thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-22 23:52:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #34287 from danlark1/master

Browse Source 
Optimize quantilesExact{Low,High} to use nth_element instead of sort
This commit is contained in:
Maksim Kita 2022-02-03 18:51:42 +01:00 committed by GitHub
commit a01a74e415
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 31 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
src/AggregateFunctions/QuantileExact.h
View File

@ -262,9 +262,7 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
{
if (!array.empty())
{
// sort inputs in ascending order
::sort(array.begin(), array.end());
size_t n = 0;
// if level is 0.5 then compute the "low" median of the sorted array
// by the method of rounding.
if (level == 0.5)
@ -272,11 +270,11 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
auto s = array.size();
if (s % 2 == 1)
{
return array[static_cast<size_t>(floor(s / 2))];
n = static_cast<size_t>(floor(s / 2));
}
else
{
return array[static_cast<size_t>((floor(s / 2)) - 1)];
n = static_cast<size_t>((floor(s / 2)) - 1);
}
}
else
@ -284,9 +282,10 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
// else quantile is the nth index of the sorted array obtained by multiplying
// level and size of array. Example if level = 0.1 and size of array is 10,
// then return array[1].
size_t n = level < 1 ? level * array.size() : (array.size() - 1);
return array[n];
n = level < 1 ? level * array.size() : (array.size() - 1);
}
::nth_element(array.begin(), array.begin() + n, array.end());
return array[n];
}
return std::numeric_limits<Value>::quiet_NaN();
}
@ -295,12 +294,11 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
{
if (!array.empty())
{
// sort inputs in ascending order
::sort(array.begin(), array.end());
size_t prev_n = 0;
for (size_t i = 0; i < size; ++i)
{
auto level = levels[indices[i]];
size_t n = 0;
// if level is 0.5 then compute the "low" median of the sorted array
// by the method of rounding.
if (level == 0.5)
@ -308,20 +306,22 @@ struct QuantileExactLow : public QuantileExactBase<Value, QuantileExactLow<Value
auto s = array.size();
if (s % 2 == 1)
{
result[indices[i]] = array[static_cast<size_t>(floor(s / 2))];
n = static_cast<size_t>(floor(s / 2));
}
else
{
result[indices[i]] = array[static_cast<size_t>(floor((s / 2) - 1))];
n = static_cast<size_t>(floor((s / 2) - 1));
}
}
else
{
// else quantile is the nth index of the sorted array obtained by multiplying
// level and size of array. Example if level = 0.1 and size of array is 10.
size_t n = level < 1 ? level * array.size() : (array.size() - 1);
result[indices[i]] = array[n];
n = level < 1 ? level * array.size() : (array.size() - 1);
}
::nth_element(array.begin() + prev_n, array.begin() + n, array.end());
result[indices[i]] = array[n];
prev_n = n;
}
}
else
@ -344,23 +344,22 @@ struct QuantileExactHigh : public QuantileExactBase<Value, QuantileExactHigh<Val
{
if (!array.empty())
{
// sort inputs in ascending order
::sort(array.begin(), array.end());
size_t n = 0;
// if level is 0.5 then compute the "high" median of the sorted array
// by the method of rounding.
if (level == 0.5)
{
auto s = array.size();
return array[static_cast<size_t>(floor(s / 2))];
n = static_cast<size_t>(floor(s / 2));
}
else
{
// else quantile is the nth index of the sorted array obtained by multiplying
// level and size of array. Example if level = 0.1 and size of array is 10.
size_t n = level < 1 ? level * array.size() : (array.size() - 1);
return array[n];
n = level < 1 ? level * array.size() : (array.size() - 1);
}
::nth_element(array.begin(), array.begin() + n, array.end());
return array[n];
}
return std::numeric_limits<Value>::quiet_NaN();
}
@ -369,26 +368,27 @@ struct QuantileExactHigh : public QuantileExactBase<Value, QuantileExactHigh<Val
{
if (!array.empty())
{
// sort inputs in ascending order
::sort(array.begin(), array.end());
size_t prev_n = 0;
for (size_t i = 0; i < size; ++i)
{
auto level = levels[indices[i]];
size_t n = 0;
// if level is 0.5 then compute the "high" median of the sorted array
// by the method of rounding.
if (level == 0.5)
{
auto s = array.size();
result[indices[i]] = array[static_cast<size_t>(floor(s / 2))];
n = static_cast<size_t>(floor(s / 2));
}
else
{
// else quantile is the nth index of the sorted array obtained by multiplying
// level and size of array. Example if level = 0.1 and size of array is 10.
size_t n = level < 1 ? level * array.size() : (array.size() - 1);
result[indices[i]] = array[n];
n = level < 1 ? level * array.size() : (array.size() - 1);
}
::nth_element(array.begin() + prev_n, array.begin() + n, array.end());
result[indices[i]] = array[n];
prev_n = n;
}
}
else

5
tests/performance/decimal_aggregates.xml
View File

@ -28,6 +28,11 @@
<query>SELECT quantile(d64), quantileExact(d64), quantileExactWeighted(d64, 2) FROM (SELECT * FROM t LIMIT 1000000)</query>
<query>SELECT quantile(d128), quantileExact(d128), quantileExactWeighted(d128, 2) FROM (SELECT * FROM t LIMIT 1000000)</query>
<query>SELECT quantilesExactLow(0.5)(d32) FROM (SELECT * FROM t LIMIT 10000000)</query>
<query>SELECT quantilesExactHigh(0.5)(d32) FROM (SELECT * FROM t LIMIT 10000000)</query>
<query>SELECT quantilesExactLow(0.1, 0.5, 0.9)(d32) FROM (SELECT * FROM t LIMIT 10000000)</query>
<query>SELECT quantilesExactHigh(0.1, 0.5, 0.9)(d32) FROM (SELECT * FROM t LIMIT 10000000)</query>
<query>SELECT quantilesExact(0.1, 0.9)(d32), quantilesExactWeighted(0.1, 0.9)(d32, 2) FROM (SELECT * FROM t LIMIT 10000000)</query>
<query>SELECT quantilesExact(0.1, 0.9)(d64), quantilesExactWeighted(0.1, 0.9)(d64, 2) FROM (SELECT * FROM t LIMIT 1000000)</query>
<query>SELECT quantilesExact(0.1, 0.9)(d128), quantilesExactWeighted(0.1, 0.9)(d128, 2) FROM (SELECT * FROM t LIMIT 1000000)</query>