http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out index 8b73ef2..19bc439 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out @@ -34,7 +34,7 @@ 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>] @@ -45,7 +45,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(ctinyint), max(ctinyint), count(ctinyint), count() Group By Vectorization: @@ -213,7 +213,7 @@ 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>] @@ -224,7 +224,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(ctinyint) Group By Vectorization: @@ -401,11 +401,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) mode: hash @@ -540,7 +540,7 @@ 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>] @@ -551,7 +551,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - 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: min(cbigint), max(cbigint), count(cbigint), count() Group By Vectorization: @@ -719,7 +719,7 @@ 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>] @@ -730,7 +730,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - 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(cbigint) Group By Vectorization: @@ -907,11 +907,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) mode: hash @@ -1009,7 +1009,7 @@ ORDER BY c1 POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### --1.8515862077935246E8 2.07689300543070106E18 2.07689300543070106E18 2.07711944383076992E18 1.441142951074147E9 1.441142951074147E9 1.441142951074147E9 1.441221511021387E9 +-1.8515862077935246E8 2.07689300543082035E18 2.07689300543082035E18 2.07711944383088922E18 1.4411429510741882E9 1.4411429510741882E9 1.4411429510741882E9 1.4412215110214283E9 PREHOOK: query: EXPLAIN VECTORIZATION DETAIL SELECT MIN(cfloat) as c1, MAX(cfloat), @@ -1046,7 +1046,7 @@ 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>] @@ -1057,7 +1057,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [4] - 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: min(cfloat), max(cfloat), count(cfloat), count() Group By Vectorization: @@ -1225,7 +1225,7 @@ 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>] @@ -1236,7 +1236,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [4] - 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(cfloat) Group By Vectorization: @@ -1413,11 +1413,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) mode: hash @@ -1590,7 +1590,7 @@ 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>] @@ -1600,7 +1600,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterDecimalColNotEqualDecimalScalar(col 13:decimal(13,3), val 79.553)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)), FilterDoubleColLessDoubleColumn(col 14:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterLongColEqualLongScalar(col 11:boolean, val 1), FilterLongColEqualLongScalar(col 0:int, val 3569)(children: col 0:tinyint))) predicate: (((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (UDFToInteger(ctinyint) = 3569)) or (CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (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: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4 @@ -1609,7 +1609,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 0, 14, 17] selectExpressions: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 3:bigint) -> 15:double, CastLongToDouble(col 3:bigint) -> 16:double) -> 17:double - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col4), sum(_col3), count(), sum(_col1), min(_col2) Group By Vectorization: @@ -1759,7 +1759,7 @@ 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 PREHOOK: query: EXPLAIN extended select count(*) from alltypesorc where (((cstring1 LIKE 'a%') or ((cstring1 like 'b%') or (cstring1 like 'c%'))) or @@ -1785,14 +1785,14 @@ 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 GatherStats: false Filter Operator isSamplingPred: false predicate: (((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0)) or (cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%')) (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 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1826,11 +1826,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1848,11 +1848,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.alltypesorc @@ -30595,22 +30595,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (((cint = 45) and (cfloat = 3.02)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 49) and (cfloat = 3.5))) (type: boolean) - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - 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 GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - 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 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30648,11 +30648,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -30670,11 +30670,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.alltypesorc @@ -30711,22 +30711,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30763,11 +30763,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -30785,11 +30785,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.alltypesorc @@ -30826,22 +30826,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (((cint = 45) or (cfloat = 3.02)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 49) or (cfloat = 3.5))) (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), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30879,11 +30879,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -30901,11 +30901,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.alltypesorc @@ -30943,24 +30943,24 @@ 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 GatherStats: false Filter Operator isSamplingPred: false predicate: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) - 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 Group By Operator aggregations: count() keys: cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - 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 tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -30985,11 +30985,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -31007,11 +31007,11 @@ STAGE PLANS: name default.alltypesorc numFiles 1 numRows 12288 - rawDataSize 2641964 + rawDataSize 2907994 serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 377237 + totalSize 295616 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.alltypesorc @@ -31027,16 +31027,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -31047,13 +31047,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_1.q.out b/ql/src/test/results/clientpositive/spark/vectorization_1.q.out index 71625e0..5303fe4 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_1.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_1.q.out @@ -59,7 +59,7 @@ 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>] @@ -69,7 +69,7 @@ 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 @@ -78,7 +78,7 @@ 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/spark/vectorization_10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_10.q.out b/ql/src/test/results/clientpositive/spark/vectorization_10.q.out index 8ff6e48..a2e5786 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_10.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: 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 @@ -82,13 +82,13 @@ 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:smallint) -> 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/spark/vectorization_11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_11.q.out b/ql/src/test/results/clientpositive/spark/vectorization_11.q.out index ef029b2..dcf7c3e 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_11.q.out @@ -45,7 +45,7 @@ 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>] @@ -55,7 +55,7 @@ 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 @@ -64,13 +64,13 @@ 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/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 24cfa4e..1c302e1 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out @@ -82,7 +82,7 @@ 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>] @@ -92,7 +92,7 @@ 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 @@ -101,7 +101,7 @@ 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: @@ -115,7 +115,7 @@ 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: ++++ @@ -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 valueColumnNums: [4, 5, 6, 7, 8, 9, 10] - 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: @@ -173,7 +173,7 @@ 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, _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 @@ -182,7 +182,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3, 2, 0, 11, 12, 4, 13, 14, 19, 15, 20, 22, 24, 9, 26, 25, 21, 27] selectExpressions: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 11:double, LongColUnaryMinus(col 1:bigint) -> 12:bigint, LongColMultiplyLongColumn(col 1:bigint, col 4:bigint) -> 13:bigint, FuncPowerDoubleToDouble(col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 14:double) -> 15:double) -> 14:double, IfExprNullCondExpr(col 16:boolean, null, col 17:bigint)(children: LongColEqualLongScalar(col 4:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 4:bigint, val 1) -> 17:bigint) -> 18:bigint) -> 15:double) -> 14:double, DoubleColDivideDoubleScalar(col 15:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 15:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(ch ildren: DoubleColDivideDoubleScalar(col 15:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 15:double) -> 20:double) -> 15:double, DoubleColDivideLongColumn(col 7:double, col 8:bigint) -> 20:double, DoubleColUnaryMinus(col 21:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 22:double, DecimalScalarAddDecimalColumn(val -5638.15, col 23:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 23:decimal(19,0)) -> 24:decimal(22,2), DoubleColDivideDoubleColumn(col 21:double, col 25:double)(children: DoubleColDivideLongColumn(col 7:double, col 8:bigint) -> 21:double, DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 25:double) -> 26:double, DoubleColUnaryMinus(col 21:double)(children: DoubleColUnaryMinus(col 25:double)(children: DoubleColDivideDoubleScalar(col 21:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 25:double) -> 21:double) -> 25:double, DoubleColAddDoubleColumn(col 27:double, col 28:double)(children: DoubleColDivideDoubleScalar(col 21:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 27:double, DoubleColUnaryMinus(col 21:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 28:double) -> 21:double, FuncPowerDoubleToDouble(col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 8:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 8:bigint)(children: DoubleColMultiplyDoubleColumn(col 7:double, col 7:double) -> 27:double) -> 28:double) -> 27:double) -> 28:double) -> 27:double - 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 Reduce Output Operator key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string) sort order: +++ @@ -192,7 +192,7 @@ 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 valueColumnNums: [3, 11, 12, 4, 13, 14, 19, 15, 20, 22, 24, 9, 26, 25, 21, 27] - 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) Reducer 3 Execution mode: vectorized @@ -218,13 +218,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [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: 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 File Sink Vectorization: className: VectorFileSinkOperator native: 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/spark/vectorization_13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out index c2a8006..0f1b228 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out @@ -84,7 +84,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true 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>] @@ -94,7 +94,7 @@ 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 @@ -103,7 +103,7 @@ 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: @@ -117,7 +117,7 @@ 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: +++++ @@ -128,7 +128,7 @@ 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 valueColumnNums: [5, 6, 7, 8, 9, 10, 11, 12, 13, 14] - 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: @@ -175,7 +175,7 @@ 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 @@ -184,7 +184,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 15, 5, 17, 6, 20, 19, 21, 22, 23, 24, 27, 28, 25, 13, 31, 14] selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 19:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 6:double) -> 19:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 21:float, FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 22:double) -> 23:double) -> 22:double) -> 23:double) -> 22:double, DoubleColUnar yMinus(col 6:double) -> 23:double, FuncPowerDoubleToDouble(col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 24:double) -> 25:double) -> 24:double) -> 25:double) -> 24:double, DecimalColSubtractDecimalScalar(col 26:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 26:decimal(3,0)) -> 27:decimal(7,3), DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 28:double, DoubleScalarDivideDoubleColumn(val -26.28, col 29:double)(children: DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 29:double) -> 25:double, D oubleColDivideDoubleColumn(col 30:double, col 29:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 29:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 29:double) -> 30:double, CastLongToDouble(col 1:tinyint) -> 29:double) -> 31: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: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -194,7 +194,7 @@ 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 valueColumnNums: [] - 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 Reducer 3 Execution mode: vectorized @@ -219,19 +219,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - 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 Limit Vectorization: className: VectorLimitOperator native: true - 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 File Sink Vectorization: className: VectorFileSinkOperator native: 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 @@ -437,7 +437,7 @@ 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 @@ -446,7 +446,7 @@ 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 @@ -455,7 +455,7 @@ 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: @@ -469,7 +469,7 @@ 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: +++++ @@ -478,7 +478,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator 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: 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: @@ -512,7 +512,7 @@ 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 @@ -521,7 +521,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 15, 5, 17, 6, 20, 19, 21, 22, 23, 24, 27, 28, 25, 13, 31, 14] selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 19:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 6:double) -> 19:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 21:float, FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 22:double) -> 23:double) -> 22:double) -> 23:double) -> 22:double, DoubleColUnar yMinus(col 6:double) -> 23:double, FuncPowerDoubleToDouble(col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 24:double) -> 25:double) -> 24:double) -> 25:double) -> 24:double, DecimalColSubtractDecimalScalar(col 26:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 26:decimal(3,0)) -> 27:decimal(7,3), DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 28:double, DoubleScalarDivideDoubleColumn(val -26.28, col 29:double)(children: DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 29:double) -> 25:double, D oubleColDivideDoubleColumn(col 30:double, col 29:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 29:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 29:double) -> 30:double, CastLongToDouble(col 1:tinyint) -> 29:double) -> 31: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: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -529,7 +529,7 @@ 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 Reducer 3 Execution mode: vectorized @@ -547,19 +547,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - 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 Limit Vectorization: className: VectorLimitOperator native: true - 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 File Sink Vectorization: className: VectorFileSinkOperator native: 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
