Skip to content

fix kernel usage through chunked arrays #1987

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ivanmorozov333 merged 2 commits into from
Feb 16, 2024
Merged

fix kernel usage through chunked arrays #1987

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0008d2b
fix kernel usage through chunked arrays
ivanmorozov333 Feb 15, 2024
3b2d327
correction
ivanmorozov333 Feb 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions ydb/core/formats/arrow/arrow_filter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -611,4 +611,12 @@ std::optional<ui32> TColumnFilter::GetFilteredCount() const {
return *FilteredCount;
}

void TColumnFilter::Append(const TColumnFilter& filter) {
bool currentVal = filter.GetStartValue();
for (auto&& i : filter.Filter) {
Add(currentVal, i);
currentVal = !currentVal;
}
}

}
1 change: 1 addition & 0 deletions ydb/core/formats/arrow/arrow_filter.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@ class TColumnFilter {
FilteredCount.reset();
}
public:
void Append(const TColumnFilter& filter);
void Add(const bool value, const ui32 count = 1);
std::optional<ui32> GetFilteredCount() const;
const std::vector<bool>& BuildSimpleFilter() const;
Expand Down
31 changes: 31 additions & 0 deletions ydb/core/formats/arrow/arrow_helpers.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -977,4 +977,35 @@ std::shared_ptr<arrow::RecordBatch> MergeColumns(const std::vector<std::shared_p
return arrow::RecordBatch::Make(schema, *recordsCount, columns);
}

std::vector<std::shared_ptr<arrow::RecordBatch>> SliceToRecordBatches(const std::shared_ptr<arrow::Table>& t) {
std::set<ui32> splitPositions;
const ui32 numRows = t->num_rows();
for (auto&& i : t->columns()) {
ui32 pos = 0;
for (auto&& arr : i->chunks()) {
splitPositions.emplace(pos);
pos += arr->length();
}
AFL_VERIFY(pos == t->num_rows());
}
std::vector<std::vector<std::shared_ptr<arrow::Array>>> slicedData;
slicedData.resize(splitPositions.size());
std::vector<ui32> positions(splitPositions.begin(), splitPositions.end());
for (auto&& i : t->columns()) {
for (ui32 idx = 0; idx < positions.size(); ++idx) {
auto slice = i->Slice(positions[idx], ((idx + 1 == positions.size()) ? numRows : positions[idx + 1]) - positions[idx]);
AFL_VERIFY(slice->num_chunks() == 1);
slicedData[idx].emplace_back(slice->chunks().front());
}
}
std::vector<std::shared_ptr<arrow::RecordBatch>> result;
ui32 count = 0;
for (auto&& i : slicedData) {
result.emplace_back(arrow::RecordBatch::Make(t->schema(), i.front()->length(), i));
count += result.back()->num_rows();
}
AFL_VERIFY(count == t->num_rows())("count", count)("t", t->num_rows());
return result;
}

}
2 changes: 2 additions & 0 deletions ydb/core/formats/arrow/arrow_helpers.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,8 @@ inline bool HasNulls(const std::shared_ptr<arrow::Array>& column) {
return column->null_bitmap_data();
}

std::vector<std::shared_ptr<arrow::RecordBatch>> SliceToRecordBatches(const std::shared_ptr<arrow::Table>& t);

bool ArrayScalarsEqual(const std::shared_ptr<arrow::Array>& lhs, const std::shared_ptr<arrow::Array>& rhs);
std::shared_ptr<arrow::Array> BoolVecToArray(const std::vector<bool>& vec);

Expand Down
18 changes: 12 additions & 6 deletions ydb/core/formats/arrow/program.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -871,12 +871,18 @@ std::shared_ptr<NArrow::TColumnFilter> TProgramStep::BuildFilter(const std::shar
if (Filters.empty()) {
return nullptr;
}
auto datumBatch = TDatumBatch::FromTable(t);

NArrow::TStatusValidator::Validate(ApplyAssignes(*datumBatch, NArrow::GetCustomExecContext()));
NArrow::TColumnFilter local = NArrow::TColumnFilter::BuildAllowFilter();
NArrow::TStatusValidator::Validate(MakeCombinedFilter(*datumBatch, local));
return std::make_shared<NArrow::TColumnFilter>(std::move(local));
std::vector<std::shared_ptr<arrow::RecordBatch>> batches = NArrow::SliceToRecordBatches(t);
NArrow::TColumnFilter fullLocal = NArrow::TColumnFilter::BuildAllowFilter();
for (auto&& rb : batches) {
auto datumBatch = TDatumBatch::FromRecordBatch(rb);
NArrow::TStatusValidator::Validate(ApplyAssignes(*datumBatch, NArrow::GetCustomExecContext()));
NArrow::TColumnFilter local = NArrow::TColumnFilter::BuildAllowFilter();
NArrow::TStatusValidator::Validate(MakeCombinedFilter(*datumBatch, local));
AFL_VERIFY(local.Size() == datumBatch->Rows)("local", local.Size())("datum", datumBatch->Rows);
fullLocal.Append(local);
}
AFL_VERIFY(fullLocal.Size() == t->num_rows())("filter", fullLocal.Size())("t", t->num_rows());
return std::make_shared<NArrow::TColumnFilter>(std::move(fullLocal));
}

const std::set<ui32>& TProgramStep::GetFilterOriginalColumnIds() const {
Expand Down