Examples with CompressedMatrixBlock org.apache.sysml.runtime.compress.CompressedMatrixBlock used on opensource projects

Example 56 with CompressedMatrixBlock

use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project systemml by apache.

the class CompressionCPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) {
    // get matrix block input
    MatrixBlock in = ec.getMatrixInput(input1.getName(), getExtendedOpcode());
    // compress the matrix block
    MatrixBlock out = new CompressedMatrixBlock(in).compress(OptimizerUtils.getConstrainedNumThreads(-1));
    // set output and release input
    ec.releaseMatrixInput(input1.getName(), getExtendedOpcode());
    ec.setMatrixOutput(output.getName(), out, getExtendedOpcode());
}

Example 57 with CompressedMatrixBlock

use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project systemml by apache.

the class SpoofCellwise method execute.

@Override
public MatrixBlock execute(ArrayList<MatrixBlock> inputs, ArrayList<ScalarObject> scalarObjects, MatrixBlock out, int k) {
    // sanity check
    if (inputs == null || inputs.size() < 1 || out == null)
        throw new RuntimeException("Invalid input arguments.");
    // input preparation
    MatrixBlock a = inputs.get(0);
    SideInput[] b = prepInputMatrices(inputs);
    double[] scalars = prepInputScalars(scalarObjects);
    final int m = a.getNumRows();
    final int n = a.getNumColumns();
    // sparse safe check
    boolean sparseSafe = isSparseSafe() || (b.length == 0 && genexec(0, b, scalars, m, n, 0, 0) == 0);
    long inputSize = sparseSafe ? getTotalInputNnz(inputs) : getTotalInputSize(inputs);
    if (inputSize < PAR_NUMCELL_THRESHOLD) {
        // serial execution
        k = 1;
    }
    // result allocation and preparations
    boolean sparseOut = _type == CellType.NO_AGG && sparseSafe && a.isInSparseFormat();
    switch(_type) {
        case NO_AGG:
            out.reset(m, n, sparseOut);
            break;
        case ROW_AGG:
            out.reset(m, 1, false);
            break;
        case COL_AGG:
            out.reset(1, n, false);
            break;
        default:
            throw new DMLRuntimeException("Invalid cell type: " + _type);
    }
    out.allocateBlock();
    long lnnz = 0;
    if (// SINGLE-THREADED
    k <= 1) {
        if (inputs.get(0) instanceof CompressedMatrixBlock)
            lnnz = executeCompressed((CompressedMatrixBlock) a, b, scalars, out, m, n, sparseSafe, 0, m);
        else if (!inputs.get(0).isInSparseFormat())
            lnnz = executeDense(a.getDenseBlock(), b, scalars, out, m, n, sparseSafe, 0, m);
        else
            lnnz = executeSparse(a.getSparseBlock(), b, scalars, out, m, n, sparseSafe, 0, m);
    } else // MULTI-THREADED
    {
        try {
            ExecutorService pool = CommonThreadPool.get(k);
            ArrayList<ParExecTask> tasks = new ArrayList<>();
            int nk = UtilFunctions.roundToNext(Math.min(8 * k, m / 32), k);
            int blklen = (int) (Math.ceil((double) m / nk));
            if (a instanceof CompressedMatrixBlock)
                blklen = BitmapEncoder.getAlignedBlocksize(blklen);
            for (int i = 0; i < nk & i * blklen < m; i++) tasks.add(new ParExecTask(a, b, scalars, out, m, n, sparseSafe, i * blklen, Math.min((i + 1) * blklen, m)));
            // execute tasks
            List<Future<Long>> taskret = pool.invokeAll(tasks);
            pool.shutdown();
            // aggregate nnz and error handling
            for (Future<Long> task : taskret) lnnz += task.get();
            if (_type == CellType.COL_AGG) {
                // aggregate partial results
                double[] c = out.getDenseBlockValues();
                ValueFunction vfun = getAggFunction();
                if (vfun instanceof KahanFunction) {
                    for (ParExecTask task : tasks) LibMatrixMult.vectAdd(task.getResult().getDenseBlockValues(), c, 0, 0, n);
                } else {
                    for (ParExecTask task : tasks) {
                        double[] tmp = task.getResult().getDenseBlockValues();
                        for (int j = 0; j < n; j++) c[j] = vfun.execute(c[j], tmp[j]);
                    }
                }
                lnnz = out.recomputeNonZeros();
            }
        } catch (Exception ex) {
            throw new DMLRuntimeException(ex);
        }
    }
    // post-processing
    out.setNonZeros(lnnz);
    out.examSparsity();
    return out;
}

Example 58 with CompressedMatrixBlock

use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project systemml by apache.

the class SpoofCellwise method execute.

@Override
public ScalarObject execute(ArrayList<MatrixBlock> inputs, ArrayList<ScalarObject> scalarObjects, int k) {
    // sanity check
    if (inputs == null || inputs.size() < 1)
        throw new RuntimeException("Invalid input arguments.");
    // input preparation
    MatrixBlock a = inputs.get(0);
    SideInput[] b = prepInputMatrices(inputs);
    double[] scalars = prepInputScalars(scalarObjects);
    final int m = a.getNumRows();
    final int n = a.getNumColumns();
    // sparse safe check
    boolean sparseSafe = isSparseSafe() || (b.length == 0 && genexec(0, b, scalars, m, n, 0, 0) == 0);
    long inputSize = sparseSafe ? getTotalInputNnz(inputs) : getTotalInputSize(inputs);
    if (inputSize < PAR_NUMCELL_THRESHOLD) {
        // serial execution
        k = 1;
    }
    double ret = 0;
    if (// SINGLE-THREADED
    k <= 1) {
        if (inputs.get(0) instanceof CompressedMatrixBlock)
            ret = executeCompressedAndAgg((CompressedMatrixBlock) a, b, scalars, m, n, sparseSafe, 0, m);
        else if (!inputs.get(0).isInSparseFormat())
            ret = executeDenseAndAgg(a.getDenseBlock(), b, scalars, m, n, sparseSafe, 0, m);
        else
            ret = executeSparseAndAgg(a.getSparseBlock(), b, scalars, m, n, sparseSafe, 0, m);
    } else // MULTI-THREADED
    {
        try {
            ExecutorService pool = CommonThreadPool.get(k);
            ArrayList<ParAggTask> tasks = new ArrayList<>();
            int nk = (a instanceof CompressedMatrixBlock) ? k : UtilFunctions.roundToNext(Math.min(8 * k, m / 32), k);
            int blklen = (int) (Math.ceil((double) m / nk));
            if (a instanceof CompressedMatrixBlock)
                blklen = BitmapEncoder.getAlignedBlocksize(blklen);
            for (int i = 0; i < nk & i * blklen < m; i++) tasks.add(new ParAggTask(a, b, scalars, m, n, sparseSafe, i * blklen, Math.min((i + 1) * blklen, m)));
            // execute tasks
            List<Future<Double>> taskret = pool.invokeAll(tasks);
            pool.shutdown();
            // aggregate partial results
            ValueFunction vfun = getAggFunction();
            if (vfun instanceof KahanFunction) {
                KahanObject kbuff = new KahanObject(0, 0);
                KahanPlus kplus = KahanPlus.getKahanPlusFnObject();
                for (Future<Double> task : taskret) kplus.execute2(kbuff, task.get());
                ret = kbuff._sum;
            } else {
                for (Future<Double> task : taskret) ret = vfun.execute(ret, task.get());
            }
        } catch (Exception ex) {
            throw new DMLRuntimeException(ex);
        }
    }
    // correction for min/max
    if ((_aggOp == AggOp.MIN || _aggOp == AggOp.MAX) && sparseSafe && a.getNonZeros() < a.getNumRows() * a.getNumColumns())
        // unseen 0 might be max or min value
        ret = getAggFunction().execute(ret, 0);
    return new DoubleObject(ret);
}

Example 59 with CompressedMatrixBlock

use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project systemml by apache.

the class SpoofMultiAggregate method execute.

