http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_4.q.out b/ql/src/test/results/clientpositive/vectorization_4.q.out index 395431c..6dd398d 100644 --- a/ql/src/test/results/clientpositive/vectorization_4.q.out +++ b/ql/src/test/results/clientpositive/vectorization_4.q.out @@ -58,7 +58,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553)), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0)))) predicate: (((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or (UDFToInteger(csmallint) >= cint)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -77,7 +77,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 5, 0, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2) Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_5.q.out b/ql/src/test/results/clientpositive/vectorization_5.q.out index dfe9715..dc539e0 100644 --- a/ql/src/test/results/clientpositive/vectorization_5.q.out +++ b/ql/src/test/results/clientpositive/vectorization_5.q.out @@ -52,7 +52,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -62,7 +62,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11:boolean), FilterStringColLikeStringScalar(col 6:string, pattern %b%)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), SelectColumnIsNotNull(col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern a))) predicate: (((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a')) or (cboolean2 is not null and (cstring1 like '%b%'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) outputColumnNames: ctinyint, csmallint, cint @@ -70,7 +70,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) Group By Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_6.q.out b/ql/src/test/results/clientpositive/vectorization_6.q.out index 857cb31..6d17130 100644 --- a/ql/src/test/results/clientpositive/vectorization_6.q.out +++ b/ql/src/test/results/clientpositive/vectorization_6.q.out @@ -54,7 +54,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -64,7 +64,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: SelectColumnIsNotNull(col 3:bigint), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0))))) predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257)))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -73,13 +73,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22] selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int - Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_7.q.out b/ql/src/test/results/clientpositive/vectorization_7.q.out index 64c6fd8..3999bf2 100644 --- a/ql/src/test/results/clientpositive/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/vectorization_7.q.out @@ -66,7 +66,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -76,7 +76,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -15.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0)))) predicate: (((UDFToDouble(ctimestamp1) <= 0.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -15.0D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -85,7 +85,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: col 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: col 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -94,7 +94,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -120,13 +120,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -287,7 +287,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -296,7 +296,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val 7.6850000000000005)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0)))) predicate: (((UDFToDouble(ctimestamp1) <= 0.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -305,7 +305,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: col 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: col 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -314,7 +314,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -334,13 +334,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_8.q.out b/ql/src/test/results/clientpositive/vectorization_8.q.out index 80fdb0b..f658f80 100644 --- a/ql/src/test/results/clientpositive/vectorization_8.q.out +++ b/ql/src/test/results/clientpositive/vectorization_8.q.out @@ -62,7 +62,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -72,7 +72,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 10.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 16.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0))) predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -81,7 +81,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, col 23:float) -> 22:double - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -90,7 +90,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -116,13 +116,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -270,7 +270,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -279,7 +279,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 12.503)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 11.998)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0))) predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -288,7 +288,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, col 23:float) -> 22:double - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -297,7 +297,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -317,13 +317,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out index 571eae0..18120f2 100644 --- a/ql/src/test/results/clientpositive/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/vectorization_9.q.out @@ -52,7 +52,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -62,7 +62,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -71,7 +71,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -85,7 +85,7 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -95,7 +95,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -123,14 +123,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_limit.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_limit.q.out b/ql/src/test/results/clientpositive/vectorization_limit.q.out index 7474547..438c060 100644 --- a/ql/src/test/results/clientpositive/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -19,18 +19,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -50,13 +50,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 1505 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1505 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -104,7 +104,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -114,7 +114,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 @@ -122,7 +122,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double), _col2 (type: smallint) sort order: +++ @@ -131,7 +131,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -157,13 +157,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -224,7 +224,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -236,7 +236,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 13] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), count(_col1) Group By Vectorization: @@ -250,7 +250,7 @@ STAGE PLANS: keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -260,7 +260,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -288,11 +288,11 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), (_col1 / _col2) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -315,7 +315,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -341,13 +341,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -407,7 +407,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -418,7 +418,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -430,7 +430,7 @@ STAGE PLANS: keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -440,7 +440,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -467,13 +467,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -534,22 +534,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: ctinyint, cdouble - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT cdouble) keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Map Vectorization: enabled: true enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true @@ -566,7 +566,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -589,7 +589,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -615,13 +615,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -710,7 +710,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -720,7 +720,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(ctinyint) Group By Vectorization: @@ -734,7 +734,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -744,7 +744,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -772,7 +772,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -795,7 +795,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -821,13 +821,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out b/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out index 2c4fa69..c0677bd 100644 --- a/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out +++ b/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out @@ -18,7 +18,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -30,7 +30,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13] selectExpressions: FuncAbsLongToLong(col 0:tinyint) -> 13:int - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) Group By Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_not.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_not.q.out b/ql/src/test/results/clientpositive/vectorization_not.q.out index cf92a6f..5d9a1ef 100644 --- a/ql/src/test/results/clientpositive/vectorization_not.q.out +++ b/ql/src/test/results/clientpositive/vectorization_not.q.out @@ -55,4 +55,4 @@ WHERE (((cstring2 LIKE '%b%') POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### --3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64 +-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593987E9 3.875716535945533E8 0.0 2.06347151720204262E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.051733737257113E9 -2.06347151720204262E18 1.5020929380914048E17 -64 64 http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out index 0bdbd97..18d236c 100644 --- a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out @@ -17,21 +17,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 Offset of rows: 3 - Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -84,7 +84,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -93,7 +93,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 @@ -101,7 +101,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ @@ -110,7 +110,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: smallint) Execution mode: vectorized @@ -131,14 +131,14 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Offset of rows: 10 - Statistics: Num rows: 3 Data size: 645 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 708 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 645 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 708 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorization_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out index d8a5b08..6216581 100644 --- a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out @@ -18,14 +18,14 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(cbigint), count(cbigint) mode: hash http://git-wip-us.apache.org/repos/asf/hive/blob/76148bb6/ql/src/test/results/clientpositive/vectorized_case.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorized_case.q.out b/ql/src/test/results/clientpositive/vectorized_case.q.out index 31dcd37..d4cb176 100644 --- a/ql/src/test/results/clientpositive/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/vectorized_case.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -58,7 +58,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:smallint, val 418), FilterLongColEqualLongScalar(col 1:smallint, val 12205), FilterLongColEqualLongScalar(col 1:smallint, val 10583)) predicate: ((csmallint = 10583S) or (csmallint = 12205S) or (csmallint = 418S)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -67,13 +67,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 17, 21] selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 16:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprStringScalarStringScalar(col 15:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean) -> 16:string) -> 17:string, IfExprColumnCondExpr(col 15:boolean, col 18:stringcol 20:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 15:boolean, ConstantVectorExpression(val a) -> 18:string, IfExprStringScalarStringScalar(col 19:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 19:boolean) -> 20:string) -> 21:string - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -193,7 +193,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -203,7 +203,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:smallint, val 418), FilterLongColEqualLongScalar(col 1:smallint, val 12205), FilterLongColEqualLongScalar(col 1:smallint, val 10583)) predicate: ((csmallint = 10583S) or (csmallint = 12205S) or (csmallint = 418S)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN (null) ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -212,13 +212,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 18, 24] selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 17:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprColumnNull(col 15:boolean, col 16:string, null)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean, ConstantVectorExpression(val b) -> 16:string) -> 17:string) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 23:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 19:boolean, ConstantVectorExpression(val a) -> 20:string, IfExprNullColumn(col 21:boolean, null, col 22)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 21:boolean, ConstantVectorExpression(val c) -> 22:string) -> 23:string) -> 24:string - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -272,7 +272,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -284,7 +284,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 14] selectExpressions: IfExprLongScalarLongScalar(col 14:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongScalarLongScalar(col 15:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), sum(_col1) Group By Vectorization: @@ -387,7 +387,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -399,7 +399,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 14] selectExpressions: IfExprLongColumnLongScalar(col 14:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongColumnLongScalar(col 15:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), sum(_col1) Group By Vectorization:
