http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_varchar_simple.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out index 0a144d2..b880838 100644 --- a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out +++ b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out @@ -285,7 +285,7 @@ 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 Select Operator @@ -295,13 +295,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - 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: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -309,7 +309,7 @@ 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: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int) Execution mode: vectorized @@ -330,17 +330,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS varchar(25)) (type: varchar(25)) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_1.q.out b/ql/src/test/results/clientpositive/vectorization_1.q.out index bb8e483..767db3c 100644 --- a/ql/src/test/results/clientpositive/vectorization_1.q.out +++ b/ql/src/test/results/clientpositive/vectorization_1.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: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0)), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColLessLongScalar(col 10:boolean, val 0)) predicate: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (UDFToLong(cint) > cbigint) or (cbigint < UDFToLong(ctinyint)) or (cboolean1 < 0)) (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), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -73,7 +73,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 4, 2, 5, 13, 16, 14] selectExpressions: CastLongToDouble(col 0:tinyint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14: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(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2) Group By Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_10.q.out b/ql/src/test/results/clientpositive/vectorization_10.q.out index 2c35fd9..57a6fe9 100644 --- a/ql/src/test/results/clientpositive/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/vectorization_10.q.out @@ -60,7 +60,7 @@ 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>] @@ -70,7 +70,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a)))) predicate: (((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a'))) or (cstring2 <= '10')) (type: boolean) - Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -79,13 +79,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 8, 0, 10, 6, 13, 17, 16, 18, 20, 21, 19, 23, 24, 26] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 18:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 18:double) -> 16:double, DoubleColUnaryMinus(col 5:double) -> 18:double, DoubleColModuloDoubleColumn(col 19:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 21:smallint, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColMultiplyLongColumn(col 3:bigint, col 22:bigint)(children: col 22:smallint) -> 23:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 25:double)(children: DoubleColAddDoubleColumn(col 5:double, col 24:double)(children: CastLongToDouble(col 1:smal lint) -> 24:double) -> 25:double) -> 24:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 5:double) -> 25:double) -> 26:double - Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 2261694 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_11.q.out b/ql/src/test/results/clientpositive/vectorization_11.q.out index b378343..5792d0d 100644 --- a/ql/src/test/results/clientpositive/vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/vectorization_11.q.out @@ -42,7 +42,7 @@ 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>] @@ -52,7 +52,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string), FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a))) predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (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: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -61,13 +61,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 16] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 16:double - 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 File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - 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 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_12.q.out b/ql/src/test/results/clientpositive/vectorization_12.q.out index e129730..39c3476 100644 --- a/ql/src/test/results/clientpositive/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/vectorization_12.q.out @@ -77,7 +77,7 @@ 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>] @@ -87,7 +87,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint)))) predicate: (((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ctimestamp1 is null) (type: boolean) - Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -96,7 +96,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 14] selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double - Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6) Group By Vectorization: @@ -110,7 +110,7 @@ STAGE PLANS: keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) sort order: ++++ @@ -120,7 +120,7 @@ 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: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double) Execution mode: vectorized Map Vectorization: @@ -148,11 +148,11 @@ STAGE PLANS: 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, _col9, _col10 - Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -175,7 +175,7 @@ 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: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 444197 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) Execution mode: vectorized Map Vectorization: @@ -201,10 +201,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 444197 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out index 96eda74..1cf64a3 100644 --- a/ql/src/test/results/clientpositive/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/vectorization_13.q.out @@ -79,7 +79,7 @@ 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>] @@ -89,7 +89,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val 11.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 12.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4)))) predicate: (((UDFToDouble(ctimestamp1) > 11.0D) and (UDFToDouble(ctimestamp2) <> 12.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean) - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -98,7 +98,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -112,7 +112,7 @@ STAGE PLANS: keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 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) sort order: +++++ @@ -122,7 +122,7 @@ 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: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -150,11 +150,11 @@ STAGE PLANS: 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, _col11, _col12, _col13, _col14 - 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: _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), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -177,7 +177,7 @@ 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: 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: @@ -203,13 +203,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 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: 40 - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -410,7 +410,7 @@ 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 @@ -419,7 +419,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -1.