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

Example 36 with InputInfo

use of org.apache.sysml.runtime.matrix.data.InputInfo 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());
}

Example 37 with InputInfo

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

the class ResultMergeRemoteSpark method executeMerge.

@SuppressWarnings("unchecked")
protected RDDObject executeMerge(MatrixObject compare, MatrixObject[] inputs, String varname, long rlen, long clen, int brlen, int bclen) throws DMLRuntimeException {
    String jobname = "ParFor-RMSP";
    long t0 = DMLScript.STATISTICS ? System.nanoTime() : 0;
    SparkExecutionContext sec = (SparkExecutionContext) _ec;
    boolean withCompare = (compare != null);
    RDDObject ret = null;
    //determine degree of parallelism
    int numRed = (int) determineNumReducers(rlen, clen, brlen, bclen, _numReducers);
    //sanity check for empty src files
    if (inputs == null || inputs.length == 0)
        throw new DMLRuntimeException("Execute merge should never be called with no inputs.");
    try {
        //note: initial implementation via union over all result rdds discarded due to 
        //stack overflow errors with many parfor tasks, and thus many rdds
        //Step 1: construct input rdd from all result files of parfor workers
        //a) construct job conf with all files
        InputInfo ii = InputInfo.BinaryBlockInputInfo;
        JobConf job = new JobConf(ResultMergeRemoteMR.class);
        job.setJobName(jobname);
        job.setInputFormat(ii.inputFormatClass);
        Path[] paths = new Path[inputs.length];
        for (int i = 0; i < paths.length; i++) {
            //ensure input exists on hdfs (e.g., if in-memory or RDD)
            inputs[i].exportData();
            paths[i] = new Path(inputs[i].getFileName());
            //update rdd handle to allow lazy evaluation by guarding 
            //against cleanup of temporary result files
            setRDDHandleForMerge(inputs[i], sec);
        }
        FileInputFormat.setInputPaths(job, paths);
        //b) create rdd from input files w/ deep copy of keys and blocks
        JavaPairRDD<MatrixIndexes, MatrixBlock> rdd = sec.getSparkContext().hadoopRDD(job, ii.inputFormatClass, ii.inputKeyClass, ii.inputValueClass).mapPartitionsToPair(new CopyBlockPairFunction(true), true);
        //Step 2a: merge with compare
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = null;
        if (withCompare) {
            JavaPairRDD<MatrixIndexes, MatrixBlock> compareRdd = (JavaPairRDD<MatrixIndexes, MatrixBlock>) sec.getRDDHandleForMatrixObject(compare, InputInfo.BinaryBlockInputInfo);
            //merge values which differ from compare values
            ResultMergeRemoteSparkWCompare cfun = new ResultMergeRemoteSparkWCompare();
            out = //group all result blocks per key
            rdd.groupByKey(numRed).join(//join compare block and result blocks 
            compareRdd).mapToPair(//merge result blocks w/ compare
            cfun);
        } else //Step 2b: merge without compare
        {
            //direct merge in any order (disjointness guaranteed)
            out = RDDAggregateUtils.mergeByKey(rdd, false);
        }
        //Step 3: create output rdd handle w/ lineage
        ret = new RDDObject(out, varname);
        for (int i = 0; i < paths.length; i++) ret.addLineageChild(inputs[i].getRDDHandle());
        if (withCompare)
            ret.addLineageChild(compare.getRDDHandle());
    } catch (Exception ex) {
        throw new DMLRuntimeException(ex);
    }
    //maintain statistics
    Statistics.incrementNoOfCompiledSPInst();
    Statistics.incrementNoOfExecutedSPInst();
    if (DMLScript.STATISTICS) {
        Statistics.maintainCPHeavyHitters(jobname, System.nanoTime() - t0);
    }
    return ret;
}

Example 38 with InputInfo

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

the class TransformReadMetaTest method runTransformReadMetaTest.

/**
	 * 
	 * @param sparseM1
	 * @param sparseM2
	 * @param instType
	 * @throws IOException 
	 * @throws DMLRuntimeException 
	 */
private void runTransformReadMetaTest(RUNTIME_PLATFORM rt, String ofmt, String delim) throws IOException, DMLRuntimeException {
    RUNTIME_PLATFORM platformOld = rtplatform;
    rtplatform = rt;
    boolean sparkConfigOld = DMLScript.USE_LOCAL_SPARK_CONFIG;
    if (rtplatform == RUNTIME_PLATFORM.SPARK || rtplatform == RUNTIME_PLATFORM.HYBRID_SPARK)
        DMLScript.USE_LOCAL_SPARK_CONFIG = true;
    try {
        String testname = delim.equals(",") ? TEST_NAME1 : TEST_NAME2;
        getAndLoadTestConfiguration(testname);
        //generate input data
        double[][] X = DataConverter.convertToDoubleMatrix(MatrixBlock.seqOperations(0.5, rows / 2, 0.5).appendOperations(MatrixBlock.seqOperations(0.5, rows / 2, 0.5), new MatrixBlock()));
        MatrixBlock mbX = DataConverter.convertToMatrixBlock(X);
        CSVFileFormatProperties fprops = new CSVFileFormatProperties(false, delim, false);
        MatrixWriter writer = MatrixWriterFactory.createMatrixWriter(OutputInfo.CSVOutputInfo, 1, fprops);
        writer.writeMatrixToHDFS(mbX, input("X"), rows, 2, -1, -1, -1);
        //read specs transform X and Y
        String specX = MapReduceTool.readStringFromHDFSFile(SCRIPT_DIR + TEST_DIR + SPEC_X);
        fullDMLScriptName = SCRIPT_DIR + TEST_DIR + testname + ".dml";
        programArgs = new String[] { "-args", input("X"), specX, output("M1"), output("M"), ofmt, delim };
        //run test
        runTest(true, false, null, -1);
        //compare meta data frames
        InputInfo iinfo = InputInfo.stringExternalToInputInfo(ofmt);
        FrameReader reader = FrameReaderFactory.createFrameReader(iinfo);
        FrameBlock mExpected = TfMetaUtils.readTransformMetaDataFromFile(specX, output("M1"), delim);
        FrameBlock mRet = reader.readFrameFromHDFS(output("M"), rows, 2);
        for (int i = 0; i < rows; i++) for (int j = 0; j < 2; j++) {
            Assert.assertTrue("Wrong result: " + mRet.get(i, j) + ".", UtilFunctions.compareTo(ValueType.STRING, mExpected.get(i, j), mRet.get(i, j)) == 0);
        }
    } catch (Exception ex) {
        throw new IOException(ex);
    } finally {
        rtplatform = platformOld;
        DMLScript.USE_LOCAL_SPARK_CONFIG = sparkConfigOld;
    }
}