http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out index 504dfa7..e6a0b5c 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out @@ -26,7 +26,7 @@ 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 @@ -37,7 +37,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 14, 0, 15, 3, 16, 5, 13] selectExpressions: DoubleColDivideDoubleScalar(col 13:double, val 0.0)(children: CastLongToDouble(col 2:int) -> 13:double) -> 14:double, DoubleColDivideDoubleScalar(col 13:double, val 0.0)(children: CastLongToDouble(col 0:tinyint) -> 13:double) -> 15:double, DoubleColDivideDoubleScalar(col 13:double, val 0.0)(children: CastLongToDouble(col 3:bigint) -> 13:double) -> 16:double, DoubleColDivideDoubleScalar(col 5:double, val 0.0) -> 13:double - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: tinyint), _col4 (type: bigint), _col6 (type: double) sort order: ++++ @@ -45,7 +45,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double), _col3 (type: double), _col5 (type: double), _col7 (type: double) Execution mode: vectorized @@ -74,19 +74,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 4, 1, 5, 2, 6, 3, 7] - 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: 100 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -237,7 +237,7 @@ 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 @@ -246,7 +246,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000)) predicate: ((cbigint < 100000000L) and (cbigint > 0L)) (type: boolean) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / CAST( (cbigint - 988888) AS decimal(19,0))) (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 @@ -255,7 +255,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 18] selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double, DecimalScalarDivideDecimalColumn(val 1.2, col 17:decimal(19,0))(children: CastLongToDecimal(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 17:decimal(19,0)) -> 18:decimal(22,21) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: decimal(22,21)) sort order: +++ @@ -263,7 +263,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -291,19 +291,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - 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: 100 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -454,7 +454,7 @@ 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 @@ -463,7 +463,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0)) predicate: ((cdouble < -199.0D) and (cdouble >= -500.0D)) (type: boolean) - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -472,7 +472,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 17, 18, 15, 19] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 17:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 18:double, DoubleScalarDivideDoubleColumn(val 3.0, col 14:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double) -> 15:double, DoubleScalarDivideDoubleColumn(val 1.2, col 14:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double) -> 19:double - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double) sort order: ++++++ @@ -480,7 +480,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -508,19 +508,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 1, 4, 5] - 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: 100 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -671,7 +671,7 @@ 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 @@ -680,7 +680,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 2:int, val 500000000), FilterDoubleColGreaterDoubleScalar(col 5:double, val 1.0E9), FilterLongColEqualLongScalar(col 0:tinyint, val 0)) predicate: ((cdouble > 1.0E9D) or (cint > 500000000) or (ctinyint = 0Y)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), ctinyint (type: tinyint), (UDFToDouble(cint) / UDFToDouble((cint - 528534767))) (type: double), (UDFToDouble(cbigint) / UDFToDouble((cbigint - 1018195815L))) (type: double), (UDFToDouble(ctinyint) / UDFToDouble(ctinyint)) (type: double), (cint % (cint - 528534767)) (type: int), (cbigint % (cbigint - 1018195815L)) (type: bigint), (ctinyint % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -689,7 +689,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 3, 0, 16, 17, 18, 19, 20, 14] selectExpressions: DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 2:int) -> 13:double, CastLongToDouble(col 14:int)(children: LongColSubtractLongScalar(col 2:int, val 528534767) -> 14:int) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 13:double, CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 1018195815) -> 14:bigint) -> 15:double) -> 17:double, DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 18:double, LongColModuloLongColumn(col 2:int, col 14:int)(children: LongColSubtractLongScalar(col 2:int, val 528534767) -> 14:int) -> 19:int, LongColModuloLongColumn(col 3:bigint, col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 1018195815) -> 14:bigint) -> 20:bigint, LongCol ModuloLongColumn(col 0:tinyint, col 0:tinyint) -> 14:tinyint - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: tinyint), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: int), _col7 (type: bigint), _col8 (type: tinyint) sort order: +++++++++ @@ -697,7 +697,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -725,19 +725,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8] - 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: 100 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 23600 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/spark/vectorization_nested_udf.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out b/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out index c46fc03..7f81581 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out @@ -23,7 +23,7 @@ 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>] @@ -35,7 +35,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13] selectExpressions: FuncAbsLongToLong(col 0:tinyint) -> 13:int - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) Group By Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_not.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_not.q.out b/ql/src/test/results/clientpositive/spark/vectorization_not.q.out index cf92a6f..5d9a1ef 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_not.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_not.q.out @@ -55,4 +55,4 @@ WHERE (((cstring2 LIKE '%b%') POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### --3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64 +-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593987E9 3.875716535945533E8 0.0 2.06347151720204262E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.051733737257113E9 -2.06347151720204262E18 1.5020929380914048E17 -64 64 http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out index 0cf6955..9001a2a 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out @@ -23,14 +23,14 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(cbigint), count(cbigint) mode: hash