@Override
public MatrixBlock execute(ArrayList<MatrixBlock> inputs, ArrayList<ScalarObject> scalarObjects, MatrixBlock out, int k) {
    // sanity check
    if (inputs == null || inputs.size() < 1)
        throw new RuntimeException("Invalid input arguments.");
    long inputSize = isSparseSafe() ? getTotalInputNnz(inputs) : getTotalInputSize(inputs);
    if (inputSize < PAR_NUMCELL_THRESHOLD) {
        // serial execution
        k = 1;
    }
    // result allocation and preparations
    out.reset(1, _aggOps.length, false);
    out.allocateDenseBlock();
    // 1x<num_agg>
    double[] c = out.getDenseBlockValues();
    setInitialOutputValues(c);
    // input preparation
    SideInput[] b = prepInputMatrices(inputs);
    double[] scalars = prepInputScalars(scalarObjects);
    final int m = inputs.get(0).getNumRows();
    final int n = inputs.get(0).getNumColumns();
    boolean sparseSafe = isSparseSafe();
    if (// SINGLE-THREADED
    k <= 1) {
        if (inputs.get(0) instanceof CompressedMatrixBlock)
            executeCompressed((CompressedMatrixBlock) inputs.get(0), b, scalars, c, m, n, 0, m);
        else if (!inputs.get(0).isInSparseFormat())
            executeDense(inputs.get(0).getDenseBlock(), b, scalars, c, m, n, sparseSafe, 0, m);
        else
            executeSparse(inputs.get(0).getSparseBlock(), b, scalars, c, m, n, sparseSafe, 0, m);
    } else // MULTI-THREADED
    {
        try {
            ExecutorService pool = CommonThreadPool.get(k);
            ArrayList<ParAggTask> tasks = new ArrayList<>();
            int nk = UtilFunctions.roundToNext(Math.min(8 * k, m / 32), k);
            int blklen = (int) (Math.ceil((double) m / nk));
            for (int i = 0; i < nk & i * blklen < m; i++) tasks.add(new ParAggTask(inputs.get(0), b, scalars, m, n, sparseSafe, i * blklen, Math.min((i + 1) * blklen, m)));
            // execute tasks
            List<Future<double[]>> taskret = pool.invokeAll(tasks);
            pool.shutdown();
            // aggregate partial results
            ArrayList<double[]> pret = new ArrayList<>();
            for (Future<double[]> task : taskret) pret.add(task.get());
            aggregatePartialResults(c, pret);
        } catch (Exception ex) {
            throw new DMLRuntimeException(ex);
        }
    }
    // post-processing
    out.recomputeNonZeros();
    out.examSparsity();
    return out;
}

Example 60 with CompressedMatrixBlock

use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project systemml by apache.

the class SpoofOperator method prepInputMatrices.

protected SideInput[] prepInputMatrices(ArrayList<MatrixBlock> inputs, int offset, int len, boolean denseOnly, boolean tB1) {
    SideInput[] b = new SideInput[len];
    for (int i = offset; i < offset + len; i++) {
        // decompress if necessary
        if (inputs.get(i) instanceof CompressedMatrixBlock)
            inputs.set(i, ((CompressedMatrixBlock) inputs.get(i)).decompress());
        // transpose if necessary
        int clen = inputs.get(i).getNumColumns();
        MatrixBlock in = (tB1 && i == 1) ? LibMatrixReorg.transpose(inputs.get(i), new MatrixBlock(clen, inputs.get(i).getNumRows(), false)) : inputs.get(i);
        // create side input
        if (denseOnly && (in.isInSparseFormat() || !in.isAllocated())) {
            // this in place because this block might be used by multiple threads)
            if (// dense empty
            in.getNumColumns() == 1 && in.isEmptyBlock(false))
                b[i - offset] = new SideInput(null, null, clen);
            else {
                b[i - offset] = new SideInput(DataConverter.convertToDenseBlock(in, false), null, clen);
                LOG.warn(getClass().getName() + ": Converted " + in.getNumRows() + "x" + in.getNumColumns() + ", nnz=" + in.getNonZeros() + " sideways input matrix from sparse to dense.");
            }
        } else if (in.isInSparseFormat() || !in.isAllocated()) {
            b[i - offset] = new SideInput(null, in, clen);
        } else {
            b[i - offset] = new SideInput(in.getDenseBlock(), null, clen);
        }
    }
    return b;
}