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

Example 31 with OutputInfo

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

the class ParForProgramBlock method executeRemoteMRParForDP.

private void executeRemoteMRParForDP(ExecutionContext ec, IntObject itervar, IntObject from, IntObject to, IntObject incr) throws IOException {
    /* Step 0) check and recompile MR inst
		 * Step 1) serialize child PB and inst
		 * Step 2) create and serialize tasks
		 * Step 3) submit MR Jobs and wait for results
		 * Step 4) collect results from each parallel worker
		 */
    Timing time = (_monitor ? new Timing(true) : null);
    // Step 0) check and compile to CP (if forced remote parfor)
    boolean flagForced = checkMRAndRecompileToCP(0);
    // Step 1) prepare partitioned input matrix (needs to happen before serializing the program)
    ParForStatementBlock sb = (ParForStatementBlock) getStatementBlock();
    MatrixObject inputMatrix = ec.getMatrixObject(_colocatedDPMatrix);
    PartitionFormat inputDPF = sb.determineDataPartitionFormat(_colocatedDPMatrix);
    // mark matrix var as partitioned
    inputMatrix.setPartitioned(inputDPF._dpf, inputDPF._N);
    // Step 2) init parallel workers (serialize PBs)
    // NOTES: each mapper changes filenames with regard to his ID as we submit a single
    // job, cannot reuse serialized string, since variables are serialized as well.
    ParForBody body = new ParForBody(_childBlocks, _resultVars, ec);
    String program = ProgramConverter.serializeParForBody(body);
    if (_monitor)
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_INIT_PARWRK_T, time.stop());
    // Step 3) create tasks
    TaskPartitioner partitioner = createTaskPartitioner(from, to, incr);
    String resultFile = constructResultFileName();
    long numIterations = partitioner.getNumIterations();
    // partitioner.createTasks().size();
    long numCreatedTasks = numIterations;
    if (_monitor)
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_INIT_TASKS_T, time.stop());
    // write matrices to HDFS
    exportMatricesToHDFS(ec);
    // Step 4) submit MR job (wait for finished work)
    OutputInfo inputOI = ((inputMatrix.getSparsity() < 0.1 && inputDPF == PartitionFormat.COLUMN_WISE) || (inputMatrix.getSparsity() < 0.001 && inputDPF == PartitionFormat.ROW_WISE)) ? OutputInfo.BinaryCellOutputInfo : OutputInfo.BinaryBlockOutputInfo;
    RemoteParForJobReturn ret = RemoteDPParForMR.runJob(_ID, _iterPredVar, _colocatedDPMatrix, program, resultFile, inputMatrix, inputDPF, inputOI, _tSparseCol, _enableCPCaching, _numThreads, _replicationDP);
    if (_monitor)
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_WAIT_EXEC_T, time.stop());
    // Step 5) collecting results from each parallel worker
    int numExecutedTasks = ret.getNumExecutedTasks();
    int numExecutedIterations = ret.getNumExecutedIterations();
    // consolidate results into global symbol table
    consolidateAndCheckResults(ec, numIterations, numCreatedTasks, numExecutedIterations, numExecutedTasks, ret.getVariables());
    if (// see step 0
    flagForced)
        releaseForcedRecompile(0);
    inputMatrix.unsetPartitioned();
    if (_monitor) {
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_WAIT_RESULTS_T, time.stop());
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_NUMTASKS, numExecutedTasks);
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_NUMITERS, numExecutedIterations);
    }
}

Example 32 with OutputInfo

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

the class ParForProgramBlock method executeRemoteSparkParForDP.

private void executeRemoteSparkParForDP(ExecutionContext ec, IntObject itervar, IntObject from, IntObject to, IntObject incr) throws IOException {
    Timing time = (_monitor ? new Timing(true) : null);
    // Step 0) check and compile to CP (if forced remote parfor)
    boolean flagForced = checkMRAndRecompileToCP(0);
    // Step 1) prepare partitioned input matrix (needs to happen before serializing the program)
    ParForStatementBlock sb = (ParForStatementBlock) getStatementBlock();
    MatrixObject inputMatrix = ec.getMatrixObject(_colocatedDPMatrix);
    PartitionFormat inputDPF = sb.determineDataPartitionFormat(_colocatedDPMatrix);
    // mark matrix var as partitioned
    inputMatrix.setPartitioned(inputDPF._dpf, inputDPF._N);
    // Step 2) init parallel workers (serialize PBs)
    // NOTES: each mapper changes filenames with regard to his ID as we submit a single
    // job, cannot reuse serialized string, since variables are serialized as well.
    ParForBody body = new ParForBody(_childBlocks, _resultVars, ec);
    HashMap<String, byte[]> clsMap = new HashMap<>();
    String program = ProgramConverter.serializeParForBody(body, clsMap);
    if (_monitor)
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_INIT_PARWRK_T, time.stop());
    // Step 3) create tasks
    TaskPartitioner partitioner = createTaskPartitioner(from, to, incr);
    String resultFile = constructResultFileName();
    long numIterations = partitioner.getNumIterations();
    // partitioner.createTasks().size();
    long numCreatedTasks = numIterations;
    if (_monitor)
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_INIT_TASKS_T, time.stop());
    // write matrices to HDFS, except DP matrix which is the input to the RemoteDPParForSpark job
    exportMatricesToHDFS(ec, _colocatedDPMatrix);
    // Step 4) submit MR job (wait for finished work)
    // TODO runtime support for binary cell partitioning
    OutputInfo inputOI = OutputInfo.BinaryBlockOutputInfo;
    RemoteParForJobReturn ret = RemoteDPParForSpark.runJob(_ID, _iterPredVar, _colocatedDPMatrix, program, clsMap, resultFile, inputMatrix, ec, inputDPF, inputOI, _tSparseCol, _enableCPCaching, _numThreads);
    if (_monitor)
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_WAIT_EXEC_T, time.stop());
    // Step 5) collecting results from each parallel worker
    int numExecutedTasks = ret.getNumExecutedTasks();
    int numExecutedIterations = ret.getNumExecutedIterations();
    // consolidate results into global symbol table
    consolidateAndCheckResults(ec, numIterations, numCreatedTasks, numExecutedIterations, numExecutedTasks, ret.getVariables());
    if (// see step 0
    flagForced)
        releaseForcedRecompile(0);
    inputMatrix.unsetPartitioned();
    if (_monitor) {
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_WAIT_RESULTS_T, time.stop());
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_NUMTASKS, numExecutedTasks);
        StatisticMonitor.putPFStat(_ID, Stat.PARFOR_NUMITERS, numExecutedIterations);
    }
}

Example 33 with OutputInfo

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

the class VariableCPInstruction method parseInstruction.

