hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mmccl...@apache.org
Subject [11/51] [partial] hive git commit: HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)
Date Fri, 03 Feb 2017 20:03:36 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
index 64ac81c..67fcdaa 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT MIN(ctinyint) as c1,
        MAX(ctinyint),
        COUNT(ctinyint),
@@ -6,7 +6,7 @@ SELECT MIN(ctinyint) as c1,
 FROM   alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT MIN(ctinyint) as c1,
        MAX(ctinyint),
        COUNT(ctinyint),
@@ -14,6 +14,10 @@ SELECT MIN(ctinyint) as c1,
 FROM   alltypesorc
 ORDER BY c1
 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
@@ -32,43 +36,101 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Select Operator
                     expressions: ctinyint (type: tinyint)
                     outputColumnNames: ctinyint
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0]
                     Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       aggregations: min(ctinyint), max(ctinyint), count(ctinyint), count()
+                      Group By Vectorization:
+                          aggregators: VectorUDAFMinLong(col 0) -> tinyint, VectorUDAFMaxLong(col 0) -> tinyint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCountStar(*) -> bigint
+                          className: VectorGroupByOperator
+                          vectorOutput: true
+                          native: false
+                          projectedOutputColumns: [0, 1, 2, 3]
                       mode: hash
                       outputColumnNames: _col0, _col1, _col2, _col3
                       Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkOperator
+                            native: false
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                            nativeConditionsNotMet: Uniform Hash IS false
                         Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: tinyint), _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3)
+                Group By Vectorization:
+                    aggregators: VectorUDAFMinLong(col 0) -> tinyint, VectorUDAFMaxLong(col 1) -> tinyint, VectorUDAFCountMerge(col 2) -> bigint, VectorUDAFCountMerge(col 3) -> bigint
+                    className: VectorGroupByOperator
+                    vectorOutput: true
+                    native: false
+                    projectedOutputColumns: [0, 1, 2, 3]
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3
                 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                 Reduce Output Operator
                   key expressions: _col0 (type: tinyint)
                   sort order: +
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkOperator
+                      native: false
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                      nativeConditionsNotMet: Uniform Hash IS false
                   Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                   value expressions: _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint)
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: tinyint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint)
                 outputColumnNames: _col0, _col1, _col2, _col3
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumns: [0, 1, 2, 3]
                 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
+                  File Sink Vectorization:
+                      className: VectorFileSinkOperator
+                      native: false
                   Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -100,16 +162,20 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -64	62	9173	12288
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT SUM(ctinyint) as c1
 FROM   alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT SUM(ctinyint) as c1
 FROM   alltypesorc
 ORDER BY c1
 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
@@ -128,42 +194,100 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Select Operator
                     expressions: ctinyint (type: tinyint)
                     outputColumnNames: ctinyint
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0]
                     Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       aggregations: sum(ctinyint)
+                      Group By Vectorization:
+                          aggregators: VectorUDAFSumLong(col 0) -> bigint
+                          className: VectorGroupByOperator
+                          vectorOutput: true
+                          native: false
+                          projectedOutputColumns: [0]
                       mode: hash
                       outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkOperator
+                            native: false
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                            nativeConditionsNotMet: Uniform Hash IS false
                         Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: sum(VALUE._col0)
+                Group By Vectorization:
+                    aggregators: VectorUDAFSumLong(col 0) -> bigint
+                    className: VectorGroupByOperator
+                    vectorOutput: true
+                    native: false
+                    projectedOutputColumns: [0]
                 mode: mergepartial
                 outputColumnNames: _col0
                 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                 Reduce Output Operator
                   key expressions: _col0 (type: bigint)
                   sort order: +
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkOperator
+                      native: false
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                      nativeConditionsNotMet: Uniform Hash IS false
                   Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: bigint)
                 outputColumnNames: _col0
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumns: [0]
                 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
+                  File Sink Vectorization:
+                      className: VectorFileSinkOperator
+                      native: false
                   Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -189,7 +313,7 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -39856
-PREHOOK: query: EXPLAIN 
+PREHOOK: query: EXPLAIN VECTORIZATION 
 SELECT
   avg(ctinyint) as c1,
   variance(ctinyint),
@@ -202,7 +326,7 @@ SELECT
 FROM alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN 
+POSTHOOK: query: EXPLAIN VECTORIZATION 
 SELECT
   avg(ctinyint) as c1,
   variance(ctinyint),
@@ -215,6 +339,10 @@ SELECT
 FROM alltypesorc
 ORDER BY c1
 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
@@ -248,8 +376,21 @@ STAGE PLANS:
                         value expressions: _col0 (type: struct<count:bigint,sum:double,input:tinyint>), _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: false
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                notVectorizedReason: Aggregation Function UDF avg parameter expression for GROUPBY operator: Data type struct<count:bigint,sum:double,input:tinyint> of Column[VALUE._col0] not supported
+                vectorized: false
             Reduce Operator Tree:
               Group By Operator
                 aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7)
@@ -263,6 +404,13 @@ STAGE PLANS:
                   value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double)
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double)
@@ -311,7 +459,7 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -4.344925324321378	1158.3003004768184	1158.3003004768184	1158.4265870337827	34.033811136527426	34.033811136527426	34.033811136527426	34.03566639620536
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT MIN(cbigint) as c1,
        MAX(cbigint),
        COUNT(cbigint),
@@ -319,7 +467,7 @@ SELECT MIN(cbigint) as c1,
 FROM   alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT MIN(cbigint) as c1,
        MAX(cbigint),
        COUNT(cbigint),
@@ -327,6 +475,10 @@ SELECT MIN(cbigint) as c1,
 FROM   alltypesorc
 ORDER BY c1
 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
@@ -345,43 +497,101 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Select Operator
                     expressions: cbigint (type: bigint)
                     outputColumnNames: cbigint
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [3]
                     Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       aggregations: min(cbigint), max(cbigint), count(cbigint), count()
+                      Group By Vectorization:
+                          aggregators: VectorUDAFMinLong(col 3) -> bigint, VectorUDAFMaxLong(col 3) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCountStar(*) -> bigint
+                          className: VectorGroupByOperator
+                          vectorOutput: true
+                          native: false
+                          projectedOutputColumns: [0, 1, 2, 3]
                       mode: hash
                       outputColumnNames: _col0, _col1, _col2, _col3
                       Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkOperator
+                            native: false
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                            nativeConditionsNotMet: Uniform Hash IS false
                         Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3)
+                Group By Vectorization:
+                    aggregators: VectorUDAFMinLong(col 0) -> bigint, VectorUDAFMaxLong(col 1) -> bigint, VectorUDAFCountMerge(col 2) -> bigint, VectorUDAFCountMerge(col 3) -> bigint
+                    className: VectorGroupByOperator
+                    vectorOutput: true
+                    native: false
+                    projectedOutputColumns: [0, 1, 2, 3]
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3
                 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                 Reduce Output Operator
                   key expressions: _col0 (type: bigint)
                   sort order: +
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkOperator
+                      native: false
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                      nativeConditionsNotMet: Uniform Hash IS false
                   Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                   value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint)
                 outputColumnNames: _col0, _col1, _col2, _col3
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumns: [0, 1, 2, 3]
                 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
+                  File Sink Vectorization:
+                      className: VectorFileSinkOperator
+                      native: false
                   Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -413,16 +623,20 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -2147311592	2145498388	9173	12288
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT SUM(cbigint) as c1
 FROM   alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT SUM(cbigint) as c1
 FROM   alltypesorc
 ORDER BY c1
 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
@@ -441,42 +655,100 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Select Operator
                     expressions: cbigint (type: bigint)
                     outputColumnNames: cbigint
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [3]
                     Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       aggregations: sum(cbigint)
+                      Group By Vectorization:
+                          aggregators: VectorUDAFSumLong(col 3) -> bigint
+                          className: VectorGroupByOperator
+                          vectorOutput: true
+                          native: false
+                          projectedOutputColumns: [0]
                       mode: hash
                       outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkOperator
+                            native: false
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                            nativeConditionsNotMet: Uniform Hash IS false
                         Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: sum(VALUE._col0)
+                Group By Vectorization:
+                    aggregators: VectorUDAFSumLong(col 0) -> bigint
+                    className: VectorGroupByOperator
+                    vectorOutput: true
+                    native: false
+                    projectedOutputColumns: [0]
                 mode: mergepartial
                 outputColumnNames: _col0
                 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                 Reduce Output Operator
                   key expressions: _col0 (type: bigint)
                   sort order: +
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkOperator
+                      native: false
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                      nativeConditionsNotMet: Uniform Hash IS false
                   Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: bigint)
                 outputColumnNames: _col0
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumns: [0]
                 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
+                  File Sink Vectorization:
+                      className: VectorFileSinkOperator
+                      native: false
                   Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -502,7 +774,7 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -1698460028409
-PREHOOK: query: EXPLAIN 
+PREHOOK: query: EXPLAIN VECTORIZATION 
 SELECT
   avg(cbigint) as c1,
   variance(cbigint),
@@ -515,7 +787,7 @@ SELECT
 FROM alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN 
+POSTHOOK: query: EXPLAIN VECTORIZATION 
 SELECT
   avg(cbigint) as c1,
   variance(cbigint),
@@ -528,6 +800,10 @@ SELECT
 FROM alltypesorc
 ORDER BY c1
 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
@@ -561,8 +837,21 @@ STAGE PLANS:
                         value expressions: _col0 (type: struct<count:bigint,sum:double,input:bigint>), _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: false
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                notVectorizedReason: Aggregation Function UDF avg parameter expression for GROUPBY operator: Data type struct<count:bigint,sum:double,input:bigint> of Column[VALUE._col0] not supported
+                vectorized: false
             Reduce Operator Tree:
               Group By Operator
                 aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7)
@@ -576,6 +865,13 @@ STAGE PLANS:
                   value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double)
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double)
@@ -624,7 +920,7 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -1.8515862077935246E8	2.07689300543081907E18	2.07689300543081907E18	2.07711944383088768E18	1.441142951074188E9	1.441142951074188E9	1.441142951074188E9	1.4412215110214279E9
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT MIN(cfloat) as c1,
        MAX(cfloat),
        COUNT(cfloat),
@@ -632,7 +928,7 @@ SELECT MIN(cfloat) as c1,
 FROM   alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT MIN(cfloat) as c1,
        MAX(cfloat),
        COUNT(cfloat),
@@ -640,6 +936,10 @@ SELECT MIN(cfloat) as c1,
 FROM   alltypesorc
 ORDER BY c1
 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
@@ -658,43 +958,101 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Select Operator
                     expressions: cfloat (type: float)
                     outputColumnNames: cfloat
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [4]
                     Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       aggregations: min(cfloat), max(cfloat), count(cfloat), count()
+                      Group By Vectorization:
+                          aggregators: VectorUDAFMinDouble(col 4) -> float, VectorUDAFMaxDouble(col 4) -> float, VectorUDAFCount(col 4) -> bigint, VectorUDAFCountStar(*) -> bigint
+                          className: VectorGroupByOperator
+                          vectorOutput: true
+                          native: false
+                          projectedOutputColumns: [0, 1, 2, 3]
                       mode: hash
                       outputColumnNames: _col0, _col1, _col2, _col3
                       Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkOperator
+                            native: false
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                            nativeConditionsNotMet: Uniform Hash IS false
                         Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3)
+                Group By Vectorization:
+                    aggregators: VectorUDAFMinDouble(col 0) -> float, VectorUDAFMaxDouble(col 1) -> float, VectorUDAFCountMerge(col 2) -> bigint, VectorUDAFCountMerge(col 3) -> bigint
+                    className: VectorGroupByOperator
+                    vectorOutput: true
+                    native: false
+                    projectedOutputColumns: [0, 1, 2, 3]
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3
                 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                 Reduce Output Operator
                   key expressions: _col0 (type: float)
                   sort order: +
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkOperator
+                      native: false
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                      nativeConditionsNotMet: Uniform Hash IS false
                   Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                   value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint)
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: float), VALUE._col0 (type: float), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint)
                 outputColumnNames: _col0, _col1, _col2, _col3
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumns: [0, 1, 2, 3]
                 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
+                  File Sink Vectorization:
+                      className: VectorFileSinkOperator
+                      native: false
                   Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -726,16 +1084,20 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -64.0	79.553	9173	12288
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT SUM(cfloat) as c1
 FROM   alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT SUM(cfloat) as c1
 FROM   alltypesorc
 ORDER BY c1
 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
@@ -754,42 +1116,100 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Select Operator
                     expressions: cfloat (type: float)
                     outputColumnNames: cfloat
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [4]
                     Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       aggregations: sum(cfloat)
+                      Group By Vectorization:
+                          aggregators: VectorUDAFSumDouble(col 4) -> double
+                          className: VectorGroupByOperator
+                          vectorOutput: true
+                          native: false
+                          projectedOutputColumns: [0]
                       mode: hash
                       outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         sort order: 
+                        Reduce Sink Vectorization:
+                            className: VectorReduceSinkOperator
+                            native: false
+                            nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                            nativeConditionsNotMet: Uniform Hash IS false
                         Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                         value expressions: _col0 (type: double)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: sum(VALUE._col0)
+                Group By Vectorization:
+                    aggregators: VectorUDAFSumDouble(col 0) -> double
+                    className: VectorGroupByOperator
+                    vectorOutput: true
+                    native: false
+                    projectedOutputColumns: [0]
                 mode: mergepartial
                 outputColumnNames: _col0
