HIVE-18797 : ExprConstNodeDesc's getExprString should put appropriate qualifier with...
[hive.git] / ql / src / test / results / clientpositive / spark / parquet_vectorization_limit.q.out
1 WARNING: Comparing a bigint and a double may result in a loss of precision.
2 PREHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7
3 PREHOOK: type: QUERY
4 POSTHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7
5 POSTHOOK: type: QUERY
6 PLAN VECTORIZATION:
7   enabled: true
8   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
9
10 STAGE DEPENDENCIES:
11   Stage-1 is a root stage
12   Stage-0 depends on stages: Stage-1
13
14 STAGE PLANS:
15   Stage: Stage-1
16     Spark
17 #### A masked pattern was here ####
18       Vertices:
19         Map 1 
20             Map Operator Tree:
21                 TableScan
22                   alias: alltypesparquet
23                   Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
24                   Filter Operator
25                     predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean)
26                     Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE
27                     Select Operator
28                       expressions: cbigint (type: bigint), cdouble (type: double)
29                       outputColumnNames: _col0, _col1
30                       Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE
31                       Limit
32                         Number of rows: 7
33                         Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE
34                         File Output Operator
35                           compressed: false
36                           Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE
37                           table:
38                               input format: org.apache.hadoop.mapred.SequenceFileInputFormat
39                               output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
40                               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
41             Execution mode: vectorized
42             Map Vectorization:
43                 enabled: true
44                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
45                 inputFormatFeatureSupport: []
46                 featureSupportInUse: []
47                 inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
48                 allNative: false
49                 usesVectorUDFAdaptor: false
50                 vectorized: true
51
52   Stage: Stage-0
53     Fetch Operator
54       limit: 7
55       Processor Tree:
56         ListSink
57
58 WARNING: Comparing a bigint and a double may result in a loss of precision.
59 PREHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7
60 PREHOOK: type: QUERY
61 PREHOOK: Input: default@alltypesparquet
62 #### A masked pattern was here ####
63 POSTHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7
64 POSTHOOK: type: QUERY
65 POSTHOOK: Input: default@alltypesparquet
66 #### A masked pattern was here ####
67 -1887561756     -10011.0
68 -1887561756     -13877.0
69 -1887561756     -2281.0
70 -1887561756     -8881.0
71 -1887561756     10361.0
72 -1887561756     1839.0
73 -1887561756     9531.0
74 PREHOOK: query: explain vectorization detail
75 select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20
76 PREHOOK: type: QUERY
77 POSTHOOK: query: explain vectorization detail
78 select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20
79 POSTHOOK: type: QUERY
80 PLAN VECTORIZATION:
81   enabled: true
82   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
83
84 STAGE DEPENDENCIES:
85   Stage-1 is a root stage
86   Stage-0 depends on stages: Stage-1
87
88 STAGE PLANS:
89   Stage: Stage-1
90     Spark
91       Edges:
92         Reducer 2 <- Map 1 (SORT, 1)
93 #### A masked pattern was here ####
94       Vertices:
95         Map 1 
96             Map Operator Tree:
97                 TableScan
98                   alias: alltypesparquet
99                   Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
100                   TableScan Vectorization:
101                       native: true
102                       vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
103                   Filter Operator
104                     Filter Vectorization:
105                         className: VectorFilterOperator
106                         native: true
107                         predicateExpression: SelectColumnIsNotNull(col 0:tinyint)
108                     predicate: ctinyint is not null (type: boolean)
109                     Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
110                     Select Operator
111                       expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint)
112                       outputColumnNames: _col0, _col1, _col2
113                       Select Vectorization:
114                           className: VectorSelectOperator
115                           native: true
116                           projectedOutputColumnNums: [0, 5, 1]
117                       Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
118                       Reduce Output Operator
119                         key expressions: _col0 (type: tinyint), _col1 (type: double)
120                         sort order: ++
121                         Reduce Sink Vectorization:
122                             className: VectorReduceSinkObjectHashOperator
123                             keyColumnNums: [0, 5]
124                             native: true
125                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
126                             valueColumnNums: [1]
127                         Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
128                         TopN Hash Memory Usage: 0.3
