
    //step 1: offset generation 
    JavaRDD<Double> offsetsRDD = null;
    long nnz = (long) Math.abs(Math.round((seq_to - seq_from) / seq_incr)) + 1;
    double totalSize = OptimizerUtils.estimatePartitionedSizeExactSparsity(nnz, 1, rowsInBlock, colsInBlock, //overestimate for on disk, ensures hdfs block per partition
    nnz);
    double hdfsBlkSize = InfrastructureAnalyzer.getHDFSBlockSize();
    long numBlocks = (long) Math.ceil(((double) nnz) / rowsInBlock);
    //a) in-memory offset rdd construction 
    if (numBlocks < INMEMORY_NUMBLOCKS_THRESHOLD) {
        ArrayList<Double> offsets = new ArrayList<Double>();
        for (long i = 0; i < numBlocks; i++) {
            double off = seq_from + seq_incr * i * rowsInBlock;
            offsets.add(off);
        }
        //for load balancing: degree of parallelism such that ~128MB per partition
        int numPartitions = (int) Math.max(Math.min(totalSize / hdfsBlkSize, numBlocks), 1);
        //create offset rdd
        offsetsRDD = sec.getSparkContext().parallelize(offsets, numPartitions);
    } else //b) file-based offset rdd construction (for robustness wrt large number of blocks)
    {
        Path path = new Path(LibMatrixDatagen.generateUniqueSeedPath(dir));
        PrintWriter pw = null;
        try {
            FileSystem fs = IOUtilFunctions.getFileSystem(path);
            pw = new PrintWriter(fs.create(path));
            for (long i = 0; i < numBlocks; i++) {
                double off = seq_from + seq_incr * i * rowsInBlock;
                pw.println(off);
            }
        } catch (IOException ex) {
            throw new DMLRuntimeException(ex);
        } finally {
            IOUtilFunctions.closeSilently(pw);
        }
        //for load balancing: degree of parallelism such that ~128MB per partition
        int numPartitions = (int) Math.max(Math.min(totalSize / hdfsBlkSize, numBlocks), 1);
        //create seeds rdd 
        offsetsRDD = sec.getSparkContext().textFile(path.toString(), numPartitions).map(new ExtractOffsetTuple());
    }
    //sanity check number of non-zeros
    if (nnz != rows && rows != -1) {
        throw new DMLRuntimeException("Incorrect number of non-zeros: " + nnz + " != " + rows);
    }
    //step 2: execute seq instruction over offset input
    JavaPairRDD<MatrixIndexes, MatrixBlock> out = offsetsRDD.mapToPair(new GenerateSequenceBlock(rowsInBlock, seq_from, seq_to, seq_incr));
    //step 3: output handling
    MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
    if (!mcOut.dimsKnown()) {
        mcOut.set(nnz, 1, rowsInBlock, colsInBlock, nnz);
    }
    sec.setRDDHandleForVariable(output.getName(), out);
}

Example 9 with MatrixIndexes

use of org.apache.sysml.runtime.matrix.data.MatrixIndexes in project incubator-systemml by apache.

the class RandSPInstruction method generateRandData.

private void generateRandData(SparkExecutionContext sec) throws DMLRuntimeException {
    //step 1: generate pseudo-random seed (because not specified) 
    //seed per invocation
    long lSeed = seed;
    if (lSeed == DataGenOp.UNSPECIFIED_SEED)
        lSeed = DataGenOp.generateRandomSeed();
    if (LOG.isTraceEnabled())
        LOG.trace("Process RandSPInstruction rand with seed = " + lSeed + ".");
    //step 2: potential in-memory rand operations if applicable
    if (isMemAvail(rows, cols, sparsity, minValue, maxValue) && DMLScript.rtplatform != RUNTIME_PLATFORM.SPARK) {
        RandomMatrixGenerator rgen = LibMatrixDatagen.createRandomMatrixGenerator(pdf, (int) rows, (int) cols, rowsInBlock, colsInBlock, sparsity, minValue, maxValue, pdfParams);
        MatrixBlock mb = MatrixBlock.randOperations(rgen, lSeed);
        sec.setMatrixOutput(output.getName(), mb);
        Statistics.decrementNoOfExecutedSPInst();
        return;
    }
    //step 3: seed generation 
    JavaPairRDD<MatrixIndexes, Tuple2<Long, Long>> seedsRDD = null;
    Well1024a bigrand = LibMatrixDatagen.setupSeedsForRand(lSeed);
    LongStream nnz = LibMatrixDatagen.computeNNZperBlock(rows, cols, rowsInBlock, colsInBlock, sparsity);
    PrimitiveIterator.OfLong nnzIter = nnz.iterator();
    double totalSize = OptimizerUtils.estimatePartitionedSizeExactSparsity(rows, cols, rowsInBlock, colsInBlock, //overestimate for on disk, ensures hdfs block per partition
    rows * cols * sparsity);
    double hdfsBlkSize = InfrastructureAnalyzer.getHDFSBlockSize();
    long numBlocks = new MatrixCharacteristics(rows, cols, rowsInBlock, colsInBlock).getNumBlocks();
    long numColBlocks = (long) Math.ceil((double) cols / (double) colsInBlock);
    //a) in-memory seed rdd construction 
    if (numBlocks < INMEMORY_NUMBLOCKS_THRESHOLD) {
        ArrayList<Tuple2<MatrixIndexes, Tuple2<Long, Long>>> seeds = new ArrayList<Tuple2<MatrixIndexes, Tuple2<Long, Long>>>();
        for (long i = 0; i < numBlocks; i++) {
            long r = 1 + i / numColBlocks;
            long c = 1 + i % numColBlocks;
            MatrixIndexes indx = new MatrixIndexes(r, c);
            Long seedForBlock = bigrand.nextLong();
            seeds.add(new Tuple2<MatrixIndexes, Tuple2<Long, Long>>(indx, new Tuple2<Long, Long>(seedForBlock, nnzIter.nextLong())));
        }
        //for load balancing: degree of parallelism such that ~128MB per partition
        int numPartitions = (int) Math.max(Math.min(totalSize / hdfsBlkSize, numBlocks), 1);
        //create seeds rdd 
        seedsRDD = sec.getSparkContext().parallelizePairs(seeds, numPartitions);
    } else //b) file-based seed rdd construction (for robustness wrt large number of blocks)
    {
        Path path = new Path(LibMatrixDatagen.generateUniqueSeedPath(dir));
        PrintWriter pw = null;
        try {
            FileSystem fs = IOUtilFunctions.getFileSystem(path);
            pw = new PrintWriter(fs.create(path));
            StringBuilder sb = new StringBuilder();
            for (long i = 0; i < numBlocks; i++) {
                sb.append(1 + i / numColBlocks);
                sb.append(',');
                sb.append(1 + i % numColBlocks);
                sb.append(',');
                sb.append(bigrand.nextLong());
                sb.append(',');
                sb.append(nnzIter.nextLong());
                pw.println(sb.toString());
                sb.setLength(0);
            }
        } catch (IOException ex) {
            throw new DMLRuntimeException(ex);
        } finally {
            IOUtilFunctions.closeSilently(pw);
        }
        //for load balancing: degree of parallelism such that ~128MB per partition
        int numPartitions = (int) Math.max(Math.min(totalSize / hdfsBlkSize, numBlocks), 1);
        //create seeds rdd 
        seedsRDD = sec.getSparkContext().textFile(path.toString(), numPartitions).mapToPair(new ExtractSeedTuple());
    }
    //step 4: execute rand instruction over seed input
    JavaPairRDD<MatrixIndexes, MatrixBlock> out = seedsRDD.mapToPair(new GenerateRandomBlock(rows, cols, rowsInBlock, colsInBlock, sparsity, minValue, maxValue, pdf, pdfParams));
    //step 5: output handling
    MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
    if (!mcOut.dimsKnown(true)) {
        //note: we cannot compute the nnz from sparsity because this would not reflect the 
        //actual number of non-zeros, except for extreme values of sparsity equals 0 or 1.
        long lnnz = (sparsity == 0 || sparsity == 1) ? (long) (sparsity * rows * cols) : -1;
        mcOut.set(rows, cols, rowsInBlock, colsInBlock, lnnz);
    }
    sec.setRDDHandleForVariable(output.getName(), out);
}

Example 10 with MatrixIndexes

use of org.apache.sysml.runtime.matrix.data.MatrixIndexes in project incubator-systemml by apache.

the class RandSPInstruction method generateSample.

/**
	 * Helper function to construct a sample.
	 * 
	 * @param sec spark execution context
	 * @throws DMLRuntimeException if DMLRuntimeException occurs
	 */
private void generateSample(SparkExecutionContext sec) throws DMLRuntimeException {
    if (maxValue < rows && !replace)
        throw new DMLRuntimeException("Sample (size=" + rows + ") larger than population (size=" + maxValue + ") can only be generated with replacement.");
    if (LOG.isTraceEnabled())
        LOG.trace("Process RandSPInstruction sample with range=" + maxValue + ", size=" + rows + ", replace=" + replace + ", seed=" + seed);
    // sampling rate that guarantees a sample of size >= sampleSizeLowerBound 99.99% of the time.
    double fraction = SamplingUtils.computeFractionForSampleSize((int) rows, UtilFunctions.toLong(maxValue), replace);
    Well1024a bigrand = LibMatrixDatagen.setupSeedsForRand(seed);
    // divide the population range across numPartitions by creating SampleTasks
    double hdfsBlockSize = InfrastructureAnalyzer.getHDFSBlockSize();
    long outputSize = MatrixBlock.estimateSizeDenseInMemory(rows, 1);
    int numPartitions = (int) Math.ceil((double) outputSize / hdfsBlockSize);
    long partitionSize = (long) Math.ceil(maxValue / numPartitions);
    ArrayList<SampleTask> offsets = new ArrayList<SampleTask>();
    long st = 1;
    while (st <= maxValue) {
        SampleTask s = new SampleTask();
        s.range_start = st;
        s.seed = bigrand.nextLong();
        offsets.add(s);
        st = st + partitionSize;
    }
    JavaRDD<SampleTask> offsetRDD = sec.getSparkContext().parallelize(offsets, numPartitions);
    // Construct the sample in a distributed manner
    JavaRDD<Double> rdd = offsetRDD.flatMap((new GenerateSampleBlock(replace, fraction, (long) maxValue, partitionSize)));
    // Randomize the sampled elements
    JavaRDD<Double> randomizedRDD = rdd.mapToPair(new AttachRandom()).sortByKey().values();
    // Trim the sampled list to required size & attach matrix indexes to randomized elements
    JavaPairRDD<MatrixIndexes, MatrixCell> miRDD = randomizedRDD.zipWithIndex().filter(new TrimSample(rows)).mapToPair(new Double2MatrixCell());
    MatrixCharacteristics mcOut = new MatrixCharacteristics(rows, 1, rowsInBlock, colsInBlock, rows);
    // Construct BinaryBlock representation
    JavaPairRDD<MatrixIndexes, MatrixBlock> mbRDD = RDDConverterUtils.binaryCellToBinaryBlock(sec.getSparkContext(), miRDD, mcOut, true);
    MatrixCharacteristics retDims = sec.getMatrixCharacteristics(output.getName());
    retDims.setNonZeros(rows);
    sec.setRDDHandleForVariable(output.getName(), mbRDD);
}