Examples with DMLRuntimeException org.apache.sysml.runtime.DMLRuntimeException used on opensource projects

Example 11 with DMLRuntimeException

use of org.apache.sysml.runtime.DMLRuntimeException in project incubator-systemml by apache.

the class ReblockSPInstruction method processMatrixReblockInstruction.

@SuppressWarnings("unchecked")
protected void processMatrixReblockInstruction(SparkExecutionContext sec, InputInfo iinfo) throws DMLRuntimeException {
    MatrixObject mo = sec.getMatrixObject(input1.getName());
    MatrixCharacteristics mc = sec.getMatrixCharacteristics(input1.getName());
    MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
    if (iinfo == InputInfo.TextCellInputInfo || iinfo == InputInfo.MatrixMarketInputInfo) {
        //check jdk version (prevent double.parseDouble contention on <jdk8)
        sec.checkAndRaiseValidationWarningJDKVersion();
        //get the input textcell rdd
        JavaPairRDD<LongWritable, Text> lines = (JavaPairRDD<LongWritable, Text>) sec.getRDDHandleForVariable(input1.getName(), iinfo);
        //convert textcell to binary block
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = RDDConverterUtils.textCellToBinaryBlock(sec.getSparkContext(), lines, mcOut, outputEmptyBlocks);
        //put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
    } else if (iinfo == InputInfo.CSVInputInfo) {
        // HACK ALERT: Until we introduces the rewrite to insert csvrblock for non-persistent read
        // throw new DMLRuntimeException("CSVInputInfo is not supported for ReblockSPInstruction");
        CSVReblockSPInstruction csvInstruction = null;
        boolean hasHeader = false;
        String delim = ",";
        boolean fill = false;
        double fillValue = 0;
        if (mo.getFileFormatProperties() instanceof CSVFileFormatProperties && mo.getFileFormatProperties() != null) {
            CSVFileFormatProperties props = (CSVFileFormatProperties) mo.getFileFormatProperties();
            hasHeader = props.hasHeader();
            delim = props.getDelim();
            fill = props.isFill();
            fillValue = props.getFillValue();
        }
        csvInstruction = new CSVReblockSPInstruction(null, input1, output, mcOut.getRowsPerBlock(), mcOut.getColsPerBlock(), hasHeader, delim, fill, fillValue, "csvrblk", instString);
        csvInstruction.processInstruction(sec);
        return;
    } else if (iinfo == InputInfo.BinaryCellInputInfo) {
        JavaPairRDD<MatrixIndexes, MatrixCell> binaryCells = (JavaPairRDD<MatrixIndexes, MatrixCell>) sec.getRDDHandleForVariable(input1.getName(), iinfo);
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = RDDConverterUtils.binaryCellToBinaryBlock(sec.getSparkContext(), binaryCells, mcOut, outputEmptyBlocks);
        //put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
    } else if (iinfo == InputInfo.BinaryBlockInputInfo) {
        //BINARY BLOCK <- BINARY BLOCK (different sizes)
        JavaPairRDD<MatrixIndexes, MatrixBlock> in1 = sec.getBinaryBlockRDDHandleForVariable(input1.getName());
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = in1.flatMapToPair(new ExtractBlockForBinaryReblock(mc, mcOut));
        out = RDDAggregateUtils.mergeByKey(out, false);
        //put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
    } else {
        throw new DMLRuntimeException("The given InputInfo is not implemented " + "for ReblockSPInstruction:" + InputInfo.inputInfoToString(iinfo));
    }
}

Example 12 with DMLRuntimeException

use of org.apache.sysml.runtime.DMLRuntimeException in project incubator-systemml by apache.

the class ReblockSPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) throws DMLRuntimeException {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    //set the output characteristics
    CacheableData<?> obj = sec.getCacheableData(input1.getName());
    MatrixCharacteristics mc = sec.getMatrixCharacteristics(input1.getName());
    MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
    mcOut.set(mc.getRows(), mc.getCols(), brlen, bclen, mc.getNonZeros());
    //get the source format form the meta data
    MatrixFormatMetaData iimd = (MatrixFormatMetaData) obj.getMetaData();
    if (iimd == null)
        throw new DMLRuntimeException("Error: Metadata not found");
    InputInfo iinfo = iimd.getInputInfo();
    //check for in-memory reblock (w/ lazy spark context, potential for latency reduction)
    if (Recompiler.checkCPReblock(sec, input1.getName())) {
        if (input1.getDataType() == DataType.MATRIX)
            Recompiler.executeInMemoryMatrixReblock(sec, input1.getName(), output.getName());
        else if (input1.getDataType() == DataType.FRAME)
            Recompiler.executeInMemoryFrameReblock(sec, input1.getName(), output.getName());
        return;
    }
    //execute matrix/frame reblock
    if (input1.getDataType() == DataType.MATRIX)
        processMatrixReblockInstruction(sec, iinfo);
    else if (input1.getDataType() == DataType.FRAME)
        processFrameReblockInstruction(sec, iinfo);
}

Example 13 with DMLRuntimeException

use of org.apache.sysml.runtime.DMLRuntimeException 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 14 with DMLRuntimeException

use of org.apache.sysml.runtime.DMLRuntimeException 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 15 with DMLRuntimeException

use of org.apache.sysml.runtime.DMLRuntimeException 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);
}