Repository: hive Updated Branches: refs/heads/master 6a282657c -> cc38bcc5a
http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/llap/vector_windowing_order_null.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_order_null.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_order_null.q.out index 91b52e7..7b6fa66 100644 --- a/ql/src/test/results/clientpositive/llap/vector_windowing_order_null.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_windowing_order_null.q.out @@ -113,16 +113,28 @@ STAGE PLANS: partitionColumnCount: 0 scratchColumnTypeNames: [] Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aza + reduceColumnSortOrder: +++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: KEY.reducesinkkey0:int, KEY.reducesinkkey1:string, KEY.reducesinkkey2:bigint + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: bigint), KEY.reducesinkkey1 (type: string) outputColumnNames: _col2, _col3, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 2, 1] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -143,16 +155,39 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorStreamingLongSum] + functionInputExpressions: [col 2:bigint] + functionNames: [sum] + keyInputColumns: [0, 2, 1] + native: true + nonKeyInputColumns: [] + orderExpressions: [col 1:string, col 2:bigint] + outputColumns: [3, 0, 2, 1] + outputTypes: [bigint, int, bigint, string] + partitionExpressions: [col 0:int] + streamingColumns: [3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col7 (type: string), _col3 (type: bigint), sum_window_0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -245,16 +280,28 @@ STAGE PLANS: partitionColumnCount: 0 scratchColumnTypeNames: [] Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aaa + reduceColumnSortOrder: ++- + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: KEY.reducesinkkey0:double, KEY.reducesinkkey1:string, KEY.reducesinkkey2:float + partitionColumnCount: 0 + scratchColumnTypeNames: [double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey2 (type: float), KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: string) outputColumnNames: _col4, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [2, 0, 1] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -275,16 +322,39 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 2:float] + functionNames: [sum] + keyInputColumns: [2, 0, 1] + native: true + nonKeyInputColumns: [] + orderExpressions: [col 1:string, col 2:float] + outputColumns: [3, 2, 0, 1] + outputTypes: [double, float, double, string] + partitionExpressions: [col 0:double] + streamingColumns: [3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col5 (type: double), _col7 (type: string), _col4 (type: float), sum_window_0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/llap/vector_windowing_windowspec.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_windowspec.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_windowspec.q.out index 93b8655..584453c 100644 --- a/ql/src/test/results/clientpositive/llap/vector_windowing_windowspec.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_windowing_windowspec.q.out @@ -105,16 +105,28 @@ STAGE PLANS: partitionColumnCount: 0 scratchColumnTypeNames: [] Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aaa + reduceColumnSortOrder: +++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: KEY.reducesinkkey0:int, KEY.reducesinkkey1:string, KEY.reducesinkkey2:bigint + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: bigint), KEY.reducesinkkey1 (type: string) outputColumnNames: _col2, _col3, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 2, 1] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -135,16 +147,39 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorStreamingLongSum] + functionInputExpressions: [col 2:bigint] + functionNames: [sum] + keyInputColumns: [0, 2, 1] + native: true + nonKeyInputColumns: [] + orderExpressions: [col 1:string, col 2:bigint] + outputColumns: [3, 0, 2, 1] + outputTypes: [bigint, int, bigint, string] + partitionExpressions: [col 0:int] + streamingColumns: [3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col7 (type: string), sum_window_0 (type: bigint) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -327,16 +362,28 @@ STAGE PLANS: partitionColumnCount: 0 scratchColumnTypeNames: [] Reducer 2 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aaa + reduceColumnSortOrder: +++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: KEY.reducesinkkey0:double, KEY.reducesinkkey1:string, KEY.reducesinkkey2:float + partitionColumnCount: 0 + scratchColumnTypeNames: [double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey2 (type: float), KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: string) outputColumnNames: _col4, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [2, 0, 1] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -357,16 +404,39 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 2:float] + functionNames: [sum] + keyInputColumns: [2, 0, 1] + native: true + nonKeyInputColumns: [] + orderExpressions: [col 1:string, col 2:float] + outputColumns: [3, 2, 0, 1] + outputTypes: [double, float, double, string] + partitionExpressions: [col 0:double] + streamingColumns: [3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col7 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 3] Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out b/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out index cc6631e..b6b6cc2 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out @@ -212,16 +212,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: @@ -256,13 +268,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -846,16 +879,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: @@ -890,13 +935,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2141,16 +2207,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: @@ -2185,13 +2263,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2356,16 +2455,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: @@ -2400,13 +2511,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2637,16 +2769,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int), _col7 (type: double) Reducer 4 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: @@ -2681,13 +2825,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 12974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3152,7 +3317,7 @@ STAGE PLANS: Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type + notVectorizedReason: PTF operator: lag not in supported functions [avg, count, dense_rank, first_value, last_value, max, min, rank, row_number, sum] vectorized: false Reduce Operator Tree: Select Operator @@ -3889,7 +4054,7 @@ STAGE PLANS: Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type + notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported vectorized: false Reduce Operator Tree: Select Operator @@ -4784,16 +4949,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int) Reducer 5 - Execution mode: llap + Execution mode: vectorized, llap Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, bigint] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2] Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: @@ -4828,13 +5005,33 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingLongSum] + functionInputExpressions: [col 1:string, col 1:string, col 2:int] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2] + orderExpressions: [col 1:string] + outputColumns: [3, 4, 5, 1, 0, 2] + outputTypes: [int, int, bigint, string, string, int] + partitionExpressions: [col 0:string] + streamingColumns: [3, 4, 5] Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 3, 4, 2, 5] Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/perf/spark/query51.