hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jcama...@apache.org
Subject [28/34] hive git commit: HIVE-18979: Enable AggregateReduceFunctionsRule from Calcite (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Date Thu, 22 Mar 2018 16:57:51 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/5cb8867b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
index dabc987..74caa3f 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
@@ -76,18 +76,18 @@ STAGE PLANS:
                         projectedOutputColumnNums: [0, 1, 2]
                     Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column
stats: NONE
                     Group By Operator
-                      aggregations: avg(c_dec), count()
+                      aggregations: sum(c_dec), count(c_dec), count()
                       Group By Vectorization:
-                          aggregators: VectorUDAFAvgDecimal(col 2:decimal(10,2)) -> struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VectorUDAFCountStar(*) -> bigint
+                          aggregators: VectorUDAFSumDecimal(col 2:decimal(10,2)) -> decimal(20,2),
VectorUDAFCount(col 2:decimal(10,2)) -> bigint, VectorUDAFCountStar(*) -> bigint
                           className: VectorGroupByOperator
                           groupByMode: HASH
                           keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val
0) -> 4:bigint
                           native: false
                           vectorProcessingMode: HASH
-                          projectedOutputColumnNums: [0, 1]
+                          projectedOutputColumnNums: [0, 1, 2]
                       keys: a (type: string), b (type: string), 0L (type: bigint)
                       mode: hash
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
                       Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string), _col2
(type: bigint)
@@ -98,9 +98,9 @@ STAGE PLANS:
                             keyColumnNums: [0, 1, 2]
                             native: true
                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                            valueColumnNums: [3, 4]
+                            valueColumnNums: [3, 4, 5]
                         Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col3 (type: struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>),
_col4 (type: bigint)
+                        value expressions: _col3 (type: decimal(20,2)), _col4 (type: bigint),
_col5 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -129,33 +129,34 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
                 rowBatchContext:
-                    dataColumnCount: 5
-                    dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VALUE._col1:bigint
+                    dataColumnCount: 6
+                    dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:decimal(20,2),
VALUE._col1:bigint, VALUE._col2:bigint
                     partitionColumnCount: 0
                     scratchColumnTypeNames: []
             Reduce Operator Tree:
               Group By Operator
-                aggregations: avg(VALUE._col0), count(VALUE._col1)
+                aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
                 Group By Vectorization:
-                    aggregators: VectorUDAFAvgDecimalFinal(col 3:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>)
-> decimal(14,6), VectorUDAFCountMerge(col 4:bigint) -> bigint
+                    aggregators: VectorUDAFSumDecimal(col 3:decimal(20,2)) -> decimal(20,2),
VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFCountMerge(col 5:bigint) ->
bigint
                     className: VectorGroupByOperator
                     groupByMode: MERGEPARTIAL
                     keyExpressions: col 0:string, col 1:string, col 2:bigint
                     native: false
                     vectorProcessingMode: MERGE_PARTIAL
-                    projectedOutputColumnNums: [0, 1]
+                    projectedOutputColumnNums: [0, 1, 2]
                 keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type:
bigint)
                 mode: mergepartial
-                outputColumnNames: _col0, _col1, _col3, _col4
+                outputColumnNames: _col0, _col1, _col3, _col4, _col5
                 Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats:
NONE
                 pruneGroupingSetId: true
                 Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(14,6)),
_col4 (type: bigint)
+                  expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4)
(type: decimal(38,20)), _col5 (type: bigint)
                   outputColumnNames: _col0, _col1, _col2, _col3
                   Select Vectorization:
                       className: VectorSelectOperator
                       native: true
-                      projectedOutputColumnNums: [0, 1, 2, 3]
+                      projectedOutputColumnNums: [0, 1, 6, 4]
+                      selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(20,2),
col 5:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 5:decimal(19,0)) ->
6:decimal(38,20)
                   Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column
stats: NONE
                   File Output Operator
                     compressed: false
@@ -214,18 +215,18 @@ STAGE PLANS:
                         projectedOutputColumnNums: [0, 1, 2]
                     Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column
stats: NONE
                     Group By Operator
-                      aggregations: avg(c_dec), count()
+                      aggregations: sum(c_dec), count(c_dec), count()
                       Group By Vectorization:
-                          aggregators: VectorUDAFAvgDecimal(col 2:decimal(10,2)) -> struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VectorUDAFCountStar(*) -> bigint
+                          aggregators: VectorUDAFSumDecimal(col 2:decimal(10,2)) -> decimal(20,2),
VectorUDAFCount(col 2:decimal(10,2)) -> bigint, VectorUDAFCountStar(*) -> bigint
                           className: VectorGroupByOperator
                           groupByMode: HASH
                           keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val
0) -> 4:bigint
                           native: false
                           vectorProcessingMode: HASH
-                          projectedOutputColumnNums: [0, 1]
+                          projectedOutputColumnNums: [0, 1, 2]
                       keys: a (type: string), b (type: string), 0L (type: bigint)
                       mode: hash
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
                       Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string), _col2
(type: bigint)
@@ -236,9 +237,9 @@ STAGE PLANS:
                             keyColumnNums: [0, 1, 2]
                             native: true
                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                            valueColumnNums: [3, 4]
+                            valueColumnNums: [3, 4, 5]
                         Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col3 (type: struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>),
_col4 (type: bigint)
+                        value expressions: _col3 (type: decimal(20,2)), _col4 (type: bigint),
_col5 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -267,33 +268,34 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
                 rowBatchContext:
-                    dataColumnCount: 5
-                    dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VALUE._col1:bigint
+                    dataColumnCount: 6
+                    dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:decimal(20,2),
VALUE._col1:bigint, VALUE._col2:bigint
                     partitionColumnCount: 0
                     scratchColumnTypeNames: []
             Reduce Operator Tree:
               Group By Operator
-                aggregations: avg(VALUE._col0), count(VALUE._col1)
+                aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
                 Group By Vectorization:
-                    aggregators: VectorUDAFAvgDecimalFinal(col 3:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>)
-> decimal(14,6), VectorUDAFCountMerge(col 4:bigint) -> bigint
+                    aggregators: VectorUDAFSumDecimal(col 3:decimal(20,2)) -> decimal(20,2),
VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFCountMerge(col 5:bigint) ->
bigint
                     className: VectorGroupByOperator
                     groupByMode: MERGEPARTIAL
                     keyExpressions: col 0:string, col 1:string, col 2:bigint
                     native: false
                     vectorProcessingMode: MERGE_PARTIAL
-                    projectedOutputColumnNums: [0, 1]
+                    projectedOutputColumnNums: [0, 1, 2]
                 keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type:
bigint)
                 mode: mergepartial
-                outputColumnNames: _col0, _col1, _col3, _col4
+                outputColumnNames: _col0, _col1, _col3, _col4, _col5
                 Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats:
NONE
                 pruneGroupingSetId: true
                 Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(14,6)),
_col4 (type: bigint)
+                  expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4)
(type: decimal(38,20)), _col5 (type: bigint)
                   outputColumnNames: _col0, _col1, _col2, _col3
                   Select Vectorization:
                       className: VectorSelectOperator
                       native: true
-                      projectedOutputColumnNums: [0, 1, 2, 3]
+                      projectedOutputColumnNums: [0, 1, 6, 4]
+                      selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(20,2),
col 5:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 5:decimal(19,0)) ->
6:decimal(38,20)
                   Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column
stats: NONE
                   File Output Operator
                     compressed: false
