You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by mm...@apache.org on 2018/08/08 07:37:32 UTC

[09/51] [partial] hive git commit: HIVE-20315: Vectorization: Fix more NULL / Wrong Results issues and avoid unnecessary casts/conversions (Matt McCline, reviewed by Teddy Choi)

http://git-wip-us.apache.org/repos/asf/hive/blob/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query76.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query76.q.out b/ql/src/test/results/clientpositive/perf/spark/query76.q.out
index 05ec505..3adfc10 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query76.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query76.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select  channel, col_name, d_year, d_qoy, i_category, COUNT(*) sales_cnt, SUM(ext_sales_price) sales_amt FROM (
         SELECT 'store' as channel, 'ss_addr_sk' col_name, d_year, d_qoy, i_category, ss_ext_sales_price ext_sales_price
          FROM store_sales, item, date_dim
@@ -21,7 +21,7 @@ GROUP BY channel, col_name, d_year, d_qoy, i_category
 ORDER BY channel, col_name, d_year, d_qoy, i_category
 limit 100
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select  channel, col_name, d_year, d_qoy, i_category, COUNT(*) sales_cnt, SUM(ext_sales_price) sales_amt FROM (
         SELECT 'store' as channel, 'ss_addr_sk' col_name, d_year, d_qoy, i_category, ss_ext_sales_price ext_sales_price
          FROM store_sales, item, date_dim
@@ -44,6 +44,10 @@ GROUP BY channel, col_name, d_year, d_qoy, i_category
 ORDER BY channel, col_name, d_year, d_qoy, i_category
 limit 100
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: true
+  enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -68,181 +72,393 @@ STAGE PLANS:
                   alias: item
                   filterExpr: i_item_sk is not null (type: boolean)
                   Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0:int)
                     predicate: i_item_sk is not null (type: boolean)
                     Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: i_item_sk (type: int), i_category (type: string)
                       outputColumnNames: _col0, _col1
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 12]
                       Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 11 
             Map Operator Tree:
                 TableScan
                   alias: item
                   filterExpr: i_item_sk is not null (type: boolean)
                   Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0:int)
                     predicate: i_item_sk is not null (type: boolean)
                     Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: i_item_sk (type: int), i_category (type: string)
                       outputColumnNames: _col0, _col1
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 12]
                       Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 12 
             Map Operator Tree:
                 TableScan
                   alias: date_dim
                   filterExpr: d_date_sk is not null (type: boolean)
                   Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0:int)
                     predicate: d_date_sk is not null (type: boolean)
                     Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int)
                       outputColumnNames: _col0, _col1, _col2
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 6, 10]
                       Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: int), _col2 (type: int)
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 13 
             Map Operator Tree:
                 TableScan
                   alias: catalog_sales
                   filterExpr: (cs_warehouse_sk is null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean)
                   Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 14:int), SelectColumnIsNotNull(col 15:int), SelectColumnIsNotNull(col 0:int))
                     predicate: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is null) (type: boolean)
                     Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2))
                       outputColumnNames: _col0, _col2, _col3
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 15, 23]
                       Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col2 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col2 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: int), _col3 (type: decimal(7,2))
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 16 
             Map Operator Tree:
                 TableScan
                   alias: item
                   filterExpr: i_item_sk is not null (type: boolean)
                   Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0:int)
                     predicate: i_item_sk is not null (type: boolean)
                     Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: i_item_sk (type: int), i_category (type: string)
                       outputColumnNames: _col0, _col1
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 12]
                       Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 17 
             Map Operator Tree:
                 TableScan
                   alias: date_dim
                   filterExpr: d_date_sk is not null (type: boolean)
                   Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0:int)
                     predicate: d_date_sk is not null (type: boolean)
                     Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int)
                       outputColumnNames: _col0, _col1, _col2
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 6, 10]
                       Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: int), _col2 (type: int)
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: store_sales
                   filterExpr: (ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean)
                   Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 6:int), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int))
                     predicate: (ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean)
                     Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2))
                       outputColumnNames: _col0, _col1, _col3
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 2, 15]
                       Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col1 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col1 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: int), _col3 (type: decimal(7,2))
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 7 
             Map Operator Tree:
                 TableScan
                   alias: date_dim
                   filterExpr: d_date_sk is not null (type: boolean)
                   Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0:int)
                     predicate: d_date_sk is not null (type: boolean)
                     Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int)
                       outputColumnNames: _col0, _col1, _col2
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 6, 10]
                       Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: int), _col2 (type: int)
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 8 
             Map Operator Tree:
                 TableScan
                   alias: web_sales
                   filterExpr: (ws_web_page_sk is null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean)
                   Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 12:int), SelectColumnIsNotNull(col 3:int), SelectColumnIsNotNull(col 0:int))
                     predicate: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_web_page_sk is null) (type: boolean)
                     Statistics: Num rows: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2))
                       outputColumnNames: _col0, _col1, _col3
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumnNums: [0, 3, 23]
                       Statistics: Num rows: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col1 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col1 (type: int)
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkLongOperator
+                            native: true
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: int), _col3 (type: decimal(7,2))
             Execution mode: vectorized
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                inputFormatFeatureSupport: [DECIMAL_64]
+                featureSupportInUse: [DECIMAL_64]
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 10 
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                notVectorizedReason: Tagging not supported
+                vectorized: false
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -267,6 +483,11 @@ STAGE PLANS:
                       TopN Hash Memory Usage: 0.1
                       value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2))
         Reducer 14 
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                notVectorizedReason: Tagging not supported
+                vectorized: false
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -283,6 +504,11 @@ STAGE PLANS:
                   Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE
                   value expressions: _col3 (type: decimal(7,2)), _col5 (type: string)
         Reducer 15 
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                notVectorizedReason: Tagging not supported
+                vectorized: false
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -307,6 +533,11 @@ STAGE PLANS:
                       TopN Hash Memory Usage: 0.1
                       value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2))
         Reducer 2 
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                notVectorizedReason: Tagging not supported
+                vectorized: false
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -323,6 +554,11 @@ STAGE PLANS:
                   Statistics: Num rows: 316797605 Data size: 27947976704 Basic stats: COMPLETE Column stats: NONE
                   value expressions: _col1 (type: string), _col5 (type: decimal(7,2))
         Reducer 3 
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                notVectorizedReason: Tagging not supported
+                vectorized: false
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -348,9 +584,23 @@ STAGE PLANS:
                       value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2))
         Reducer 4 
             Execution mode: vectorized
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0), sum(VALUE._col1)
+                Group By Vectorization:
+                    aggregators: VectorUDAFCountMerge(col 5:bigint) -> bigint, VectorUDAFSumDecimal(col 6:decimal(17,2)) -> decimal(17,2)
+                    className: VectorGroupByOperator
+                    groupByMode: MERGEPARTIAL
+                    keyExpressions: col 0:string, col 1:string, col 2:int, col 3:int, col 4:string
+                    native: false
+                    vectorProcessingMode: MERGE_PARTIAL
+                    projectedOutputColumnNums: [0, 1]
                 keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -358,27 +608,52 @@ STAGE PLANS:
                 Reduce Output Operator
                   key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string)
                   sort order: +++++
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkObjectHashOperator
+                      native: true
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 304916424 Data size: 33091779954 Basic stats: COMPLETE Column stats: NONE
                   TopN Hash Memory Usage: 0.1
                   value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2))
         Reducer 5 
             Execution mode: vectorized
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(17,2))
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
                 Statistics: Num rows: 304916424 Data size: 33091779954 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 100
+                  Limit Vectorization:
+                      className: VectorLimitOperator
+                      native: true
                   Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
+                    File Sink Vectorization:
+                        className: VectorFileSinkOperator
+                        native: false
                     Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
         Reducer 9 
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+                notVectorizedReason: Tagging not supported
+                vectorized: false
             Reduce Operator Tree:
               Join Operator
                 condition map: