Examples with SeqInstruction org.apache.sysml.runtime.instructions.mr.SeqInstruction used on opensource projects

Example 1 with SeqInstruction

use of org.apache.sysml.runtime.instructions.mr.SeqInstruction in project incubator-systemml by apache.

the class Recompiler method checkCPDataGen.

public static boolean checkCPDataGen(MRJobInstruction inst, String updatedRandInst) {
    boolean ret = true;
    // check only shuffle inst
    String shuffleInst = inst.getIv_shuffleInstructions();
    String rrInst = inst.getIv_recordReaderInstructions();
    String mapInst = inst.getIv_instructionsInMapper();
    String aggInst = inst.getIv_aggInstructions();
    String otherInst = inst.getIv_otherInstructions();
    if ((shuffleInst != null && shuffleInst.length() > 0) || (rrInst != null && rrInst.length() > 0) || (mapInst != null && mapInst.length() > 0) || (aggInst != null && aggInst.length() > 0) || (otherInst != null && otherInst.length() > 0)) {
        ret = false;
    }
    // check only rand inst
    if (ret) {
        String[] instParts = updatedRandInst.split(Lop.INSTRUCTION_DELIMITOR);
        for (String lrandStr : instParts) {
            if (InstructionUtils.getOpCode(lrandStr).equals(DataGen.RAND_OPCODE)) {
                // check recompile memory budget
                RandInstruction lrandInst = (RandInstruction) RandInstruction.parseInstruction(lrandStr);
                long rows = lrandInst.getRows();
                long cols = lrandInst.getCols();
                double sparsity = lrandInst.getSparsity();
                double mem = MatrixBlock.estimateSizeInMemory(rows, cols, sparsity);
                if (!OptimizerUtils.isValidCPDimensions(rows, cols) || !OptimizerUtils.isValidCPMatrixSize(rows, cols, sparsity) || mem >= OptimizerUtils.getLocalMemBudget()) {
                    ret = false;
                    break;
                }
            } else if (InstructionUtils.getOpCode(lrandStr).equals(DataGen.SEQ_OPCODE)) {
                // check recompile memory budget
                // (don't account for sparsity because always dense)
                SeqInstruction lrandInst = (SeqInstruction) SeqInstruction.parseInstruction(lrandStr);
                long rows = lrandInst.getRows();
                long cols = lrandInst.getCols();
                double mem = MatrixBlock.estimateSizeInMemory(rows, cols, 1.0d);
                if (!OptimizerUtils.isValidCPDimensions(rows, cols) || !OptimizerUtils.isValidCPMatrixSize(rows, cols, 1.0d) || mem >= OptimizerUtils.getLocalMemBudget()) {
                    ret = false;
                    break;
                }
            } else {
                ret = false;
                break;
            }
        }
    }
    return ret;
}

Example 2 with SeqInstruction

use of org.apache.sysml.runtime.instructions.mr.SeqInstruction in project incubator-systemml by apache.

the class MatrixCharacteristics method computeDimension.

public static void computeDimension(HashMap<Byte, MatrixCharacteristics> dims, MRInstruction ins) {
    MatrixCharacteristics dimOut = dims.get(ins.output);
    if (dimOut == null) {
        dimOut = new MatrixCharacteristics();
        dims.put(ins.output, dimOut);
    }
    if (ins instanceof ReorgInstruction) {
        ReorgInstruction realIns = (ReorgInstruction) ins;
        reorg(dims.get(realIns.input), (ReorgOperator) realIns.getOperator(), dimOut);
    } else if (ins instanceof AppendInstruction) {
        AppendInstruction realIns = (AppendInstruction) ins;
        MatrixCharacteristics in_dim1 = dims.get(realIns.input1);
        MatrixCharacteristics in_dim2 = dims.get(realIns.input2);
        if (realIns.isCBind())
            dimOut.set(in_dim1.numRows, in_dim1.numColumns + in_dim2.numColumns, in_dim1.numRowsPerBlock, in_dim2.numColumnsPerBlock);
        else
            dimOut.set(in_dim1.numRows + in_dim2.numRows, in_dim1.numColumns, in_dim1.numRowsPerBlock, in_dim2.numColumnsPerBlock);
    } else if (ins instanceof CumulativeAggregateInstruction) {
        AggregateUnaryInstruction realIns = (AggregateUnaryInstruction) ins;
        MatrixCharacteristics in = dims.get(realIns.input);
        dimOut.set((long) Math.ceil((double) in.getRows() / in.getRowsPerBlock()), in.getCols(), in.getRowsPerBlock(), in.getColsPerBlock());
    } else if (ins instanceof AggregateUnaryInstruction) {
        AggregateUnaryInstruction realIns = (AggregateUnaryInstruction) ins;
        aggregateUnary(dims.get(realIns.input), (AggregateUnaryOperator) realIns.getOperator(), dimOut);
    } else if (ins instanceof AggregateBinaryInstruction) {
        AggregateBinaryInstruction realIns = (AggregateBinaryInstruction) ins;
        aggregateBinary(dims.get(realIns.input1), dims.get(realIns.input2), (AggregateBinaryOperator) realIns.getOperator(), dimOut);
    } else if (ins instanceof MapMultChainInstruction) {
        // output size independent of chain type
        MapMultChainInstruction realIns = (MapMultChainInstruction) ins;
        MatrixCharacteristics mc1 = dims.get(realIns.getInput1());
        MatrixCharacteristics mc2 = dims.get(realIns.getInput2());
        dimOut.set(mc1.numColumns, mc2.numColumns, mc1.numRowsPerBlock, mc1.numColumnsPerBlock);
    } else if (ins instanceof QuaternaryInstruction) {
        QuaternaryInstruction realIns = (QuaternaryInstruction) ins;
        MatrixCharacteristics mc1 = dims.get(realIns.getInput1());
        MatrixCharacteristics mc2 = dims.get(realIns.getInput2());
        MatrixCharacteristics mc3 = dims.get(realIns.getInput3());
        realIns.computeMatrixCharacteristics(mc1, mc2, mc3, dimOut);
    } else if (ins instanceof ReblockInstruction) {
        ReblockInstruction realIns = (ReblockInstruction) ins;
        MatrixCharacteristics in_dim = dims.get(realIns.input);
        dimOut.set(in_dim.numRows, in_dim.numColumns, realIns.brlen, realIns.bclen, in_dim.nonZero);
    } else if (ins instanceof MatrixReshapeMRInstruction) {
        MatrixReshapeMRInstruction mrinst = (MatrixReshapeMRInstruction) ins;
        MatrixCharacteristics in_dim = dims.get(mrinst.input);
        dimOut.set(mrinst.getNumRows(), mrinst.getNumColunms(), in_dim.getRowsPerBlock(), in_dim.getColsPerBlock(), in_dim.getNonZeros());
    } else if (ins instanceof RandInstruction || ins instanceof SeqInstruction) {
        DataGenMRInstruction dataIns = (DataGenMRInstruction) ins;
        dimOut.set(dims.get(dataIns.getInput()));
    } else if (ins instanceof ReplicateInstruction) {
        ReplicateInstruction realIns = (ReplicateInstruction) ins;
        realIns.computeOutputDimension(dims.get(realIns.input), dimOut);
    } else if (// before unary
    ins instanceof ParameterizedBuiltinMRInstruction) {
        ParameterizedBuiltinMRInstruction realIns = (ParameterizedBuiltinMRInstruction) ins;
        realIns.computeOutputCharacteristics(dims.get(realIns.input), dimOut);
    } else if (ins instanceof ScalarInstruction || ins instanceof AggregateInstruction || (ins instanceof UnaryInstruction && !(ins instanceof MMTSJMRInstruction)) || ins instanceof ZeroOutInstruction) {
        UnaryMRInstructionBase realIns = (UnaryMRInstructionBase) ins;
        dimOut.set(dims.get(realIns.input));
    } else if (ins instanceof MMTSJMRInstruction) {
        MMTSJMRInstruction mmtsj = (MMTSJMRInstruction) ins;
        MMTSJType tstype = mmtsj.getMMTSJType();
        MatrixCharacteristics mc = dims.get(mmtsj.input);
        dimOut.set(tstype.isLeft() ? mc.numColumns : mc.numRows, tstype.isLeft() ? mc.numColumns : mc.numRows, mc.numRowsPerBlock, mc.numColumnsPerBlock);
    } else if (ins instanceof PMMJMRInstruction) {
        PMMJMRInstruction pmmins = (PMMJMRInstruction) ins;
        MatrixCharacteristics mc = dims.get(pmmins.input2);
        dimOut.set(pmmins.getNumRows(), mc.numColumns, mc.numRowsPerBlock, mc.numColumnsPerBlock);
    } else if (ins instanceof RemoveEmptyMRInstruction) {
        RemoveEmptyMRInstruction realIns = (RemoveEmptyMRInstruction) ins;
        MatrixCharacteristics mc = dims.get(realIns.input1);
        long min = realIns.isEmptyReturn() ? 1 : 0;
        if (realIns.isRemoveRows())
            dimOut.set(Math.max(realIns.getOutputLen(), min), mc.getCols(), mc.numRowsPerBlock, mc.numColumnsPerBlock);
        else
            dimOut.set(mc.getRows(), Math.max(realIns.getOutputLen(), min), mc.numRowsPerBlock, mc.numColumnsPerBlock);
    } else if (// needs to be checked before binary
    ins instanceof UaggOuterChainInstruction) {
        UaggOuterChainInstruction realIns = (UaggOuterChainInstruction) ins;
        MatrixCharacteristics mc1 = dims.get(realIns.input1);
        MatrixCharacteristics mc2 = dims.get(realIns.input2);
        realIns.computeOutputCharacteristics(mc1, mc2, dimOut);
    } else if (ins instanceof GroupedAggregateMInstruction) {
        GroupedAggregateMInstruction realIns = (GroupedAggregateMInstruction) ins;
        MatrixCharacteristics mc1 = dims.get(realIns.input1);
        realIns.computeOutputCharacteristics(mc1, dimOut);
    } else if (ins instanceof BinaryInstruction || ins instanceof BinaryMInstruction || ins instanceof CombineBinaryInstruction) {
        BinaryMRInstructionBase realIns = (BinaryMRInstructionBase) ins;
        MatrixCharacteristics mc1 = dims.get(realIns.input1);
        MatrixCharacteristics mc2 = dims.get(realIns.input2);
        if (mc1.getRows() > 1 && mc1.getCols() == 1 && mc2.getRows() == 1 && // outer
        mc2.getCols() > 1) {
            dimOut.set(mc1.getRows(), mc2.getCols(), mc1.getRowsPerBlock(), mc2.getColsPerBlock());
        } else {
            // default case
            dimOut.set(mc1);
        }
    } else if (ins instanceof TernaryInstruction) {
        dimOut.set(dims.get(ins.getInputIndexes()[0]));
    } else if (ins instanceof CombineTernaryInstruction) {
        CtableInstruction realIns = (CtableInstruction) ins;
        dimOut.set(dims.get(realIns.input1));
    } else if (ins instanceof CombineUnaryInstruction) {
        dimOut.set(dims.get(((CombineUnaryInstruction) ins).input));
    } else if (ins instanceof CM_N_COVInstruction || ins instanceof GroupedAggregateInstruction) {
        dimOut.set(1, 1, 1, 1);
    } else if (ins instanceof RangeBasedReIndexInstruction) {
        RangeBasedReIndexInstruction realIns = (RangeBasedReIndexInstruction) ins;
        MatrixCharacteristics dimIn = dims.get(realIns.input);
        realIns.computeOutputCharacteristics(dimIn, dimOut);
    } else if (ins instanceof CtableInstruction) {
        CtableInstruction realIns = (CtableInstruction) ins;
        MatrixCharacteristics in_dim = dims.get(realIns.input1);
        dimOut.set(realIns.getOutputDim1(), realIns.getOutputDim2(), in_dim.numRowsPerBlock, in_dim.numColumnsPerBlock);
    } else {
        /*
			 * if ins is none of the above cases then we assume that dim_out dimensions are unknown
			 */
        dimOut.numRows = -1;
        dimOut.numColumns = -1;
        dimOut.numRowsPerBlock = 1;
        dimOut.numColumnsPerBlock = 1;
    }
}

Example 3 with SeqInstruction

use of org.apache.sysml.runtime.instructions.mr.SeqInstruction in project systemml by apache.

the class Recompiler method checkCPDataGen.

public static boolean checkCPDataGen(MRJobInstruction inst, String updatedRandInst) {
    boolean ret = true;
    // check only shuffle inst
    String shuffleInst = inst.getIv_shuffleInstructions();
    String rrInst = inst.getIv_recordReaderInstructions();
    String mapInst = inst.getIv_instructionsInMapper();
    String aggInst = inst.getIv_aggInstructions();
    String otherInst = inst.getIv_otherInstructions();
    if ((shuffleInst != null && shuffleInst.length() > 0) || (rrInst != null && rrInst.length() > 0) || (mapInst != null && mapInst.length() > 0) || (aggInst != null && aggInst.length() > 0) || (otherInst != null && otherInst.length() > 0)) {
        ret = false;
    }
    // check only rand inst
    if (ret) {
        String[] instParts = updatedRandInst.split(Lop.INSTRUCTION_DELIMITOR);
        for (String lrandStr : instParts) {
            if (InstructionUtils.getOpCode(lrandStr).equals(DataGen.RAND_OPCODE)) {
                // check recompile memory budget
                RandInstruction lrandInst = (RandInstruction) RandInstruction.parseInstruction(lrandStr);
                long rows = lrandInst.getRows();
                long cols = lrandInst.getCols();
                double sparsity = lrandInst.getSparsity();
                double mem = MatrixBlock.estimateSizeInMemory(rows, cols, sparsity);
                if (!OptimizerUtils.isValidCPDimensions(rows, cols) || !OptimizerUtils.isValidCPMatrixSize(rows, cols, sparsity) || mem >= OptimizerUtils.getLocalMemBudget()) {
                    ret = false;
                    break;
                }
            } else if (InstructionUtils.getOpCode(lrandStr).equals(DataGen.SEQ_OPCODE)) {
                // check recompile memory budget
                // (don't account for sparsity because always dense)
                SeqInstruction lrandInst = (SeqInstruction) SeqInstruction.parseInstruction(lrandStr);
                long rows = lrandInst.getRows();
                long cols = lrandInst.getCols();
                double mem = MatrixBlock.estimateSizeInMemory(rows, cols, 1.0d);
                if (!OptimizerUtils.isValidCPDimensions(rows, cols) || !OptimizerUtils.isValidCPMatrixSize(rows, cols, 1.0d) || mem >= OptimizerUtils.getLocalMemBudget()) {
                    ret = false;
                    break;
                }
            } else {
                ret = false;
                break;
            }
        }
    }
    return ret;
}

Example 4 with SeqInstruction

use of org.apache.sysml.runtime.instructions.mr.SeqInstruction in project incubator-systemml by apache.

the class RunMRJobs method executeInMemoryDataGenOperations.

private static JobReturn executeInMemoryDataGenOperations(MRJobInstruction inst, String randInst, MatrixObject[] outputMatrices) {
    MatrixCharacteristics[] mc = new MatrixCharacteristics[outputMatrices.length];
    DataGenMRInstruction[] dgSet = MRInstructionParser.parseDataGenInstructions(randInst);
    byte[] results = inst.getIv_resultIndices();
    for (DataGenMRInstruction ldgInst : dgSet) {
        if (ldgInst instanceof RandInstruction) {
            // CP Rand block operation
            RandInstruction lrand = (RandInstruction) ldgInst;
            RandomMatrixGenerator rgen = LibMatrixDatagen.createRandomMatrixGenerator(lrand.getProbabilityDensityFunction(), (int) lrand.getRows(), (int) lrand.getCols(), lrand.getRowsInBlock(), lrand.getColsInBlock(), lrand.getSparsity(), lrand.getMinValue(), lrand.getMaxValue(), lrand.getPdfParams());
            MatrixBlock mb = MatrixBlock.randOperations(rgen, lrand.getSeed());
            for (int i = 0; i < results.length; i++) if (lrand.output == results[i]) {
                outputMatrices[i].acquireModify(mb);
                outputMatrices[i].release();
                mc[i] = new MatrixCharacteristics(mb.getNumRows(), mb.getNumColumns(), lrand.getRowsInBlock(), lrand.getColsInBlock(), mb.getNonZeros());
            }
        } else if (ldgInst instanceof SeqInstruction) {
            SeqInstruction lseq = (SeqInstruction) ldgInst;
            MatrixBlock mb = MatrixBlock.seqOperations(lseq.fromValue, lseq.toValue, lseq.incrValue);
            for (int i = 0; i < results.length; i++) if (lseq.output == results[i]) {
                outputMatrices[i].acquireModify(mb);
                outputMatrices[i].release();
                mc[i] = new MatrixCharacteristics(mb.getNumRows(), mb.getNumColumns(), lseq.getRowsInBlock(), lseq.getColsInBlock(), mb.getNonZeros());
            }
        }
    }
    return new JobReturn(mc, inst.getOutputInfos(), true);
}

Example 5 with SeqInstruction

use of org.apache.sysml.runtime.instructions.mr.SeqInstruction in project incubator-systemml by apache.

the class DataGenMR method runJob.

/**
 * <p>Starts a Rand MapReduce job which will produce one or more random objects.</p>
 *
 * @param inst MR job instruction
 * @param dataGenInstructions array of data gen instructions
 * @param instructionsInMapper instructions in mapper
 * @param aggInstructionsInReducer aggregate instructions in reducer
 * @param otherInstructionsInReducer other instructions in reducer
 * @param numReducers number of reducers
 * @param replication file replication
 * @param resultIndexes result indexes for each random object
 * @param dimsUnknownFilePrefix file path prefix when dimensions unknown
 * @param outputs output file for each random object
 * @param outputInfos output information for each random object
 * @return matrix characteristics for each random object
 * @throws Exception if Exception occurs
 */
public static JobReturn runJob(MRJobInstruction inst, String[] dataGenInstructions, String instructionsInMapper, String aggInstructionsInReducer, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception {
    JobConf job = new JobConf(DataGenMR.class);
    job.setJobName("DataGen-MR");
    // whether use block representation or cell representation
    MRJobConfiguration.setMatrixValueClass(job, true);
    byte[] realIndexes = new byte[dataGenInstructions.length];
    for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;
    String[] inputs = new String[dataGenInstructions.length];
    InputInfo[] inputInfos = new InputInfo[dataGenInstructions.length];
    long[] rlens = new long[dataGenInstructions.length];
    long[] clens = new long[dataGenInstructions.length];
    int[] brlens = new int[dataGenInstructions.length];
    int[] bclens = new int[dataGenInstructions.length];
    FileSystem fs = FileSystem.get(job);
    String dataGenInsStr = "";
    int numblocks = 0;
    int maxbrlen = -1, maxbclen = -1;
    double maxsparsity = -1;
    for (int i = 0; i < dataGenInstructions.length; i++) {
        dataGenInsStr = dataGenInsStr + Lop.INSTRUCTION_DELIMITOR + dataGenInstructions[i];
        MRInstruction mrins = MRInstructionParser.parseSingleInstruction(dataGenInstructions[i]);
        MRType mrtype = mrins.getMRInstructionType();
        DataGenMRInstruction genInst = (DataGenMRInstruction) mrins;
        rlens[i] = genInst.getRows();
        clens[i] = genInst.getCols();
        brlens[i] = genInst.getRowsInBlock();
        bclens[i] = genInst.getColsInBlock();
        maxbrlen = Math.max(maxbrlen, brlens[i]);
        maxbclen = Math.max(maxbclen, bclens[i]);
        if (mrtype == MRType.Rand) {
            RandInstruction randInst = (RandInstruction) mrins;
            inputs[i] = LibMatrixDatagen.generateUniqueSeedPath(genInst.getBaseDir());
            maxsparsity = Math.max(maxsparsity, randInst.getSparsity());
            PrintWriter pw = null;
            try {
                pw = new PrintWriter(fs.create(new Path(inputs[i])));
                // for obj reuse and preventing repeated buffer re-allocations
                StringBuilder sb = new StringBuilder();
                // seed generation
                Well1024a bigrand = LibMatrixDatagen.setupSeedsForRand(randInst.getSeed());
                for (long r = 0; r < Math.max(rlens[i], 1); r += brlens[i]) {
                    long curBlockRowSize = Math.min(brlens[i], (rlens[i] - r));
                    for (long c = 0; c < Math.max(clens[i], 1); c += bclens[i]) {
                        long curBlockColSize = Math.min(bclens[i], (clens[i] - c));
                        sb.append((r / brlens[i]) + 1);
                        sb.append(',');
                        sb.append((c / bclens[i]) + 1);
                        sb.append(',');
                        sb.append(curBlockRowSize);
                        sb.append(',');
                        sb.append(curBlockColSize);
                        sb.append(',');
                        sb.append(bigrand.nextLong());
                        pw.println(sb.toString());
                        sb.setLength(0);
                        numblocks++;
                    }
                }
            } finally {
                IOUtilFunctions.closeSilently(pw);
            }
            inputInfos[i] = InputInfo.TextCellInputInfo;
        } else if (mrtype == MRType.Seq) {
            SeqInstruction seqInst = (SeqInstruction) mrins;
            inputs[i] = genInst.getBaseDir() + System.currentTimeMillis() + ".seqinput";
            // always dense
            maxsparsity = 1.0;
            double from = seqInst.fromValue;
            double to = seqInst.toValue;
            double incr = seqInst.incrValue;
            // handle default 1 to -1 for special case of from>to
            incr = LibMatrixDatagen.updateSeqIncr(from, to, incr);
            // Correctness checks on (from, to, incr)
            boolean neg = (from > to);
            if (incr == 0)
                throw new DMLRuntimeException("Invalid value for \"increment\" in seq().");
            if (neg != (incr < 0))
                throw new DMLRuntimeException("Wrong sign for the increment in a call to seq()");
            // Compute the number of rows in the sequence
            long numrows = UtilFunctions.getSeqLength(from, to, incr);
            if (rlens[i] > 0) {
                if (numrows != rlens[i])
                    throw new DMLRuntimeException("Unexpected error while processing sequence instruction. Expected number of rows does not match given number: " + rlens[i] + " != " + numrows);
            } else {
                rlens[i] = numrows;
            }
            if (clens[i] > 0 && clens[i] != 1)
                throw new DMLRuntimeException("Unexpected error while processing sequence instruction. Number of columns (" + clens[i] + ") must be equal to 1.");
            else
                clens[i] = 1;
            PrintWriter pw = null;
            try {
                pw = new PrintWriter(fs.create(new Path(inputs[i])));
                StringBuilder sb = new StringBuilder();
                double temp = from;
                double block_from, block_to;
                for (long r = 0; r < rlens[i]; r += brlens[i]) {
                    long curBlockRowSize = Math.min(brlens[i], (rlens[i] - r));
                    // block (bid_i,bid_j) generates a sequence from the interval [block_from, block_to] (inclusive of both end points of the interval)
                    long bid_i = ((r / brlens[i]) + 1);
                    long bid_j = 1;
                    block_from = temp;
                    block_to = temp + (curBlockRowSize - 1) * incr;
                    // next block starts from here
                    temp = block_to + incr;
                    sb.append(bid_i);
                    sb.append(',');
                    sb.append(bid_j);
                    sb.append(',');
                    sb.append(block_from);
                    sb.append(',');
                    sb.append(block_to);
                    sb.append(',');
                    sb.append(incr);
                    pw.println(sb.toString());
                    sb.setLength(0);
                    numblocks++;
                }
            } finally {
                IOUtilFunctions.closeSilently(pw);
            }
            inputInfos[i] = InputInfo.TextCellInputInfo;
        } else {
            throw new DMLRuntimeException("Unexpected Data Generation Instruction Type: " + mrtype);
        }
    }
    // remove the first ","
    dataGenInsStr = dataGenInsStr.substring(1);
    RunningJob runjob;
    MatrixCharacteristics[] stats;
    try {
        // set up the block size
        MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens);
        // set up the input files and their format information
        MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, false, ConvertTarget.BLOCK);
        // set up the dimensions of input matrices
        MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens);
        MRJobConfiguration.setDimsUnknownFilePrefix(job, dimsUnknownFilePrefix);
        // set up the block size
        MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens);
        // set up the rand Instructions
        MRJobConfiguration.setRandInstructions(job, dataGenInsStr);
        // set up unary instructions that will perform in the mapper
        MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper);
        // set up the aggregate instructions that will happen in the combiner and reducer
        MRJobConfiguration.setAggregateInstructions(job, aggInstructionsInReducer);
        // set up the instructions that will happen in the reducer, after the aggregation instrucions
        MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer);
        // set up the replication factor for the results
        job.setInt(MRConfigurationNames.DFS_REPLICATION, replication);
        // set up map/reduce memory configurations (if in AM context)
        DMLConfig config = ConfigurationManager.getDMLConfig();
        DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config);
        // set up custom map/reduce configurations
        MRJobConfiguration.setupCustomMRConfigurations(job, config);
        // determine degree of parallelism (nmappers: 1<=n<=capacity)
        // TODO use maxsparsity whenever we have a way of generating sparse rand data
        int capacity = InfrastructureAnalyzer.getRemoteParallelMapTasks();
        long dfsblocksize = InfrastructureAnalyzer.getHDFSBlockSize();
        // correction max number of mappers on yarn clusters
        if (InfrastructureAnalyzer.isYarnEnabled())
            capacity = (int) Math.max(capacity, YarnClusterAnalyzer.getNumCores());
        int nmapers = Math.max(Math.min((int) (8 * maxbrlen * maxbclen * (long) numblocks / dfsblocksize), capacity), 1);
        job.setNumMapTasks(nmapers);
        // set up what matrices are needed to pass from the mapper to reducer
        HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, dataGenInsStr, instructionsInMapper, null, aggInstructionsInReducer, otherInstructionsInReducer, resultIndexes);
        MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, dataGenInsStr, instructionsInMapper, null, aggInstructionsInReducer, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false);
        stats = ret.stats;
        // set up the number of reducers
        MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers);
        // print the complete MRJob instruction
        if (LOG.isTraceEnabled())
            inst.printCompleteMRJobInstruction(stats);
        // Update resultDimsUnknown based on computed "stats"
        byte[] resultDimsUnknown = new byte[resultIndexes.length];
        for (int i = 0; i < resultIndexes.length; i++) {
            if (stats[i].getRows() == -1 || stats[i].getCols() == -1) {
                resultDimsUnknown[i] = (byte) 1;
            } else {
                resultDimsUnknown[i] = (byte) 0;
            }
        }
        boolean mayContainCtable = instructionsInMapper.contains("ctabletransform") || instructionsInMapper.contains("groupedagg");
        // set up the multiple output files, and their format information
        MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, mayContainCtable);
        // configure mapper and the mapper output key value pairs
        job.setMapperClass(DataGenMapper.class);
        if (numReducers == 0) {
            job.setMapOutputKeyClass(Writable.class);
            job.setMapOutputValueClass(Writable.class);
        } else {
            job.setMapOutputKeyClass(MatrixIndexes.class);
            job.setMapOutputValueClass(TaggedMatrixBlock.class);
        }
        // set up combiner
        if (numReducers != 0 && aggInstructionsInReducer != null && !aggInstructionsInReducer.isEmpty())
            job.setCombinerClass(GMRCombiner.class);
        // configure reducer
        job.setReducerClass(GMRReducer.class);
        // job.setReducerClass(PassThroughReducer.class);
        // By default, the job executes in "cluster" mode.
        // Determine if we can optimize and run it in "local" mode.
        MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length];
        for (int i = 0; i < inputs.length; i++) {
            inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]);
        }
        // set unique working dir
        MRJobConfiguration.setUniqueWorkingDir(job);
        runjob = JobClient.runJob(job);
        /* Process different counters */
        Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS);
        for (int i = 0; i < resultIndexes.length; i++) {
            // number of non-zeros
            stats[i].setNonZeros(group.getCounter(Integer.toString(i)));
        }
        String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile";
        stats = MapReduceTool.processDimsFiles(dir, stats);
        MapReduceTool.deleteFileIfExistOnHDFS(dir);
    } finally {
        for (String input : inputs) MapReduceTool.deleteFileIfExistOnHDFS(new Path(input), job);
    }
    return new JobReturn(stats, outputInfos, runjob.isSuccessful());
}