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query51.q.out b/ql/src/test/results/clientpositive/perf/spark/query51.q.out index c0bb72b..21afbe2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query51.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query51.q.out @@ -284,6 +284,7 @@ STAGE PLANS: Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: decimal(27,2)), _col3 (type: int), _col4 (type: string), _col5 (type: decimal(27,2)) Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: decimal(27,2)), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: decimal(27,2)) http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/perf/tez/query51.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query51.q.out b/ql/src/test/results/clientpositive/perf/tez/query51.q.out index be123ae..ba3f994 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query51.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query51.q.out @@ -106,20 +106,20 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_113] - Limit [LIM_112] (rows=100 width=88) + File Output Operator [FS_117] + Limit [LIM_116] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_111] (rows=116159124 width=88) + Select Operator [SEL_115] (rows=116159124 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_50] - Select Operator [SEL_46] (rows=116159124 width=88) + <-Reducer 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] + Select Operator [SEL_113] (rows=116159124 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_58] (rows=116159124 width=88) + Filter Operator [FIL_112] (rows=116159124 width=88) predicate:(max_window_0 > max_window_1) - PTF Operator [PTF_45] (rows=348477374 width=88) + PTF Operator [PTF_111] (rows=348477374 width=88) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END ASC NULLS FIRST","partition by:":"CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END"}] - Select Operator [SEL_44] (rows=348477374 width=88) + Select Operator [SEL_110] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_43] http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/spark/ptf.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/ptf.q.out b/ql/src/test/results/clientpositive/spark/ptf.q.out index 2017923..62d0942 100644 --- a/ql/src/test/results/clientpositive/spark/ptf.q.out +++ b/ql/src/test/results/clientpositive/spark/ptf.q.out @@ -69,6 +69,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) @@ -547,6 +548,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) @@ -1572,6 +1574,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) @@ -1744,6 +1747,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) @@ -1976,6 +1980,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 4 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) @@ -2916,6 +2921,7 @@ STAGE PLANS: value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized Reducer 3 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) @@ -3672,6 +3678,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int) Reducer 5 + Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) http://git-wip-us.apache.org/repos/asf/hive/blob/cc38bcc5/ql/src/test/results/clientpositive/spark/vectorized_ptf.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorized_ptf.q.out b/ql/src/test/results/clientpositive/spark/vectorized_ptf.q.out index f82e248..a133aad 100644 --- a/ql/src/test/results/clientpositive/spark/vectorized_ptf.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorized_ptf.q.out @@ -209,15 +209,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -252,13 +265,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -835,15 +869,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -878,13 +925,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2112,15 +2180,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -2155,13 +2236,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2323,15 +2425,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 3 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -2366,13 +2481,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2599,15 +2735,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int), _col7 (type: double) Reducer 4 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -2642,13 +2791,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3108,7 +3278,7 @@ STAGE PLANS: Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type + notVectorizedReason: PTF operator: lag not in supported functions [avg, count, dense_rank, first_value, last_value, max, min, rank, row_number, sum] vectorized: false Reduce Operator Tree: Select Operator @@ -3792,15 +3962,28 @@ STAGE PLANS: partitionColumnCount: 0 scratchColumnTypeNames: [] Reducer 3 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 4 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int, VALUE._col5:double + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, double, double] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2, 3] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -3835,13 +4018,34 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingDoubleSum] + functionInputExpressions: [col 1:string, col 1:string, col 3:double] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2, 3] + orderExpressions: [col 1:string] + outputColumns: [4, 5, 6, 1, 0, 2, 3] + outputTypes: [int, int, double, string, string, int, double] + partitionExpressions: [col 0:string] + streamingColumns: [4, 5, 6] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), round(sum_window_2, 2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 4, 5, 7] + selectExpressions: RoundWithNumDigitsDoubleToDouble(col 6, decimalPlaces 2) -> 7:double Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4659,15 +4863,28 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: int) Reducer 5 + Execution mode: vectorized Reduce Vectorization: enabled: true enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true - notVectorizedReason: PTF operator: sum UNBOUNDED end frame is not supported for ROWS window type - vectorized: false + reduceColumnNullOrder: aa + reduceColumnSortOrder: ++ + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: KEY.reducesinkkey0:string, KEY.reducesinkkey1:string, VALUE._col3:int + partitionColumnCount: 0 + scratchColumnTypeNames: [bigint, bigint, bigint] Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 2] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: @@ -4702,13 +4919,33 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~CURRENT + PTF Vectorization: + className: VectorPTFOperator + evaluatorClasses: [VectorPTFEvaluatorRank, VectorPTFEvaluatorDenseRank, VectorPTFEvaluatorStreamingLongSum] + functionInputExpressions: [col 1:string, col 1:string, col 2:int] + functionNames: [rank, dense_rank, sum] + keyInputColumns: [1, 0] + native: true + nonKeyInputColumns: [2] + orderExpressions: [col 1:string] + outputColumns: [3, 4, 5, 1, 0, 2] + outputTypes: [int, int, bigint, string, string, int] + partitionExpressions: [col 0:string] + streamingColumns: [3, 4, 5] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 3, 4, 2, 5] Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat