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 2018/02/21 06:34:18 UTC
[2/6] hive git commit: HIVE-18756: Vectorization: VectorUDAFVarFinal
produces Wrong Results (Matt McCline, reviewed by Sergey Shelukhin)
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
index f4a5b55..591de4b 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
@@ -144,31 +144,14 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: []
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder: aaaa
- reduceColumnSortOrder: ++++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 9
- dataColumns: KEY._col0:double, KEY._col1:bigint, KEY._col2:string, KEY._col3:boolean, VALUE._col0:bigint, VALUE._col1:struct<count:bigint,sum:double,variance:double>, VALUE._col2:struct<count:bigint,sum:double,input:double>, VALUE._col3:bigint, VALUE._col4:struct<count:bigint,sum:double,variance:double>
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_samp" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdSampleEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), avg(VALUE._col2), sum(VALUE._col3), stddev_pop(VALUE._col4)
- Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFVarFinal(col 5:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_samp, VectorUDAFAvgFinal(col 6:struct<count:bigint,sum:double,input:double>) -> double, VectorUDAFSumLong(col 7:bigint) -> bigint, VectorUDAFVarFinal(col 8:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- keyExpressions: col 0:double, col 1:bigint, col 2:string, col 3:boolean
- native: false
- vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4]
keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -176,21 +159,10 @@ STAGE PLANS:
Select Operator
expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0 * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), _col5 (type: double), ((-6432.0 * _col0) / -6432.0) (type: double), (- ((-6432.0 * _col0) / -6432.0)) (type: double), _col6 (type: double), (- (-6432.0 * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col7 (type: bigint), (_col6 / (-6432.0 * _col0)) (type: double), (- (- ((-6432.0 * _col0) / -6432.0))) (type: double), (((-6432.0 * _col0) / -6432.0) + (- (-6432.0 * _col0))) (type: double), _col8 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [1, 3, 2, 0, 9, 10, 4, 11, 5, 13, 12, 6, 15, 17, 7, 18, 19, 14, 8]
- selectExpressions: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 9:double, LongColUnaryMinus(col 1:bigint) -> 10:bigint, LongColMultiplyLongColumn(col 1:bigint, col 4:bigint) -> 11:bigint, DoubleColDivideDoubleScalar(col 12:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 12:double) -> 13:double, DoubleColUnaryMinus(col 14:double)(children: DoubleColDivideDoubleScalar(col 12:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 12:double) -> 14:double) -> 12:double, DoubleColUnaryMinus(col 14:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 14:double) -> 15:double, DecimalScalarAddDecimalColumn(val -5638.15, col 16:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 16:decimal(19,0)) -> 17:decimal(22,2), DoubleColDivideDoubleColumn(col 6:double, col 14:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:
double) -> 14:double) -> 18:double, DoubleColUnaryMinus(col 14:double)(children: DoubleColUnaryMinus(col 19:double)(children: DoubleColDivideDoubleScalar(col 14:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 14:double) -> 19:double) -> 14:double) -> 19:double, DoubleColAddDoubleColumn(col 20:double, col 21:double)(children: DoubleColDivideDoubleScalar(col 14:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 14:double) -> 20:double, DoubleColUnaryMinus(col 14:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 14:double) -> 21:double) -> 14:double
Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string)
sort order: +++
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- keyColumnNums: [0, 1, 2]
- 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
- valueColumnNums: [3, 9, 10, 4, 11, 5, 13, 12, 6, 15, 17, 7, 18, 19, 14, 8]
Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double)
Reducer 3
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
index 6d5c27f..e6c1f12 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
@@ -146,31 +146,14 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: [double, decimal(11,4)]
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder: aaaaa
- reduceColumnSortOrder: +++++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 11
- dataColumns: KEY._col0:boolean, KEY._col1:tinyint, KEY._col2:timestamp, KEY._col3:float, KEY._col4:string, VALUE._col0:tinyint, VALUE._col1:double, VALUE._col2:struct<count:bigint,sum:double,variance:double>, VALUE._col3:struct<count:bigint,sum:double,variance:double>, VALUE._col4:float, VALUE._col5:tinyint
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5)
- Group By Vectorization:
- aggregators: VectorUDAFMaxLong(col 5:tinyint) -> tinyint, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFVarFinal(col 7:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFVarFinal(col 8:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFMaxDouble(col 9:float) -> float, VectorUDAFMinLong(col 10:tinyint) -> tinyint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- keyExpressions: col 0:boolean, col 1:tinyint, col 2:timestamp, col 3:float, col 4:string
- native: false
- vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -178,21 +161,10 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10]
- selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 11:tinyint, LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 13:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 15:double)(children: CastLongToDouble(col 14:tinyint)(children: LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 14:tinyint) -> 15:double) -> 16:double, DoubleColUnaryMinus(col 6:double) -> 15:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 17:float, DoubleColUnaryMinus(col 6:double) -> 18:double, DecimalColSubtractDecimalScalar(col 19:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 14:tinyint)(children: LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 14:tinyint) -> 19:decimal(3,0)) -> 20:decimal(7,3), DoubleColUnaryMinus(col 21:double)(children: DoubleColUna
ryMinus(col 6:double) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val -26.28, col 23:double)(children: DoubleColUnaryMinus(col 21:double)(children: DoubleColUnaryMinus(col 6:double) -> 21:double) -> 23:double) -> 21:double, DoubleColDivideDoubleColumn(col 24:double, col 23:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 23:double)(children: CastLongToDouble(col 14:tinyint)(children: LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 14:tinyint) -> 23:double) -> 24:double, CastLongToDouble(col 1:tinyint) -> 23:double) -> 25:double
Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint)
sort order: +++++++++++++++++++++
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- keyColumnNums: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10]
- 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
- valueColumnNums: []
Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
@@ -489,24 +461,14 @@ STAGE PLANS:
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
- 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
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5)
- Group By Vectorization:
- aggregators: VectorUDAFMaxLong(col 5:tinyint) -> tinyint, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFVarFinal(col 7:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFVarFinal(col 8:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFMaxDouble(col 9:float) -> float, VectorUDAFMinLong(col 10:tinyint) -> tinyint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- keyExpressions: col 0:boolean, col 1:tinyint, col 2:timestamp, col 3:float, col 4:string
- native: false
- vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -514,19 +476,10 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10]
- selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 11:tinyint, LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 13:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 15:double)(children: CastLongToDouble(col 14:tinyint)(children: LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 14:tinyint) -> 15:double) -> 16:double, DoubleColUnaryMinus(col 6:double) -> 15:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 17:float, DoubleColUnaryMinus(col 6:double) -> 18:double, DecimalColSubtractDecimalScalar(col 19:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 14:tinyint)(children: LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 14:tinyint) -> 19:decimal(3,0)) -> 20:decimal(7,3), DoubleColUnaryMinus(col 21:double)(children: DoubleColUna
ryMinus(col 6:double) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val -26.28, col 23:double)(children: DoubleColUnaryMinus(col 21:double)(children: DoubleColUnaryMinus(col 6:double) -> 21:double) -> 23:double) -> 21:double, DoubleColDivideDoubleColumn(col 24:double, col 23:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 23:double)(children: CastLongToDouble(col 14:tinyint)(children: LongColAddLongColumn(col 12:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 12:tinyint) -> 14:tinyint) -> 23:double) -> 24:double, CastLongToDouble(col 1:tinyint) -> 23:double) -> 25:double
Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint)
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: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
index 3016203..6fa51e5 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
@@ -147,31 +147,14 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: [double, double]
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder: aaaaa
- reduceColumnSortOrder: +++++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 11
- dataColumns: KEY._col0:string, KEY._col1:float, KEY._col2:double, KEY._col3:timestamp, KEY._col4:boolean, VALUE._col0:struct<count:bigint,sum:double,variance:double>, VALUE._col1:float, VALUE._col2:struct<count:bigint,sum:double,variance:double>, VALUE._col3:bigint, VALUE._col4:struct<count:bigint,sum:double,variance:double>, VALUE._col5:struct<count:bigint,sum:double,variance:double>
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_samp" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdSampleEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: stddev_samp(VALUE._col0), max(VALUE._col1), stddev_pop(VALUE._col2), count(VALUE._col3), var_pop(VALUE._col4), var_samp(VALUE._col5)
- Group By Vectorization:
- aggregators: VectorUDAFVarFinal(col 5:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_samp, VectorUDAFMaxDouble(col 6:float) -> float, VectorUDAFVarFinal(col 7:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFCountMerge(col 8:bigint) -> bigint, VectorUDAFVarFinal(col 9:struct<count:bigint,sum:double,variance:double>) -> double aggregation: var_pop, VectorUDAFVarFinal(col 10:struct<count:bigint,sum:double,variance:double>) -> double aggregation: var_samp
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- keyExpressions: col 0:string, col 1:float, col 2:double, col 3:timestamp, col 4:boolean
- native: false
- vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -179,21 +162,10 @@ STAGE PLANS:
Select Operator
expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28 + _col2) (type: double), (- (-26.28 + _col2)) (type: double), _col5 (type: double), (_col1 * -26.28) (type: float), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col2)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col2)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col2) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [3, 1, 0, 4, 2, 11, 13, 5, 12, 6, 14, 15, 16, 7, 8, 18, 17, 19, 9, 20, 10, 22]
- selectExpressions: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 11:double, DoubleColUnaryMinus(col 12:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 12:double) -> 13:double, DoubleColMultiplyDoubleScalar(col 1:float, val -26.280000686645508) -> 12:float, DoubleColUnaryMinus(col 1:float) -> 14:float, DoubleColUnaryMinus(col 6:float) -> 15:float, DoubleColDivideDoubleScalar(col 17:double, val 10.175)(children: DoubleColUnaryMinus(col 16:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 16:double) -> 17:double) -> 16:double, DoubleColUnaryMinus(col 17:double)(children: DoubleColDivideDoubleScalar(col 18:double, val 10.175)(children: DoubleColUnaryMinus(col 17:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 17:double) -> 18:double) -> 17:double) -> 18:double, DoubleScalarModuloDoubleColumn(val -1.389, col 5:double) -> 17:double, DoubleColSubtractDoubleColumn(col 1:double, co
l 2:double)(children: col 1:float) -> 19:double, DoubleColModuloDoubleScalar(col 9:double, val 10.175) -> 20:double, DoubleColUnaryMinus(col 21:double)(children: DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 21:double) -> 22:double
Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp)
sort order: ++++
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- keyColumnNums: [0, 1, 2, 3]
- 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
- valueColumnNums: [4, 11, 13, 5, 12, 6, 14, 15, 16, 7, 8, 18, 17, 19, 9, 20, 10, 22]
Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double)
Reducer 3
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
index b270aea..24cae48 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
@@ -119,31 +119,14 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: []
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder: aaa
- reduceColumnSortOrder: +++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 6
- dataColumns: KEY._col0:double, KEY._col1:string, KEY._col2:timestamp, VALUE._col0:bigint, VALUE._col1:struct<count:bigint,sum:double,variance:double>, VALUE._col2:double
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_samp" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdSampleEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFVarFinal(col 4:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_samp, VectorUDAFMinDouble(col 5:double) -> double
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- keyExpressions: col 0:double, col 1:string, col 2:timestamp
- native: false
- vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumnNums: [0, 1, 2]
keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -151,17 +134,9 @@ STAGE PLANS:
Select Operator
expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [1, 0, 2, 6, 8, 3, 4, 7, 10, 5, 9, 12, 4]
- selectExpressions: DoubleColSubtractDoubleScalar(col 0:double, val 9763215.5639) -> 6:double, DoubleColUnaryMinus(col 7:double)(children: DoubleColSubtractDoubleScalar(col 0:double, val 9763215.5639) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 4:double) -> 7:double, DoubleColMultiplyDoubleColumn(col 4:double, col 9:double)(children: CastLongToDouble(col 3:bigint) -> 9:double) -> 10:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 0:double) -> 9:double, DecimalColDivideDecimalScalar(col 11:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 11:decimal(19,0)) -> 12:decimal(28,6)
Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_2.q.out b/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
index 09267d7..f11854c 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
@@ -121,47 +121,23 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: [double]
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder:
- reduceColumnSortOrder:
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 6
- dataColumns: VALUE._col0:struct<count:bigint,sum:double,input:smallint>, VALUE._col1:double, VALUE._col2:struct<count:bigint,sum:double,variance:double>, VALUE._col3:bigint, VALUE._col4:tinyint, VALUE._col5:struct<count:bigint,sum:double,input:double>
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "var_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFVarianceEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: avg(VALUE._col0), sum(VALUE._col1), var_pop(VALUE._col2), count(VALUE._col3), min(VALUE._col4), avg(VALUE._col5)
- Group By Vectorization:
- aggregators: VectorUDAFAvgFinal(col 0:struct<count:bigint,sum:double,input:smallint>) -> double, VectorUDAFSumDouble(col 1:double) -> double, VectorUDAFVarFinal(col 2:struct<count:bigint,sum:double,variance:double>) -> double aggregation: var_pop, VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFMinLong(col 4:tinyint) -> tinyint, VectorUDAFAvgFinal(col 5:struct<count:bigint,sum:double,input:double>) -> double
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: double), (_col0 % -563.0) (type: double), (_col0 + 762.0) (type: double), _col1 (type: double), _col2 (type: double), (- _col2) (type: double), (_col1 - _col0) (type: double), _col3 (type: bigint), (- (_col1 - _col0)) (type: double), (_col2 - 762.0) (type: double), _col4 (type: tinyint), ((- _col2) + UDFToDouble(_col4)) (type: double), _col5 (type: double), (((- _col2) + UDFToDouble(_col4)) - _col1) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 6, 7, 1, 2, 8, 9, 3, 11, 10, 4, 14, 5, 12]
- selectExpressions: DoubleColModuloDoubleScalar(col 0:double, val -563.0) -> 6:double, DoubleColAddDoubleScalar(col 0:double, val 762.0) -> 7:double, DoubleColUnaryMinus(col 2:double) -> 8:double, DoubleColSubtractDoubleColumn(col 1:double, col 0:double) -> 9:double, DoubleColUnaryMinus(col 10:double)(children: DoubleColSubtractDoubleColumn(col 1:double, col 0:double) -> 10:double) -> 11:double, DoubleColSubtractDoubleScalar(col 2:double, val 762.0) -> 10:double, DoubleColAddDoubleColumn(col 12:double, col 13:double)(children: DoubleColUnaryMinus(col 2:double) -> 12:double, CastLongToDouble(col 4:tinyint) -> 13:double) -> 14:double, DoubleColSubtractDoubleColumn(col 15:double, col 1:double)(children: DoubleColAddDoubleColumn(col 12:double, col 13:double)(children: DoubleColUnaryMinus(col 2:double) -> 12:double, CastLongToDouble(col 4:tinyint) -> 13:double) -> 15:double) -> 12:double
Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_3.q.out b/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
index 444b534..253e12c 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
@@ -126,47 +126,23 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: [double, decimal(22,3), decimal(8,3)]
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder:
- reduceColumnSortOrder:
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 6
- dataColumns: VALUE._col0:struct<count:bigint,sum:double,variance:double>, VALUE._col1:struct<count:bigint,sum:double,variance:double>, VALUE._col2:struct<count:bigint,sum:double,variance:double>, VALUE._col3:double, VALUE._col4:struct<count:bigint,sum:double,input:int>, VALUE._col5:struct<count:bigint,sum:double,variance:double>
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_samp" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdSampleEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: stddev_samp(VALUE._col0), stddev_pop(VALUE._col1), stddev_samp(VALUE._col2), sum(VALUE._col3), avg(VALUE._col4), stddev_pop(VALUE._col5)
- Group By Vectorization:
- aggregators: VectorUDAFVarFinal(col 0:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_samp, VectorUDAFVarFinal(col 1:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFVarFinal(col 2:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_samp, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFAvgFinal(col 4:struct<count:bigint,sum:double,input:int>) -> double, VectorUDAFVarFinal(col 5:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: double), (_col0 - 10.175) (type: double), _col1 (type: double), (_col0 * (_col0 - 10.175)) (type: double), (- _col1) (type: double), (_col0 % 79.553) (type: double), (- (_col0 * (_col0 - 10.175))) (type: double), _col2 (type: double), (- _col0) (type: double), _col3 (type: double), ((- (_col0 * (_col0 - 10.175))) / (_col0 - 10.175)) (type: double), (- (_col0 - 10.175)) (type: double), _col4 (type: double), (-3728.0 - _col0) (type: double), _col5 (type: double), (_col4 / _col2) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 6, 1, 8, 7, 9, 10, 2, 11, 3, 14, 13, 4, 12, 5, 15]
- selectExpressions: DoubleColSubtractDoubleScalar(col 0:double, val 10.175) -> 6:double, DoubleColMultiplyDoubleColumn(col 0:double, col 7:double)(children: DoubleColSubtractDoubleScalar(col 0:double, val 10.175) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 1:double) -> 7:double, DoubleColModuloDoubleScalar(col 0:double, val 79.553) -> 9:double, DoubleColUnaryMinus(col 11:double)(children: DoubleColMultiplyDoubleColumn(col 0:double, col 10:double)(children: DoubleColSubtractDoubleScalar(col 0:double, val 10.175) -> 10:double) -> 11:double) -> 10:double, DoubleColUnaryMinus(col 0:double) -> 11:double, DoubleColDivideDoubleColumn(col 12:double, col 13:double)(children: DoubleColUnaryMinus(col 13:double)(children: DoubleColMultiplyDoubleColumn(col 0:double, col 12:double)(children: DoubleColSubtractDoubleScalar(col 0:double, val 10.175) -> 12:double) -> 13:double) -> 12:double, DoubleColSubtractDoubleScalar(col 0:double, val 10.175) -> 13:double) -> 14:double,
DoubleColUnaryMinus(col 12:double)(children: DoubleColSubtractDoubleScalar(col 0:double, val 10.175) -> 12:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -3728.0, col 0:double) -> 12:double, DoubleColDivideDoubleColumn(col 4:double, col 2:double) -> 15:double
Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_4.q.out b/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
index 664ff5e..436fdd9 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
@@ -121,47 +121,23 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: []
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder:
- reduceColumnSortOrder:
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 5
- dataColumns: VALUE._col0:bigint, VALUE._col1:struct<count:bigint,sum:double,variance:double>, VALUE._col2:struct<count:bigint,sum:double,input:double>, VALUE._col3:struct<count:bigint,sum:double,variance:double>, VALUE._col4:tinyint
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), stddev_pop(VALUE._col1), avg(VALUE._col2), var_pop(VALUE._col3), min(VALUE._col4)
- Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint, VectorUDAFVarFinal(col 1:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_pop, VectorUDAFAvgFinal(col 2:struct<count:bigint,sum:double,input:double>) -> double, VectorUDAFVarFinal(col 3:struct<count:bigint,sum:double,variance:double>) -> double aggregation: var_pop, VectorUDAFMinLong(col 4:tinyint) -> tinyint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2, 3, 4]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Statistics: Num rows: 1 Data size: 252 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: bigint), (_col0 * -563) (type: bigint), (-3728 + _col0) (type: bigint), _col1 (type: double), (- _col1) (type: double), _col2 (type: double), ((_col0 * -563) % _col0) (type: bigint), (UDFToDouble(((_col0 * -563) % _col0)) / _col2) (type: double), _col3 (type: double), (- (UDFToDouble(((_col0 * -563) % _col0)) / _col2)) (type: double), ((-3728 + _col0) - (_col0 * -563)) (type: bigint), _col4 (type: tinyint), _col4 (type: tinyint), (UDFToDouble(_col4) * (- (UDFToDouble(((_col0 * -563) % _col0)) / _col2))) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 5, 6, 1, 7, 2, 9, 12, 3, 11, 14, 4, 4, 16]
- selectExpressions: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 5:bigint, LongScalarAddLongColumn(val -3728, col 0:bigint) -> 6:bigint, DoubleColUnaryMinus(col 1:double) -> 7:double, LongColModuloLongColumn(col 8:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 8:bigint) -> 9:bigint, DoubleColDivideDoubleColumn(col 11:double, col 2:double)(children: CastLongToDouble(col 10:bigint)(children: LongColModuloLongColumn(col 8:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 8:bigint) -> 10:bigint) -> 11:double) -> 12:double, DoubleColUnaryMinus(col 13:double)(children: DoubleColDivideDoubleColumn(col 11:double, col 2:double)(children: CastLongToDouble(col 10:bigint)(children: LongColModuloLongColumn(col 8:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 8:bigint) -> 10:bigint) -> 11:double) -> 13:double) -> 11:double, LongColSubtractLongColumn(col 8:big
int, col 10:bigint)(children: LongScalarAddLongColumn(val -3728, col 0:bigint) -> 8:bigint, LongColMultiplyLongScalar(col 0:bigint, val -563) -> 10:bigint) -> 14:bigint, DoubleColMultiplyDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 4:tinyint) -> 13:double, DoubleColUnaryMinus(col 16:double)(children: DoubleColDivideDoubleColumn(col 15:double, col 2:double)(children: CastLongToDouble(col 10:bigint)(children: LongColModuloLongColumn(col 8:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 8:bigint) -> 10:bigint) -> 15:double) -> 16:double) -> 15:double) -> 16:double
Statistics: Num rows: 1 Data size: 252 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 1 Data size: 252 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
index b270aea..24cae48 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
@@ -119,31 +119,14 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: []
Reducer 2
- Execution mode: vectorized
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- reduceColumnNullOrder: aaa
- reduceColumnSortOrder: +++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 6
- dataColumns: KEY._col0:double, KEY._col1:string, KEY._col2:timestamp, VALUE._col0:bigint, VALUE._col1:struct<count:bigint,sum:double,variance:double>, VALUE._col2:double
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_samp" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdSampleEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFVarFinal(col 4:struct<count:bigint,sum:double,variance:double>) -> double aggregation: stddev_samp, VectorUDAFMinDouble(col 5:double) -> double
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- keyExpressions: col 0:double, col 1:string, col 2:timestamp
- native: false
- vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumnNums: [0, 1, 2]
keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -151,17 +134,9 @@ STAGE PLANS:
Select Operator
expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [1, 0, 2, 6, 8, 3, 4, 7, 10, 5, 9, 12, 4]
- selectExpressions: DoubleColSubtractDoubleScalar(col 0:double, val 9763215.5639) -> 6:double, DoubleColUnaryMinus(col 7:double)(children: DoubleColSubtractDoubleScalar(col 0:double, val 9763215.5639) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 4:double) -> 7:double, DoubleColMultiplyDoubleColumn(col 4:double, col 9:double)(children: CastLongToDouble(col 3:bigint) -> 9:double) -> 10:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 0:double) -> 9:double, DecimalColDivideDecimalScalar(col 11:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 11:decimal(19,0)) -> 12:decimal(28,6)
Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/8975924e/ql/src/test/results/clientpositive/spark/vectorization_input_format_excludes.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_input_format_excludes.q.out b/ql/src/test/results/clientpositive/spark/vectorization_input_format_excludes.q.out
index 18295e1..01eb4b4 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_input_format_excludes.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_input_format_excludes.q.out
@@ -197,13 +197,11 @@ STAGE PLANS:
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
- 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
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), min(VALUE._col1), count(VALUE._col2), avg(VALUE._col3), stddev_pop(VALUE._col4)
@@ -514,13 +512,11 @@ STAGE PLANS:
enabledConditionsNotMet: Row deserialization of vectorized input format not supported IS false, hive.vectorized.use.vectorized.input.format IS true AND hive.vectorized.input.format.excludes NOT CONTAINS org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat IS false
inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
Reducer 2
- 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
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), min(VALUE._col1), count(VALUE._col2), avg(VALUE._col3), stddev_pop(VALUE._col4)
@@ -843,13 +839,11 @@ STAGE PLANS:
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
- 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
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), min(VALUE._col1), count(VALUE._col2), avg(VALUE._col3), stddev_pop(VALUE._col4)
@@ -1208,13 +1202,11 @@ STAGE PLANS:
enabledConditionsNotMet: hive.vectorized.use.vectorized.input.format IS true AND hive.vectorized.input.format.excludes NOT CONTAINS org.apache.hadoop.hive.ql.io.orc.OrcInputFormat IS false
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
Reducer 2
- 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
+ notVectorizedReason: GROUPBY operator: Vector aggregation : "stddev_pop" for input type: "STRUCT" and output type: "DOUBLE" and mode: FINAL not supported for evaluator GenericUDAFStdEvaluator
+ vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), min(VALUE._col1), count(VALUE._col2), avg(VALUE._col3), stddev_pop(VALUE._col4)