You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/04/30 20:05:27 UTC
[01/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Repository: hive
Updated Branches:
refs/heads/master 6953b6799 -> 95d6d9b3d
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_casts.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_casts.q.out b/ql/src/test/results/clientpositive/vectorized_casts.q.out
index 58c4846..c79d8d7 100644
--- a/ql/src/test/results/clientpositive/vectorized_casts.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_casts.q.out
@@ -162,7 +162,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -172,7 +172,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 250) -> 13:bigint)
predicate: ((cbigint % 250) = 0) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToBoolean(ctinyint) (type: boolean), UDFToBoolean(csmallint) (type: boolean), UDFToBoolean(cint) (type: boolean), UDFToBoolean(cbigint) (type: boolean), UDFToBoolean(cfloat) (type: boolean), UDFToBoolean(cdouble) (type: boolean), cboolean1 (type: boolean), UDFToBoolean((cbigint * 0L)) (type: boolean), UDFToBoolean(ctimestamp1) (type: boolean), UDFToBoolean(cstring1) (type: boolean), UDFToInteger(ctinyint) (type: int), UDFToInteger(csmallint) (type: int), cint (type: int), UDFToInteger(cbigint) (type: int), UDFToInteger(cfloat) (type: int), UDFToInteger(cdouble) (type: int), UDFToInteger(cboolean1) (type: int), UDFToInteger(ctimestamp1) (type: int), UDFToInteger(cstring1) (type: int), UDFToInteger(substr(cstring1, 1, 1)) (type: int), UDFToByte(cfloat) (type: tinyint), UDFToShort(cfloat) (type: smallint), UDFToLong(cfloat) (type: bigint), UDFToDouble(ctinyint) (type: double), UDFToDouble(csmallint) (type: double), UDFToDouble(cint) (type: double), UDFTo
Double(cbigint) (type: double), UDFToDouble(cfloat) (type: double), cdouble (type: double), UDFToDouble(cboolean1) (type: double), UDFToDouble(ctimestamp1) (type: double), UDFToDouble(cstring1) (type: double), UDFToDouble(substr(cstring1, 1, 1)) (type: double), UDFToFloat(cint) (type: float), UDFToFloat(cdouble) (type: float), CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), CAST( CAST( ctimestamp1 AS DATE) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp), UDFToString(ctinyint) (type: string), UDFToString(csmallint) (type: string),
UDFToString(cint) (type: string), UDFToString(cbigint) (type: string), UDFToString(cfloat) (type: string), UDFToString(cdouble) (type: string), UDFToString(cboolean1) (type: string), UDFToString((cbigint * 0L)) (type: string), UDFToString(ctimestamp1) (type: string), cstring1 (type: string), UDFToString(CAST( cstring1 AS CHAR(10))) (type: string), UDFToString(CAST( cstring1 AS varchar(10))) (type: string), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), UDFToString(sin(cfloat)) (type: string), (UDFToDouble(UDFToFloat(cint)) + UDFToDouble(cboolean1)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55, _col56, _col57, _col58, _col59, _col60, _col61, _col62
@@ -181,13 +181,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 14, 15, 16, 17, 18, 10, 20, 19, 21, 0, 1, 2, 3, 22, 23, 10, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 4, 5, 35, 36, 37, 38, 39, 5, 41, 43, 45, 47, 48, 49, 51, 54, 55, 8, 56, 57, 26, 58, 59, 60, 61, 62, 63, 64, 65, 6, 67, 68, 69, 70, 66, 73]
selectExpressions: CastLongToBooleanViaLongToLong(col 0:tinyint) -> 13:boolean, CastLongToBooleanViaLongToLong(col 1:smallint) -> 14:boolean, CastLongToBooleanViaLongToLong(col 2:int) -> 15:boolean, CastLongToBooleanViaLongToLong(col 3:bigint) -> 16:boolean, CastDoubleToBooleanViaDoubleToLong(col 4:float) -> 17:boolean, CastDoubleToBooleanViaDoubleToLong(col 5:double) -> 18:boolean, CastLongToBooleanViaLongToLong(col 19:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 19:bigint) -> 20:boolean, CastTimestampToBoolean(col 8:timestamp) -> 19:boolean, CastStringToBoolean(col 6) -> 21:boolean, CastDoubleToLong(col 4:float) -> 22:int, CastDoubleToLong(col 5:double) -> 23:int, CastTimestampToLong(col 8:timestamp) -> 24:int, CastStringToLong(col 6:string) -> 25:int, CastStringToLong(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 27:int, CastDoubleToLong(col 4:float) -> 28:tinyint, CastDoubleToLong(col
4:float) -> 29:smallint, CastDoubleToLong(col 4:float) -> 30:bigint, CastLongToDouble(col 0:tinyint) -> 31:double, CastLongToDouble(col 1:smallint) -> 32:double, CastLongToDouble(col 2:int) -> 33:double, CastLongToDouble(col 3:bigint) -> 34:double, CastLongToDouble(col 10:boolean) -> 35:double, CastTimestampToDouble(col 8:timestamp) -> 36:double, CastStringToDouble(col 6:string) -> 37:double, CastStringToDouble(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 38:double, CastLongToFloatViaLongToDouble(col 2:int) -> 39:float, CastMillisecondsLongToTimestamp(col 0:tinyint) -> 41:timestamp, CastMillisecondsLongToTimestamp(col 1:smallint) -> 43:timestamp, CastMillisecondsLongToTimestamp(col 2:int) -> 45:timestamp, CastMillisecondsLongToTimestamp(col 3:bigint) -> 47:timestamp, CastDoubleToTimestamp(col 4:float) -> 48:timestamp, CastDoubleToTimestamp(col 5:double) -> 49:timestamp, CastMillisecondsLongToTimestamp(col 10:boolean) -> 51:times
