Repository: hive Updated Branches: refs/heads/master 527d13b08 -> 20b84523d
http://git-wip-us.apache.org/repos/asf/hive/blob/20b84523/ql/src/test/results/clientpositive/spark/vectorization_12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out index 4e26314..813bf7d 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out @@ -92,7 +92,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10, col 11) -> boolean, FilterLongColNotEqualLongColumn(col 0, col 1)(children: col 0) -> boolean) -> boolean, FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean, FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11, val 1) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 1)(children: col 1) -> boolean) -> boolean) -> boolean) -> boolean predicate: (ctimestamp1 is null and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint))))) (type: boolean) - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double), cstring1 (type: string), cboolean1 (type: boolean) outputColumnNames: cbigint, cdouble, cstring1, cboolean1 @@ -100,7 +100,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3, 5, 6, 10] - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cbigint), stddev_samp(cbigint), avg(cdouble), sum(cbigint), stddev_pop(cdouble) Group By Vectorization: @@ -115,7 +115,7 @@ STAGE PLANS: keys: cdouble (type: double), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 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: ++++ @@ -126,7 +126,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [4, 5, 6, 7, 8] - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,input:double>), _col7 (type: bigint), _col8 (type: struct<count:bigint,sum:double,variance:double>) Execution mode: vectorized Map Vectorization: @@ -172,7 +172,7 @@ 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 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0 * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), _col5 (type: double), ((-6432.0 * _col0) / -6432.0) (type: double), (- ((-6432.0 * _col0) / -6432.0)) (type: double), _col6 (type: double), (- (-6432.0 * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col7 (type: bigint), (_col6 / (-6432.0 * _col0)) (type: double), (- (- ((-6432.0 * _col0) / -6432.0))) (type: double), (((-6432.0 * _col0) / -6432.0) + (- (-6432.0 * _col0))) (type: double), _col8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 @@ -181,7 +181,7 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 3, 2, 0, 9, 10, 4, 11, 5, 13, 12, 6, 15, 17, 7, 18, 19, 14, 8] selectExpressions: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 9:double, LongColUnaryMinus(col 1) -> 10:long, LongColMultiplyLongColumn(col 1, col 4) -> 11:long, DoubleColDivideDoubleScalar(col 12, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 12:double) -> 13:double, DoubleColUnaryMinus(col 14)(children: DoubleColDivideDoubleScalar(col 12, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 12:double) -> 14:double) -> 12:double, DoubleColUnaryMinus(col 14)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 15:double, DecimalScalarAddDecimalColumn(val -5638.15, col 16)(children: CastLongToDecimal(col 1) -> 16:decimal(19,0)) -> 17:decimal(22,2), DoubleColDivideDoubleColumn(col 6, col 14)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 18:double, DoubleColUnaryMinus(col 14)(children: DoubleColUnaryMinus(col 19)(children: DoubleColDi videDoubleScalar(col 14, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 19:double) -> 14:double) -> 19:double, DoubleColAddDoubleColumn(col 20, col 21)(children: DoubleColDivideDoubleScalar(col 14, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 20:double, DoubleColUnaryMinus(col 14)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 21:double) -> 14:double - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string) sort order: +++ @@ -191,7 +191,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [3, 9, 10, 4, 11, 5, 13, 12, 6, 15, 17, 7, 18, 19, 14, 8] - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) Reducer 3 Execution mode: vectorized @@ -218,13 +218,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 3, 2, 19, 0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 11, 16, 17, 18] selectExpressions: ConstantVectorExpression(val null) -> 19:timestamp - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 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/20b84523/ql/src/test/results/clientpositive/spark/vectorization_17.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_17.q.out b/ql/src/test/results/clientpositive/spark/vectorization_17.q.out index b43c506..e85c2ba 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_17.q.out @@ -75,7 +75,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3, val -23) -> boolean, FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5, val 988888.0) -> boolean, FilterDecimalColGreaterDecimalScalar(col 12, val -863.257)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0, val 33) -> boolean, FilterLongColGreaterEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterDoubleColEqualDoubleColumn(col 4, col 5)(children: col 4) -> boolean) -> boolean) -> boolean predicate: ((cbigint > -23) and ((cdouble <> 988888.0) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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)), (2563.58 + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -84,7 +84,7 @@ STAGE PLANS: native: true projectedOutputColumns: [4, 6, 2, 8, 5, 3, 14, 15, 13, 16, 18, 19, 21, 17] selectExpressions: DoubleColDivideDoubleColumn(col 4, col 13)(children: col 4, CastLongToDouble(col 0) -> 13:double) -> 14:double, LongColModuloLongColumn(col 2, col 3)(children: col 2) -> 15:long, DoubleColUnaryMinus(col 5) -> 13:double, DoubleColAddDoubleColumn(col 5, col 17)(children: DoubleColDivideDoubleColumn(col 4, col 16)(children: col 4, CastLongToDouble(col 0) -> 16:double) -> 17:double) -> 16:double, DoubleColDivideDoubleColumn(col 5, col 17)(children: CastLongToDouble(col 2) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 19:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 20)(children: CastLongToDecimal(col 3) -> 20:decimal(19,0)) -> 21:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 22)(children: DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 22:double) -> 17:double - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -94,7 +94,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [6, 2, 8, 5, 14, 15, 13, 16, 18, 19, 21, 17] - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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: @@ -134,13 +134,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2, 3, 4, 5, 0, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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/20b84523/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 d2d9bf6..791414f 100644 --- a/ql/src/test/results/clientpositive/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/vectorization_10.q.out @@ -70,7 +70,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7, val 10) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterDecimalScalarGreaterEqualDecimalColumn(val -5638.15, col 13)(children: CastLongToDecimal(col 0) -> 13:decimal(6,2)) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5, val 6981.0) -> boolean, FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 14, val 9763215.5639)(children: CastLongToDecimal(col 1) -> 14:decimal(11,4)) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (-5638.15 >= CAST( ctinyint AS decimal(6,2)))) or ((cdouble > 6981.0) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 2054789 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)) % 33.0) (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), (9763215.5639 - (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 projectedOutputColumns: [5, 8, 0, 10, 6, 12, 16, 15, 17, 19, 20, 18, 22, 23, 25] selectExpressions: DoubleColUnaryMinus(col 5) -> 12:double, DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 16:double, DoubleColModuloDoubleScalar(col 17, val 33.0)(children: DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 17:double) -> 15:double, DoubleColUnaryMinus(col 5) -> 17:double, DoubleColModuloDoubleColumn(col 18, col 5)(children: CastLongToDouble(col 0) -> 18:double) -> 19:double, LongColModuloLongColumn(col 0, col 1)(children: col 0) -> 20:long, DoubleColUnaryMinus(col 5) -> 18:double, LongColMultiplyLongColumn(col 3, col 21)(children: col 21) -> 22:long, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 24)(children: DoubleColAddDoubleColumn(col 5, col 23)(children: CastLongToDouble(col 1) -> 23:double) -> 24:double) -> 23:double, DoubleColUnaryMinus(col 24)(children: DoubleColUnaryMinus(col 5) -> 24:double) -> 25:double - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 2054789 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/20b84523/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 63ea984..2f08aaa 100644 --- a/ql/src/test/results/clientpositive/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/vectorization_12.q.out @@ -87,7 +87,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10, col 11) -> boolean, FilterLongColNotEqualLongColumn(col 0, col 1)(children: col 0) -> boolean) -> boolean, FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean, FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11, val 1) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 1)(children: col 1) -> boolean) -> boolean) -> boolean) -> boolean predicate: (ctimestamp1 is null and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint))))) (type: boolean) - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double), cstring1 (type: string), cboolean1 (type: boolean) outputColumnNames: cbigint, cdouble, cstring1, cboolean1 @@ -95,7 +95,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3, 5, 6, 10] - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cbigint), stddev_samp(cbigint), avg(cdouble), sum(cbigint), stddev_pop(cdouble) Group By Vectorization: @@ -110,7 +110,7 @@ STAGE PLANS: keys: cdouble (type: double), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 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: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,input:double>), _col7 (type: bigint), _col8 (type: struct<count:bigint,sum:double,variance:double>) Execution mode: vectorized Map Vectorization: @@ -152,11 +152,11 @@ 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 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0 * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), _col5 (type: double), ((-6432.0 * _col0) / -6432.0) (type: double), (- ((-6432.0 * _col0) / -6432.0)) (type: double), _col6 (type: double), (- (-6432.0 * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col7 (type: bigint), (_col6 / (-6432.0 * _col0)) (type: double), (- (- ((-6432.0 * _col0) / -6432.0))) (type: double), (((-6432.0 * _col0) / -6432.0) + (- (-6432.0 * _col0))) (type: double), _col8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -179,7 +179,7 @@ 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: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) Execution mode: vectorized Map Vectorization: @@ -203,10 +203,10 @@ 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: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1877 Data size: 403561 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/20b84523/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 c018608..d60c28a 100644 --- a/ql/src/test/results/clientpositive/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/vectorization_17.q.out @@ -70,7 +70,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3, val -23) -> boolean, FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5, val 988888.0) -> boolean, FilterDecimalColGreaterDecimalScalar(col 12, val -863.257)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0, val 33) -> boolean, FilterLongColGreaterEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterDoubleColEqualDoubleColumn(col 4, col 5)(children: col 4) -> boolean) -> boolean) -> boolean predicate: ((cbigint > -23) and ((cdouble <> 988888.0) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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)), (2563.58 + (- (- 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 projectedOutputColumns: [4, 6, 2, 8, 5, 3, 14, 15, 13, 16, 18, 19, 21, 17] selectExpressions: DoubleColDivideDoubleColumn(col 4, col 13)(children: col 4, CastLongToDouble(col 0) -> 13:double) -> 14:double, LongColModuloLongColumn(col 2, col 3)(children: col 2) -> 15:long, DoubleColUnaryMinus(col 5) -> 13:double, DoubleColAddDoubleColumn(col 5, col 17)(children: DoubleColDivideDoubleColumn(col 4, col 16)(children: col 4, CastLongToDouble(col 0) -> 16:double) -> 17:double) -> 16:double, DoubleColDivideDoubleColumn(col 5, col 17)(children: CastLongToDouble(col 2) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 19:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 20)(children: CastLongToDecimal(col 3) -> 20:decimal(19,0)) -> 21:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 22)(children: DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 22:double) -> 17:double - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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: @@ -113,10 +113,10 @@ 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: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 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/20b84523/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 218d307..afa9891 100644 --- a/ql/src/test/results/clientpositive/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/vectorization_7.q.out @@ -76,7 +76,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 0, col 2)(children: col 0) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarLessDoubleColumn(val 988888.0, col 5) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val -15.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 3569.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 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 projectedOutputColumns: [10, 3, 1, 0, 8, 6, 13, 14, 15, 16, 18, 19, 17, 20, 22] selectExpressions: LongColAddLongColumn(col 3, col 3) -> 13:long, LongColModuloLongScalar(col 1, val -257)(children: col 1) -> 14:long, LongColUnaryMinus(col 1) -> 15:long, LongColUnaryMinus(col 0) -> 16:long, LongColAddLongScalar(col 17, val 17)(children: col 17) -> 18:long, LongColMultiplyLongColumn(col 3, col 17)(children: col 17) -> 19:long, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 17:long, LongColUnaryMinus(col 0) -> 20:long, LongColModuloLongColumn(col 21, col 0)(children: LongColUnaryMinus(col 0) -> 21:long) -> 22:long - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 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: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -119,7 +119,7 @@ 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: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE @@ -296,7 +296,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 0, col 2)(children: col 0) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarLessDoubleColumn(val 988888.0, col 5) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val 7.6850000000000005)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 3569.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 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 projectedOutputColumns: [10, 3, 1, 0, 8, 6, 13, 14, 15, 16, 18, 19, 17, 20, 22] selectExpressions: LongColAddLongColumn(col 3, col 3) -> 13:long, LongColModuloLongScalar(col 1, val -257)(children: col 1) -> 14:long, LongColUnaryMinus(col 1) -> 15:long, LongColUnaryMinus(col 0) -> 16:long, LongColAddLongScalar(col 17, val 17)(children: col 17) -> 18:long, LongColMultiplyLongColumn(col 3, col 17)(children: col 17) -> 19:long, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 17:long, LongColUnaryMinus(col 0) -> 20:long, LongColModuloLongColumn(col 21, col 0)(children: LongColUnaryMinus(col 0) -> 21:long) -> 22:long - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 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: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -333,7 +333,7 @@ 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: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
