private boolean requiresAggregation(Hop input, Direction dir) {
if (!ALLOW_UNARYAGG_WO_FINAL_AGG) return false; // customization not allowed
boolean noAggRequired =
(input.getDim1() > 1
&& input.getDim1() <= input.getRowsInBlock()
&& dir == Direction.Col) // e.g., colSums(X) with nrow(X)<=1000
|| (input.getDim2() > 1
&& input.getDim2() <= input.getColsInBlock()
&& dir == Direction.Row); // e.g., rowSums(X) with ncol(X)<=1000
return !noAggRequired;
}
@Override
public Lop constructLops() throws HopsException, LopsException {
// return already created lops
if (getLops() != null) return getLops();
try {
ExecType et = optFindExecType();
Hop input = getInput().get(0);
if (et == ExecType.CP) {
Lop agg1 = null;
if (isTernaryAggregateRewriteApplicable()) {
agg1 = constructLopsTernaryAggregateRewrite(et);
} else if (isUnaryAggregateOuterCPRewriteApplicable()) {
OperationTypes op = HopsAgg2Lops.get(_op);
DirectionTypes dir = HopsDirection2Lops.get(_direction);
BinaryOp binput = (BinaryOp) getInput().get(0);
agg1 =
new UAggOuterChain(
binput.getInput().get(0).constructLops(),
binput.getInput().get(1).constructLops(),
op,
dir,
HopsOpOp2LopsB.get(binput.getOp()),
DataType.MATRIX,
getValueType(),
ExecType.CP);
PartialAggregate.setDimensionsBasedOnDirection(
agg1, getDim1(), getDim2(), input.getRowsInBlock(), input.getColsInBlock(), dir);
if (getDataType() == DataType.SCALAR) {
UnaryCP unary1 =
new UnaryCP(
agg1, HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR), getDataType(), getValueType());
unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
setLineNumbers(unary1);
setLops(unary1);
}
} else { // general case
int k = OptimizerUtils.getConstrainedNumThreads(_maxNumThreads);
if (DMLScript.USE_ACCELERATOR
&& (DMLScript.FORCE_ACCELERATOR
|| getMemEstimate() < OptimizerUtils.GPU_MEMORY_BUDGET)
&& (_op == AggOp.SUM)) {
et = ExecType.GPU;
k = 1;
}
agg1 =
new PartialAggregate(
input.constructLops(),
HopsAgg2Lops.get(_op),
HopsDirection2Lops.get(_direction),
getDataType(),
getValueType(),
et,
k);
}
setOutputDimensions(agg1);
setLineNumbers(agg1);
setLops(agg1);
if (getDataType() == DataType.SCALAR) {
agg1.getOutputParameters()
.setDimensions(1, 1, getRowsInBlock(), getColsInBlock(), getNnz());
}
} else if (et == ExecType.MR) {
OperationTypes op = HopsAgg2Lops.get(_op);
DirectionTypes dir = HopsDirection2Lops.get(_direction);
// unary aggregate operation
Lop transform1 = null;
if (isUnaryAggregateOuterRewriteApplicable()) {
BinaryOp binput = (BinaryOp) getInput().get(0);
transform1 =
new UAggOuterChain(
binput.getInput().get(0).constructLops(),
binput.getInput().get(1).constructLops(),
op,
dir,
HopsOpOp2LopsB.get(binput.getOp()),
DataType.MATRIX,
getValueType(),
ExecType.MR);
PartialAggregate.setDimensionsBasedOnDirection(
transform1,
getDim1(),
getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
dir);
} else // default
{
transform1 =
new PartialAggregate(input.constructLops(), op, dir, DataType.MATRIX, getValueType());
((PartialAggregate) transform1)
.setDimensionsBasedOnDirection(
getDim1(), getDim2(), input.getRowsInBlock(), input.getColsInBlock());
}
setLineNumbers(transform1);
// aggregation if required
Lop aggregate = null;
Group group1 = null;
Aggregate agg1 = null;
if (requiresAggregation(input, _direction) || transform1 instanceof UAggOuterChain) {
group1 =
new Group(transform1, Group.OperationTypes.Sort, DataType.MATRIX, getValueType());
group1
.getOutputParameters()
.setDimensions(
getDim1(), getDim2(), input.getRowsInBlock(), input.getColsInBlock(), getNnz());
setLineNumbers(group1);
agg1 = new Aggregate(group1, HopsAgg2Lops.get(_op), DataType.MATRIX, getValueType(), et);
agg1.getOutputParameters()
.setDimensions(
getDim1(), getDim2(), input.getRowsInBlock(), input.getColsInBlock(), getNnz());
agg1.setupCorrectionLocation(PartialAggregate.getCorrectionLocation(op, dir));
setLineNumbers(agg1);
aggregate = agg1;
} else {
((PartialAggregate) transform1).setDropCorrection();
aggregate = transform1;
}
setLops(aggregate);
// cast if required
if (getDataType() == DataType.SCALAR) {
// Set the dimensions of PartialAggregate LOP based on the
// direction in which aggregation is performed
PartialAggregate.setDimensionsBasedOnDirection(
transform1,
input.getDim1(),
input.getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
dir);
if (group1 != null && agg1 != null) { // if aggregation required
group1
.getOutputParameters()
.setDimensions(
input.getDim1(),
input.getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
getNnz());
agg1.getOutputParameters()
.setDimensions(1, 1, input.getRowsInBlock(), input.getColsInBlock(), getNnz());
}
UnaryCP unary1 =
new UnaryCP(
aggregate,
HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR),
getDataType(),
getValueType());
unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
setLineNumbers(unary1);
setLops(unary1);
}
} else if (et == ExecType.SPARK) {
OperationTypes op = HopsAgg2Lops.get(_op);
DirectionTypes dir = HopsDirection2Lops.get(_direction);
// unary aggregate
if (isTernaryAggregateRewriteApplicable()) {
Lop aggregate = constructLopsTernaryAggregateRewrite(et);
setOutputDimensions(aggregate); // 0x0 (scalar)
setLineNumbers(aggregate);
setLops(aggregate);
} else if (isUnaryAggregateOuterSPRewriteApplicable()) {
BinaryOp binput = (BinaryOp) getInput().get(0);
Lop transform1 =
new UAggOuterChain(
binput.getInput().get(0).constructLops(),
binput.getInput().get(1).constructLops(),
op,
dir,
HopsOpOp2LopsB.get(binput.getOp()),
DataType.MATRIX,
getValueType(),
ExecType.SPARK);
PartialAggregate.setDimensionsBasedOnDirection(
transform1,
getDim1(),
getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
dir);
setLineNumbers(transform1);
setLops(transform1);
if (getDataType() == DataType.SCALAR) {
UnaryCP unary1 =
new UnaryCP(
transform1,
HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR),
getDataType(),
getValueType());
unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
setLineNumbers(unary1);
setLops(unary1);
}
} else // default
{
boolean needAgg = requiresAggregation(input, _direction);
SparkAggType aggtype = getSparkUnaryAggregationType(needAgg);
PartialAggregate aggregate =
new PartialAggregate(
input.constructLops(),
HopsAgg2Lops.get(_op),
HopsDirection2Lops.get(_direction),
DataType.MATRIX,
getValueType(),
aggtype,
et);
aggregate.setDimensionsBasedOnDirection(
getDim1(), getDim2(), input.getRowsInBlock(), input.getColsInBlock());
setLineNumbers(aggregate);
setLops(aggregate);
if (getDataType() == DataType.SCALAR) {
UnaryCP unary1 =
new UnaryCP(
aggregate,
HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR),
getDataType(),
getValueType());
unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
setLineNumbers(unary1);
setLops(unary1);
}
}
}
} catch (Exception e) {
throw new HopsException(
this.printErrorLocation() + "In AggUnary Hop, error constructing Lops ", e);
}
// add reblock/checkpoint lops if necessary
constructAndSetLopsDataFlowProperties();
// return created lops
return getLops();
}
/**
* MR Cumsum is currently based on a multipass algorithm of (1) preaggregation and (2) subsequent
* offsetting. Note that we currently support one robust physical operator but many alternative
* realizations are possible for specific scenarios (e.g., when the preaggregated intermediate fit
* into the map task memory budget) or by creating custom job types.
*
* @return
* @throws HopsException
* @throws LopsException
*/
private Lop constructLopsMRCumulativeUnary() throws HopsException, LopsException {
Hop input = getInput().get(0);
long rlen = input.getDim1();
long clen = input.getDim2();
long brlen = input.getRowsInBlock();
long bclen = input.getColsInBlock();
boolean force = !dimsKnown() || _etypeForced == ExecType.MR;
OperationTypes aggtype = getCumulativeAggType();
Lop X = input.constructLops();
Lop TEMP = X;
ArrayList<Lop> DATA = new ArrayList<Lop>();
int level = 0;
// recursive preaggregation until aggregates fit into CP memory budget
while (((2 * OptimizerUtils.estimateSize(TEMP.getOutputParameters().getNumRows(), clen)
+ OptimizerUtils.estimateSize(1, clen))
> OptimizerUtils.getLocalMemBudget()
&& TEMP.getOutputParameters().getNumRows() > 1)
|| force) {
DATA.add(TEMP);
// preaggregation per block
long rlenAgg = (long) Math.ceil((double) TEMP.getOutputParameters().getNumRows() / brlen);
Lop preagg =
new CumulativePartialAggregate(
TEMP, DataType.MATRIX, ValueType.DOUBLE, aggtype, ExecType.MR);
preagg.getOutputParameters().setDimensions(rlenAgg, clen, brlen, bclen, -1);
setLineNumbers(preagg);
Group group = new Group(preagg, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
group.getOutputParameters().setDimensions(rlenAgg, clen, brlen, bclen, -1);
setLineNumbers(group);
Aggregate agg =
new Aggregate(
group, HopsAgg2Lops.get(AggOp.SUM), getDataType(), getValueType(), ExecType.MR);
agg.getOutputParameters().setDimensions(rlenAgg, clen, brlen, bclen, -1);
agg.setupCorrectionLocation(
CorrectionLocationType
.NONE); // aggregation uses kahanSum but the inputs do not have correction values
setLineNumbers(agg);
TEMP = agg;
level++;
force = false; // in case of unknowns, generate one level
}
// in-memory cum sum (of partial aggregates)
if (TEMP.getOutputParameters().getNumRows() != 1) {
int k = OptimizerUtils.getConstrainedNumThreads(_maxNumThreads);
Unary unary1 =
new Unary(
TEMP, HopsOpOp1LopsU.get(_op), DataType.MATRIX, ValueType.DOUBLE, ExecType.CP, k);
unary1
.getOutputParameters()
.setDimensions(TEMP.getOutputParameters().getNumRows(), clen, brlen, bclen, -1);
setLineNumbers(unary1);
TEMP = unary1;
}
// split, group and mr cumsum
while (level-- > 0) {
double init = getCumulativeInitValue();
CumulativeSplitAggregate split =
new CumulativeSplitAggregate(TEMP, DataType.MATRIX, ValueType.DOUBLE, init);
split.getOutputParameters().setDimensions(rlen, clen, brlen, bclen, -1);
setLineNumbers(split);
Group group1 =
new Group(DATA.get(level), Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
group1.getOutputParameters().setDimensions(rlen, clen, brlen, bclen, -1);
setLineNumbers(group1);
Group group2 = new Group(split, Group.OperationTypes.Sort, DataType.MATRIX, ValueType.DOUBLE);
group2.getOutputParameters().setDimensions(rlen, clen, brlen, bclen, -1);
setLineNumbers(group2);
CumulativeOffsetBinary binary =
new CumulativeOffsetBinary(
group1, group2, DataType.MATRIX, ValueType.DOUBLE, aggtype, ExecType.MR);
binary.getOutputParameters().setDimensions(rlen, clen, brlen, bclen, -1);
setLineNumbers(binary);
TEMP = binary;
}
return TEMP;
}
/**
* @return
* @throws HopsException
* @throws LopsException
*/
private Lop constructLopsSparkCumulativeUnary() throws HopsException, LopsException {
Hop input = getInput().get(0);
long rlen = input.getDim1();
long clen = input.getDim2();
long brlen = input.getRowsInBlock();
long bclen = input.getColsInBlock();
boolean force = !dimsKnown() || _etypeForced == ExecType.SPARK;
OperationTypes aggtype = getCumulativeAggType();
Lop X = input.constructLops();
Lop TEMP = X;
ArrayList<Lop> DATA = new ArrayList<Lop>();
int level = 0;
// recursive preaggregation until aggregates fit into CP memory budget
while (((2 * OptimizerUtils.estimateSize(TEMP.getOutputParameters().getNumRows(), clen)
+ OptimizerUtils.estimateSize(1, clen))
> OptimizerUtils.getLocalMemBudget()
&& TEMP.getOutputParameters().getNumRows() > 1)
|| force) {
DATA.add(TEMP);
// preaggregation per block (for spark, the CumulativePartialAggregate subsumes both
// the preaggregation and subsequent block aggregation)
long rlenAgg = (long) Math.ceil((double) TEMP.getOutputParameters().getNumRows() / brlen);
Lop preagg =
new CumulativePartialAggregate(
TEMP, DataType.MATRIX, ValueType.DOUBLE, aggtype, ExecType.SPARK);
preagg.getOutputParameters().setDimensions(rlenAgg, clen, brlen, bclen, -1);
setLineNumbers(preagg);
TEMP = preagg;
level++;
force = false; // in case of unknowns, generate one level
}
// in-memory cum sum (of partial aggregates)
if (TEMP.getOutputParameters().getNumRows() != 1) {
int k = OptimizerUtils.getConstrainedNumThreads(_maxNumThreads);
Unary unary1 =
new Unary(
TEMP, HopsOpOp1LopsU.get(_op), DataType.MATRIX, ValueType.DOUBLE, ExecType.CP, k);
unary1
.getOutputParameters()
.setDimensions(TEMP.getOutputParameters().getNumRows(), clen, brlen, bclen, -1);
setLineNumbers(unary1);
TEMP = unary1;
}
// split, group and mr cumsum
while (level-- > 0) {
// (for spark, the CumulativeOffsetBinary subsumes both the split aggregate and
// the subsequent offset binary apply of split aggregates against the original data)
double initValue = getCumulativeInitValue();
CumulativeOffsetBinary binary =
new CumulativeOffsetBinary(
DATA.get(level),
TEMP,
DataType.MATRIX,
ValueType.DOUBLE,
initValue,
aggtype,
ExecType.SPARK);
binary.getOutputParameters().setDimensions(rlen, clen, brlen, bclen, -1);
setLineNumbers(binary);
TEMP = binary;
}
return TEMP;
}
private Lop constructLopsIQM() throws HopsException, LopsException {
ExecType et = optFindExecType();
Hop input = getInput().get(0);
if (et == ExecType.MR) {
CombineUnary combine =
CombineUnary.constructCombineLop(input.constructLops(), DataType.MATRIX, getValueType());
combine
.getOutputParameters()
.setDimensions(
input.getDim1(),
input.getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
input.getNnz());
SortKeys sort =
SortKeys.constructSortByValueLop(
combine,
SortKeys.OperationTypes.WithoutWeights,
DataType.MATRIX,
ValueType.DOUBLE,
ExecType.MR);
// Sort dimensions are same as the first input
sort.getOutputParameters()
.setDimensions(
input.getDim1(),
input.getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
input.getNnz());
Data lit = Data.createLiteralLop(ValueType.DOUBLE, Double.toString(0.25));
lit.setAllPositions(
this.getBeginLine(), this.getBeginColumn(), this.getEndLine(), this.getEndColumn());
PickByCount pick =
new PickByCount(
sort, lit, DataType.MATRIX, getValueType(), PickByCount.OperationTypes.RANGEPICK);
pick.getOutputParameters().setDimensions(-1, -1, getRowsInBlock(), getColsInBlock(), -1);
setLineNumbers(pick);
PartialAggregate pagg =
new PartialAggregate(
pick,
HopsAgg2Lops.get(Hop.AggOp.SUM),
HopsDirection2Lops.get(Hop.Direction.RowCol),
DataType.MATRIX,
getValueType());
setLineNumbers(pagg);
// Set the dimensions of PartialAggregate LOP based on the
// direction in which aggregation is performed
pagg.setDimensionsBasedOnDirection(getDim1(), getDim2(), getRowsInBlock(), getColsInBlock());
Group group1 = new Group(pagg, Group.OperationTypes.Sort, DataType.MATRIX, getValueType());
group1
.getOutputParameters()
.setDimensions(getDim1(), getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
setLineNumbers(group1);
Aggregate agg1 =
new Aggregate(
group1,
HopsAgg2Lops.get(Hop.AggOp.SUM),
DataType.MATRIX,
getValueType(),
ExecType.MR);
agg1.getOutputParameters()
.setDimensions(getDim1(), getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
agg1.setupCorrectionLocation(pagg.getCorrectionLocation());
setLineNumbers(agg1);
UnaryCP unary1 =
new UnaryCP(
agg1, HopsOpOp1LopsUS.get(OpOp1.CAST_AS_SCALAR), getDataType(), getValueType());
unary1.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
setLineNumbers(unary1);
Unary iqm =
new Unary(
sort,
unary1,
Unary.OperationTypes.MR_IQM,
DataType.SCALAR,
ValueType.DOUBLE,
ExecType.CP);
iqm.getOutputParameters().setDimensions(0, 0, 0, 0, -1);
setLineNumbers(iqm);
return iqm;
} else {
SortKeys sort =
SortKeys.constructSortByValueLop(
input.constructLops(),
SortKeys.OperationTypes.WithoutWeights,
DataType.MATRIX,
ValueType.DOUBLE,
et);
sort.getOutputParameters()
.setDimensions(
input.getDim1(),
input.getDim2(),
input.getRowsInBlock(),
input.getColsInBlock(),
input.getNnz());
PickByCount pick =
new PickByCount(
sort, null, getDataType(), getValueType(), PickByCount.OperationTypes.IQM, et, true);
pick.getOutputParameters()
.setDimensions(getDim1(), getDim2(), getRowsInBlock(), getColsInBlock(), getNnz());
setLineNumbers(pick);
return pick;
}
}