Skip to content

[Improvement](function) opt for case when #27054

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
xiaokang merged 1 commit into from
Nov 16, 2023
Merged

[Improvement](function) opt for case when #27054

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 10 additions & 0 deletions be/src/vec/columns/column_nullable.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,16 @@ class ColumnNullable final : public COWHelper<IColumn, ColumnNullable> {
void insert(const Field& x) override;
void insert_from(const IColumn& src, size_t n) override;

template <typename ColumnType>
void insert_from_with_type(const IColumn& src, size_t n) {
const ColumnNullable& src_concrete = assert_cast<const ColumnNullable&>(src);
assert_cast<ColumnType*>(nested_column.get())
->insert_from(src_concrete.get_nested_column(), n);
auto is_null = src_concrete.get_null_map_data()[n];
_has_null |= is_null;
_get_null_map_data().push_back(is_null);
}

void insert_from_not_nullable(const IColumn& src, size_t n);
void insert_range_from_not_nullable(const IColumn& src, size_t start, size_t length);
void insert_many_from_not_nullable(const IColumn& src, size_t position, size_t length);
Expand Down
42 changes: 32 additions & 10 deletions be/src/vec/functions/function_case.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
#include "vec/aggregate_functions/aggregate_function.h"
#include "vec/columns/column.h"
#include "vec/columns/column_complex.h"
#include "vec/columns/column_const.h"
#include "vec/columns/column_nullable.h"
#include "vec/columns/columns_number.h"
#include "vec/core/block.h"
Expand Down Expand Up @@ -197,7 +198,8 @@ class FunctionCase : public IFunction {
}

auto result_column_ptr = data_type->create_column();
update_result_normal(result_column_ptr, then_idx, column_holder);
update_result_normal<int, ColumnType, then_null>(result_column_ptr, then_idx,
column_holder);
block.replace_by_position(result, std::move(result_column_ptr));
return Status::OK();
}
Expand Down Expand Up @@ -269,11 +271,13 @@ class FunctionCase : public IFunction {
std::is_same_v<ColumnType, ColumnHLL>) {
// result_column and all then_column is not nullable.
// can't simd when type is string.
update_result_normal(result_column_ptr, then_idx, column_holder);
update_result_normal<uint8_t, ColumnType, then_null>(result_column_ptr, then_idx,
column_holder);
} else if constexpr (then_null) {
// result_column and all then_column is nullable.
// TODO: make here simd automatically.
update_result_normal(result_column_ptr, then_idx, column_holder);
update_result_normal<uint8_t, ColumnType, then_null>(result_column_ptr, then_idx,
column_holder);
} else {
update_result_auto_simd<ColumnType>(result_column_ptr, then_idx, column_holder);
}
Expand All @@ -282,25 +286,45 @@ class FunctionCase : public IFunction {
return Status::OK();
}

template <typename IndexType>
template <typename IndexType, typename ColumnType, bool then_null>
void update_result_normal(MutableColumnPtr& result_column_ptr, IndexType* then_idx,
CaseWhenColumnHolder& column_holder) {
std::vector<uint8_t> is_consts(column_holder.then_ptrs.size());
std::vector<ColumnPtr> raw_columns(column_holder.then_ptrs.size());
for (size_t i = 0; i < column_holder.then_ptrs.size(); i++) {
if (column_holder.then_ptrs[i].has_value()) {
std::tie(raw_columns[i], is_consts[i]) =
unpack_if_const(column_holder.then_ptrs[i].value());
}
}
for (int row_idx = 0; row_idx < column_holder.rows_count; row_idx++) {
if constexpr (!has_else) {
if (!then_idx[row_idx]) {
result_column_ptr->insert_default();
continue;
}
}
result_column_ptr->insert_from(*column_holder.then_ptrs[then_idx[row_idx]].value(),
row_idx);
size_t target = is_consts[then_idx[row_idx]] ? 0 : row_idx;
if constexpr (then_null) {
assert_cast<ColumnNullable*>(result_column_ptr.get())
->insert_from_with_type<ColumnType>(*raw_columns[then_idx[row_idx]],
target);
} else {
assert_cast<ColumnType*>(result_column_ptr.get())
->insert_from(*raw_columns[then_idx[row_idx]], target);
}
}
}

template <typename ColumnType>
void update_result_auto_simd(MutableColumnPtr& result_column_ptr,
const uint8* __restrict then_idx,
CaseWhenColumnHolder& column_holder) {
for (size_t i = 0; i < column_holder.then_ptrs.size(); i++) {
column_holder.then_ptrs[i]->reset(
column_holder.then_ptrs[i].value()->convert_to_full_column_if_const());
}

size_t rows_count = column_holder.rows_count;
result_column_ptr->resize(rows_count);
auto* __restrict result_raw_data =
Expand Down Expand Up @@ -361,20 +385,18 @@ class FunctionCase : public IFunction {
size_t input_rows_count) {
bool when_null = false;
if constexpr (has_case) {
block.replace_by_position_if_const(arguments[0]);
if (block.get_by_position(arguments[0]).type->is_nullable()) {
when_null = true;
}
}
for (int i = has_case; i < arguments.size() - has_else; i += 2) {
block.replace_by_position_if_const(arguments[i]);
if (block.get_by_position(arguments[i]).type->is_nullable()) {
when_null = true;
}
}

for (int i = 0; i < arguments.size(); i++) {
block.replace_by_position_if_const(arguments[i]);
}

if (when_null) {
return execute_get_then_null<ColumnType, true>(data_type, block, arguments, result,
input_rows_count);
Expand Down