@@ -321,22 +323,22 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@t1
 #### A masked pattern was here ####
 a	b	_c2	_c3
-1	1	3.000000	2
-1	2	2.000000	1
-1	NULL	2.666667	3
-2	2	5.333333	3
-2	3	5.000000	2
-2	NULL	5.200000	5
-3	2	8.000000	1
-3	NULL	8.000000	1
-5	1	2.000000	1
-5	NULL	2.000000	1
-8	1	1.000000	2
-8	NULL	1.000000	2
-NULL	1	2.000000	5
-NULL	2	5.200000	5
-NULL	3	5.000000	2
-NULL	NULL	3.833333	12
+1	1	3.00000000000000000000	2
+1	2	2.00000000000000000000	1
+1	NULL	2.66666666666666666667	3
+2	2	5.33333333333333333333	3
+2	3	5.00000000000000000000	2
+2	NULL	5.20000000000000000000	5
+3	2	8.00000000000000000000	1
+3	NULL	8.00000000000000000000	1
+5	1	2.00000000000000000000	1
+5	NULL	2.00000000000000000000	1
+8	1	1.00000000000000000000	2
+8	NULL	1.00000000000000000000	2
+NULL	1	2.00000000000000000000	5
+NULL	2	5.20000000000000000000	5
+NULL	3	5.00000000000000000000	2
+NULL	NULL	3.83333333333333333333	12
 PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
 SELECT a, b, avg(c_dec), count(*) from T1 group by a, b with cube
 PREHOOK: type: QUERY
@@ -378,18 +380,18 @@ STAGE PLANS:
                         projectedOutputColumnNums: [0, 1, 2]
                     Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column
stats: NONE
                     Group By Operator
-                      aggregations: avg(c_dec), count()
+                      aggregations: sum(c_dec), count(c_dec), count()
                       Group By Vectorization:
-                          aggregators: VectorUDAFAvgDecimal(col 2:decimal(10,2)) -> struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VectorUDAFCountStar(*) -> bigint
+                          aggregators: VectorUDAFSumDecimal(col 2:decimal(10,2)) -> decimal(20,2),
VectorUDAFCount(col 2:decimal(10,2)) -> bigint, VectorUDAFCountStar(*) -> bigint
                           className: VectorGroupByOperator
                           groupByMode: HASH
                           keyExpressions: col 0:string, col 1:string
                           native: false
                           vectorProcessingMode: HASH
-                          projectedOutputColumnNums: [0, 1]
+                          projectedOutputColumnNums: [0, 1, 2]
                       keys: a (type: string), b (type: string)
                       mode: hash
-                      outputColumnNames: _col0, _col1, _col2, _col3
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4
                       Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string)
@@ -400,9 +402,9 @@ STAGE PLANS:
                             keyColumnNums: [0, 1]
                             native: true
                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                            valueColumnNums: [2, 3]
+                            valueColumnNums: [2, 3, 4]
                         Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col2 (type: struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>),
_col3 (type: bigint)
+                        value expressions: _col2 (type: decimal(20,2)), _col3 (type: bigint),
_col4 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -431,24 +433,24 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
                 rowBatchContext:
-                    dataColumnCount: 4
-                    dataColumns: KEY._col0:string, KEY._col1:string, VALUE._col0:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VALUE._col1:bigint
+                    dataColumnCount: 5
+                    dataColumns: KEY._col0:string, KEY._col1:string, VALUE._col0:decimal(20,2),
VALUE._col1:bigint, VALUE._col2:bigint
                     partitionColumnCount: 0
                     scratchColumnTypeNames: [bigint]
             Reduce Operator Tree:
               Group By Operator
-                aggregations: avg(VALUE._col0), count(VALUE._col1)
+                aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
                 Group By Vectorization:
-                    aggregators: VectorUDAFAvgDecimalPartial2(col 2:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>)
-> struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>, VectorUDAFCountMerge(col
3:bigint) -> bigint
+                    aggregators: VectorUDAFSumDecimal(col 2:decimal(20,2)) -> decimal(20,2),
VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFCountMerge(col 4:bigint) ->
bigint
                     className: VectorGroupByOperator
                     groupByMode: PARTIALS
-                    keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val
0) -> 4:bigint
+                    keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val
0) -> 5:bigint
                     native: false
                     vectorProcessingMode: STREAMING
-                    projectedOutputColumnNums: [0, 1]
+                    projectedOutputColumnNums: [0, 1, 2]
                 keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
                 mode: partials
-                outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
                 Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats:
NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string), _col1 (type: string), _col2 (type:
bigint)
@@ -459,9 +461,9 @@ STAGE PLANS:
                       keyColumnNums: [0, 1, 2]
                       native: true
                       nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                      valueColumnNums: [3, 4]
+                      valueColumnNums: [3, 4, 5]
                   Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column
stats: NONE
-                  value expressions: _col3 (type: struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>),
_col4 (type: bigint)
+                  value expressions: _col3 (type: decimal(20,2)), _col4 (type: bigint), _col5
(type: bigint)
         Reducer 3 
             Execution mode: vectorized, llap
             Reduce Vectorization:
@@ -473,33 +475,34 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
                 rowBatchContext:
-                    dataColumnCount: 5
-                    dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>,
VALUE._col1:bigint
+                    dataColumnCount: 6
+                    dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:decimal(20,2),
VALUE._col1:bigint, VALUE._col2:bigint
                     partitionColumnCount: 0
                     scratchColumnTypeNames: []
             Reduce Operator Tree:
               Group By Operator
-                aggregations: avg(VALUE._col0), count(VALUE._col1)
+                aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
                 Group By Vectorization:
-                    aggregators: VectorUDAFAvgDecimalFinal(col 3:struct<count:bigint,sum:decimal(20,2),input:decimal(10,2)>)
-> decimal(14,6), VectorUDAFCountMerge(col 4:bigint) -> bigint
+                    aggregators: VectorUDAFSumDecimal(col 3:decimal(20,2)) -> decimal(20,2),
VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFCountMerge(col 5:bigint) ->
bigint
                     className: VectorGroupByOperator
                     groupByMode: FINAL
                     keyExpressions: col 0:string, col 1:string, col 2:bigint
                     native: false
                     vectorProcessingMode: STREAMING
-                    projectedOutputColumnNums: [0, 1]
+                    projectedOutputColumnNums: [0, 1, 2]
                 keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type:
bigint)
                 mode: final
-                outputColumnNames: _col0, _col1, _col3, _col4
+                outputColumnNames: _col0, _col1, _col3, _col4, _col5
                 Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats:
NONE
                 pruneGroupingSetId: true
                 Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(14,6)),
_col4 (type: bigint)
+                  expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4)
(type: decimal(38,20)), _col5 (type: bigint)
                   outputColumnNames: _col0, _col1, _col2, _col3
                   Select Vectorization:
                       className: VectorSelectOperator
                       native: true
-                      projectedOutputColumnNums: [0, 1, 2, 3]
+                      projectedOutputColumnNums: [0, 1, 6, 4]
+                      selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(20,2),
col 5:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 5:decimal(19,0)) ->
6:decimal(38,20)
                   Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column
stats: NONE
                   File Output Operator
                     compressed: false
@@ -527,19 +530,19 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@t1
 #### A masked pattern was here ####
 a	b	_c2	_c3
-1	1	3.000000	2
-1	2	2.000000	1
-1	NULL	2.666667	3
-2	2	5.333333	3
-2	3	5.000000	2
-2	NULL	5.200000	5
-3	2	8.000000	1
-3	NULL	8.000000	1
-5	1	2.000000	1
-5	NULL	2.000000	1
-8	1	1.000000	2
-8	NULL	1.000000	2
-NULL	1	2.000000	5
-NULL	2	5.200000	5
-NULL	3	5.000000	2
-NULL	NULL	3.833333	12
+1	1	3.00000000000000000000	2
+1	2	2.00000000000000000000	1
+1	NULL	2.66666666666666666667	3
+2	2	5.33333333333333333333	3
+2	3	5.00000000000000000000	2
+2	NULL	5.20000000000000000000	5
+3	2	8.00000000000000000000	1
+3	NULL	8.00000000000000000000	1
+5	1	2.00000000000000000000	1
+5	NULL	2.00000000000000000000	1
+8	1	1.00000000000000000000	2
+8	NULL	1.00000000000000000000	2
+NULL	1	2.00000000000000000000	5
+NULL	2	5.20000000000000000000	5
+NULL	3	5.00000000000000000000	2
+NULL	NULL	3.83333333333333333333	12

http://git-wip-us.apache.org/repos/asf/hive/blob/5cb8867b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out
index c21a4fc..d90ebf0 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out
@@ -822,9 +822,9 @@ STAGE PLANS:
                       projectedOutputColumnNums: [0, 1, 2, 3]
                   Statistics: Num rows: 6 Data size: 768 Basic stats: COMPLETE Column stats:
COMPLETE
                   Group By Operator
-                    aggregations: sum(_col1), sum(_col2), avg(_col2), sum(_col3), avg(_col3),
sum(_col4), avg(_col4)
+                    aggregations: sum(_col1), sum(_col2), count(_col2), sum(_col3), count(_col3),
sum(_col4), count(_col4)
                     Group By Vectorization:
-                        aggregators: VectorUDAFSumLong(col 0:int) -> bigint, VectorUDAFSumLong(col
1:int) -> bigint, VectorUDAFAvgLong(col 1:int) -> struct<count:bigint,sum:double,input:int>,
VectorUDAFSumDouble(col 2:double) -> double, VectorUDAFAvgDouble(col 2:double) -> struct<count:bigint,sum:double,input:double>,
VectorUDAFSumDecimal(col 3:decimal(38,18)) -> decimal(38,18), VectorUDAFAvgDecimal(col
3:decimal(38,18)) -> struct<count:bigint,sum:decimal(38,18),input:decimal(38,18)>
+                        aggregators: VectorUDAFSumLong(col 0:int) -> bigint, VectorUDAFSumLong(col
1:int) -> bigint, VectorUDAFCount(col 1:int) -> bigint, VectorUDAFSumDouble(col 2:double)
-> double, VectorUDAFCount(col 2:double) -> bigint, VectorUDAFSumDecimal(col 3:decimal(38,18))
-> decimal(38,18), VectorUDAFCount(col 3:decimal(38,18)) -> bigint
                         className: VectorGroupByOperator
                         groupByMode: HASH
                         keyExpressions: ConstantVectorExpression(val 1) -> 4:int
@@ -834,7 +834,7 @@ STAGE PLANS:
                     keys: 1 (type: int)
                     mode: hash
                     outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                    Statistics: Num rows: 1 Data size: 584 Basic stats: COMPLETE Column stats:
COMPLETE
+                    Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats:
COMPLETE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
@@ -843,8 +843,8 @@ STAGE PLANS:
                           className: VectorReduceSinkLongOperator
                           native: true
                           nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                      Statistics: Num rows: 1 Data size: 584 Basic stats: COMPLETE Column
stats: COMPLETE
-                      value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3
(type: struct<count:bigint,sum:double,input:int>), _col4 (type: double), _col5 (type:
struct<count:bigint,sum:double,input:double>), _col6 (type: decimal(38,18)), _col7 (type:
struct<count:bigint,sum:decimal(38,18),input:decimal(38,18)>)
+                      Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column
stats: COMPLETE
+                      value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3
(type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: decimal(38,18)),
_col7 (type: bigint)
         Reducer 3 
             Execution mode: vectorized, llap
             Reduce Vectorization:
@@ -855,9 +855,9 @@ STAGE PLANS:
                 vectorized: true
             Reduce Operator Tree:
               Group By Operator
-                aggregations: sum(VALUE._col0), sum(VALUE._col1), avg(VALUE._col2), sum(VALUE._col3),
avg(VALUE._col4), sum(VALUE._col5), avg(VALUE._col6)
+                aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3),
count(VALUE._col4), sum(VALUE._col5), count(VALUE._col6)
                 Group By Vectorization:
-                    aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint, VectorUDAFSumLong(col
2:bigint) -> bigint, VectorUDAFAvgFinal(col 3:struct<count:bigint,sum:double,input:int>)
-> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFAvgFinal(col 5:struct<count:bigint,sum:double,input:double>)
-> double, VectorUDAFSumDecimal(col 6:decimal(38,18)) -> decimal(38,18), VectorUDAFAvgDecimalFinal(col
7:struct<count:bigint,sum:decimal(38,18),input:decimal(38,18)>) -> decimal(38,18)
+                    aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint, VectorUDAFSumLong(col
2:bigint) -> bigint, VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFSumDouble(col
4:double) -> double, VectorUDAFCountMerge(col 5:bigint) -> bigint, VectorUDAFSumDecimal(col
6:decimal(38,18)) -> decimal(38,18), VectorUDAFCountMerge(col 7:bigint) -> bigint
                     className: VectorGroupByOperator
                     groupByMode: MERGEPARTIAL
                     keyExpressions: col 0:int
@@ -867,15 +867,15 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats:
COMPLETE
+                Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats:
COMPLETE
                 Select Operator
-                  expressions: 1 (type: int), _col1 (type: bigint), _col2 (type: bigint),
_col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: decimal(38,18)),
_col7 (type: decimal(38,18))
+                  expressions: 1 (type: int), _col1 (type: bigint), _col2 (type: bigint),
(UDFToDouble(_col2) / _col3) (type: double), _col4 (type: double), (_col4 / _col5) (type:
double), _col6 (type: decimal(38,18)), (_col6 / _col7) (type: decimal(38,18))
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
                   Select Vectorization:
                       className: VectorSelectOperator
                       native: true
-                      projectedOutputColumnNums: [8, 1, 2, 3, 4, 5, 6, 7]
-                      selectExpressions: ConstantVectorExpression(val 1) -> 8:int
+                      projectedOutputColumnNums: [8, 1, 2, 10, 4, 9, 6, 12]
+                      selectExpressions: ConstantVectorExpression(val 1) -> 8:int, DoubleColDivideLongColumn(col
9:double, col 3:bigint)(children: CastLongToDouble(col 2:bigint) -> 9:double) -> 10:double,
DoubleColDivideLongColumn(col 4:double, col 5:bigint) -> 9:double, DecimalColDivideDecimalColumn(col
6:decimal(38,18), col 11:decimal(19,0))(children: CastLongToDecimal(col 7:bigint) -> 11:decimal(19,0))
-> 12:decimal(38,18)
                   Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats:
COMPLETE
                   File Output Operator
                     compressed: false
@@ -1046,9 +1046,9 @@ STAGE PLANS:
                       projectedOutputColumnNums: [1, 0, 2, 3, 4]
                   Statistics: Num rows: 500 Data size: 66000 Basic stats: COMPLETE Column
stats: COMPLETE
                   Group By Operator
-                    aggregations: sum(_col2), avg(_col2), sum(_col3), avg(_col3), sum(_col4),
avg(_col4)
+                    aggregations: sum(_col2), count(_col2), sum(_col3), count(_col3), sum(_col4),
count(_col4)
                     Group By Vectorization:
-                        aggregators: VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFAvgLongComplete(col
2:int) -> double, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFAvgDoubleComplete(col
3:double) -> double, VectorUDAFSumDecimal(col 4:decimal(38,18)) -> decimal(38,18), VectorUDAFAvgDecimalComplete(col
4:decimal(38,18)) -> decimal(38,18)
+                        aggregators: VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFCount(col
2:int) -> bigint, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFCount(col 3:double)
-> bigint, VectorUDAFSumDecimal(col 4:decimal(38,18)) -> decimal(38,18), VectorUDAFCount(col
4:decimal(38,18)) -> bigint
                         className: VectorGroupByOperator
                         groupByMode: COMPLETE
                         keyExpressions: col 0:int, col 1:int
@@ -1058,15 +1058,16 @@ STAGE PLANS:
                     keys: _col1 (type: int), _col0 (type: int)
                     mode: complete
                     outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                    Statistics: Num rows: 500 Data size: 290000 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Statistics: Num rows: 500 Data size: 80000 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
-                      expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint),
_col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: decimal(38,18)),
_col7 (type: decimal(38,18))
+                      expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint),
(UDFToDouble(_col2) / _col3) (type: double), _col4 (type: double), (_col4 / _col5) (type:
double), _col6 (type: decimal(38,18)), (_col6 / _col7) (type: decimal(38,18))
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6,
_col7
                       Select Vectorization:
                           className: VectorSelectOperator
                           native: true
-                          projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7]
-                      Statistics: Num rows: 500 Data size: 290000 Basic stats: COMPLETE Column
stats: COMPLETE
+                          projectedOutputColumnNums: [0, 1, 2, 9, 4, 8, 6, 11]
+                          selectExpressions: DoubleColDivideLongColumn(col 8:double, col
3:bigint)(children: CastLongToDouble(col 2:bigint) -> 8:double) -> 9:double, DoubleColDivideLongColumn(col
4:double, col 5:bigint) -> 8:double, DecimalColDivideDecimalColumn(col 6:decimal(38,18),
col 10:decimal(19,0))(children: CastLongToDecimal(col 7:bigint) -> 10:decimal(19,0)) ->
11:decimal(38,18)
+                      Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column
stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col0 (type: int), _col1 (type: int)
                         sort order: ++
@@ -1074,7 +1075,7 @@ STAGE PLANS:
                             className: VectorReduceSinkObjectHashOperator
                             native: true
                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                        Statistics: Num rows: 500 Data size: 290000 Basic stats: COMPLETE
Column stats: COMPLETE
+                        Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE
Column stats: COMPLETE
                         value expressions: _col2 (type: bigint), _col3 (type: double), _col4
(type: double), _col5 (type: double), _col6 (type: decimal(38,18)), _col7 (type: decimal(38,18))
         Reducer 3 
             Execution mode: vectorized, llap
@@ -1092,13 +1093,13 @@ STAGE PLANS:
                     className: VectorSelectOperator
                     native: true
                     projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7]
-                Statistics: Num rows: 500 Data size: 290000 Basic stats: COMPLETE Column
stats: COMPLETE
+                Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column
stats: COMPLETE
                 File Output Operator
                   compressed: false
                   File Sink Vectorization:
                       className: VectorFileSinkOperator
                       native: false
-                  Statistics: Num rows: 500 Data size: 290000 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column
stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/5cb8867b/ql/src/test/results/clientpositive/llap/vector_ptf_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_ptf_1.q.out b/ql/src/test/results/clientpositive/llap/vector_ptf_1.q.out
index 8d9ffb8..c0cb6c0 100644
--- a/ql/src/test/results/clientpositive/llap/vector_ptf_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_ptf_1.q.out
@@ -79,18 +79,18 @@ STAGE PLANS:
                         projectedOutputColumnNums: [0, 1, 2]
                     Statistics: Num rows: 100 Data size: 18816 Basic stats: COMPLETE Column
stats: NONE
                     Group By Operator
-                      aggregations: avg(gpa)
+                      aggregations: sum(gpa), count(gpa)
                       Group By Vectorization:
-                          aggregators: VectorUDAFAvgDouble(col 2:double) -> struct<count:bigint,sum:double,input:double>
+                          aggregators: VectorUDAFSumDouble(col 2:double) -> double, VectorUDAFCount(col
2:double) -> bigint
                           className: VectorGroupByOperator
                           groupByMode: HASH
                           keyExpressions: col 0:string, col 1:int
                           native: false
                           vectorProcessingMode: HASH
-                          projectedOutputColumnNums: [0]
+                          projectedOutputColumnNums: [0, 1]
                       keys: name (type: string), age (type: int)
                       mode: hash
-                      outputColumnNames: _col0, _col1, _col2
+                      outputColumnNames: _col0, _col1, _col2, _col3
                       Statistics: Num rows: 100 Data size: 18816 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: int)
@@ -102,9 +102,9 @@ STAGE PLANS:
                             native: true
                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT
columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
                             partitionColumnNums: [0]
-                            valueColumnNums: [2]
+                            valueColumnNums: [2, 3]
                         Statistics: Num rows: 100 Data size: 18816 Basic stats: COMPLETE
Column stats: NONE
-                        value expressions: _col2 (type: struct<count:bigint,sum:double,input:double>)
+                        value expressions: _col2 (type: double), _col3 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: no inputs
             Map Vectorization:
@@ -132,20 +132,20 @@ STAGE PLANS:
                 vectorized: false
             Reduce Operator Tree:
               Group By Operator
-                aggregations: avg(VALUE._col0)
+                aggregations: sum(VALUE._col0), count(VALUE._col1)
                 keys: KEY._col0 (type: string), KEY._col1 (type: int)
                 mode: mergepartial
-                outputColumnNames: _col0, _col1, _col2
+                outputColumnNames: _col0, _col1, _col2, _col3
                 Statistics: Num rows: 50 Data size: 9408 Basic stats: COMPLETE Column stats:
NONE
                 Select Operator
-                  expressions: _col1 (type: int), _col0 (type: string), _col2 (type: double)
-                  outputColumnNames: _col0, _col1, _col2
+                  expressions: _col1 (type: int), _col0 (type: string), _col2 (type: double),
_col3 (type: bigint)
+                  outputColumnNames: _col0, _col1, _col2, _col3
                   Statistics: Num rows: 50 Data size: 9408 Basic stats: COMPLETE Column stats:
NONE
                   PTF Operator
                     Function definitions:
                         Input definition
                           input alias: ptf_0
-                          output shape: _col0: int, _col1: string, _col2: double
+                          output shape: _col0: int, _col1: string, _col2: double, _col3:
bigint
                           type: WINDOWING
                         Windowing table definition
                           input alias: ptf_1
@@ -162,7 +162,7 @@ STAGE PLANS:
                                 window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
                     Statistics: Num rows: 50 Data size: 9408 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col2 (type:
double), sum_window_0 (type: bigint)
+                      expressions: _col0 (type: int), _col1 (type: string), (_col2 / _col3)
(type: double), sum_window_0 (type: bigint)
                       outputColumnNames: _col0, _col1, _col2, _col3
                       Statistics: Num rows: 50 Data size: 9408 Basic stats: COMPLETE Column
stats: NONE
                       File Output Operator


Mime
View raw message