thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-24 08:32:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improve performance of geo distance functions

Browse Source
This commit is contained in:
Maksim Kita 2022-05-25 14:22:22 +02:00
parent b9bea7d803
commit 45da28ecae
2 changed files with 45 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
src/Functions/greatCircleDistance.cpp
View File

@ -7,6 +7,7 @@
#include <Functions/FunctionHelpers.h> #include <Functions/FunctionHelpers.h>
#include <Functions/FunctionFactory.h> #include <Functions/FunctionFactory.h>
#include <Functions/PerformanceAdaptors.h> #include <Functions/PerformanceAdaptors.h>
#include <Interpreters/castColumn.h>
#include <Common/TargetSpecific.h> #include <Common/TargetSpecific.h>
#include <base/range.h> #include <base/range.h>
#include <cmath> #include <cmath>
@ -14,9 +15,11 @@
namespace DB namespace DB
{ {
namespace ErrorCodes namespace ErrorCodes
{ {
extern const int ILLEGAL_TYPE_OF_ARGUMENT; extern const int ILLEGAL_TYPE_OF_ARGUMENT;
extern const int ILLEGAL_COLUMN;
} }
/** Calculates the distance between two geographical locations. /** Calculates the distance between two geographical locations.
@ -262,24 +265,46 @@ private:
return std::make_shared<DataTypeFloat32>(); return std::make_shared<DataTypeFloat32>();
} }
ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t input_rows_count) const override
{ {
auto dst = ColumnVector<Float32>::create(); auto dst = ColumnVector<Float32>::create();
auto & dst_data = dst->getData(); auto & dst_data = dst->getData();
dst_data.resize(input_rows_count); dst_data.resize(input_rows_count);
const IColumn & col_lon1 = *arguments[0].column; auto arguments_copy = arguments;
const IColumn & col_lat1 = *arguments[1].column; for (auto & argument : arguments_copy) {
const IColumn & col_lon2 = *arguments[2].column; argument.column = castColumn(argument, result_type);
const IColumn & col_lat2 = *arguments[3].column; argument.type = result_type;
}
const auto * col_lon1 = convertArgumentColumnToFloat32(arguments_copy, 0);
const auto * col_lat1 = convertArgumentColumnToFloat32(arguments_copy, 1);
const auto * col_lon2 = convertArgumentColumnToFloat32(arguments_copy, 2);
const auto * col_lat2 = convertArgumentColumnToFloat32(arguments_copy, 3);
for (size_t row_num = 0; row_num < input_rows_count; ++row_num) for (size_t row_num = 0; row_num < input_rows_count; ++row_num)
{
dst_data[row_num] = distance<method>( dst_data[row_num] = distance<method>(
col_lon1.getFloat32(row_num), col_lat1.getFloat32(row_num), col_lon1->getData()[row_num], col_lat1->getData()[row_num],
col_lon2.getFloat32(row_num), col_lat2.getFloat32(row_num)); col_lon2->getData()[row_num], col_lat2->getData()[row_num]);
}
return dst; return dst;
} }
const ColumnFloat32 * convertArgumentColumnToFloat32(const ColumnsWithTypeAndName & arguments, size_t argument_index) const
{
const auto * column_typed = checkAndGetColumn<ColumnFloat32>(arguments[argument_index].column.get());
if (!column_typed)
throw Exception(
ErrorCodes::ILLEGAL_COLUMN,
"Illegal type {} of argument {} of function {}. Must be Float32.",
arguments[argument_index].type->getName(),
argument_index + 1,
getName());
return column_typed;
}
}; };
) // DECLARE_MULTITARGET_CODE ) // DECLARE_MULTITARGET_CODE

15
tests/performance/great_circle_dist.xml
View File

@ -1,7 +1,18 @@
<test> <test>
<substitutions>
<substitution>
<name>func</name>
<values>
<value>greatCircleDistance</value>
<value>greatCircleAngle</value>
<value>geoDistance</value>
</values>
</substitution>
</substitutions>
<!-- lon [-180; 180], lat [-90; 90] --> <!-- lon [-180; 180], lat [-90; 90] -->
<query>SELECT count() FROM numbers(1000000) WHERE NOT ignore(greatCircleDistance((rand(1) % 360) * 1. - 180, (number % 150) * 1.2 - 90, (number % 360) + toFloat64(rand(2)) / 4294967296 - 180, (rand(3) % 180) * 1. - 90))</query> <query>SELECT count() FROM numbers(10000000) WHERE NOT ignore({func}((rand(1) % 360) * 1. - 180, (number % 150) * 1.2 - 90, (number % 360) + toFloat64(rand(2)) / 4294967296 - 180, (rand(3) % 180) * 1. - 90))</query>
<!-- 55.755830, 37.617780 is center of Moscow --> <!-- 55.755830, 37.617780 is center of Moscow -->
<query>SELECT count() FROM zeros(10000000) WHERE NOT ignore(greatCircleDistance(55. + toFloat64(rand(1)) / 4294967296, 37. + toFloat64(rand(2)) / 4294967296, 55. + toFloat64(rand(3)) / 4294967296, 37. + toFloat64(rand(4)) / 4294967296))</query> <query>SELECT count() FROM zeros(100000000) WHERE NOT ignore({func}(55. + toFloat64(rand(1)) / 4294967296, 37. + toFloat64(rand(2)) / 4294967296, 55. + toFloat64(rand(3)) / 4294967296, 37. + toFloat64(rand(4)) / 4294967296))</query>
</test> </test>