http://git-wip-us.apache.org/repos/asf/hive/blob/92fbe256/ql/src/test/results/clientpositive/llap/vector_udf1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_udf1.q.out b/ql/src/test/results/clientpositive/llap/vector_udf1.q.out index 0dd278e..16edaac 100644 --- a/ql/src/test/results/clientpositive/llap/vector_udf1.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_udf1.q.out @@ -30,20 +30,24 @@ POSTHOOK: Lineage: varchar_udf_1.d1 SIMPLE [] POSTHOOK: Lineage: varchar_udf_1.d2 SIMPLE [] POSTHOOK: Lineage: varchar_udf_1.d3 EXPRESSION [] POSTHOOK: Lineage: varchar_udf_1.d4 EXPRESSION [] -PREHOOK: query: explain -select +PREHOOK: query: explain vectorization detail +select concat(c1, c2), concat(c3, c4), concat(c1, c2) = concat(c3, c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain -select +POSTHOOK: query: explain vectorization detail +select concat(c1, c2), concat(c3, c4), concat(c1, c2) = concat(c3, c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -58,15 +62,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: concat(c1, c2) (type: string), concat(c3, c4) (type: varchar(30)), (concat(c1, c2) = UDFToString(concat(c3, c4))) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 13] + selectExpressions: StringGroupConcatColCol(col 0, col 1) -> 8:String_Family, StringGroupConcatColCol(col 2, col 3) -> 9:String_Family, StringGroupColEqualStringGroupColumn(col 10, col 12)(children: StringGroupConcatColCol(col 0, col 1) -> 10:String_Family, CastStringGroupToString(col 11)(children: StringGroupConcatColCol(col 2, col 3) -> 11:String_Family) -> 12:String) -> 13:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -74,6 +92,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [0, 1, 2, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -81,7 +113,7 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: select +PREHOOK: query: select concat(c1, c2), concat(c3, c4), concat(c1, c2) = concat(c3, c4) @@ -89,7 +121,7 @@ from varchar_udf_1 limit 1 PREHOOK: type: QUERY PREHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### -POSTHOOK: query: select +POSTHOOK: query: select concat(c1, c2), concat(c3, c4), concat(c1, c2) = concat(c3, c4) @@ -98,20 +130,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 238val_238 238val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select upper(c2), upper(c4), upper(c2) = upper(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select upper(c2), upper(c4), upper(c2) = upper(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -126,15 +162,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: upper(c2) (type: string), upper(c4) (type: varchar(20)), (upper(c2) = UDFToString(upper(c4))) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 13] + selectExpressions: StringUpper(col 1) -> 8:String, StringUpper(col 3) -> 9:String, StringGroupColEqualStringGroupColumn(col 10, col 12)(children: StringUpper(col 1) -> 10:String, CastStringGroupToString(col 11)(children: StringUpper(col 3) -> 11:String) -> 12:String) -> 13:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -142,6 +192,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -166,20 +230,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### VAL_238 VAL_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select lower(c2), lower(c4), lower(c2) = lower(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select lower(c2), lower(c4), lower(c2) = lower(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -194,15 +262,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: lower(c2) (type: string), lower(c4) (type: varchar(20)), (lower(c2) = UDFToString(lower(c4))) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 13] + selectExpressions: StringLower(col 1) -> 8:String, StringLower(col 3) -> 9:String, StringGroupColEqualStringGroupColumn(col 10, col 12)(children: StringLower(col 1) -> 10:String, CastStringGroupToString(col 11)(children: StringLower(col 3) -> 11:String) -> 12:String) -> 13:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -210,6 +292,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -234,20 +330,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### val_238 val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select ascii(c2), ascii(c4), ascii(c2) = ascii(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select ascii(c2), ascii(c4), ascii(c2) = ascii(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -262,15 +362,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: ascii(c2) (type: int), ascii(c4) (type: int), (ascii(c2) = ascii(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(ascii(c2)) -> 8:int, VectorUDFAdaptor(ascii(c4)) -> 9:int, LongColEqualLongColumn(col 10, col 11)(children: VectorUDFAdaptor(ascii(c2)) -> 10:int, VectorUDFAdaptor(ascii(c4)) -> 11:int) -> 12:long Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -278,6 +392,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: bigint, bigint, bigint, bigint, bigint Stage: Stage-0 Fetch Operator @@ -302,20 +430,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 118 118 true -PREHOOK: query: explain -select +PREHOOK: query: explain vectorization detail +select concat_ws('|', c1, c2), concat_ws('|', c3, c4), concat_ws('|', c1, c2) = concat_ws('|', c3, c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain -select +POSTHOOK: query: explain vectorization detail +select concat_ws('|', c1, c2), concat_ws('|', c3, c4), concat_ws('|', c1, c2) = concat_ws('|', c3, c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -330,15 +462,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: concat_ws('|', c1, c2) (type: string), concat_ws('|', c3, c4) (type: string), (concat_ws('|', c1, c2) = concat_ws('|', c3, c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(concat_ws('|', c1, c2)) -> 8:string, VectorUDFAdaptor(concat_ws('|', c3, c4)) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(concat_ws('|', c1, c2)) -> 10:string, VectorUDFAdaptor(concat_ws('|', c3, c4)) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -346,6 +492,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [0, 1, 2, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -353,7 +513,7 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: select +PREHOOK: query: select concat_ws('|', c1, c2), concat_ws('|', c3, c4), concat_ws('|', c1, c2) = concat_ws('|', c3, c4) @@ -361,7 +521,7 @@ from varchar_udf_1 limit 1 PREHOOK: type: QUERY PREHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### -POSTHOOK: query: select +POSTHOOK: query: select concat_ws('|', c1, c2), concat_ws('|', c3, c4), concat_ws('|', c1, c2) = concat_ws('|', c3, c4) @@ -370,20 +530,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 238|val_238 238|val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select decode(encode(c2, 'US-ASCII'), 'US-ASCII'), decode(encode(c4, 'US-ASCII'), 'US-ASCII'), decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select decode(encode(c2, 'US-ASCII'), 'US-ASCII'), decode(encode(c4, 'US-ASCII'), 'US-ASCII'), decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -398,15 +562,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: decode(encode(c2,'US-ASCII'),'US-ASCII') (type: string), decode(encode(c4,'US-ASCII'),'US-ASCII') (type: string), (decode(encode(c2,'US-ASCII'),'US-ASCII') = decode(encode(c4,'US-ASCII'),'US-ASCII')) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [9, 10, 13] + selectExpressions: VectorUDFAdaptor(decode(encode(c2,'US-ASCII'),'US-ASCII'))(children: VectorUDFAdaptor(encode(c2,'US-ASCII')) -> 8:binary) -> 9:string, VectorUDFAdaptor(decode(encode(c4,'US-ASCII'),'US-ASCII'))(children: VectorUDFAdaptor(encode(c4,'US-ASCII')) -> 8:binary) -> 10:string, StringGroupColEqualStringGroupColumn(col 11, col 12)(children: VectorUDFAdaptor(decode(encode(c2,'US-ASCII'),'US-ASCII'))(children: VectorUDFAdaptor(encode(c2,'US-ASCII')) -> 8:binary) -> 11:string, VectorUDFAdaptor(decode(encode(c4,'US-ASCII'),'US-ASCII'))(children: VectorUDFAdaptor(encode(c4,'US-ASCII')) -> 8:binary) -> 12:string) -> 13:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -414,6 +592,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -438,20 +630,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### val_238 val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select instr(c2, '_'), instr(c4, '_'), instr(c2, '_') = instr(c4, '_') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select instr(c2, '_'), instr(c4, '_'), instr(c2, '_') = instr(c4, '_') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -466,15 +662,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: instr(c2, '_') (type: int), instr(c4, '_') (type: int), (instr(c2, '_') = instr(c4, '_')) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(instr(c2, '_')) -> 8:int, VectorUDFAdaptor(instr(c4, '_')) -> 9:int, LongColEqualLongColumn(col 10, col 11)(children: VectorUDFAdaptor(instr(c2, '_')) -> 10:int, VectorUDFAdaptor(instr(c4, '_')) -> 11:int) -> 12:long Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -482,6 +692,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: bigint, bigint, bigint, bigint, bigint Stage: Stage-0 Fetch Operator @@ -506,20 +730,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 4 4 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select replace(c1, '_', c2), replace(c3, '_', c4), replace(c1, '_', c2) = replace(c3, '_', c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select replace(c1, '_', c2), replace(c3, '_', c4), replace(c1, '_', c2) = replace(c3, '_', c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -534,15 +762,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: replace(c1, '_', c2) (type: string), replace(c3, '_', c4) (type: string), (replace(c1, '_', c2) = replace(c3, '_', c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(replace(c1, '_', c2)) -> 8:string, VectorUDFAdaptor(replace(c3, '_', c4)) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(replace(c1, '_', c2)) -> 10:string, VectorUDFAdaptor(replace(c3, '_', c4)) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -550,6 +792,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [0, 1, 2, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -574,20 +830,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 238 238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select reverse(c2), reverse(c4), reverse(c2) = reverse(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select reverse(c2), reverse(c4), reverse(c2) = reverse(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -602,15 +862,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: reverse(c2) (type: string), reverse(c4) (type: string), (reverse(c2) = reverse(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(reverse(c2)) -> 8:string, VectorUDFAdaptor(reverse(c4)) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(reverse(c2)) -> 10:string, VectorUDFAdaptor(reverse(c4)) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -618,6 +892,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -642,20 +930,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 832_lav 832_lav true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select next_day(d1, 'TU'), next_day(d4, 'WE'), next_day(d1, 'TU') = next_day(d4, 'WE') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select next_day(d1, 'TU'), next_day(d4, 'WE'), next_day(d1, 'TU') = next_day(d4, 'WE') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -670,15 +962,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: next_day(d1, 'TU') (type: string), next_day(d4, 'WE') (type: string), (next_day(d1, 'TU') = next_day(d4, 'WE')) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(next_day(d1, 'TU')) -> 8:string, VectorUDFAdaptor(next_day(d4, 'WE')) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(next_day(d1, 'TU')) -> 10:string, VectorUDFAdaptor(next_day(d4, 'WE')) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -686,6 +992,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [4, 7] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -710,20 +1030,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 2015-01-20 2017-01-18 false -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select months_between(d1, d3), months_between(d2, d4), months_between(d1, d3) = months_between(d2, d4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select months_between(d1, d3), months_between(d2, d4), months_between(d1, d3) = months_between(d2, d4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -738,15 +1062,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: months_between(d1, d3) (type: double), months_between(d2, d4) (type: double), (months_between(d1, d3) = months_between(d2, d4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(months_between(d1, d3)) -> 8:double, VectorUDFAdaptor(months_between(d2, d4)) -> 9:double, DoubleColEqualDoubleColumn(col 10, col 11)(children: VectorUDFAdaptor(months_between(d1, d3)) -> 10:double, VectorUDFAdaptor(months_between(d2, d4)) -> 11:double) -> 12:long Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -754,6 +1092,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [4, 5, 6, 7] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: double, double, double, double, bigint Stage: Stage-0 Fetch Operator @@ -778,20 +1130,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### -23.90322581 -23.90322581 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select length(c2), length(c4), length(c2) = length(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select length(c2), length(c4), length(c2) = length(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -806,15 +1162,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: length(c2) (type: int), length(c4) (type: int), (length(c2) = length(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: StringLength(col 1) -> 8:Long, StringLength(col 3) -> 9:Long, LongColEqualLongColumn(col 10, col 11)(children: StringLength(col 1) -> 10:Long, StringLength(col 3) -> 11:Long) -> 12:long Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -822,6 +1192,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: bigint, bigint, bigint, bigint, bigint Stage: Stage-0 Fetch Operator @@ -846,20 +1230,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 7 7 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select locate('a', 'abcdabcd', 3), locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3), locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select locate('a', 'abcdabcd', 3), locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3), locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -874,15 +1262,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: 5 (type: int), 5 (type: int), true (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 10] + selectExpressions: ConstantVectorExpression(val 5) -> 8:long, ConstantVectorExpression(val 5) -> 9:long, ConstantVectorExpression(val 1) -> 10:long Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -890,6 +1292,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: bigint, bigint, bigint Stage: Stage-0 Fetch Operator @@ -914,20 +1330,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 5 5 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select lpad(c2, 15, ' '), lpad(c4, 15, ' '), lpad(c2, 15, ' ') = lpad(c4, 15, ' ') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select lpad(c2, 15, ' '), lpad(c4, 15, ' '), lpad(c2, 15, ' ') = lpad(c4, 15, ' ') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -942,15 +1362,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: lpad(c2, 15, ' ') (type: string), lpad(c4, 15, ' ') (type: string), (lpad(c2, 15, ' ') = lpad(c4, 15, ' ')) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(lpad(c2, 15, ' ')) -> 8:string, VectorUDFAdaptor(lpad(c4, 15, ' ')) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(lpad(c2, 15, ' ')) -> 10:string, VectorUDFAdaptor(lpad(c4, 15, ' ')) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -958,6 +1392,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -982,20 +1430,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### val_238 val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select ltrim(c2), ltrim(c4), ltrim(c2) = ltrim(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select ltrim(c2), ltrim(c4), ltrim(c2) = ltrim(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1010,15 +1462,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: ltrim(c2) (type: string), ltrim(c4) (type: string), (ltrim(c2) = ltrim(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: StringLTrim(col 1) -> 8:String, StringLTrim(col 3) -> 9:String, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: StringLTrim(col 1) -> 10:String, StringLTrim(col 3) -> 11:String) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1026,6 +1492,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -1050,20 +1530,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### val_238 val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select c2 regexp 'val', c4 regexp 'val', (c2 regexp 'val') = (c4 regexp 'val') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select c2 regexp 'val', c4 regexp 'val', (c2 regexp 'val') = (c4 regexp 'val') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1078,15 +1562,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: c2 regexp 'val' (type: boolean), c4 regexp 'val' (type: boolean), (c2 regexp 'val' = c4 regexp 'val') (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(c2 regexp 'val') -> 8:boolean, VectorUDFAdaptor(c4 regexp 'val') -> 9:boolean, LongColEqualLongColumn(col 10, col 11)(children: VectorUDFAdaptor(c2 regexp 'val') -> 10:boolean, VectorUDFAdaptor(c4 regexp 'val') -> 11:boolean) -> 12:long Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1094,6 +1592,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: bigint, bigint, bigint, bigint, bigint Stage: Stage-0 Fetch Operator @@ -1118,20 +1630,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### true true true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select regexp_extract(c2, 'val_([0-9]+)', 1), regexp_extract(c4, 'val_([0-9]+)', 1), regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select regexp_extract(c2, 'val_([0-9]+)', 1), regexp_extract(c4, 'val_([0-9]+)', 1), regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1146,15 +1662,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: regexp_extract(c2, 'val_([0-9]+)', 1) (type: string), regexp_extract(c4, 'val_([0-9]+)', 1) (type: string), (regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(regexp_extract(c2, 'val_([0-9]+)', 1)) -> 8:string, VectorUDFAdaptor(regexp_extract(c4, 'val_([0-9]+)', 1)) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(regexp_extract(c2, 'val_([0-9]+)', 1)) -> 10:string, VectorUDFAdaptor(regexp_extract(c4, 'val_([0-9]+)', 1)) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1162,6 +1692,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -1186,20 +1730,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 238 238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select regexp_replace(c2, 'val', 'replaced'), regexp_replace(c4, 'val', 'replaced'), regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select regexp_replace(c2, 'val', 'replaced'), regexp_replace(c4, 'val', 'replaced'), regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1214,15 +1762,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: regexp_replace(c2, 'val', 'replaced') (type: string), regexp_replace(c4, 'val', 'replaced') (type: string), (regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(regexp_replace(c2, 'val', 'replaced')) -> 8:string, VectorUDFAdaptor(regexp_replace(c4, 'val', 'replaced')) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(regexp_replace(c2, 'val', 'replaced')) -> 10:string, VectorUDFAdaptor(regexp_replace(c4, 'val', 'replaced')) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1230,6 +1792,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -1254,20 +1830,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### replaced_238 replaced_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select reverse(c2), reverse(c4), reverse(c2) = reverse(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select reverse(c2), reverse(c4), reverse(c2) = reverse(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1282,15 +1862,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: reverse(c2) (type: string), reverse(c4) (type: string), (reverse(c2) = reverse(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(reverse(c2)) -> 8:string, VectorUDFAdaptor(reverse(c4)) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(reverse(c2)) -> 10:string, VectorUDFAdaptor(reverse(c4)) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1298,6 +1892,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -1322,20 +1930,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### 832_lav 832_lav true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select rpad(c2, 15, ' '), rpad(c4, 15, ' '), rpad(c2, 15, ' ') = rpad(c4, 15, ' ') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select rpad(c2, 15, ' '), rpad(c4, 15, ' '), rpad(c2, 15, ' ') = rpad(c4, 15, ' ') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1350,15 +1962,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: rpad(c2, 15, ' ') (type: string), rpad(c4, 15, ' ') (type: string), (rpad(c2, 15, ' ') = rpad(c4, 15, ' ')) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: VectorUDFAdaptor(rpad(c2, 15, ' ')) -> 8:string, VectorUDFAdaptor(rpad(c4, 15, ' ')) -> 9:string, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: VectorUDFAdaptor(rpad(c2, 15, ' ')) -> 10:string, VectorUDFAdaptor(rpad(c4, 15, ' ')) -> 11:string) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1366,6 +1992,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -1390,20 +2030,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### val_238 val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select rtrim(c2), rtrim(c4), rtrim(c2) = rtrim(c4) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select rtrim(c2), rtrim(c4), rtrim(c2) = rtrim(c4) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1418,15 +2062,29 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: rtrim(c2) (type: string), rtrim(c4) (type: string), (rtrim(c2) = rtrim(c4)) (type: boolean) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9, 12] + selectExpressions: StringRTrim(col 1) -> 8:String, StringRTrim(col 3) -> 9:String, StringGroupColEqualStringGroupColumn(col 10, col 11)(children: StringRTrim(col 1) -> 10:String, StringRTrim(col 3) -> 11:String) -> 12:boolean Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1434,6 +2092,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: string, string, string, string, bigint Stage: Stage-0 Fetch Operator @@ -1458,18 +2130,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### val_238 val_238 true -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select sentences('See spot run. See jane run.'), sentences(cast('See spot run. See jane run.' as varchar(50))) from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select sentences('See spot run. See jane run.'), sentences(cast('See spot run. See jane run.' as varchar(50))) from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1484,22 +2160,50 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: sentences('See spot run. See jane run.') (type: array<array<string>>), sentences('See spot run. See jane run.') (type: array<array<string>>) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9] + selectExpressions: VectorUDFAdaptor(sentences('See spot run. See jane run.')) -> 8:array<array<string>>, VectorUDFAdaptor(sentences('See spot run. See jane run.')) -> 9:array<array<string>> Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: array<array<string>>, array<array<string>> Stage: Stage-0 Fetch Operator @@ -1522,18 +2226,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pattern was here #### [["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]] -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select split(c2, '_'), split(c4, '_') from varchar_udf_1 limit 1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select split(c2, '_'), split(c4, '_') from varchar_udf_1 limit 1 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -1548,22 +2256,50 @@ STAGE PLANS: TableScan alias: varchar_udf_1 Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7] Select Operator expressions: split(c2, '_') (type: array<string>), split(c4, '_') (type: array<string>) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [8, 9] + selectExpressions: VectorUDFAdaptor(split(c2, '_')) -> 8:array<string>, VectorUDFAdaptor(split(c4, '_')) -> 9:array<string> Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 732 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: llap + Execution mode: vectorized, llap LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: false + usesVectorUDFAdaptor: true + vectorized: true + rowBatchContext: + dataColumnCount: 8 + includeColumns: [1, 3] + dataColumns: c1:string, c2:string, c3:varchar(10), c4:varchar(20), d1:string, d2:string, d3:varchar(10), d4:varchar(10) + partitionColumnCount: 0 + scratchColumnTypeNames: array<string>, array<string> Stage: Stage-0 Fetch Operator @@ -1586,18 +2322,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@varchar_udf_1 #### A masked pat
<TRUNCATED>
