Skip to content

P
Postgres FD Implementation
Commit af025eed authored by Robert Haas's avatar Robert Haas
Browse files
Options

Add combine functions for various floating-point aggregates. 

This allows parallel aggregation to use them.  It may seem surprising
that we use float8_combine for both float4_accum and float8_accum
transition functions, but that's because those functions differ only
in the type of the non-transition-state argument.

Haribabu Kommi, reviewed by David Rowley and Tomas Vondra
parent 38627f68
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 159 additions and 46 deletions
doc/src/sgml/func.sgml
View file @ af025eed
......@@ -12743,7 +12743,7 @@ NULL baz</literallayout>(3 rows)</entry>
<type>double precision</type> for a floating-point argument,
otherwise the same as the argument data type
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>the average (arithmetic mean) of all input values</entry>
</row>
......@@ -13001,7 +13001,7 @@ NULL baz</literallayout>(3 rows)</entry>
<type>bigint</type> arguments, otherwise the same as the
argument data type
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>sum of <replaceable class="parameter">expression</replaceable> across all input values</entry>
</row>
......@@ -13153,7 +13153,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>correlation coefficient</entry>
</row>
......@@ -13174,7 +13174,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>population covariance</entry>
</row>
......@@ -13195,7 +13195,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>sample covariance</entry>
</row>
......@@ -13212,7 +13212,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>average of the independent variable
(<literal>sum(<replaceable class="parameter">X</replaceable>)/<replaceable class="parameter">N</replaceable></literal>)</entry>
</row>
......@@ -13230,7 +13230,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>average of the dependent variable
(<literal>sum(<replaceable class="parameter">Y</replaceable>)/<replaceable class="parameter">N</replaceable></literal>)</entry>
</row>
......@@ -13248,7 +13248,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>bigint</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>number of input rows in which both expressions are nonnull</entry>
</row>
......@@ -13268,7 +13268,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>y-intercept of the least-squares-fit linear equation
determined by the (<replaceable
class="parameter">X</replaceable>, <replaceable
......@@ -13288,7 +13288,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>square of the correlation coefficient</entry>
</row>
......@@ -13308,7 +13308,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry>slope of the least-squares-fit linear equation determined
by the (<replaceable class="parameter">X</replaceable>,
<replaceable class="parameter">Y</replaceable>) pairs</entry>
......@@ -13327,7 +13327,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry><literal>sum(<replaceable
class="parameter">X</replaceable>^2) - sum(<replaceable
class="parameter">X</replaceable>)^2/<replaceable
......@@ -13348,7 +13348,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry><literal>sum(<replaceable
class="parameter">X</replaceable>*<replaceable
class="parameter">Y</replaceable>) - sum(<replaceable
......@@ -13372,7 +13372,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<entry>
<type>double precision</type>
</entry>
<entry>No</entry>
<entry>Yes</entry>
<entry><literal>sum(<replaceable
class="parameter">Y</replaceable>^2) - sum(<replaceable
class="parameter">Y</replaceable>)^2/<replaceable
......@@ -13399,7 +13399,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<type>double precision</type> for floating-point arguments,
otherwise <type>numeric</type>
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>historical alias for <function>stddev_samp</function></entry>
</row>
......@@ -13423,7 +13423,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<type>double precision</type> for floating-point arguments,
otherwise <type>numeric</type>
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>population standard deviation of the input values</entry>
</row>
......@@ -13447,7 +13447,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<type>double precision</type> for floating-point arguments,
otherwise <type>numeric</type>
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>sample standard deviation of the input values</entry>
</row>
......@@ -13467,7 +13467,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<type>double precision</type> for floating-point arguments,
otherwise <type>numeric</type>
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>historical alias for <function>var_samp</function></entry>
</row>
......@@ -13491,7 +13491,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<type>double precision</type> for floating-point arguments,
otherwise <type>numeric</type>
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>population variance of the input values (square of the population standard deviation)</entry>
</row>
......@@ -13515,7 +13515,7 @@ SELECT xmlagg(x) FROM (SELECT x FROM test ORDER BY y DESC) AS tab;
<type>double precision</type> for floating-point arguments,
otherwise <type>numeric</type>
</entry>
<entry>All types apart from floating-point types</entry>
<entry>Yes</entry>
<entry>sample variance of the input values (square of the sample standard deviation)</entry>
</row>
</tbody>
......
src/backend/utils/adt/float.c
View file @ af025eed
......@@ -2435,6 +2435,50 @@ check_float8_array(ArrayType *transarray, const char *caller, int n)
return (float8 *) ARR_DATA_PTR(transarray);
}
/*
* float8_combine
*
* An aggregate combine function used to combine two 3 fields
* aggregate transition data into a single transition data.
* This function is used only in two stage aggregation and
* shouldn't be called outside aggregate context.
*/
Datum
float8_combine(PG_FUNCTION_ARGS)
{
ArrayType *transarray1 = PG_GETARG_ARRAYTYPE_P(0);
ArrayType *transarray2 = PG_GETARG_ARRAYTYPE_P(1);
float8 *transvalues1;
float8 *transvalues2;
float8 N,
sumX,
sumX2;
if (!AggCheckCallContext(fcinfo, NULL))
elog(ERROR, "aggregate function called in non-aggregate context");
transvalues1 = check_float8_array(transarray1, "float8_combine", 3);
N = transvalues1[0];
sumX = transvalues1[1];
sumX2 = transvalues1[2];
transvalues2 = check_float8_array(transarray2, "float8_combine", 3);
N += transvalues2[0];
sumX += transvalues2[1];
CHECKFLOATVAL(sumX, isinf(transvalues1[1]) || isinf(transvalues2[1]),
true);
sumX2 += transvalues2[2];
CHECKFLOATVAL(sumX2, isinf(transvalues1[2]) || isinf(transvalues2[2]),
true);
transvalues1[0] = N;
transvalues1[1] = sumX;
transvalues1[2] = sumX2;
PG_RETURN_ARRAYTYPE_P(transarray1);
}
Datum
float8_accum(PG_FUNCTION_ARGS)
{
......@@ -2762,6 +2806,69 @@ float8_regr_accum(PG_FUNCTION_ARGS)
}
}
/*
* float8_regr_combine
*
* An aggregate combine function used to combine two 6 fields
* aggregate transition data into a single transition data.
* This function is used only in two stage aggregation and
* shouldn't be called outside aggregate context.
*/
Datum
float8_regr_combine(PG_FUNCTION_ARGS)
{
ArrayType *transarray1 = PG_GETARG_ARRAYTYPE_P(0);
ArrayType *transarray2 = PG_GETARG_ARRAYTYPE_P(1);
float8 *transvalues1;
float8 *transvalues2;
float8 N,
sumX,
sumX2,
sumY,
sumY2,
sumXY;
if (!AggCheckCallContext(fcinfo, NULL))
elog(ERROR, "aggregate function called in non-aggregate context");
transvalues1 = check_float8_array(transarray1, "float8_regr_combine", 6);
N = transvalues1[0];
sumX = transvalues1[1];
sumX2 = transvalues1[2];
sumY = transvalues1[3];
sumY2 = transvalues1[4];
sumXY = transvalues1[5];
transvalues2 = check_float8_array(transarray2, "float8_regr_combine", 6);
N += transvalues2[0];
sumX += transvalues2[1];
CHECKFLOATVAL(sumX, isinf(transvalues1[1]) || isinf(transvalues2[1]),
true);
sumX2 += transvalues2[2];
CHECKFLOATVAL(sumX2, isinf(transvalues1[2]) || isinf(transvalues2[2]),
true);
sumY += transvalues2[3];
CHECKFLOATVAL(sumY, isinf(transvalues1[3]) || isinf(transvalues2[3]),
true);
sumY2 += transvalues2[4];
CHECKFLOATVAL(sumY2, isinf(transvalues1[4]) || isinf(transvalues2[4]),
true);
sumXY += transvalues2[5];
CHECKFLOATVAL(sumXY, isinf(transvalues1[5]) || isinf(transvalues2[5]),
true);
transvalues1[0] = N;
transvalues1[1] = sumX;
transvalues1[2] = sumX2;
transvalues1[3] = sumY;
transvalues1[4] = sumY2;
transvalues1[5] = sumXY;
PG_RETURN_ARRAYTYPE_P(transarray1);
}
Datum
float8_regr_sxx(PG_FUNCTION_ARGS)
{
......
src/include/catalog/pg_aggregate.h
View file @ af025eed
This diff is collapsed.
src/include/catalog/pg_proc.h
View file @ af025eed
......@@ -400,6 +400,8 @@ DATA(insert OID = 220 ( float8um PGNSP PGUID 12 1 0 0 0 f f f f t f i s 1 0
DATA(insert OID = 221 ( float8abs PGNSP PGUID 12 1 0 0 0 f f f f t f i s 1 0 701 "701" _null_ _null_ _null_ _null_ _null_ float8abs _null_ _null_ _null_ ));
DATA(insert OID = 222 ( float8_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i s 2 0 1022 "1022 701" _null_ _null_ _null_ _null_ _null_ float8_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 276 ( float8_combine PGNSP PGUID 12 1 0 0 0 f f f f t f i s 2 0 1022 "1022 1022" _null_ _null_ _null_ _null_ _null_ float8_combine _null_ _null_ _null_ ));
DESCR("aggregate combine function");
DATA(insert OID = 223 ( float8larger PGNSP PGUID 12 1 0 0 0 f f f f t f i s 2 0 701 "701 701" _null_ _null_ _null_ _null_ _null_ float8larger _null_ _null_ _null_ ));
DESCR("larger of two");
DATA(insert OID = 224 ( float8smaller PGNSP PGUID 12 1 0 0 0 f f f f t f i s 2 0 701 "701 701" _null_ _null_ _null_ _null_ _null_ float8smaller _null_ _null_ _null_ ));
......@@ -2542,6 +2544,8 @@ DATA(insert OID = 2805 ( int8inc_float8_float8 PGNSP PGUID 12 1 0 0 0 f f f f
DESCR("aggregate transition function");
DATA(insert OID = 2806 ( float8_regr_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i s 3 0 1022 "1022 701 701" _null_ _null_ _null_ _null_ _null_ float8_regr_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 3342 ( float8_regr_combine PGNSP PGUID 12 1 0 0 0 f f f f t f i s 2 0 1022 "1022 1022" _null_ _null_ _null_ _null_ _null_ float8_regr_combine _null_ _null_ _null_ ));
DESCR("aggregate combine function");
DATA(insert OID = 2807 ( float8_regr_sxx PGNSP PGUID 12 1 0 0 0 f f f f t f i s 1 0 701 "1022" _null_ _null_ _null_ _null_ _null_ float8_regr_sxx _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 2808 ( float8_regr_syy PGNSP PGUID 12 1 0 0 0 f f f f t f i s 1 0 701 "1022" _null_ _null_ _null_ _null_ _null_ float8_regr_syy _null_ _null_ _null_ ));
......
src/include/utils/builtins.h
View file @ af025eed
......@@ -427,6 +427,7 @@ extern Datum dpi(PG_FUNCTION_ARGS);
extern Datum radians(PG_FUNCTION_ARGS);
extern Datum drandom(PG_FUNCTION_ARGS);
extern Datum setseed(PG_FUNCTION_ARGS);
extern Datum float8_combine(PG_FUNCTION_ARGS);
extern Datum float8_accum(PG_FUNCTION_ARGS);
extern Datum float4_accum(PG_FUNCTION_ARGS);
extern Datum float8_avg(PG_FUNCTION_ARGS);
......@@ -435,6 +436,7 @@ extern Datum float8_var_samp(PG_FUNCTION_ARGS);
extern Datum float8_stddev_pop(PG_FUNCTION_ARGS);
extern Datum float8_stddev_samp(PG_FUNCTION_ARGS);
extern Datum float8_regr_accum(PG_FUNCTION_ARGS);
extern Datum float8_regr_combine(PG_FUNCTION_ARGS);
extern Datum float8_regr_sxx(PG_FUNCTION_ARGS);
extern Datum float8_regr_syy(PG_FUNCTION_ARGS);
extern Datum float8_regr_sxy(PG_FUNCTION_ARGS);
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment