http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/union_remove_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/union_remove_8.q.out b/ql/src/test/results/clientpositive/spark/union_remove_8.q.out index 7aee2af..f580bd8 100644 --- a/ql/src/test/results/clientpositive/spark/union_remove_8.q.out +++ b/ql/src/test/results/clientpositive/spark/union_remove_8.q.out @@ -88,11 +88,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -108,7 +108,7 @@ STAGE PLANS: alias: inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), UDFToLong(1) (type: bigint) + expressions: key (type: string), 1 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -125,7 +125,7 @@ STAGE PLANS: alias: inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), UDFToLong(2) (type: bigint) + expressions: key (type: string), 2 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/union_remove_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/union_remove_9.q.out b/ql/src/test/results/clientpositive/spark/union_remove_9.q.out index 87ceca2..0931d11 100644 --- a/ql/src/test/results/clientpositive/spark/union_remove_9.q.out +++ b/ql/src/test/results/clientpositive/spark/union_remove_9.q.out @@ -95,11 +95,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: key + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: key (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/union_top_level.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/union_top_level.q.out b/ql/src/test/results/clientpositive/spark/union_top_level.q.out index 5136989..dede1ef 100644 --- a/ql/src/test/results/clientpositive/spark/union_top_level.q.out +++ b/ql/src/test/results/clientpositive/spark/union_top_level.q.out @@ -37,7 +37,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 0) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 0 (type: int) @@ -56,7 +56,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 1) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) @@ -75,7 +75,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 2) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) @@ -414,7 +414,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 0) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 0 (type: int) @@ -433,7 +433,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 1) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) @@ -452,7 +452,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 2) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) @@ -616,7 +616,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 0) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 0 (type: int) @@ -635,7 +635,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 1) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) @@ -654,7 +654,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 2) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) @@ -805,7 +805,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 0) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 0 (type: int) @@ -824,7 +824,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 1) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) @@ -843,7 +843,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key % 3) = 2) (type: boolean) + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out index aaac8aa..9e1402b 100644 --- a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out +++ b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out @@ -133,11 +133,11 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: i + outputColumnNames: _col0 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(50), avg(UDFToDouble(50)), avg(CAST( 50 AS decimal(10,0))) - keys: i (type: int) + aggregations: avg(50), avg(50.0), avg(50) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out index 44ecd09..69f4754 100644 --- a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out +++ b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out @@ -133,11 +133,11 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: i + outputColumnNames: _col0 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(50), avg(UDFToDouble(50)), avg(CAST( 50 AS decimal(10,0))) - keys: i (type: int) + aggregations: avg(50), avg(50.0), avg(50) + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out index cb2d56b..7e161d1 100644 --- a/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_decimal_aggregate.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: cint, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() - keys: cint (type: int) + aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -159,11 +159,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: cint, cdecimal1, cdecimal2 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() - keys: cint (type: int) + aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), avg(_col1), stddev_pop(_col1), stddev_samp(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), avg(_col2), stddev_pop(_col2), stddev_samp(_col2), count() + keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out index 23f2b98..322270f 100644 --- a/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_distinct_2.q.out @@ -129,10 +129,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), t (type: tinyint) - outputColumnNames: s, t + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: s (type: string), t (type: tinyint) + keys: _col0 (type: string), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_elt.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_elt.q.out b/ql/src/test/results/clientpositive/spark/vector_elt.q.out index 818e266..49d1458 100644 --- a/ql/src/test/results/clientpositive/spark/vector_elt.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_elt.q.out @@ -21,7 +21,7 @@ STAGE PLANS: predicate: (ctinyint > 0) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ((ctinyint % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((ctinyint % 2) + 1), cstring1, cint) (type: string) + expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Limit http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out index 6f62820..3d6a236 100644 --- a/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_groupby_3.q.out @@ -129,11 +129,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), t (type: tinyint), b (type: bigint) - outputColumnNames: s, t, b + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(b) - keys: s (type: string), t (type: tinyint) + aggregations: max(_col2) + keys: _col0 (type: string), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out index 02c1fc6..8cf1a81 100644 --- a/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out @@ -30,23 +30,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-2 Spark + Edges: + Reducer 4 <- Map 3 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: li - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((l_partkey is not null and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) - Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 l_partkey (type: int) - Local Work: - Map Reduce Local Work - Map 4 + Map 2 Map Operator Tree: TableScan alias: lineitem @@ -65,18 +53,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (GROUP, 2) -#### A masked pattern was here #### - Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan alias: lineitem @@ -84,17 +65,21 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: l_partkey (type: int) - mode: hash + Select Operator + expressions: l_partkey (type: int) outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reducer 2 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Reducer 4 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -103,38 +88,60 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 + Spark HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 l_partkey (type: int) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 4 - Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-1 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem + Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized + expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 2 + Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Reducer 4 + Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Local Work: + Map Reduce Local Work Stage: Stage-0 Fetch Operator @@ -181,60 +188,80 @@ where li.l_linenumber = 1 and li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 3 - Map Operator Tree: - TableScan - alias: li - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((l_partkey is not null and l_orderkey is not null) and l_linenumber is not null) and (l_linenumber = 1)) (type: boolean) - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 l_partkey (type: int) - Local Work: - Map Reduce Local Work - Map 4 + Map 2 Map Operator Tree: TableScan alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) and (l_linenumber = 1)) (type: boolean) - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + predicate: (((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) (type: boolean) + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), 1 (type: int) + expressions: l_orderkey (type: int), l_linenumber (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int), _col4 (type: int) + 0 _col0 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) Local Work: Map Reduce Local Work + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem + Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: int), _col3 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 2 + Statistics: Num rows: 14 Data size: 1714 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 2) + Reducer 4 <- Map 3 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan alias: lineitem @@ -242,17 +269,21 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: l_partkey (type: int) - mode: hash + Select Operator + expressions: l_partkey (type: int) outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Reducer 2 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Reducer 4 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -265,33 +296,23 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 l_partkey (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 input vertices: - 1 Map 3 + 0 Map 1 Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int), _col4 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 4 - Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col1 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized Stage: Stage-0 http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out index 3363c8b..6bbb6b9 100644 --- a/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_orderby_5.q.out @@ -126,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo (type: boolean), b (type: bigint) - outputColumnNames: bo, b + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(b) - keys: bo (type: boolean) + aggregations: max(_col1) + keys: _col0 (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vector_string_concat.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vector_string_concat.q.out b/ql/src/test/results/clientpositive/spark/vector_string_concat.q.out index 9ec8538..b78aec9 100644 --- a/ql/src/test/results/clientpositive/spark/vector_string_concat.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_string_concat.q.out @@ -300,11 +300,11 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dt (type: date) - outputColumnNames: dt + expressions: concat(concat(concat('Quarter ', UDFToString(UDFToInteger(((UDFToDouble((month(dt) - 1)) / 3.0) + 1.0)))), '-'), UDFToString(year(dt))) (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: concat(concat(concat('Quarter ', UDFToString(UDFToInteger((((month(dt) - 1) / 3) + 1)))), '-'), UDFToString(year(dt))) (type: string) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out index f61ef7d..b2dd09d 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out @@ -129,10 +129,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(ctinyint) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -435,10 +435,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: cbigint + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(cbigint) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -741,10 +741,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: cfloat + outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(cfloat) + aggregations: sum(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -990,14 +990,14 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 like '%b%') or ((79.553 <> cint) or (cbigint < cdouble))) (type: boolean) + predicate: ((cstring2 like '%b%') or ((79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: cbigint, cfloat, ctinyint + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) + aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -1014,7 +1014,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (-6432 + _col0) (type: double), _col1 (type: double), (- (-6432 + _col0)) (type: double), ((- (-6432 + _col0)) + (-6432 + _col0)) (type: double), _col2 (type: double), (- (-6432 + _col0)) (type: double), (-6432 + (- (-6432 + _col0))) (type: double), (- (-6432 + _col0)) (type: double), ((- (-6432 + _col0)) / (- (-6432 + _col0))) (type: double), _col3 (type: bigint), _col4 (type: double), (_col2 % _col1) (type: double), (- _col2) (type: double), ((- (-6432 + _col0)) * (- _col0)) (type: double), _col5 (type: tinyint), (- _col5) (type: tinyint) + expressions: _col0 (type: double), (- _col0) (type: double), (-6432.0 + _col0) (type: double), _col1 (type: double), (- (-6432.0 + _col0)) (type: double), ((- (-6432.0 + _col0)) + (-6432.0 + _col0)) (type: double), _col2 (type: double), (- (-6432.0 + _col0)) (type: double), (-6432.0 + (- (-6432.0 + _col0))) (type: double), (- (-6432.0 + _col0)) (type: double), ((- (-6432.0 + _col0)) / (- (-6432.0 + _col0))) (type: double), _col3 (type: bigint), _col4 (type: double), (_col2 % _col1) (type: double), (- _col2) (type: double), ((- (-6432.0 + _col0)) * (- _col0)) (type: double), _col5 (type: tinyint), (- _col5) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out index 41ee583..be00d16 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out @@ -82,15 +82,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > 11) and ((ctimestamp2 <> 12) and (ctinyint < 9763215.5639)))) (type: boolean) + predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > 11.0) and ((UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) - keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) + keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE @@ -110,7 +110,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * ((- _col1) + _col5)) (type: double) + expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -336,15 +336,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((ctimestamp1 > -1.388) and ((ctimestamp2 <> -1.3359999999999999) and (ctinyint < 9763215.5639)))) (type: boolean) + predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > -1.388) and ((UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) - keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) + keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE @@ -364,7 +364,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * _col3) (type: double), _col7 (type: double), _col8 (type: double), (((- _col1) + _col5) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * ((- _col1) + _col5)) / _col1) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * ((- _col1) + _col5)) (type: double) + expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out index 1de639b..cbfa70e 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out @@ -82,15 +82,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((ctinyint <= cbigint) and ((cint <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < ctinyint)) and ((cbigint > -257) or (cfloat < cint))) (type: boolean) + predicate: ((((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < UDFToDouble(ctinyint))) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double) - outputColumnNames: ctimestamp1, cfloat, cstring1, cboolean1, cdouble + expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp((- ((- 26.28) + cdouble))), max(cfloat), stddev_pop(cfloat), count(cfloat), var_pop(cfloat), var_samp(cfloat) - keys: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double) + aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) + keys: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE @@ -110,7 +110,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double), (-26.28 + _col4) (type: double), (- (-26.28 + _col4)) (type: double), _col5 (type: double), (_col1 * -26.28) (type: double), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col4)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col4)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (_col1 - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (_col1 - _col4)) (type: double) + expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double), (-26.28 + _col4) (type: double), (- (-26.28 + _col4)) (type: double), _col5 (type: double), (UDFToDouble(_col1) * -26.28) (type: double), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col4)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col4)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col4)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out index 960a058..a58d941 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out @@ -78,15 +78,15 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cstring2 like '%ss%') or (cstring1 like '10%')) or ((cint >= -75) and ((ctinyint = csmallint) and (cdouble >= -3728)))) (type: boolean) + predicate: ((cstring2 like '%ss%') or ((cstring1 like '10%') or ((cint >= -75) and ((UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) - outputColumnNames: cfloat, cboolean1, cdouble, cstring1, ctinyint, cint, ctimestamp1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) - keys: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) + aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) + keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE @@ -106,7 +106,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - _col5) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (_col5 - _col0) (type: float), (-23 % _col4) (type: int), (- (-26.28 - _col5)) (type: double), _col12 (type: double) + expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_16.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out index 473eaf4..a42c30a 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out @@ -63,11 +63,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: cstring1, cdouble, ctimestamp1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) - keys: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) + aggregations: count(_col1), stddev_samp(_col1), min(_col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE @@ -87,7 +87,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * _col3) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (_col3 / -1.389) (type: double), _col4 (type: double) + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out index 17b35fe..8bbeb51 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: cstring1, cdouble, ctimestamp1 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) - keys: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) + aggregations: count(_col1), stddev_samp(_col1), min(_col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE @@ -83,7 +83,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * _col3) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (_col3 / -1.389) (type: double), _col4 (type: double) + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out index 30d116f..5887839 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out @@ -168,7 +168,7 @@ STAGE PLANS: predicate: ((cbigint > 0) and (cbigint < 100000000)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cbigint - 988888) (type: bigint), (cdouble / (cbigint - 988888)) (type: double), (1.2 / (cbigint - 988888)) (type: double) + expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -340,10 +340,10 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble >= -500) and (cdouble < -199)) (type: boolean) + predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 200.0) (type: double), (cbigint / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) + expressions: (cdouble + 200.0) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3.0 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) outputColumnNames: _col0, _col1, _col2, _col4, _col5 Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_part_project.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_part_project.q.out b/ql/src/test/results/clientpositive/spark/vectorization_part_project.q.out index f92e823..f0852ea 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_part_project.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_part_project.q.out @@ -67,7 +67,7 @@ STAGE PLANS: alias: alltypesorc_part Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 2) (type: double) + expressions: (cdouble + 2.0) (type: double) outputColumnNames: _col0 Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/330c31ae/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out index 6e784cd..eb8914b 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out @@ -18,17 +18,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - filterExpr: (cbigint < cdouble) (type: boolean) + filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cbigint < cdouble) (type: boolean) + predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: cbigint + outputColumnNames: _col0 Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(cbigint) + aggregations: avg(_col0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