129                         value expressions: _col2 (type: smallint)
130             Execution mode: vectorized
131             Map Vectorization:
132                 enabled: true
133                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
134                 inputFormatFeatureSupport: []
135                 featureSupportInUse: []
136                 inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
137                 allNative: true
138                 usesVectorUDFAdaptor: false
139                 vectorized: true
140                 rowBatchContext:
141                     dataColumnCount: 12
142                     includeColumns: [0, 1, 5]
143                     dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
144                     partitionColumnCount: 0
145                     scratchColumnTypeNames: []
146         Reducer 2 
147             Execution mode: vectorized
148             Reduce Vectorization:
149                 enabled: true
150                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
151                 reduceColumnNullOrder: aa
152                 reduceColumnSortOrder: ++
153                 allNative: false
154                 usesVectorUDFAdaptor: false
155                 vectorized: true
156                 rowBatchContext:
157                     dataColumnCount: 3
158                     dataColumns: KEY.reducesinkkey0:tinyint, KEY.reducesinkkey1:double, VALUE._col0:smallint
159                     partitionColumnCount: 0
160                     scratchColumnTypeNames: []
161             Reduce Operator Tree:
162               Select Operator
163                 expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint)
164                 outputColumnNames: _col0, _col1, _col2
165                 Select Vectorization:
166                     className: VectorSelectOperator
167                     native: true
168                     projectedOutputColumnNums: [0, 1, 2]
169                 Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
170                 Limit
171                   Number of rows: 20
172                   Limit Vectorization:
173                       className: VectorLimitOperator
174                       native: true
175                   Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
176                   File Output Operator
177                     compressed: false
178                     File Sink Vectorization:
179                         className: VectorFileSinkOperator
180                         native: false
181                     Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
182                     table:
183                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
184                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
185                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
186
187   Stage: Stage-0
188     Fetch Operator
189       limit: 20
190       Processor Tree:
191         ListSink
192
193 PREHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20
194 PREHOOK: type: QUERY
195 PREHOOK: Input: default@alltypesparquet
196 #### A masked pattern was here ####
197 POSTHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20
198 POSTHOOK: type: QUERY
199 POSTHOOK: Input: default@alltypesparquet
200 #### A masked pattern was here ####
201 -64     -10462.0        -10462
202 -64     -15920.0        -15920
203 -64     -1600.0 -1600
204 -64     -200.0  -200
205 -64     -2919.0 -2919
206 -64     -3097.0 -3097
207 -64     -3586.0 -3586
208 -64     -4018.0 -4018
209 -64     -4040.0 -4040
210 -64     -4803.0 -4803
211 -64     -6907.0 -6907
212 -64     -7196.0 -7196
213 -64     -7196.0 -7196
214 -64     -7196.0 -7196
215 -64     -7196.0 -7196
216 -64     -7196.0 -7196
217 -64     -7196.0 -7196
218 -64     -7196.0 -7196
219 -64     -8080.0 -8080
220 -64     -9842.0 -9842
221 PREHOOK: query: explain vectorization detail
222 select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20
223 PREHOOK: type: QUERY
224 POSTHOOK: query: explain vectorization detail
225 select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20
226 POSTHOOK: type: QUERY
227 PLAN VECTORIZATION:
228   enabled: true
229   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
230
231 STAGE DEPENDENCIES:
232   Stage-1 is a root stage
233   Stage-0 depends on stages: Stage-1
234
235 STAGE PLANS:
236   Stage: Stage-1
237     Spark
238       Edges:
239         Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1)
240 #### A masked pattern was here ####
241       Vertices:
242         Map 1 
243             Map Operator Tree:
244                 TableScan
245                   alias: alltypesparquet
246                   Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
247                   TableScan Vectorization:
248                       native: true
249                       vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
250                   Select Operator
251                     expressions: ctinyint (type: tinyint), (cdouble + 1.0D) (type: double)
252                     outputColumnNames: _col0, _col1
253                     Select Vectorization:
254                         className: VectorSelectOperator
255                         native: true
256                         projectedOutputColumnNums: [0, 13]
257                         selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double
258                     Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
259                     Group By Operator
260                       aggregations: avg(_col1)
261                       Group By Vectorization:
262                           aggregators: VectorUDAFAvgDouble(col 13:double) -> struct<count:bigint,sum:double,input:double>
263                           className: VectorGroupByOperator
264                           groupByMode: HASH
265                           keyExpressions: col 0:tinyint
266                           native: false
267                           vectorProcessingMode: HASH
268                           projectedOutputColumnNums: [0]
269                       keys: _col0 (type: tinyint)
270                       mode: hash
271                       outputColumnNames: _col0, _col1
272                       Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
273                       Reduce Output Operator
274                         key expressions: _col0 (type: tinyint)
275                         sort order: +
276                         Map-reduce partition columns: _col0 (type: tinyint)
277                         Reduce Sink Vectorization:
278                             className: VectorReduceSinkObjectHashOperator
279                             keyColumnNums: [0]
280                             native: true
281                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
282                             partitionColumnNums: [0]
283                             valueColumnNums: [1]
284                         Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
285                         TopN Hash Memory Usage: 0.3
286                         value expressions: _col1 (type: struct<count:bigint,sum:double,input:double>)
287             Execution mode: vectorized
288             Map Vectorization:
289                 enabled: true
290                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
291                 inputFormatFeatureSupport: []
292                 featureSupportInUse: []
293                 inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
294                 allNative: false
295                 usesVectorUDFAdaptor: false
296                 vectorized: true
297                 rowBatchContext:
298                     dataColumnCount: 12
299                     includeColumns: [0, 5]
300                     dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
301                     partitionColumnCount: 0
302                     scratchColumnTypeNames: [double]
303         Reducer 2 
304             Execution mode: vectorized
305             Reduce Vectorization:
306                 enabled: true
307                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
308                 reduceColumnNullOrder: a
309                 reduceColumnSortOrder: +
310                 allNative: false
311                 usesVectorUDFAdaptor: false
312                 vectorized: true
313                 rowBatchContext:
314                     dataColumnCount: 2
315                     dataColumns: KEY._col0:tinyint, VALUE._col0:struct<count:bigint,sum:double,input:double>
316                     partitionColumnCount: 0
317                     scratchColumnTypeNames: []
318             Reduce Operator Tree:
319               Group By Operator
320                 aggregations: avg(VALUE._col0)
321                 Group By Vectorization:
322                     aggregators: VectorUDAFAvgFinal(col 1:struct<count:bigint,sum:double,input:double>) -> double
323                     className: VectorGroupByOperator
324                     groupByMode: MERGEPARTIAL
325                     keyExpressions: col 0:tinyint
326                     native: false
327                     vectorProcessingMode: MERGE_PARTIAL
328                     projectedOutputColumnNums: [0]
329                 keys: KEY._col0 (type: tinyint)
330                 mode: mergepartial
331                 outputColumnNames: _col0, _col1
332                 Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE
333                 Limit
334                   Number of rows: 20
335                   Limit Vectorization:
336                       className: VectorLimitOperator
337                       native: true
338                   Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
339                   File Output Operator
340                     compressed: false
341                     File Sink Vectorization:
342                         className: VectorFileSinkOperator
343                         native: false
344                     Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
345                     table:
346                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
347                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
348                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
349
350   Stage: Stage-0
351     Fetch Operator
352       limit: 20
353       Processor Tree:
354         ListSink
355
356 PREHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20
357 PREHOOK: type: QUERY
358 PREHOOK: Input: default@alltypesparquet
359 #### A masked pattern was here ####
360 POSTHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20
361 POSTHOOK: type: QUERY
362 POSTHOOK: Input: default@alltypesparquet
363 #### A masked pattern was here ####
364 -46     3033.55
365 -47     -574.6428571428571
366 -48     1672.909090909091
367 -49     768.7659574468086
368 -50     -960.0192307692307
369 -51     -96.46341463414635
370 -52     2810.705882352941
371 -53     -532.7567567567568
372 -54     2712.7272727272725
373 -55     2385.595744680851
374 -56     2595.818181818182
375 -57     1867.0535714285713
376 -58     3483.2444444444445
377 -59     318.27272727272725
378 -60     1071.82
379 -61     914.3404255319149
380 -62     245.69387755102042
381 -63     2178.7272727272725
382 -64     373.52941176470586
383 NULL    9370.0945309795
384 PREHOOK: query: explain vectorization detail
385 select distinct(ctinyint) from alltypesparquet limit 20
386 PREHOOK: type: QUERY
387 POSTHOOK: query: explain vectorization detail
388 select distinct(ctinyint) from alltypesparquet limit 20
389 POSTHOOK: type: QUERY
390 PLAN VECTORIZATION:
391   enabled: true
392   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
393
394 STAGE DEPENDENCIES:
395   Stage-1 is a root stage
396   Stage-0 depends on stages: Stage-1
397
398 STAGE PLANS:
399   Stage: Stage-1
400     Spark
401       Edges:
402         Reducer 2 <- Map 1 (GROUP, 2)
403 #### A masked pattern was here ####
404       Vertices:
405         Map 1 
406             Map Operator Tree:
407                 TableScan
408                   alias: alltypesparquet
409                   Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
410                   TableScan Vectorization:
411                       native: true
412                       vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
413                   Select Operator
414                     expressions: ctinyint (type: tinyint)
415                     outputColumnNames: ctinyint
416                     Select Vectorization:
417                         className: VectorSelectOperator
418                         native: true
419                         projectedOutputColumnNums: [0]
420                     Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
421                     Group By Operator
422                       Group By Vectorization:
423                           className: VectorGroupByOperator
424                           groupByMode: HASH
425                           keyExpressions: col 0:tinyint
426                           native: false
427                           vectorProcessingMode: HASH
428                           projectedOutputColumnNums: []
429                       keys: ctinyint (type: tinyint)
430                       mode: hash
431                       outputColumnNames: _col0
432                       Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
433                       Reduce Output Operator
434                         key expressions: _col0 (type: tinyint)
435                         sort order: +
436                         Map-reduce partition columns: _col0 (type: tinyint)
437                         Reduce Sink Vectorization:
438                             className: VectorReduceSinkLongOperator
439                             keyColumnNums: [0]
440                             native: true
441                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
442                             valueColumnNums: []
443                         Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
444                         TopN Hash Memory Usage: 0.3
445             Execution mode: vectorized
446             Map Vectorization:
447                 enabled: true
448                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
449                 inputFormatFeatureSupport: []
450                 featureSupportInUse: []
451                 inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
452                 allNative: false
453                 usesVectorUDFAdaptor: false
454                 vectorized: true
455                 rowBatchContext:
456                     dataColumnCount: 12
457                     includeColumns: [0]
458                     dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
459                     partitionColumnCount: 0
460                     scratchColumnTypeNames: []
461         Reducer 2 
462             Execution mode: vectorized
463             Reduce Vectorization:
464                 enabled: true
465                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
466                 reduceColumnNullOrder: a
467                 reduceColumnSortOrder: +
468                 allNative: false
469                 usesVectorUDFAdaptor: false
470                 vectorized: true
471                 rowBatchContext:
472                     dataColumnCount: 1
473                     dataColumns: KEY._col0:tinyint
474                     partitionColumnCount: 0
475                     scratchColumnTypeNames: []
476             Reduce Operator Tree:
477               Group By Operator
478                 Group By Vectorization:
479                     className: VectorGroupByOperator
480                     groupByMode: MERGEPARTIAL
481                     keyExpressions: col 0:tinyint
482                     native: false
483                     vectorProcessingMode: MERGE_PARTIAL
484                     projectedOutputColumnNums: []
485                 keys: KEY._col0 (type: tinyint)
486                 mode: mergepartial
487                 outputColumnNames: _col0
488                 Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE
489                 Limit
490                   Number of rows: 20
491                   Limit Vectorization:
492                       className: VectorLimitOperator
493                       native: true
494                   Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
495                   File Output Operator
496                     compressed: false
497                     File Sink Vectorization:
498                         className: VectorFileSinkOperator
499                         native: false
500                     Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
501                     table:
502                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
503                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
504                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
505
506   Stage: Stage-0
507     Fetch Operator
508       limit: 20
509       Processor Tree:
510         ListSink
511
512 PREHOOK: query: select distinct(ctinyint) from alltypesparquet limit 20
513 PREHOOK: type: QUERY
514 PREHOOK: Input: default@alltypesparquet
515 #### A masked pattern was here ####
516 POSTHOOK: query: select distinct(ctinyint) from alltypesparquet limit 20
517 POSTHOOK: type: QUERY
518 POSTHOOK: Input: default@alltypesparquet
519 #### A masked pattern was here ####
520 -46
521 -47
522 -48
523 -49
524 -50
525 -51
526 -52
527 -53
528 -54
529 -55
530 -56
531 -57
532 -58
533 -59
534 -60
535 -61
536 -62
537 -63
538 -64
539 NULL
540 PREHOOK: query: explain vectorization detail
541 select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20
542 PREHOOK: type: QUERY
543 POSTHOOK: query: explain vectorization detail
544 select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20
545 POSTHOOK: type: QUERY
546 PLAN VECTORIZATION:
547   enabled: true
548   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
549
550 STAGE DEPENDENCIES:
551   Stage-1 is a root stage
552   Stage-0 depends on stages: Stage-1
553
554 STAGE PLANS:
555   Stage: Stage-1
556     Spark
557       Edges:
558         Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1)
559 #### A masked pattern was here ####
560       Vertices:
561         Map 1 
562             Map Operator Tree:
563                 TableScan
564                   alias: alltypesparquet
565                   Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
566                   TableScan Vectorization:
567                       native: true
568                       vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
569                   Select Operator
570                     expressions: ctinyint (type: tinyint), cdouble (type: double)
571                     outputColumnNames: ctinyint, cdouble
572                     Select Vectorization:
573                         className: VectorSelectOperator
574                         native: true
575                         projectedOutputColumnNums: [0, 5]
576                     Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
577                     Group By Operator
578                       Group By Vectorization:
579                           className: VectorGroupByOperator
580                           groupByMode: HASH
581                           keyExpressions: col 0:tinyint, col 5:double
582                           native: false
583                           vectorProcessingMode: HASH
584                           projectedOutputColumnNums: []
585                       keys: ctinyint (type: tinyint), cdouble (type: double)
586                       mode: hash
587                       outputColumnNames: _col0, _col1
588                       Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
589                       Reduce Output Operator
590                         key expressions: _col0 (type: tinyint), _col1 (type: double)
591                         sort order: ++
592                         Map-reduce partition columns: _col0 (type: tinyint)
593                         Reduce Sink Vectorization:
594                             className: VectorReduceSinkObjectHashOperator
595                             keyColumnNums: [0, 1]
596                             native: true
597                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
598                             partitionColumnNums: [0]
599                             valueColumnNums: []
600                         Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
601             Execution mode: vectorized
602             Map Vectorization:
603                 enabled: true
604                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
605                 inputFormatFeatureSupport: []
606                 featureSupportInUse: []
607                 inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
608                 allNative: false
609                 usesVectorUDFAdaptor: false
610                 vectorized: true
611                 rowBatchContext:
612                     dataColumnCount: 12
613                     includeColumns: [0, 5]
614                     dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
615                     partitionColumnCount: 0
616                     scratchColumnTypeNames: []
617         Reducer 2 
618             Execution mode: vectorized
619             Reduce Vectorization:
620                 enabled: true
621                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
622                 reduceColumnNullOrder: aa
623                 reduceColumnSortOrder: ++
624                 allNative: false
625                 usesVectorUDFAdaptor: false
626                 vectorized: true
627                 rowBatchContext:
628                     dataColumnCount: 2
629                     dataColumns: KEY._col0:tinyint, KEY._col1:double
630                     partitionColumnCount: 0
631                     scratchColumnTypeNames: []
632             Reduce Operator Tree:
633               Group By Operator
634                 Group By Vectorization:
635                     className: VectorGroupByOperator
636                     groupByMode: MERGEPARTIAL
637                     keyExpressions: col 0:tinyint, col 1:double
638                     native: false
639                     vectorProcessingMode: MERGE_PARTIAL
640                     projectedOutputColumnNums: []
641                 keys: KEY._col0 (type: tinyint), KEY._col1 (type: double)
642                 mode: mergepartial
643                 outputColumnNames: _col0, _col1
644                 Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE
645                 Group By Operator
646                   aggregations: count(_col1)
647                   Group By Vectorization:
648                       aggregators: VectorUDAFCount(col 1:double) -> bigint
649                       className: VectorGroupByOperator
650                       groupByMode: COMPLETE
651                       keyExpressions: col 0:tinyint
652                       native: false
653                       vectorProcessingMode: STREAMING
654                       projectedOutputColumnNums: [0]
655                   keys: _col0 (type: tinyint)
656                   mode: complete
657                   outputColumnNames: _col0, _col1
658                   Statistics: Num rows: 3072 Data size: 36864 Basic stats: COMPLETE Column stats: NONE
659                   Limit
660                     Number of rows: 20
661                     Limit Vectorization:
662                         className: VectorLimitOperator
663                         native: true
664                     Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
665                     File Output Operator
666                       compressed: false
667                       File Sink Vectorization:
668                           className: VectorFileSinkOperator
669                           native: false
670                       Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
671                       table:
672                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
673                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
674                           serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
675
676   Stage: Stage-0
677     Fetch Operator
678       limit: 20
679       Processor Tree:
680         ListSink
681
682 PREHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20
683 PREHOOK: type: QUERY
684 PREHOOK: Input: default@alltypesparquet
685 #### A masked pattern was here ####
686 POSTHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20
687 POSTHOOK: type: QUERY
688 POSTHOOK: Input: default@alltypesparquet
689 #### A masked pattern was here ####
690 -46     24
691 -47     22
692 -48     29
693 -49     26
694 -50     30
695 -51     21
696 -52     33
697 -53     22
698 -54     26
699 -55     29
700 -56     36
701 -57     35
702 -58     23
703 -59     31
704 -60     27
705 -61     25
706 -62     27
707 -63     19
708 -64     24
709 NULL    2932
710 PREHOOK: query: explain vectorization detail
711 select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0
712 PREHOOK: type: QUERY
713 POSTHOOK: query: explain vectorization detail
714 select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0
715 POSTHOOK: type: QUERY
716 PLAN VECTORIZATION:
717   enabled: true
718   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
719
720 STAGE DEPENDENCIES:
721   Stage-0 is a root stage
722
723 STAGE PLANS:
724   Stage: Stage-0
725     Fetch Operator
726       limit: 0
727       Processor Tree:
728         ListSink
729
730 PREHOOK: query: select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0
731 PREHOOK: type: QUERY
732 PREHOOK: Input: default@alltypesparquet
733 #### A masked pattern was here ####
734 POSTHOOK: query: select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0
735 POSTHOOK: type: QUERY
736 POSTHOOK: Input: default@alltypesparquet
737 #### A masked pattern was here ####
738 PREHOOK: query: explain vectorization detail
739 select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20
740 PREHOOK: type: QUERY
741 POSTHOOK: query: explain vectorization detail
742 select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20
743 POSTHOOK: type: QUERY
744 PLAN VECTORIZATION:
745   enabled: true
746   enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
747
748 STAGE DEPENDENCIES:
749   Stage-1 is a root stage
750   Stage-0 depends on stages: Stage-1
751
752 STAGE PLANS:
753   Stage: Stage-1
754     Spark
755       Edges:
756         Reducer 2 <- Map 1 (GROUP, 2)
757         Reducer 3 <- Reducer 2 (SORT, 1)
758 #### A masked pattern was here ####
759       Vertices:
760         Map 1 
761             Map Operator Tree:
762                 TableScan
763                   alias: alltypesparquet
764                   Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
765                   TableScan Vectorization:
766                       native: true
767                       vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
768                   Filter Operator
769                     Filter Vectorization:
770                         className: VectorFilterOperator
771                         native: true
772                         predicateExpression: SelectColumnIsNotNull(col 0:tinyint)
773                     predicate: ctinyint is not null (type: boolean)
774                     Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
775                     Group By Operator
776                       aggregations: sum(ctinyint)
777                       Group By Vectorization:
778                           aggregators: VectorUDAFSumLong(col 0:tinyint) -> bigint
779                           className: VectorGroupByOperator
780                           groupByMode: HASH
781                           keyExpressions: col 5:double
782                           native: false
783                           vectorProcessingMode: HASH
784                           projectedOutputColumnNums: [0]
785                       keys: cdouble (type: double)
786                       mode: hash
787                       outputColumnNames: _col0, _col1
788                       Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
789                       Reduce Output Operator
790                         key expressions: _col0 (type: double)
791                         sort order: +
792                         Map-reduce partition columns: _col0 (type: double)
793                         Reduce Sink Vectorization:
794                             className: VectorReduceSinkMultiKeyOperator
795                             keyColumnNums: [0]
796                             native: true
797                             nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
798                             valueColumnNums: [1]
799                         Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE
800                         value expressions: _col1 (type: bigint)
801             Execution mode: vectorized
802             Map Vectorization:
803                 enabled: true
804                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
805                 inputFormatFeatureSupport: []
806                 featureSupportInUse: []
807                 inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat
808                 allNative: false
809                 usesVectorUDFAdaptor: false
810                 vectorized: true
811                 rowBatchContext:
812                     dataColumnCount: 12
813                     includeColumns: [0, 5]
814                     dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
815                     partitionColumnCount: 0
816                     scratchColumnTypeNames: []
817         Reducer 2 
818             Execution mode: vectorized
819             Reduce Vectorization:
820                 enabled: true
821                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
822                 reduceColumnNullOrder: a
823                 reduceColumnSortOrder: +
824                 allNative: false
825                 usesVectorUDFAdaptor: false
826                 vectorized: true
827                 rowBatchContext:
828                     dataColumnCount: 2
829                     dataColumns: KEY._col0:double, VALUE._col0:bigint
830                     partitionColumnCount: 0
831                     scratchColumnTypeNames: []
832             Reduce Operator Tree:
833               Group By Operator
834                 aggregations: sum(VALUE._col0)
835                 Group By Vectorization:
836                     aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint
837                     className: VectorGroupByOperator
838                     groupByMode: MERGEPARTIAL
839                     keyExpressions: col 0:double
840                     native: false
841                     vectorProcessingMode: MERGE_PARTIAL
842                     projectedOutputColumnNums: [0]
843                 keys: KEY._col0 (type: double)
844                 mode: mergepartial
845                 outputColumnNames: _col0, _col1
846                 Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE
847                 Reduce Output Operator
848                   key expressions: _col1 (type: bigint), _col0 (type: double)
849                   sort order: ++
850                   Reduce Sink Vectorization:
851                       className: VectorReduceSinkObjectHashOperator
852                       keyColumnNums: [1, 0]
853                       native: true
854                       nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
855                       valueColumnNums: []
856                   Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE
857                   TopN Hash Memory Usage: 0.3
858         Reducer 3 
859             Execution mode: vectorized
860             Reduce Vectorization:
861                 enabled: true
862                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
863                 reduceColumnNullOrder: aa
864                 reduceColumnSortOrder: ++
865                 allNative: false
866                 usesVectorUDFAdaptor: false
867                 vectorized: true
868                 rowBatchContext:
869                     dataColumnCount: 2
870                     dataColumns: KEY.reducesinkkey0:bigint, KEY.reducesinkkey1:double
871                     partitionColumnCount: 0
872                     scratchColumnTypeNames: []
873             Reduce Operator Tree:
874               Select Operator
875                 expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint)
876                 outputColumnNames: _col0, _col1
877                 Select Vectorization:
878                     className: VectorSelectOperator
879                     native: true
880                     projectedOutputColumnNums: [1, 0]
881                 Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE
882                 Limit
883                   Number of rows: 20
884                   Limit Vectorization:
885                       className: VectorLimitOperator
886                       native: true
887                   Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
888                   File Output Operator
889                     compressed: false
890                     File Sink Vectorization:
891                         className: VectorFileSinkOperator
892                         native: false
893                     Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
894                     table:
895                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
896                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
897                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
898
899   Stage: Stage-0
900     Fetch Operator
901       limit: 20
902       Processor Tree:
903         ListSink
904
905 PREHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20
906 PREHOOK: type: QUERY
907 PREHOOK: Input: default@alltypesparquet
908 #### A masked pattern was here ####
909 POSTHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20
910 POSTHOOK: type: QUERY
911 POSTHOOK: Input: default@alltypesparquet
912 #### A masked pattern was here ####
913 -10462.0        -64
914 -1121.0 -89
915 -11322.0        -101
916 -11492.0        -78
917 -15920.0        -64
918 -4803.0 -64
919 -6907.0 -64
920 -7196.0 -2009
921 -8080.0 -64
922 -8118.0 -80
923 -9842.0 -64
924 10496.0 -67
925 15601.0 -1733
926 3520.0  -86
927 4811.0  -115
928 5241.0  -80
929 557.0   -75
930 7705.0  -88
931 9452.0  -76
932 NULL    -32768