                 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                 Reduce Output Operator
                   key expressions: _col0 (type: double)
                   sort order: +
+                  Reduce Sink Vectorization:
+                      className: VectorReduceSinkOperator
+                      native: false
+                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+                      nativeConditionsNotMet: Uniform Hash IS false
                   Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: double)
                 outputColumnNames: _col0
+                Select Vectorization:
+                    className: VectorSelectOperator
+                    native: true
+                    projectedOutputColumns: [0]
                 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
+                  File Sink Vectorization:
+                      className: VectorFileSinkOperator
+                      native: false
                   Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -815,7 +1235,7 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -39479.635992884636
-PREHOOK: query: EXPLAIN 
+PREHOOK: query: EXPLAIN VECTORIZATION 
 SELECT
   avg(cfloat) as c1,
   variance(cfloat),
@@ -828,7 +1248,7 @@ SELECT
 FROM alltypesorc
 ORDER BY c1
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN 
+POSTHOOK: query: EXPLAIN VECTORIZATION 
 SELECT
   avg(cfloat) as c1,
   variance(cfloat),
@@ -841,6 +1261,10 @@ SELECT
 FROM alltypesorc
 ORDER BY c1
 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
@@ -874,8 +1298,21 @@ STAGE PLANS:
                         value expressions: _col0 (type: struct<count:bigint,sum:double,input:float>), _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: false
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                notVectorizedReason: Aggregation Function UDF avg parameter expression for GROUPBY operator: Data type struct<count:bigint,sum:double,input:float> of Column[VALUE._col0] not supported
+                vectorized: false
             Reduce Operator Tree:
               Group By Operator
                 aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7)
@@ -889,6 +1326,13 @@ STAGE PLANS:
                   value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double)
         Reducer 3 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double)
@@ -938,7 +1382,7 @@ POSTHOOK: Input: default@alltypesorc
 #### A masked pattern was here ####
 -4.303895780321011	1163.8972588604984	1163.8972588604984	1164.0241556397025	34.115938487171924	34.115938487171924	34.115938487171924	34.11779822379666
 WARNING: Comparing a bigint and a double may result in a loss of precision.
-PREHOOK: query: EXPLAIN
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT AVG(cbigint),
        (-(AVG(cbigint))),
        (-6432 + AVG(cbigint)),
@@ -965,7 +1409,7 @@ WHERE  (((cstring2 LIKE '%b%')
             AND ((cboolean2 = 1)
                  AND (3569 = ctinyint))))
 PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
 SELECT AVG(cbigint),
        (-(AVG(cbigint))),
        (-6432 + AVG(cbigint)),
@@ -992,6 +1436,10 @@ WHERE  (((cstring2 LIKE '%b%')
             AND ((cboolean2 = 1)
                  AND (3569 = ctinyint))))
 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
@@ -1009,15 +1457,33 @@ STAGE PLANS:
                 TableScan
                   alias: alltypesorc
                   Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
                   Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 12)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean, FilterDoubleColLessDoubleColumn(col 13, col 5)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 0, col 1)(children: col 0) -> boolean, FilterLongColEqualLongScalar(col 11, val 1) -> boolean, FilterLongScalarEqualLongColumn(val 3569, col 0)(children: col 0) -> boolean) -> boolean) -> boolean
                     predicate: ((cstring2 like '%b%') or (79.553 <> CAST( cint AS decimal(13,3))) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (3569 = UDFToInteger(ctinyint)))) (type: boolean)
                     Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint)
                       outputColumnNames: cbigint, cfloat, ctinyint
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumns: [3, 4, 0]
                       Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint)
+                        Group By Vectorization:
+                            aggregators: VectorUDAFAvgLong(col 3) -> struct<count:bigint,sum:double>, VectorUDAFStdPopLong(col 3) -> struct<count:bigint,sum:double,variance:double>, VectorUDAFVarSampLong(col 3) -> struct<count:bigint,sum:double,variance:double>, VectorUDAFCountStar(*) -> bigint, VectorUDAFSumDouble(col 4) -> double, VectorUDAFMinLong(col 0) -> tinyint
+                            className: VectorGroupByOperator
+                            vectorOutput: false
+                            native: false
+                            projectedOutputColumns: [0, 1, 2, 3, 4, 5]
+                            vectorOutputConditionsNotMet: Vector output of VectorUDAFAvgLong(col 3) -> struct<count:bigint,sum:double> output type STRUCT requires PRIMITIVE IS false, Vector output of VectorUDAFStdPopLong(col 3) -> struct<count:bigint,sum:double,variance:double> output type STRUCT requires PRIMITIVE IS false, Vector output of VectorUDAFVarSampLong(col 3) -> struct<count:bigint,sum:double,variance:double> output type STRUCT requires PRIMITIVE IS false
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
                         Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
@@ -1027,8 +1493,21 @@ STAGE PLANS:
                           value expressions: _col0 (type: struct<count:bigint,sum:double,input:bigint>), _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: bigint), _col4 (type: double), _col5 (type: tinyint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: false
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+                notVectorizedReason: Aggregation Function UDF avg parameter expression for GROUPBY operator: Data type struct<count:bigint,sum:double,input:bigint> of Column[VALUE._col0] not supported
+                vectorized: false
             Reduce Operator Tree:
               Group By Operator
                 aggregations: avg(VALUE._col0), stddev_pop(VALUE._col1), var_samp(VALUE._col2), count(VALUE._col3), sum(VALUE._col4), min(VALUE._col5)
@@ -29934,23 +30413,109 @@ POSTHOOK: query: explain extended select * from alltypesorc where
                      (cint=45  and  cfloat=3.02)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-0 is a root stage
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: alltypesorc
+                  Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE
+                  GatherStats: false
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean)
+                    Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
+                      Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+                      File Output Operator
+                        compressed: false
+                        GlobalTableId: 0
+#### A masked pattern was here ####
+                        NumFilesPerFileSink: 1
+                        Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+#### A masked pattern was here ####
+                        table:
+                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                            properties:
+                              columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11
+                              columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+                              escape.delim \
+                              hive.serialization.extend.additional.nesting.levels true
+                              serialization.escape.crlf true
+                              serialization.format 1
+                              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        TotalFiles: 1
+                        GatherStats: false
+                        MultiFileSpray: false
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Path -> Alias:
+#### A masked pattern was here ####
+            Path -> Partition:
+#### A masked pattern was here ####
+                Partition
+                  base file name: alltypesorc
+                  input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+                  properties:
+                    COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}}
+                    bucket_count -1
+                    column.name.delimiter ,
+                    columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2
+                    columns.comments 
+                    columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+#### A masked pattern was here ####
+                    name default.alltypesorc
+                    numFiles 1
+                    numRows 12288
+                    rawDataSize 2641964
+                    serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                    totalSize 377237
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                
+                    input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+                    properties:
+                      COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}}
+                      bucket_count -1
+                      column.name.delimiter ,
+                      columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2
+                      columns.comments 
+                      columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+#### A masked pattern was here ####
+                      name default.alltypesorc
+                      numFiles 1
+                      numRows 12288
+                      rawDataSize 2641964
+                      serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
+                      serialization.format 1
+                      serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                      totalSize 377237
+#### A masked pattern was here ####
+                    serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                    name: default.alltypesorc
+                  name: default.alltypesorc
+            Truncated Path -> Alias:
+              /alltypesorc [alltypesorc]
+
   Stage: Stage-0
     Fetch Operator
       limit: -1
       Processor Tree:
-        TableScan
-          alias: alltypesorc
-          GatherStats: false
-          Filter Operator
-            isSamplingPred: false
-            predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean)
-            Select Operator
-              expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
-              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
-              ListSink
+        ListSink
 
 PREHOOK: query: explain extended select * from alltypesorc where
                                 (cint=49 and  cfloat=3.5) or
@@ -29963,23 +30528,109 @@ POSTHOOK: query: explain extended select * from alltypesorc where
                                 (cint=45  and  cfloat=3.02)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-0 is a root stage
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: alltypesorc
+                  Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE
+                  GatherStats: false
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean)
+                    Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
+                      Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+                      File Output Operator
+                        compressed: false
+                        GlobalTableId: 0
+#### A masked pattern was here ####
+                        NumFilesPerFileSink: 1
+                        Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+#### A masked pattern was here ####
+                        table:
+                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                            properties:
+                              columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11
+                              columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+                              escape.delim \
+                              hive.serialization.extend.additional.nesting.levels true
+                              serialization.escape.crlf true
+                              serialization.format 1
+                              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        TotalFiles: 1
+                        GatherStats: false
+                        MultiFileSpray: false
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Path -> Alias:
+#### A masked pattern was here ####
+            Path -> Partition:
+#### A masked pattern was here ####
+                Partition
+                  base file name: alltypesorc
+                  input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+                  properties:
+                    COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}}
+                    bucket_count -1
+                    column.name.delimiter ,
+                    columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2
+                    columns.comments 
+                    columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+#### A masked pattern was here ####
+                    name default.alltypesorc
+                    numFiles 1
+                    numRows 12288
+                    rawDataSize 2641964
+                    serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                    totalSize 377237
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                
+                    input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+                    properties:
+                      COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}}
+                      bucket_count -1
+                      column.name.delimiter ,
+                      columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2
+                      columns.comments 
+                      columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+#### A masked pattern was here ####
+                      name default.alltypesorc
+                      numFiles 1
+                      numRows 12288
+                      rawDataSize 2641964
+                      serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
+                      serialization.format 1
+                      serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                      totalSize 377237
+#### A masked pattern was here ####
+                    serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                    name: default.alltypesorc
+                  name: default.alltypesorc
+            Truncated Path -> Alias:
+              /alltypesorc [alltypesorc]
+
   Stage: Stage-0
     Fetch Operator
       limit: -1
       Processor Tree:
-        TableScan
-          alias: alltypesorc
-          GatherStats: false
-          Filter Operator
-            isSamplingPred: false
-            predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean)
-            Select Operator
-              expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
-              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
-              ListSink
+        ListSink
 
 PREHOOK: query: explain extended select * from alltypesorc where
                      (cint=49 or  cfloat=3.5) and
@@ -29992,23 +30643,109 @@ POSTHOOK: query: explain extended select * from alltypesorc where
                      (cint=45 or  cfloat=3.02)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-0 is a root stage
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: alltypesorc
+                  Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE
+                  GatherStats: false
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean)
+                    Statistics: Num rows: 30 Data size: 7690 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
+                      Statistics: Num rows: 30 Data size: 7690 Basic stats: COMPLETE Column stats: COMPLETE
+                      File Output Operator
+                        compressed: false
+                        GlobalTableId: 0
+#### A masked pattern was here ####
+                        NumFilesPerFileSink: 1
+                        Statistics: Num rows: 30 Data size: 7690 Basic stats: COMPLETE Column stats: COMPLETE
+#### A masked pattern was here ####
+                        table:
+                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                            properties:
+                              columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11
+                              columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+                              escape.delim \
+                              hive.serialization.extend.additional.nesting.levels true
+                              serialization.escape.crlf true
+                              serialization.format 1
+                              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        TotalFiles: 1
+                        GatherStats: false
+                        MultiFileSpray: false
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Path -> Alias:
+#### A masked pattern was here ####
+            Path -> Partition:
+#### A masked pattern was here ####
+                Partition
+                  base file name: alltypesorc
+                  input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+                  properties:
+                    COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}}
+                    bucket_count -1
+                    column.name.delimiter ,
+                    columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2
+                    columns.comments 
+                    columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+#### A masked pattern was here ####
+                    name default.alltypesorc
+                    numFiles 1
+                    numRows 12288
+                    rawDataSize 2641964
+                    serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                    totalSize 377237
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                
+                    input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+                    properties:
+                      COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}}
+                      bucket_count -1
+                      column.name.delimiter ,
+                      columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2
+                      columns.comments 
+                      columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean
+#### A masked pattern was here ####
+                      name default.alltypesorc
+                      numFiles 1
+                      numRows 12288
+                      rawDataSize 2641964
+                      serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
+                      serialization.format 1
+                      serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                      totalSize 377237
+#### A masked pattern was here ####
+                    serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+                    name: default.alltypesorc
+                  name: default.alltypesorc
+            Truncated Path -> Alias:
+              /alltypesorc [alltypesorc]
+
   Stage: Stage-0
     Fetch Operator
       limit: -1
       Processor Tree:
-        TableScan
-          alias: alltypesorc
-          GatherStats: false
-          Filter Operator
-            isSamplingPred: false
-            predicate: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean)
-            Select Operator
-              expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
-              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
-              ListSink
+        ListSink
 
 PREHOOK: query: explain extended select count(*),cstring1 from alltypesorc where cstring1='biology'
                                                     or cstring1='history'


Mime
View raw message