mirror of
https://github.com/apache/impala.git
synced 2025-12-30 12:02:10 -05:00
d7246d64c7
This change enables codegen for all builtin aggregate functions, e.g. timestamp functions and group_concat. There are several parts to the change: * Adding support for generic UDAs. Previous the codegen code did not handle multiple input arguments or NULL return values. * Defaulting to using the UDA interface when there is not a special codegen path (we have implementations of all builtin aggregate functions for the interpreted path). * Remove all the logic to disable codegen for the special cases that now are supported. Also fix the generation of code to get/set NULL bits since I needed to add functionality there anyway. Testing: Add tests that check that codegen was enabled for builtin aggregate functions. Also fix some gaps in the preexisting tests. Also add tests for UDAs that check input/output nulls are handled correctly, in anticipation of enabling codegen for arbitrary UDAs. The tests are run with both codegen enabled and disabled. To avoid flaky tests, we switch the UDF tests to use "unique_database". Perf: Ran local TPC-H and targeted perf. Spent a lot of time on TPC-H Q1, since my original approach regressed it ~5%. In the end the problem was to do with the ordering of loads/stores to the slot and null bit in the generated code: the previous version of the code exploited some properties of the particular aggregate function. I ended up replicating this behaviour to avoid regressing perf. Change-Id: Id9dc21d1d676505d3617e1e4f37557397c4fb260 Reviewed-on: http://gerrit.cloudera.org:8080/4655 Reviewed-by: Tim Armstrong <tarmstrong@cloudera.com> Tested-by: Internal Jenkins
316 lines
5.8 KiB
Plaintext
316 lines
5.8 KiB
Plaintext
====
|
|
---- QUERY
|
|
select hive_pi()
|
|
---- RESULTS
|
|
3.141592653589793
|
|
---- TYPES
|
|
DOUBLE
|
|
====
|
|
---- QUERY
|
|
select hive_bin(100)
|
|
---- RESULTS
|
|
'1100100'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
select min(hive_pi()) from functional.alltypesagg
|
|
---- RESULTS
|
|
3.141592653589793
|
|
---- TYPES
|
|
DOUBLE
|
|
====
|
|
---- QUERY
|
|
# Test identity functions
|
|
select identity(true);
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
select identity(cast(10 as tinyint));
|
|
---- TYPES
|
|
tinyint
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity(cast(10 as smallint));
|
|
---- TYPES
|
|
smallint
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity(cast(10 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity(cast(10 as bigint));
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity(cast(10.0 as float));
|
|
---- TYPES
|
|
float
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity(cast(10.0 as double));
|
|
---- TYPES
|
|
double
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
# IMPALA-1456. Each "identity" call below tests a different type (BytesWritable, Text,
|
|
# and String).
|
|
select identity("why hello there"),
|
|
identity("why", " hello there"),
|
|
identity("why", " hello", " there");
|
|
---- TYPES
|
|
string, string, string
|
|
---- RESULTS
|
|
'why hello there','why hello there','why hello there'
|
|
====
|
|
---- QUERY
|
|
select identity(NULL);
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
NULL
|
|
====
|
|
---- QUERY
|
|
# IMPALA-1134. Each "identity" call below tests a different type (BytesWritable, Text,
|
|
# and String). The different types are handled slightly differently.
|
|
select length(identity("0123456789")),
|
|
length(identity("0123456789", "0123456789")),
|
|
length(identity("0123456789", "0123456789", "0123456789"));
|
|
---- TYPES
|
|
int, int, int
|
|
---- RESULTS
|
|
10,20,30
|
|
====
|
|
---- QUERY
|
|
# IMPALA-1392: Hive UDFs that throw exceptions should return NULL
|
|
select throws_exception();
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
NULL
|
|
====
|
|
---- QUERY
|
|
select throws_exception() from functional.alltypestiny;
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
NULL
|
|
NULL
|
|
NULL
|
|
NULL
|
|
NULL
|
|
NULL
|
|
NULL
|
|
NULL
|
|
====
|
|
---- QUERY
|
|
select hive_add(cast(1 as int), cast(2 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
3
|
|
====
|
|
---- QUERY
|
|
select hive_add(hive_add(cast(1 as int), cast(2 as int)), cast(2 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
5
|
|
====
|
|
---- QUERY
|
|
select hive_add(cast(hive_add(cast(1 as int), cast(2 as int)) - hive_add(cast(2 as int), cast(1 as int)) as int), cast(2 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
2
|
|
====
|
|
---- QUERY
|
|
select hive_add(cast(1 as smallint), cast(2 as smallint));
|
|
---- TYPES
|
|
smallint
|
|
---- RESULTS
|
|
3
|
|
====
|
|
---- QUERY
|
|
select hive_add(cast(1.0 as float), cast(2.0 as float));
|
|
---- TYPES
|
|
float
|
|
---- RESULTS
|
|
3.0
|
|
====
|
|
---- QUERY
|
|
select hive_add(cast(1.0 as double), cast(2.0 as double));
|
|
---- TYPES
|
|
double
|
|
---- RESULTS
|
|
3.0
|
|
====
|
|
---- QUERY
|
|
select hive_add(cast(1 as boolean), cast(0 as boolean));
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
false
|
|
====
|
|
---- QUERY
|
|
# Testing whether all of persistent Java udfs are accessible.
|
|
select identity_anytype(true);
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
select identity_anytype(cast(10 as tinyint));
|
|
---- TYPES
|
|
tinyint
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity_anytype(cast(10 as smallint));
|
|
---- TYPES
|
|
smallint
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity_anytype(cast(10 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity_anytype(cast(10 as bigint));
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity_anytype(cast(10.0 as float));
|
|
---- TYPES
|
|
float
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity_anytype(cast(10.0 as double));
|
|
---- TYPES
|
|
double
|
|
---- RESULTS
|
|
10
|
|
====
|
|
---- QUERY
|
|
select identity_anytype("a", "b");
|
|
---- TYPES
|
|
string
|
|
---- RESULTS
|
|
'ab'
|
|
====
|
|
---- QUERY
|
|
select identity_anytype("a", "b", "c");
|
|
---- TYPES
|
|
string
|
|
---- RESULTS
|
|
'abc'
|
|
====
|
|
---- QUERY
|
|
# IMPALA-3378: test many Java UDFs being opened and run concurrently
|
|
select * from
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(bool_col) union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(tinyint_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(smallint_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(int_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(bigint_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(float_col) > 1.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(double_col) > 1.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(string_col) > '1' union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where not identity(bool_col) union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(tinyint_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(smallint_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(int_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(bigint_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(float_col) > 2.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(double_col) > 2.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where identity(string_col) > '2'
|
|
)))))))))))))))) v
|
|
---- TYPES
|
|
INT
|
|
---- RESULTS
|
|
998
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
====
|
|
---- QUERY
|
|
drop table if exists replace_string_input
|
|
====
|
|
---- QUERY
|
|
create table replace_string_input as
|
|
values('toast'), ('scone'), ('stuff'), ('sssss'), ('yes'), ('scone'), ('stuff');
|
|
====
|
|
---- QUERY
|
|
# Regression test for IMPALA-4266: memory management bugs with output strings from
|
|
# Java UDFS, exposed by using the UDF as a grouping key in an aggregation.
|
|
# The UDF replaces "s" with "ss" in the strings.
|
|
select distinct replace_string(_c0) as es
|
|
from replace_string_input
|
|
order by 1;
|
|
---- TYPES
|
|
string
|
|
---- RESULTS
|
|
'sscone'
|
|
'ssssssssss'
|
|
'sstuff'
|
|
'toasst'
|
|
'yess'
|
|
====
|