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -1.3359999999999999)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4)))) predicate: (((UDFToDouble(ctimestamp1) > -1.388D) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean) - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -428,7 +428,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -442,7 +442,7 @@ STAGE PLANS: keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 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) sort order: +++++ @@ -452,7 +452,7 @@ 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: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -474,11 +474,11 @@ STAGE PLANS: 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, _col11, _col12, _col13, _col14 - 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: _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), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -500,7 +500,7 @@ 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: 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: @@ -520,13 +520,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 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: 40 - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 9440 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_14.q.out b/ql/src/test/results/clientpositive/vectorization_14.q.out index 7a7a817..9dbc20c 100644 --- a/ql/src/test/results/clientpositive/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/vectorization_14.q.out @@ -79,7 +79,7 @@ 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>] @@ -89,7 +89,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 13:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp)), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float))) predicate: (((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and (UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint))) (type: boolean) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -98,7 +98,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 4, 6, 10, 5, 14, 13, 4, 15] selectExpressions: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 15:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 16:double) -> 13:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 15:double - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) Group By Vectorization: @@ -112,7 +112,7 @@ STAGE PLANS: keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -122,7 +122,7 @@ 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: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -150,11 +150,11 @@ STAGE PLANS: 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, _col11 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _ col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (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 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -177,7 +177,7 @@ 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: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 71705 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) Execution mode: vectorized Map Vectorization: @@ -203,10 +203,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 71705 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_15.q.out b/ql/src/test/results/clientpositive/vectorization_15.q.out index dbef3e7..589b8f5 100644 --- a/ql/src/test/results/clientpositive/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/vectorization_15.q.out @@ -75,7 +75,7 @@ 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>] @@ -85,7 +85,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0))) predicate: (((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D)) or (cstring1 like '10%') or (cstring2 like '%ss%')) (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: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -94,7 +94,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 15, 19] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 18:double) -> 19: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(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5) Group By Vectorization: @@ -108,7 +108,7 @@ STAGE PLANS: keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - 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: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ @@ -118,7 +118,7 @@ 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: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -145,11 +145,11 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - 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: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), pow er(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 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: @@ -172,7 +172,7 @@ 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 value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) Execution mode: vectorized Map Vectorization: @@ -197,10 +197,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 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 - 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 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_16.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out index 571eae0..18120f2 100644 --- a/ql/src/test/results/clientpositive/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/vectorization_16.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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_17.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_17.q.out b/ql/src/test/results/clientpositive/vectorization_17.q.out index 3f9b947..6c9212f 100644 --- a/ql/src/test/results/clientpositive/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/vectorization_17.q.out @@ -60,7 +60,7 @@ 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>] @@ -70,7 +70,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float))) predicate: (((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and (cbigint > -23L)) (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: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -79,7 +79,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 14, 17, 19, 20, 22, 18] selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 14:double, DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 17:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double) -> 17:double, DoubleColDivideDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 20:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 21:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 23:double)(children: DoubleColUna ryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 23:double) -> 18: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 Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -88,7 +88,7 @@ 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: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -114,10 +114,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - 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 File Output Operator compressed: 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 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/95d6d9b3/ql/src/test/results/clientpositive/vectorization_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_2.q.out b/ql/src/test/results/clientpositive/vectorization_2.q.out index e3d6ad0..05f22bb 100644 --- a/ql/src/test/results/clientpositive/vectorization_2.q.out +++ b/ql/src/test/results/clientpositive/vectorization_2.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: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375)), FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 13:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterLongColLessLongScalar(col 2:int, val 359)))) predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -77,7 +77,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 4, 3, 0, 5, 13, 16] selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4) Group By Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_3.q.out b/ql/src/test/results/clientpositive/vectorization_3.q.out index bb6c014..b5ee0fb 100644 --- a/ql/src/test/results/clientpositive/vectorization_3.q.out +++ b/ql/src/test/results/clientpositive/vectorization_3.q.out @@ -63,7 +63,7 @@ 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>] @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 13:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 13:double), FilterDecimalColGreaterEqualDecimalScalar(col 15:decimal(8,3), val 79.553)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(8,3)), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp))) predicate: (((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2)) or ((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D))) (type: boolean) - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -82,7 +82,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 0, 4, 2, 13, 18, 16, 20, 4, 17, 19, 23] selectExpressions: CastLongToDouble(col 1:smallint) -> 13:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 16:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, CastLongToDouble(col 0:tinyint) -> 16:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 17:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 17:double, CastLongToDouble(col 2:int) -> 19:double, DoubleColMultiplyDoubleColumn(col 21:double, col 22:double)(children: CastLongToDouble(col 2:int) -> 21:double, CastLongToDouble(col 2:int) -> 22:double) -> 23:double - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10) Group By Vectorization:
