You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by mm...@apache.org on 2018/02/16 15:52:30 UTC
[16/32] hive git commit: HIVE-18622: Vectorization: IF Statements,
Comparisons, and more do not handle NULLs correctly (Matt McCline,
reviewed by Sergey Shelukhin, Deepak Jaiswal, Vihang Karajgaonkar)
http://git-wip-us.apache.org/repos/asf/hive/blob/a4689020/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out
index 56248d1..a306a17 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out
@@ -48,6 +48,16 @@ POSTHOOK: Input: default@decimal_udf_txt
POSTHOOK: Output: default@decimal_udf
POSTHOOK: Lineage: decimal_udf.key SIMPLE [(decimal_udf_txt)decimal_udf_txt.FieldSchema(name:key, type:decimal(20,10), comment:null), ]
POSTHOOK: Lineage: decimal_udf.value SIMPLE [(decimal_udf_txt)decimal_udf_txt.FieldSchema(name:value, type:int, comment:null), ]
+PREHOOK: query: insert into DECIMAL_UDF values (NULL, NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@decimal_udf
+POSTHOOK: query: insert into DECIMAL_UDF values (NULL, NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@decimal_udf
+POSTHOOK: Lineage: decimal_udf.key EXPRESSION []
+POSTHOOK: Lineage: decimal_udf.value EXPRESSION []
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key + key FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -71,7 +81,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -83,13 +93,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: DecimalColAddDecimalColumn(col 0:decimal(20,10), col 0:decimal(20,10)) -> 3:decimal(21,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -126,44 +136,45 @@ POSTHOOK: query: SELECT key + key FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.6000000000
+-0.6600000000
+-0.6660000000
+-2.2400000000
+-2.2400000000
+-2.2440000000
+-2469135780.2469135780
+-2510.9800000000
-8800.0000000000
-NULL
0.0000000000
0.0000000000
-200.0000000000
-20.0000000000
-2.0000000000
-0.2000000000
-0.0200000000
-400.0000000000
-40.0000000000
-4.0000000000
0.0000000000
-0.4000000000
+0.0200000000
0.0400000000
+0.2000000000
+0.4000000000
0.6000000000
0.6600000000
0.6660000000
--0.6000000000
--0.6600000000
--0.6660000000
2.0000000000
-4.0000000000
-6.2800000000
--2.2400000000
--2.2400000000
--2.2440000000
+2.0000000000
+2.0000000000
2.2400000000
2.2440000000
+20.0000000000
+200.0000000000
+2469135780.2469135600
248.0000000000
250.4000000000
--2510.9800000000
+4.0000000000
+4.0000000000
+40.0000000000
+400.0000000000
6.2800000000
6.2800000000
6.2800000000
-2.0000000000
--2469135780.2469135780
-2469135780.2469135600
+6.2800000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key + value FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -187,7 +198,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -199,13 +210,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DecimalColAddDecimalColumn(col 0:decimal(20,10), col 3:decimal(10,0))(children: CastLongToDecimal(col 1:int) -> 3:decimal(10,0)) -> 4:decimal(21,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -242,44 +253,45 @@ POSTHOOK: query: SELECT key + value FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.3000000000
+-0.3300000000
+-0.3330000000
+-12.1220000000
+-2.1200000000
+-2.1200000000
+-2469135780.1234567890
+-2510.4900000000
0.0000000000
-NULL
0.0000000000
0.0000000000
-200.0000000000
-20.0000000000
-2.0000000000
-0.1000000000
-0.0100000000
-400.0000000000
-40.0000000000
-4.0000000000
0.0000000000
-0.2000000000
+0.0100000000
0.0200000000
+0.1000000000
+0.2000000000
0.3000000000
0.3300000000
0.3330000000
--0.3000000000
--0.3300000000
--0.3330000000
2.0000000000
-4.0000000000
-6.1400000000
--2.1200000000
--2.1200000000
--12.1220000000
+2.0000000000
+2.0000000000
2.1200000000
2.1220000000
+20.0000000000
+200.0000000000
+2469135780.1234567800
248.0000000000
250.2000000000
--2510.4900000000
+4.0000000000
+4.0000000000
+40.0000000000
+400.0000000000
+6.1400000000
6.1400000000
6.1400000000
7.1400000000
-2.0000000000
--2469135780.1234567890
-2469135780.1234567800
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key + (value/2) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -303,7 +315,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -315,13 +327,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColAddDoubleColumn(col 3:double, col 5:double)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double, DoubleColDivideDoubleScalar(col 4:double, val 2.0)(children: CastLongToDouble(col 1:int) -> 4:double) -> 5:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -358,44 +370,45 @@ POSTHOOK: query: SELECT key + (value/2) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.3
+-0.33
+-0.333
+-1.62
+-1.62
+-1.8518518351234567E9
+-1882.99
-2200.0
-NULL
+-6.622
0.0
0.0
-150.0
-15.0
-1.5
-0.1
-0.01
-300.0
-30.0
-3.0
0.0
-0.2
+0.01
0.02
+0.1
+0.2
0.3
0.33
0.333
--0.3
--0.33
--0.333
1.5
-3.0
-4.640000000000001
--1.62
--1.62
--6.622
+1.5
+1.5
1.62
1.622
+1.8518518351234567E9
+15.0
+150.0
186.0
187.7
--1882.99
+3.0
+3.0
+30.0
+300.0
+4.640000000000001
4.640000000000001
4.640000000000001
5.140000000000001
-1.5
--1.8518518351234567E9
-1.8518518351234567E9
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key + '1.0' FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -419,7 +432,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -431,13 +444,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColAddDoubleScalar(col 3:double, val 1.0)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -474,44 +487,45 @@ POSTHOOK: query: SELECT key + '1.0' FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.1200000000000001
+-0.1200000000000001
+-0.12200000000000011
+-1.2345678891234567E9
+-1254.49
-4399.0
-NULL
+0.667
+0.6699999999999999
+0.7
1.0
1.0
-101.0
-11.0
-2.0
-1.1
-1.01
-201.0
-21.0
-3.0
1.0
-1.2
+1.01
1.02
+1.1
+1.2
+1.2345678911234567E9
1.3
1.33
1.333
-0.7
-0.6699999999999999
-0.667
+101.0
+11.0
+125.0
+126.2
+2.0
+2.0
2.0
-3.0
-4.140000000000001
--0.1200000000000001
--0.1200000000000001
--0.12200000000000011
2.12
2.122
-125.0
-126.2
--1254.49
+201.0
+21.0
+3.0
+3.0
4.140000000000001
4.140000000000001
4.140000000000001
-2.0
--1.2345678891234567E9
-1.2345678911234567E9
+4.140000000000001
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key - key FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -535,7 +549,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -547,13 +561,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: DecimalColSubtractDecimalColumn(col 0:decimal(20,10), col 0:decimal(20,10)) -> 3:decimal(21,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -591,7 +605,6 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
0.0000000000
-NULL
0.0000000000
0.0000000000
0.0000000000
@@ -628,6 +641,8 @@ NULL
0.0000000000
0.0000000000
0.0000000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key - value FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -651,7 +666,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -663,13 +678,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DecimalColSubtractDecimalColumn(col 0:decimal(20,10), col 3:decimal(10,0))(children: CastLongToDecimal(col 1:int) -> 3:decimal(10,0)) -> 4:decimal(21,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -706,44 +721,45 @@ POSTHOOK: query: SELECT key - value FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.1200000000
+-0.1200000000
+-0.1234567890
+-0.3000000000
+-0.3300000000
+-0.3330000000
+-0.4900000000
+-0.8600000000
-8800.0000000000
-NULL
0.0000000000
0.0000000000
0.0000000000
0.0000000000
0.0000000000
-0.1000000000
-0.0100000000
0.0000000000
0.0000000000
0.0000000000
0.0000000000
-0.2000000000
-0.0200000000
-0.3000000000
-0.3300000000
-0.3330000000
--0.3000000000
--0.3300000000
--0.3330000000
0.0000000000
0.0000000000
-0.1400000000
--0.1200000000
--0.1200000000
-9.8780000000
+0.0000000000
+0.0000000000
+0.0100000000
+0.0200000000
+0.1000000000
0.1200000000
0.1220000000
-0.0000000000
-0.2000000000
--0.4900000000
+0.1234567800
0.1400000000
0.1400000000
--0.8600000000
-0.0000000000
--0.1234567890
-0.1234567800
+0.1400000000
+0.2000000000
+0.2000000000
+0.3000000000
+0.3300000000
+0.3330000000
+9.8780000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key - (value/2) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -767,7 +783,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -779,13 +795,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColSubtractDoubleColumn(col 3:double, col 5:double)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double, DoubleColDivideDoubleScalar(col 4:double, val 2.0)(children: CastLongToDouble(col 1:int) -> 4:double) -> 5:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -822,44 +838,45 @@ POSTHOOK: query: SELECT key - (value/2) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.3
+-0.33
+-0.333
+-0.6200000000000001
+-0.6200000000000001
+-6.172839451234567E8
+-627.99
-6600.0
-NULL
0.0
0.0
-50.0
-5.0
-0.5
-0.1
-0.01
-100.0
-10.0
-1.0
0.0
-0.2
+0.01
0.02
+0.1
+0.2
0.3
0.33
0.333
--0.3
--0.33
--0.333
0.5
-1.0
-1.6400000000000001
--0.6200000000000001
--0.6200000000000001
-4.378
+0.5
+0.5
0.6200000000000001
0.6220000000000001
-62.0
-62.7
--627.99
+1.0
+1.0
+1.1400000000000001
1.6400000000000001
1.6400000000000001
-1.1400000000000001
-0.5
--6.172839451234567E8
+1.6400000000000001
+10.0
+100.0
+4.378
+5.0
+50.0
6.172839451234567E8
+62.0
+62.7
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key - '1.0' FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -883,7 +900,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -895,13 +912,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColSubtractDoubleScalar(col 3:double, val 1.0)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -938,44 +955,45 @@ POSTHOOK: query: SELECT key - '1.0' FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
--4401.0
-NULL
--1.0
--1.0
-99.0
-9.0
-0.0
+-0.667
+-0.6699999999999999
+-0.7
+-0.8
-0.9
+-0.98
-0.99
-199.0
-19.0
-1.0
-1.0
--0.8
--0.98
--0.7
--0.6699999999999999
--0.667
+-1.0
+-1.0
+-1.2345678911234567E9
-1.3
-1.33
-1.333
-0.0
-1.0
-2.14
+-1256.49
-2.12
-2.12
-2.122
+-4401.0
+0.0
+0.0
+0.0
0.1200000000000001
0.12200000000000011
+1.0
+1.0
+1.2345678891234567E9
123.0
124.2
--1256.49
+19.0
+199.0
2.14
2.14
2.14
-0.0
--1.2345678911234567E9
-1.2345678891234567E9
+2.14
+9.0
+99.0
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key * key FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -999,7 +1017,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1011,13 +1029,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: DecimalColMultiplyDecimalColumn(col 0:decimal(20,10), col 0:decimal(20,10)) -> 3:decimal(38,17)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1054,44 +1072,45 @@ POSTHOOK: query: SELECT key * key FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-19360000.00000000000000000
-NULL
0.00000000000000000
0.00000000000000000
-10000.00000000000000000
-100.00000000000000000
-1.00000000000000000
-0.01000000000000000
-0.00010000000000000
-40000.00000000000000000
-400.00000000000000000
-4.00000000000000000
0.00000000000000000
-0.04000000000000000
+0.00010000000000000
0.00040000000000000
+0.01000000000000000
+0.04000000000000000
0.09000000000000000
-0.10890000000000000
-0.11088900000000000
0.09000000000000000
0.10890000000000000
+0.10890000000000000
+0.11088900000000000
0.11088900000000000
1.00000000000000000
-4.00000000000000000
-9.85960000000000000
+1.00000000000000000
+1.00000000000000000
1.25440000000000000
1.25440000000000000
-1.25888400000000000
1.25440000000000000
1.25888400000000000
+1.25888400000000000
+100.00000000000000000
+10000.00000000000000000
+1524157875323883652.79682997652796840
+1524157875323883675.01905199875019052
15376.00000000000000000
15675.04000000000000000
1576255.14010000000000000
+19360000.00000000000000000
+4.00000000000000000
+4.00000000000000000
+400.00000000000000000
+40000.00000000000000000
9.85960000000000000
9.85960000000000000
9.85960000000000000
-1.00000000000000000
-1524157875323883675.01905199875019052
-1524157875323883652.79682997652796840
+9.85960000000000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key, value FROM DECIMAL_UDF where key * value > 0
PREHOOK: type: QUERY
@@ -1115,7 +1134,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1125,7 +1144,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDecimalColGreaterDecimalScalar(col 4:decimal(31,10), val 0)(children: DecimalColMultiplyDecimalColumn(col 0:decimal(20,10), col 3:decimal(10,0))(children: CastLongToDecimal(col 1:int) -> 3:decimal(10,0)) -> 4:decimal(31,10))
predicate: ((key * CAST( value AS decimal(10,0))) > 0) (type: boolean)
- Statistics: Num rows: 12 Data size: 1392 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: decimal(20,10)), value (type: int)
outputColumnNames: _col0, _col1
@@ -1133,13 +1152,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 12 Data size: 1392 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 1392 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1176,29 +1195,29 @@ POSTHOOK: query: SELECT key, value FROM DECIMAL_UDF where key * value > 0
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-100.0000000000 100
-10.0000000000 10
-1.0000000000 1
-200.0000000000 200
-20.0000000000 20
-2.0000000000 2
-1.0000000000 1
-2.0000000000 2
-3.1400000000 3
-1.1200000000 -1
-1.1200000000 -1
-1.1220000000 -11
+-1234567890.1234567890 -1234567890
+-1255.4900000000 -1255
+1.0000000000 1
+1.0000000000 1
+1.0000000000 1
1.1200000000 1
1.1220000000 1
+10.0000000000 10
+100.0000000000 100
+1234567890.1234567800 1234567890
124.0000000000 124
125.2000000000 125
--1255.4900000000 -1255
+2.0000000000 2
+2.0000000000 2
+20.0000000000 20
+200.0000000000 200
+3.1400000000 3
3.1400000000 3
3.1400000000 3
3.1400000000 4
-1.0000000000 1
--1234567890.1234567890 -1234567890
-1234567890.1234567800 1234567890
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key * value FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -1222,7 +1241,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1234,13 +1253,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DecimalColMultiplyDecimalColumn(col 0:decimal(20,10), col 3:decimal(10,0))(children: CastLongToDecimal(col 1:int) -> 3:decimal(10,0)) -> 4:decimal(31,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1278,17 +1297,10 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-19360000.0000000000
-NULL
0.0000000000
0.0000000000
-10000.0000000000
-100.0000000000
-1.0000000000
0.0000000000
0.0000000000
-40000.0000000000
-400.0000000000
-4.0000000000
0.0000000000
0.0000000000
0.0000000000
@@ -1299,22 +1311,30 @@ NULL
0.0000000000
0.0000000000
1.0000000000
-4.0000000000
-9.4200000000
+1.0000000000
+1.0000000000
1.1200000000
1.1200000000
-12.3420000000
1.1200000000
1.1220000000
+100.0000000000
+10000.0000000000
+12.3420000000
+12.5600000000
+1524157875171467876.3907942000
+1524157875171467887.5019052100
15376.0000000000
15650.0000000000
1575639.9500000000
+4.0000000000
+4.0000000000
+400.0000000000
+40000.0000000000
9.4200000000
9.4200000000
-12.5600000000
-1.0000000000
-1524157875171467887.5019052100
-1524157875171467876.3907942000
+9.4200000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key * (value/2) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -1338,7 +1358,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1350,13 +1370,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColMultiplyDoubleColumn(col 3:double, col 5:double)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double, DoubleColDivideDoubleScalar(col 4:double, val 2.0)(children: CastLongToDouble(col 1:int) -> 4:double) -> 5:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1393,44 +1413,45 @@ POSTHOOK: query: SELECT key * (value/2) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.0
+-0.0
+-0.0
-9680000.0
-NULL
0.0
0.0
-5000.0
-50.0
-0.5
0.0
0.0
-20000.0
-200.0
-2.0
0.0
0.0
0.0
0.0
0.0
0.0
--0.0
--0.0
--0.0
0.5
-2.0
-4.71
+0.5
+0.5
0.56
0.56
-6.171
0.56
0.561
-7688.0
-7825.0
-787819.975
+2.0
+2.0
+200.0
+20000.0
+4.71
4.71
4.71
+50.0
+5000.0
+6.171
6.28
-0.5
7.6207893758573389E17
7.6207893758573389E17
+7688.0
+7825.0
+787819.975
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key * '2.0' FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -1454,7 +1475,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1466,13 +1487,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColMultiplyDoubleScalar(col 3:double, val 2.0)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1509,49 +1530,50 @@ POSTHOOK: query: SELECT key * '2.0' FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.6
+-0.66
+-0.666
+-2.24
+-2.24
+-2.244
+-2.4691357802469134E9
+-2510.98
-8800.0
-NULL
0.0
0.0
-200.0
-20.0
-2.0
-0.2
-0.02
-400.0
-40.0
-4.0
0.0
-0.4
+0.02
0.04
+0.2
+0.4
0.6
0.66
0.666
--0.6
--0.66
--0.666
2.0
-4.0
-6.28
--2.24
--2.24
--2.244
+2.0
+2.0
2.24
2.244
+2.4691357802469134E9
+20.0
+200.0
248.0
250.4
--2510.98
+4.0
+4.0
+40.0
+400.0
6.28
6.28
6.28
-2.0
--2.4691357802469134E9
-2.4691357802469134E9
+6.28
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
-SELECT key / 0 FROM DECIMAL_UDF limit 1
+SELECT key / 0 FROM DECIMAL_UDF
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
-SELECT key / 0 FROM DECIMAL_UDF limit 1
+SELECT key / 0 FROM DECIMAL_UDF
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
enabled: true
@@ -1570,7 +1592,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1582,23 +1604,17 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: DecimalColDivideDecimalScalar(col 0:decimal(20,10), val 0) -> 3:decimal(22,12)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 1
- Limit Vectorization:
- className: VectorLimitOperator
- native: true
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1619,19 +1635,57 @@ STAGE PLANS:
Stage: Stage-0
Fetch Operator
- limit: 1
+ limit: -1
Processor Tree:
ListSink
-PREHOOK: query: SELECT key / 0 FROM DECIMAL_UDF limit 1
+PREHOOK: query: SELECT key / 0 FROM DECIMAL_UDF
PREHOOK: type: QUERY
PREHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-POSTHOOK: query: SELECT key / 0 FROM DECIMAL_UDF limit 1
+POSTHOOK: query: SELECT key / 0 FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key / key FROM DECIMAL_UDF WHERE key is not null and key <> 0
PREHOOK: type: QUERY
@@ -1655,7 +1709,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1665,7 +1719,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDecimalColNotEqualDecimalScalar(col 0:decimal(20,10), val 0)
predicate: (key <> 0) (type: boolean)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (key / key) (type: decimal(38,18))
outputColumnNames: _col0
@@ -1674,13 +1728,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(20,10), col 0:decimal(20,10)) -> 3:decimal(38,18)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1774,7 +1828,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1784,7 +1838,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColNotEqualLongScalar(col 1:int, val 0)
predicate: (value <> 0) (type: boolean)
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (key / CAST( value AS decimal(10,0))) (type: decimal(31,21))
outputColumnNames: _col0
@@ -1793,13 +1847,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(20,10), col 3:decimal(10,0))(children: CastLongToDecimal(col 1:int) -> 3:decimal(10,0)) -> 4:decimal(31,21)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1837,6 +1891,10 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-1.000000000000000000000
+0.102000000000000000000
+0.785000000000000000000
+1.000000000000000000000
+1.000000000000000000000
1.000000000000000000000
1.000000000000000000000
1.000000000000000000000
@@ -1845,21 +1903,17 @@ POSTHOOK: Input: default@decimal_udf
1.000000000000000000000
1.000000000000000000000
1.000000000000000000000
+1.000000000099999992710
+1.000000000100000000000
+1.000390438247011952191
+1.001600000000000000000
+1.046666666666666666667
+1.046666666666666666667
1.046666666666666666667
1.120000000000000000000
1.120000000000000000000
-0.102000000000000000000
1.120000000000000000000
1.122000000000000000000
-1.000000000000000000000
-1.001600000000000000000
-1.000390438247011952191
-1.046666666666666666667
-1.046666666666666666667
-0.785000000000000000000
-1.000000000000000000000
-1.000000000100000000000
-1.000000000099999992710
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key / (value/2) FROM DECIMAL_UDF WHERE value is not null and value <> 0
PREHOOK: type: QUERY
@@ -1883,7 +1937,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -1893,7 +1947,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColNotEqualLongScalar(col 1:int, val 0)
predicate: (value <> 0) (type: boolean)
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (UDFToDouble(key) / (UDFToDouble(value) / 2.0)) (type: double)
outputColumnNames: _col0
@@ -1902,13 +1956,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: DoubleColDivideDoubleColumn(col 3:double, col 5:double)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double, DoubleColDivideDoubleScalar(col 4:double, val 2.0)(children: CastLongToDouble(col 1:int) -> 4:double) -> 5:double) -> 4:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1946,6 +2000,10 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-2.0
+0.20400000000000001
+1.57
+2.0
+2.0
2.0
2.0
2.0
@@ -1954,21 +2012,17 @@ POSTHOOK: Input: default@decimal_udf
2.0
2.0
2.0
+2.0000000002
+2.0000000002
+2.000780876494024
+2.0032
+2.0933333333333333
+2.0933333333333333
2.0933333333333333
2.24
2.24
-0.20400000000000001
2.24
2.244
-2.0
-2.0032
-2.000780876494024
-2.0933333333333333
-2.0933333333333333
-1.57
-2.0
-2.0000000002
-2.0000000002
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT 1 + (key / '2.0') FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -1992,7 +2046,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2004,13 +2058,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: DoubleScalarAddDoubleColumn(val 1.0, col 4:double)(children: DoubleColDivideDoubleScalar(col 3:double, val 2.0)(children: CastDecimalToDouble(col 0:decimal(20,10)) -> 3:double) -> 4:double) -> 3:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2048,43 +2102,44 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-2199.0
-NULL
+-6.172839440617284E8
+-626.745
+0.43899999999999995
+0.43999999999999995
+0.43999999999999995
+0.8335
+0.835
+0.85
1.0
1.0
-51.0
-6.0
-1.5
-1.05
-1.005
-101.0
-11.0
-2.0
1.0
-1.1
+1.005
1.01
+1.05
+1.1
1.15
1.165
1.1665
-0.85
-0.835
-0.8335
1.5
-2.0
-2.5700000000000003
-0.43999999999999995
-0.43999999999999995
-0.43899999999999995
+1.5
+1.5
1.56
1.561
-63.0
-63.6
--626.745
+101.0
+11.0
+2.0
+2.0
2.5700000000000003
2.5700000000000003
2.5700000000000003
-1.5
--6.172839440617284E8
+2.5700000000000003
+51.0
+6.0
6.172839460617284E8
+63.0
+63.6
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT abs(key) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -2108,7 +2163,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2120,13 +2175,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: FuncAbsDecimalToDecimal(col 0:decimal(20,10)) -> 3:decimal(20,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2163,44 +2218,45 @@ POSTHOOK: query: SELECT abs(key) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-4400.0000000000
-NULL
0.0000000000
0.0000000000
-100.0000000000
-10.0000000000
-1.0000000000
-0.1000000000
-0.0100000000
-200.0000000000
-20.0000000000
-2.0000000000
0.0000000000
-0.2000000000
+0.0100000000
0.0200000000
+0.1000000000
+0.2000000000
0.3000000000
-0.3300000000
-0.3330000000
0.3000000000
0.3300000000
+0.3300000000
+0.3330000000
0.3330000000
1.0000000000
-2.0000000000
-3.1400000000
+1.0000000000
+1.0000000000
1.1200000000
1.1200000000
-1.1220000000
1.1200000000
1.1220000000
+1.1220000000
+10.0000000000
+100.0000000000
+1234567890.1234567800
+1234567890.1234567890
124.0000000000
125.2000000000
1255.4900000000
+2.0000000000
+2.0000000000
+20.0000000000
+200.0000000000
3.1400000000
3.1400000000
3.1400000000
-1.0000000000
-1234567890.1234567890
-1234567890.1234567800
+3.1400000000
+4400.0000000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT value, sum(key) / count(key), avg(key), sum(key) FROM DECIMAL_UDF GROUP BY value ORDER BY value
PREHOOK: type: QUERY
@@ -2228,7 +2284,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2239,7 +2295,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(key), count(key), avg(key)
Group By Vectorization:
@@ -2253,7 +2309,7 @@ STAGE PLANS:
keys: value (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 17 Data size: 7004 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 18 Data size: 7416 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -2264,7 +2320,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [1, 2, 3]
- Statistics: Num rows: 17 Data size: 7004 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 18 Data size: 7416 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: decimal(30,10)), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:decimal(30,10),input:decimal(20,10)>)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2382,23 +2438,24 @@ POSTHOOK: query: SELECT value, sum(key) / count(key), avg(key), sum(key) FROM DE
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-1 -1.120000000000000000 -1.12000000000000 -2.2400000000
+-11 -1.122000000000000000 -1.12200000000000 -1.1220000000
-1234567890 -1234567890.123456789000000000 -1234567890.12345678900000 -1234567890.1234567890
-1255 -1255.490000000000000000 -1255.49000000000000 -1255.4900000000
--11 -1.122000000000000000 -1.12200000000000 -1.1220000000
--1 -1.120000000000000000 -1.12000000000000 -2.2400000000
0 0.025384615384615385 0.02538461538462 0.3300000000
1 1.048400000000000000 1.04840000000000 5.2420000000
-2 2.000000000000000000 2.00000000000000 4.0000000000
-3 3.140000000000000000 3.14000000000000 9.4200000000
-4 3.140000000000000000 3.14000000000000 3.1400000000
10 10.000000000000000000 10.00000000000000 10.0000000000
-20 20.000000000000000000 20.00000000000000 20.0000000000
100 100.000000000000000000 100.00000000000000 100.0000000000
+1234567890 1234567890.123456780000000000 1234567890.12345678000000 1234567890.1234567800
124 124.000000000000000000 124.00000000000000 124.0000000000
125 125.200000000000000000 125.20000000000000 125.2000000000
+2 2.000000000000000000 2.00000000000000 4.0000000000
+20 20.000000000000000000 20.00000000000000 20.0000000000
200 200.000000000000000000 200.00000000000000 200.0000000000
+3 3.140000000000000000 3.14000000000000 9.4200000000
+4 3.140000000000000000 3.14000000000000 3.1400000000
4400 -4400.000000000000000000 -4400.00000000000000 -4400.0000000000
-1234567890 1234567890.123456780000000000 1234567890.12345678000000 1234567890.1234567800
+NULL NULL NULL NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT -key FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -2422,7 +2479,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2434,13 +2491,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: FuncNegateDecimalToDecimal(col 0:decimal(20,10)) -> 3:decimal(20,10)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2477,44 +2534,45 @@ POSTHOOK: query: SELECT -key FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-4400.0000000000
-NULL
-0.0000000000
-0.0000000000
--100.0000000000
--10.0000000000
--1.0000000000
--0.1000000000
-0.0100000000
--200.0000000000
--20.0000000000
--2.0000000000
-0.0000000000
--0.2000000000
-0.0200000000
+-0.1000000000
+-0.2000000000
-0.3000000000
-0.3300000000
-0.3330000000
-0.3000000000
-0.3300000000
-0.3330000000
-1.0000000000
--2.0000000000
--3.1400000000
-1.1200000000
-1.1200000000
-1.1220000000
+-1.0000000000
+-1.0000000000
-1.1200000000
-1.1220000000
+-10.0000000000
+-100.0000000000
+-1234567890.1234567800
-124.0000000000
-125.2000000000
-1255.4900000000
+-2.0000000000
+-2.0000000000
+-20.0000000000
+-200.0000000000
-3.1400000000
-3.1400000000
-3.1400000000
--1.0000000000
+-3.1400000000
+0.0000000000
+0.0000000000
+0.0000000000
+0.3000000000
+0.3300000000
+0.3330000000
+1.1200000000
+1.1200000000
+1.1220000000
1234567890.1234567890
--1234567890.1234567800
+1255.4900000000
+4400.0000000000
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT +key FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -2548,44 +2606,45 @@ POSTHOOK: query: SELECT +key FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.3000000000
+-0.3300000000
+-0.3330000000
+-1.1200000000
+-1.1200000000
+-1.1220000000
+-1234567890.1234567890
+-1255.4900000000
-4400.0000000000
-NULL
0.0000000000
0.0000000000
-100.0000000000
-10.0000000000
-1.0000000000
-0.1000000000
+0.0000000000
0.0100000000
-200.0000000000
-20.0000000000
-2.0000000000
-0.0000000000
-0.2000000000
0.0200000000
+0.1000000000
+0.2000000000
0.3000000000
0.3300000000
0.3330000000
--0.3000000000
--0.3300000000
--0.3330000000
1.0000000000
-2.0000000000
-3.1400000000
--1.1200000000
--1.1200000000
--1.1220000000
+1.0000000000
+1.0000000000
1.1200000000
1.1220000000
+10.0000000000
+100.0000000000
+1234567890.1234567800
124.0000000000
125.2000000000
--1255.4900000000
+2.0000000000
+2.0000000000
+20.0000000000
+200.0000000000
3.1400000000
3.1400000000
3.1400000000
-1.0000000000
--1234567890.1234567890
-1234567890.1234567800
+3.1400000000
+NULL
+NULL
PREHOOK: query: EXPlAIN SELECT CEIL(key) FROM DECIMAL_UDF
PREHOOK: type: QUERY
POSTHOOK: query: EXPlAIN SELECT CEIL(key) FROM DECIMAL_UDF
@@ -2603,14 +2662,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ceil(key) (type: decimal(11,0))
outputColumnNames: _col0
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2632,44 +2691,45 @@ POSTHOOK: query: SELECT CEIL(key) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-1
+-1
+-1
+-1234567890
+-1255
-4400
-NULL
0
0
-100
-10
+0
+0
+0
+0
+1
1
1
1
-200
-20
-2
-0
1
1
1
1
1
-0
-0
-0
1
+10
+100
+1234567891
+124
+126
2
-4
--1
--1
--1
2
2
-124
-126
--1255
+2
+20
+200
4
4
4
-1
--1234567890
-1234567891
+4
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT FLOOR(key) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -2693,7 +2753,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2705,13 +2765,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: FuncFloorDecimalToDecimal(col 0:decimal(20,10)) -> 3:decimal(11,0)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2748,44 +2808,45 @@ POSTHOOK: query: SELECT FLOOR(key) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-1
+-1
+-1
+-1234567891
+-1256
+-2
+-2
+-2
-4400
-NULL
0
0
-100
-10
-1
0
0
-200
-20
-2
0
0
0
0
0
0
--1
--1
--1
1
-2
-3
--2
--2
--2
1
1
+1
+1
+10
+100
+1234567890
124
125
--1256
+2
+2
+20
+200
3
3
3
-1
--1234567891
-1234567890
+3
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT ROUND(key, 2) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -2809,7 +2870,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2821,13 +2882,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(20,10), decimalPlaces 2) -> 3:decimal(13,2)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2864,44 +2925,45 @@ POSTHOOK: query: SELECT ROUND(key, 2) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.30
+-0.33
+-0.33
+-1.12
+-1.12
+-1.12
+-1234567890.12
+-1255.49
-4400.00
-NULL
0.00
0.00
-100.00
-10.00
-1.00
-0.10
-0.01
-200.00
-20.00
-2.00
0.00
-0.20
+0.01
0.02
+0.10
+0.20
0.30
0.33
0.33
--0.30
--0.33
--0.33
1.00
-2.00
-3.14
--1.12
--1.12
--1.12
+1.00
+1.00
1.12
1.12
+10.00
+100.00
+1234567890.12
124.00
125.20
--1255.49
+2.00
+2.00
+20.00
+200.00
3.14
3.14
3.14
-1.00
--1234567890.12
-1234567890.12
+3.14
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT POWER(key, 2) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -2925,7 +2987,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -2937,13 +2999,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: VectorUDFAdaptor(power(key, 2)) -> 3:double
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 304 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2980,44 +3042,45 @@ POSTHOOK: query: SELECT POWER(key, 2) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-1.936E7
-NULL
0.0
0.0
-10000.0
-100.0
-1.0
-0.010000000000000002
-1.0E-4
-40000.0
-400.0
-4.0
0.0
+0.010000000000000002
0.04000000000000001
-4.0E-4
0.09
-0.10890000000000001
-0.11088900000000002
0.09
0.10890000000000001
+0.10890000000000001
+0.11088900000000002
0.11088900000000002
1.0
-4.0
-9.8596
+1.0
+1.0
+1.0E-4
1.2544000000000002
1.2544000000000002
-1.2588840000000003
1.2544000000000002
1.2588840000000003
+1.2588840000000003
+1.52415787532388352E18
+1.52415787532388352E18
+1.936E7
+100.0
+10000.0
15376.0
15675.04
1576255.1401
+4.0
+4.0
+4.0E-4
+400.0
+40000.0
9.8596
9.8596
9.8596
-1.0
-1.52415787532388352E18
-1.52415787532388352E18
+9.8596
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT (key + 1) % (key / 2) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -3041,7 +3104,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -3053,13 +3116,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5]
selectExpressions: DecimalColModuloDecimalColumn(col 3:decimal(21,10), col 4:decimal(22,12))(children: DecimalColAddDecimalScalar(col 0:decimal(20,10), val 1) -> 3:decimal(21,10), DecimalColDivideDecimalScalar(col 0:decimal(20,10), val 2) -> 4:decimal(22,12)) -> 5:decimal(22,12)
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3096,44 +3159,45 @@ POSTHOOK: query: SELECT (key + 1) % (key / 2) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
+-0.120000000000
+-0.120000000000
+-0.122000000000
-2199.000000000000
-NULL
-NULL
-NULL
-1.000000000000
-1.000000000000
+-617283944.061728394500
+-626.745000000000
0.000000000000
0.000000000000
0.000000000000
-1.000000000000
-1.000000000000
0.000000000000
-NULL
0.000000000000
0.000000000000
-0.100000000000
-0.010000000000
-0.001000000000
-0.100000000000
-0.010000000000
-0.001000000000
0.000000000000
0.000000000000
-1.000000000000
--0.120000000000
--0.120000000000
--0.122000000000
-0.440000000000
+0.000000000000
+0.001000000000
+0.001000000000
+0.010000000000
+0.010000000000
+0.100000000000
+0.100000000000
0.439000000000
+0.440000000000
+1.000000000000
+1.000000000000
1.000000000000
1.000000000000
--626.745000000000
1.000000000000
1.000000000000
1.000000000000
-0.000000000000
--617283944.061728394500
1.000000000000
+1.000000000000
+1.000000000000
+1.000000000000
+NULL
+NULL
+NULL
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT value, stddev(key), variance(key) FROM DECIMAL_UDF GROUP BY value
PREHOOK: type: QUERY
@@ -3160,7 +3224,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -3171,7 +3235,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: stddev(key), variance(key)
Group By Vectorization:
@@ -3185,7 +3249,7 @@ STAGE PLANS:
keys: value (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 17 Data size: 2788 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 18 Data size: 2952 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -3196,7 +3260,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [1, 2]
- Statistics: Num rows: 17 Data size: 2788 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 18 Data size: 2952 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3270,23 +3334,24 @@ POSTHOOK: query: SELECT value, stddev(key), variance(key) FROM DECIMAL_UDF GROUP
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-4 0.0 0.0
+-1 0.0 0.0
+-11 0.0 0.0
-1234567890 0.0 0.0
+-1255 0.0 0.0
0 0.22561046704494161 0.050900082840236685
1 0.05928102563215321 0.0035142400000000066
-2 0.0 0.0
-3 0.0 0.0
-124 0.0 0.0
-200 0.0 0.0
-4400 0.0 0.0
-1234567890 0.0 0.0
10 0.0 0.0
+100 0.0 0.0
+1234567890 0.0 0.0
+124 0.0 0.0
125 0.0 0.0
--1255 0.0 0.0
--11 0.0 0.0
--1 0.0 0.0
+2 0.0 0.0
20 0.0 0.0
-100 0.0 0.0
+200 0.0 0.0
+3 0.0 0.0
+4 0.0 0.0
+4400 0.0 0.0
+NULL NULL NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT value, stddev_samp(key), var_samp(key) FROM DECIMAL_UDF GROUP BY value
PREHOOK: type: QUERY
@@ -3313,7 +3378,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -3324,7 +3389,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4412 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: stddev_samp(key), var_samp(key)
Group By Vectorization:
@@ -3338,7 +3403,7 @@ STAGE PLANS:
keys: value (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 17 Data size: 2788 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 18 Data size: 2952 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -3349,7 +3414,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [1, 2]
- Statistics: Num rows: 17 Data size: 2788 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 18 Data size: 2952 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3423,23 +3488,24 @@ POSTHOOK: query: SELECT value, stddev_samp(key), var_samp(key) FROM DECIMAL_UDF
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf
#### A masked pattern was here ####
-4 NULL NULL
+-1 0.0 0.0
+-11 NULL NULL
-1234567890 NULL NULL
+-1255 NULL NULL
0 0.2348228191855647 0.055141756410256405
1 0.06627820154470102 0.004392800000000008
-2 0.0 0.0
-3 0.0 0.0
-124 NULL NULL
-200 NULL NULL
-4400 NULL NULL
-1234567890 NULL NULL
10 NULL NULL
+100 NULL NULL
+1234567890 NULL NULL
+124 NULL NULL
125 NULL NULL
--1255 NULL NULL
--11 NULL NULL
--1 0.0 0.0
+2 0.0 0.0
20 NULL NULL
-100 NULL NULL
+200 NULL NULL
+3 0.0 0.0
+4 NULL NULL
+4400 NULL NULL
+NULL NULL NULL
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT histogram_numeric(key, 3) FROM DECIMAL_UDF
PREHOOK: type: QUERY
@@ -3466,11 +3532,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: decimal(20,10))
outputColumnNames: _col0
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: histogram_numeric(_col0, 3)
mode: hash
@@ -3550,7 +3616,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -3561,7 +3627,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(key)
Group By Vectorization:
@@ -3681,7 +3747,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -3692,7 +3758,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(key)
Group By Vectorization:
@@ -3812,7 +3878,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_udf
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:decimal(20,10), 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -3823,7 +3889,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 38 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 39 Data size: 4256 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(key)
Group By Vectorization:
@@ -3939,6 +4005,16 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv7.txt' INTO TABLE DE
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@decimal_udf_txt_small
+PREHOOK: query: insert into DECIMAL_UDF_txt_small values (NULL, NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@decimal_udf_txt_small
+POSTHOOK: query: insert into DECIMAL_UDF_txt_small values (NULL, NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@decimal_udf_txt_small
+POSTHOOK: Lineage: decimal_udf_txt_small.key EXPRESSION []
+POSTHOOK: Lineage: decimal_udf_txt_small.value EXPRESSION []
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT key + key FROM DECIMAL_UDF_txt_small
PREHOOK: type: QUERY
@@ -4018,44 +4094,45 @@ POSTHOOK: query: SELECT key + key FROM DECIMAL_UDF_txt_small
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_udf_txt_small
#### A masked pattern was here ####
+-0.600
+-0.660
+-0.666
+-2.240
+-2.240
+-2.244
+-2469135780.246
+-2510.980
-8800.000
-NULL
0.000
0.000
-200.000
-20.000
-2.000
-0.200
-0.020
-400.000
-40.000
-4.000
0.000
-0.400
+0.020
0.040
+0.200
+0.400
0.600
-0.660
-0.666
--0.600
--0.660
--0.666
+0.660
+0.666
+2.000
+2.000
2.000
-4.000
-6.280
--2.240
--2.240
--2.244
2.240
2.244
+20.000
+200.000
+2469135780.246
248.000
250.400
--2510.980
+4.000
+4.000
+40.000
+400.000
6.280
6.280
6.280
-2.000
--2469135780.246
-2469135780.246
+6.280
+NULL
+NULL
PREHOOK: query: EXPLAIN VECTORIZ
<TRUNCATED>