public static VariableCPInstruction parseInstruction(String str) {
    String[] parts = InstructionUtils.getInstructionPartsWithValueType(str);
    String opcode = parts[0];
    VariableOperationCode voc = getVariableOperationCode(opcode);
    if (voc == VariableOperationCode.CreateVariable) {
        if (// && parts.length != 10 )
        parts.length < 5)
            throw new DMLRuntimeException("Invalid number of operands in createvar instruction: " + str);
    } else if (voc == VariableOperationCode.MoveVariable) {
        // mvvar tempA A; or mvvar mvar5 "data/out.mtx" "binary"
        if (parts.length != 3 && parts.length != 4)
            throw new DMLRuntimeException("Invalid number of operands in mvvar instruction: " + str);
    } else if (voc == VariableOperationCode.Write) {
        // Write instructions for csv files also include three additional parameters (hasHeader, delimiter, sparse)
        if (parts.length != 5 && parts.length != 8)
            throw new DMLRuntimeException("Invalid number of operands in write instruction: " + str);
    } else {
        if (voc != VariableOperationCode.RemoveVariable)
            // no output
            InstructionUtils.checkNumFields(parts, getArity(voc));
    }
    CPOperand in1 = null, in2 = null, in3 = null, in4 = null, out = null;
    switch(voc) {
        case CreateVariable:
            // variable name
            DataType dt = DataType.valueOf(parts[4]);
            ValueType vt = dt == DataType.MATRIX ? ValueType.DOUBLE : ValueType.STRING;
            int extSchema = (dt == DataType.FRAME && parts.length >= 13) ? 1 : 0;
            in1 = new CPOperand(parts[1], vt, dt);
            // file name
            in2 = new CPOperand(parts[2], ValueType.STRING, DataType.SCALAR);
            // file name override flag (always literal)
            in3 = new CPOperand(parts[3], ValueType.BOOLEAN, DataType.SCALAR);
            // format
            String fmt = parts[5];
            if (fmt.equalsIgnoreCase("csv")) {
                // 14 inputs: createvar corresponding to READ -- includes properties hasHeader, delim, fill, and fillValue
                if (parts.length < 15 + extSchema || parts.length > 17 + extSchema)
                    throw new DMLRuntimeException("Invalid number of operands in createvar instruction: " + str);
            } else {
                if (parts.length != 6 && parts.length != 12 + extSchema)
                    throw new DMLRuntimeException("Invalid number of operands in createvar instruction: " + str);
            }
            OutputInfo oi = OutputInfo.stringToOutputInfo(fmt);
            InputInfo ii = OutputInfo.getMatchingInputInfo(oi);
            MatrixCharacteristics mc = new MatrixCharacteristics();
            if (parts.length == 6) {
            // do nothing
            } else if (parts.length >= 11) {
                // matrix characteristics
                mc.setDimension(Long.parseLong(parts[6]), Long.parseLong(parts[7]));
                mc.setBlockSize(Integer.parseInt(parts[8]), Integer.parseInt(parts[9]));
                mc.setNonZeros(Long.parseLong(parts[10]));
            } else {
                throw new DMLRuntimeException("Invalid number of operands in createvar instruction: " + str);
            }
            MetaDataFormat iimd = new MetaDataFormat(mc, oi, ii);
            UpdateType updateType = UpdateType.COPY;
            if (parts.length >= 12)
                updateType = UpdateType.valueOf(parts[11].toUpperCase());
            // handle frame schema
            String schema = (dt == DataType.FRAME && parts.length >= 13) ? parts[parts.length - 1] : null;
            if (fmt.equalsIgnoreCase("csv")) {
                // Cretevar instructions for CSV format either has 13 or 14 inputs.
                // 13 inputs: createvar corresponding to WRITE -- includes properties hasHeader, delim, and sparse
                // 14 inputs: createvar corresponding to READ -- includes properties hasHeader, delim, fill, and fillValue
                FileFormatProperties fmtProperties = null;
                if (parts.length == 15 + extSchema) {
                    boolean hasHeader = Boolean.parseBoolean(parts[12]);
                    String delim = parts[13];
                    boolean sparse = Boolean.parseBoolean(parts[14]);
                    fmtProperties = new CSVFileFormatProperties(hasHeader, delim, sparse);
