use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project incubator-systemml by apache.
the class SpoofOuterProduct method execute.
@Override
public MatrixBlock execute(ArrayList<MatrixBlock> inputs, ArrayList<ScalarObject> scalarObjects, MatrixBlock out) {
// sanity check
if (inputs == null || inputs.size() < 3 || out == null)
throw new RuntimeException("Invalid input arguments.");
// check empty result
if (// U is empty
(_outerProductType == OutProdType.LEFT_OUTER_PRODUCT && inputs.get(1).isEmptyBlock(false)) || // V is empty
(_outerProductType == OutProdType.RIGHT_OUTER_PRODUCT && inputs.get(2).isEmptyBlock(false)) || inputs.get(0).isEmptyBlock(false)) {
// X is empty
// turn empty dense into sparse
out.examSparsity();
return out;
}
// input preparation and result allocation (Allocate the output that is set by Sigma2CPInstruction)
if (_outerProductType == OutProdType.CELLWISE_OUTER_PRODUCT) {
// assign it to the time and sparse representation of the major input matrix
out.reset(inputs.get(0).getNumRows(), inputs.get(0).getNumColumns(), inputs.get(0).isInSparseFormat());
} else {
// if left outerproduct gives a value of k*n instead of n*k, change it back to n*k and then transpose the output
if (_outerProductType == OutProdType.LEFT_OUTER_PRODUCT)
// n*k
out.reset(inputs.get(0).getNumColumns(), inputs.get(1).getNumColumns(), false);
else if (_outerProductType == OutProdType.RIGHT_OUTER_PRODUCT)
// m*k
out.reset(inputs.get(0).getNumRows(), inputs.get(1).getNumColumns(), false);
}
// check for empty inputs; otherwise allocate result
if (inputs.get(0).isEmptyBlock(false))
return out;
out.allocateBlock();
// input preparation
DenseBlock[] ab = getDenseMatrices(prepInputMatrices(inputs, 1, 2, true, false));
SideInput[] b = prepInputMatrices(inputs, 3, false);
double[] scalars = prepInputScalars(scalarObjects);
// core sequential execute
final int m = inputs.get(0).getNumRows();
final int n = inputs.get(0).getNumColumns();
// rank
final int k = inputs.get(1).getNumColumns();
MatrixBlock a = inputs.get(0);
switch(_outerProductType) {
case LEFT_OUTER_PRODUCT:
case RIGHT_OUTER_PRODUCT:
if (a instanceof CompressedMatrixBlock)
executeCompressed((CompressedMatrixBlock) a, ab[0], ab[1], b, scalars, out.getDenseBlock(), m, n, k, _outerProductType, 0, m, 0, ((CompressedMatrixBlock) a).getNumColGroups());
else if (!a.isInSparseFormat())
executeDense(a.getDenseBlock(), ab[0], ab[1], b, scalars, out.getDenseBlock(), m, n, k, _outerProductType, 0, m, 0, n);
else
executeSparse(a.getSparseBlock(), ab[0], ab[1], b, scalars, out.getDenseBlock(), m, n, k, a.getNonZeros(), _outerProductType, 0, m, 0, n);
break;
case CELLWISE_OUTER_PRODUCT:
if (a instanceof CompressedMatrixBlock)
executeCellwiseCompressed((CompressedMatrixBlock) a, ab[0], ab[1], b, scalars, out, m, n, k, _outerProductType, 0, m, 0, n);
else if (!a.isInSparseFormat())
executeCellwiseDense(a.getDenseBlock(), ab[0], ab[1], b, scalars, out.getDenseBlock(), m, n, k, _outerProductType, 0, m, 0, n);
else
executeCellwiseSparse(a.getSparseBlock(), ab[0], ab[1], b, scalars, out, m, n, k, a.getNonZeros(), _outerProductType, 0, m, 0, n);
break;
case AGG_OUTER_PRODUCT:
throw new DMLRuntimeException("Wrong codepath for aggregate outer product.");
}
// post-processing
if (a instanceof CompressedMatrixBlock && out.isInSparseFormat() && _outerProductType == OutProdType.CELLWISE_OUTER_PRODUCT)
out.sortSparseRows();
out.recomputeNonZeros();
out.examSparsity();
return out;
}
use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project incubator-systemml by apache.
the class SpoofRowwise method execute.
@Override
public MatrixBlock execute(ArrayList<MatrixBlock> inputs, ArrayList<ScalarObject> scalarObjects, MatrixBlock out, int k) {
// redirect to serial execution
if (k <= 1 || (_type.isColumnAgg() && !LibMatrixMult.checkParColumnAgg(inputs.get(0), k, false)) || getTotalInputSize(inputs) < PAR_NUMCELL_THRESHOLD) {
return execute(inputs, scalarObjects, out);
}
// sanity check
if (inputs == null || inputs.size() < 1 || out == null)
throw new RuntimeException("Invalid input arguments.");
// result allocation and preparations
final int m = inputs.get(0).getNumRows();
final int n = inputs.get(0).getNumColumns();
final int n2 = _type.isConstDim2(_constDim2) ? (int) _constDim2 : _type.isRowTypeB1() || hasMatrixSideInput(inputs) ? getMinColsMatrixSideInputs(inputs) : -1;
allocateOutputMatrix(m, n, n2, out);
final boolean flipOut = _type.isRowTypeB1ColumnAgg() && LibSpoofPrimitives.isFlipOuter(out.getNumRows(), out.getNumColumns());
// input preparation
MatrixBlock a = inputs.get(0);
SideInput[] b = prepInputMatrices(inputs, 1, inputs.size() - 1, false, _tB1);
double[] scalars = prepInputScalars(scalarObjects);
// core parallel execute
ExecutorService pool = CommonThreadPool.get(k);
ArrayList<Integer> blklens = (a instanceof CompressedMatrixBlock) ? LibMatrixMult.getAlignedBlockSizes(m, k, BitmapEncoder.BITMAP_BLOCK_SZ) : LibMatrixMult.getBalancedBlockSizesDefault(m, k, (long) m * n < 16 * PAR_NUMCELL_THRESHOLD);
try {
if (_type.isColumnAgg() || _type == RowType.FULL_AGG) {
// execute tasks
ArrayList<ParColAggTask> tasks = new ArrayList<>();
int outLen = out.getNumRows() * out.getNumColumns();
for (int i = 0, lb = 0; i < blklens.size(); lb += blklens.get(i), i++) tasks.add(new ParColAggTask(a, b, scalars, n, n2, outLen, lb, lb + blklens.get(i)));
List<Future<DenseBlock>> taskret = pool.invokeAll(tasks);
// aggregate partial results
int len = _type.isColumnAgg() ? out.getNumRows() * out.getNumColumns() : 1;
for (Future<DenseBlock> task : taskret) LibMatrixMult.vectAdd(task.get().valuesAt(0), out.getDenseBlockValues(), 0, 0, len);
out.recomputeNonZeros();
} else {
// execute tasks
ArrayList<ParExecTask> tasks = new ArrayList<>();
for (int i = 0, lb = 0; i < blklens.size(); lb += blklens.get(i), i++) tasks.add(new ParExecTask(a, b, out, scalars, n, n2, lb, lb + blklens.get(i)));
List<Future<Long>> taskret = pool.invokeAll(tasks);
// aggregate nnz, no need to aggregate results
long nnz = 0;
for (Future<Long> task : taskret) nnz += task.get();
out.setNonZeros(nnz);
}
pool.shutdown();
if (flipOut) {
fixTransposeDimensions(out);
out = LibMatrixReorg.transpose(out, new MatrixBlock(out.getNumColumns(), out.getNumRows(), false));
}
out.examSparsity();
} catch (Exception ex) {
throw new DMLRuntimeException(ex);
}
return out;
}
use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project incubator-systemml by apache.
the class AggregateBinaryCPInstruction method processInstruction.
@Override
public void processInstruction(ExecutionContext ec) {
// get inputs
MatrixBlock matBlock1 = ec.getMatrixInput(input1.getName(), getExtendedOpcode());
MatrixBlock matBlock2 = ec.getMatrixInput(input2.getName(), getExtendedOpcode());
// compute matrix multiplication
AggregateBinaryOperator ab_op = (AggregateBinaryOperator) _optr;
MatrixBlock main = (matBlock2 instanceof CompressedMatrixBlock) ? matBlock2 : matBlock1;
MatrixBlock ret = main.aggregateBinaryOperations(matBlock1, matBlock2, new MatrixBlock(), ab_op);
// release inputs/outputs
ec.releaseMatrixInput(input1.getName(), getExtendedOpcode());
ec.releaseMatrixInput(input2.getName(), getExtendedOpcode());
ec.setMatrixOutput(output.getName(), ret, getExtendedOpcode());
}
use of org.apache.sysml.runtime.compress.CompressedMatrixBlock in project incubator-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());
}
Aggregations