                } else {
                    boolean hasHeader = Boolean.parseBoolean(parts[12]);
                    String delim = parts[13];
                    boolean fill = Boolean.parseBoolean(parts[14]);
                    double fillValue = UtilFunctions.parseToDouble(parts[15]);
                    String naStrings = null;
                    if (parts.length == 17 + extSchema)
                        naStrings = parts[16];
                    fmtProperties = new CSVFileFormatProperties(hasHeader, delim, fill, fillValue, naStrings);
                }
                return new VariableCPInstruction(VariableOperationCode.CreateVariable, in1, in2, in3, iimd, updateType, fmtProperties, schema, opcode, str);
            } else {
                return new VariableCPInstruction(VariableOperationCode.CreateVariable, in1, in2, in3, iimd, updateType, schema, opcode, str);
            }
        case AssignVariable:
            in1 = new CPOperand(parts[1]);
            in2 = new CPOperand(parts[2]);
            break;
        case CopyVariable:
            // Value types are not given here
            in1 = new CPOperand(parts[1], ValueType.UNKNOWN, DataType.UNKNOWN);
            in2 = new CPOperand(parts[2], ValueType.UNKNOWN, DataType.UNKNOWN);
            break;
        case MoveVariable:
            in1 = new CPOperand(parts[1], ValueType.UNKNOWN, DataType.UNKNOWN);
            in2 = new CPOperand(parts[2], ValueType.UNKNOWN, DataType.UNKNOWN);
            if (parts.length > 3)
                in3 = new CPOperand(parts[3], ValueType.UNKNOWN, DataType.UNKNOWN);
            break;
        case RemoveVariable:
            VariableCPInstruction rminst = new VariableCPInstruction(getVariableOperationCode(opcode), null, null, null, out, opcode, str);
            for (int i = 1; i < parts.length; i++) rminst.addInput(new CPOperand(parts[i], ValueType.UNKNOWN, DataType.SCALAR));
            return rminst;
        case RemoveVariableAndFile:
            in1 = new CPOperand(parts[1]);
            in2 = new CPOperand(parts[2]);
            // second argument must be a boolean
            if (in2.getValueType() != ValueType.BOOLEAN)
                throw new DMLRuntimeException("Unexpected value type for second argument in: " + str);
            break;
        case CastAsScalarVariable:
        case CastAsMatrixVariable:
        case CastAsFrameVariable:
        case CastAsDoubleVariable:
        case CastAsIntegerVariable:
        case CastAsBooleanVariable:
            // first operand is a variable name => string value type
            in1 = new CPOperand(parts[1]);
            // output variable name
            out = new CPOperand(parts[2]);
            break;
        case Write:
            in1 = new CPOperand(parts[1]);
            in2 = new CPOperand(parts[2]);
            in3 = new CPOperand(parts[3]);
            FileFormatProperties fprops = null;
            if (in3.getName().equalsIgnoreCase("csv")) {
                boolean hasHeader = Boolean.parseBoolean(parts[4]);
                String delim = parts[5];
                boolean sparse = Boolean.parseBoolean(parts[6]);
                fprops = new CSVFileFormatProperties(hasHeader, delim, sparse);
                // description
                in4 = new CPOperand(parts[7]);
            } else {
                fprops = new FileFormatProperties();
                // description
                in4 = new CPOperand(parts[4]);
            }
            VariableCPInstruction inst = new VariableCPInstruction(getVariableOperationCode(opcode), in1, in2, in3, out, null, fprops, null, null, opcode, str);
            inst.addInput(in4);
            return inst;
        case Read:
            in1 = new CPOperand(parts[1]);
            in2 = new CPOperand(parts[2]);
            out = null;
            break;
        case SetFileName:
            // variable name
            in1 = new CPOperand(parts[1]);
            // file name
            in2 = new CPOperand(parts[2], ValueType.UNKNOWN, DataType.UNKNOWN);
            // option: remote or local
            in3 = new CPOperand(parts[3], ValueType.UNKNOWN, DataType.UNKNOWN);
            // return new VariableCPInstruction(getVariableOperationCode(opcode), in1, in2, in3, str);
            break;
    }
    return new VariableCPInstruction(getVariableOperationCode(opcode), in1, in2, in3, out, opcode, str);
}

Example 34 with OutputInfo

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

the class WriteSPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    // get filename (literal or variable expression)
    String fname = ec.getScalarInput(input2.getName(), ValueType.STRING, input2.isLiteral()).getStringValue();
    String desc = ec.getScalarInput(input4.getName(), ValueType.STRING, input4.isLiteral()).getStringValue();
    formatProperties.setDescription(desc);
    ValueType[] schema = (input1.getDataType() == DataType.FRAME) ? sec.getFrameObject(input1.getName()).getSchema() : null;
    try {
        // if the file already exists on HDFS, remove it.
        MapReduceTool.deleteFileIfExistOnHDFS(fname);
        // prepare output info according to meta data
        String outFmt = input3.getName();
        OutputInfo oi = OutputInfo.stringToOutputInfo(outFmt);
        // core matrix/frame write
        if (input1.getDataType() == DataType.MATRIX)
            processMatrixWriteInstruction(sec, fname, oi);
        else
            processFrameWriteInstruction(sec, fname, oi, schema);
    } catch (IOException ex) {
        throw new DMLRuntimeException("Failed to process write instruction", ex);
    }
}

Example 35 with OutputInfo

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

the class WriteCSVMR method runJob.

public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String csvWriteInstructions, int numReducers, int replication, byte[] resultIndexes, String[] outputs) throws Exception {
    JobConf job = new JobConf(WriteCSVMR.class);
    job.setJobName("WriteCSV-MR");
    // check for valid output dimensions
    for (int i = 0; i < rlens.length; i++) if (rlens[i] == 0 || clens[i] == 0)
        throw new IOException("Write of matrices with zero" + " rows or columns not supported (" + rlens[i] + "x" + clens[i] + ").");
    byte[] realIndexes = new byte[inputs.length];
    for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;
    // set up the input files and their format information
    MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, ConvertTarget.CSVWRITE);
    // set up the dimensions of input matrices
    MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens);
    // set up the block size
    MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens);
    MRJobConfiguration.setCSVWriteInstructions(job, csvWriteInstructions);
    // set up the replication factor for the results
    job.setInt(MRConfigurationNames.DFS_REPLICATION, replication);
    // set up preferred custom serialization framework for binary block format
    if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION)
        MRJobConfiguration.addBinaryBlockSerializationFramework(job);
    // set up custom map/reduce configurations
    DMLConfig config = ConfigurationManager.getDMLConfig();
    MRJobConfiguration.setupCustomMRConfigurations(job, config);
    long maxRlen = 0;
    for (long rlen : rlens) if (rlen > maxRlen)
        maxRlen = rlen;
    // set up the number of reducers (according to output size)
    int numRed = determineNumReducers(rlens, clens, config.getIntValue(DMLConfig.NUM_REDUCERS), (int) maxRlen);
    job.setNumReduceTasks(numRed);
    byte[] resultDimsUnknown = new byte[resultIndexes.length];
    MatrixCharacteristics[] stats = new MatrixCharacteristics[resultIndexes.length];
    OutputInfo[] outputInfos = new OutputInfo[outputs.length];
    HashMap<Byte, Integer> indexmap = new HashMap<>();
    for (int i = 0; i < stats.length; i++) {
        indexmap.put(resultIndexes[i], i);
        resultDimsUnknown[i] = (byte) 0;
        stats[i] = new MatrixCharacteristics();
        outputInfos[i] = OutputInfo.CSVOutputInfo;
    }
    CSVWriteInstruction[] ins = MRInstructionParser.parseCSVWriteInstructions(csvWriteInstructions);
    for (CSVWriteInstruction in : ins) stats[indexmap.get(in.output)].set(rlens[in.input], clens[in.input], -1, -1);
    // Print the complete instruction
    if (LOG.isTraceEnabled())
        inst.printCompleteMRJobInstruction(stats);
    // set up what matrices are needed to pass from the mapper to reducer
    MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, "", "", csvWriteInstructions, resultIndexes);
    // set up the multiple output files, and their format information
    MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true);
    // configure mapper and the mapper output key value pairs
    job.setMapperClass(CSVWriteMapper.class);
    job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class);
    job.setMapOutputValueClass(MatrixBlock.class);
    // configure reducer
    job.setReducerClass(CSVWriteReducer.class);
    job.setOutputKeyComparatorClass(TaggedFirstSecondIndexes.Comparator.class);
    job.setPartitionerClass(TaggedFirstSecondIndexes.FirstIndexRangePartitioner.class);
    // job.setOutputFormat(UnPaddedOutputFormat.class);
    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);
    RunningJob 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)));
    }
    return new JobReturn(stats, outputInfos, runjob.isSuccessful());
}