tamp, CastMillisecondsLongToTimestamp(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 54:timestamp, CastDateToTimestamp(col 52:date)(children: CastTimestampToDate(col 8:timestamp) -> 52:date) -> 55:timestamp, VectorUDFAdaptor(CAST( cstring1 AS TIMESTAMP)) -> 56:timestamp, VectorUDFAdaptor(CAST( substr(cstring1, 1, 1) AS TIMESTAMP))(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 57:timestamp, CastLongToString(col 0:tinyint) -> 26:string, CastLongToString(col 1:smallint) -> 58:string, CastLongToString(col 2:int) -> 59:string, CastLongToString(col 3:bigint) -> 60:string, CastFloatToString(col 4:float) -> 61:string, CastDoubleToString(col 5:double) -> 62:string, CastBooleanToStringViaLongToString(col 10:boolean) -> 63:string, CastLongToString(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 64:string, VectorUDFAdaptor(UDFToString(ctimestamp1)) -> 65:string, CastStringGro
upToString(col 66:char(10))(children: CastStringGroupToChar(col 6:string, maxLength 10) -> 66:char(10)) -> 67:string, CastStringGroupToString(col 66:varchar(10))(children: CastStringGroupToVarChar(col 6:string, maxLength 10) -> 66:varchar(10)) -> 68:string, CastLongToFloatViaLongToDouble(col 52:int)(children: CastDoubleToLong(col 4:float) -> 52:int) -> 69:float, CastLongToDouble(col 52:int)(children: LongColMultiplyLongScalar(col 2:int, val 2) -> 52:int) -> 70:double, CastDoubleToString(col 71:double)(children: FuncSinDoubleToDouble(col 4:float) -> 71:double) -> 66:string, DoubleColAddDoubleColumn(col 71:double, col 72:double)(children: col 71:float, CastLongToDouble(col 10:boolean) -> 72:double) -> 73:double
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out
index 3847481..1c292d4 100644
--- a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out
@@ -111,21 +111,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), sum(DISTINCT _col2), sum(DISTINCT _col1)
keys: _col0 (type: int), _col2 (type: double), _col1 (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: double)
sort order: +++
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out
index d9c781c..3a1c0e7 100644
--- a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out
@@ -26,14 +26,14 @@ STAGE PLANS:
$hdt$_0:$hdt$_0:t1
TableScan
alias: t1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: int)
@@ -44,7 +44,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -53,7 +53,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
@@ -61,7 +61,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -76,7 +76,7 @@ STAGE PLANS:
nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int)
outputColumnNames: _col0, _col1, _col2
@@ -85,7 +85,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2]
selectExpressions: LongColAddLongColumn(col 0:int, col 1:int) -> 2:int
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out
index 52ddd19..aea8f0a 100644
--- a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out
@@ -116,7 +116,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -125,7 +125,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 500) -> 13:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 14:double, val -1.0)(children: FuncSinDoubleToDouble(col 4:float) -> 14:double))
predicate: (((cbigint % 500) = 0) and (sin(cfloat) >= -1.0D)) (type: boolean)
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double), round(cdouble, 2) (type: double), floor(cdouble) (type: bigint), ceil(cdouble) (type: bigint), rand() (type: double), rand(98007) (type: double), exp(ln(cdouble)) (type: double), ln(cdouble) (type: double), ln(cfloat) (type: double), log10(cdouble) (type: double), log2(cdouble) (type: double), log2((cdouble - 15601.0D)) (type: double), log2(cfloat) (type: double), log2(cbigint) (type: double), log2(cint) (type: double), log2(csmallint) (type: double), log2(ctinyint) (type: double), log(2, cdouble) (type: double), power(log2(cdouble), 2) (type: double), power(log2(cdouble), 2) (type: double), sqrt(cdouble) (type: double), sqrt(cbigint) (type: double), bin(cbigint) (type: string), hex(cdouble) (type: string), conv(cbigint, 10, 16) (type: string), abs(cdouble) (type: double), abs(ctinyint) (type: int), (cint pmod 3) (type: int), sin(cdouble) (type: double), asin(cdouble) (type: double), cos(cdouble) (type: double), acos(cdouble) (typ
e: double), atan(cdouble) (type: double), degrees(cdouble) (type: double), radians(cdouble) (type: double), cdouble (type: double), cbigint (type: bigint), (- cdouble) (type: double), sign(cdouble) (type: double), sign(cbigint) (type: double), cos(((- sin(log(cdouble))) + 3.14159D)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40
@@ -134,13 +134,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 14, 13, 15, 16, 17, 19, 18, 20, 21, 22, 24, 23, 25, 26, 27, 28, 29, 31, 32, 30, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 5, 3, 47, 48, 49, 50]
selectExpressions: RoundWithNumDigitsDoubleToDouble(col 5, decimalPlaces 2) -> 14:double, FuncFloorDoubleToLong(col 5:double) -> 13:bigint, FuncCeilDoubleToLong(col 5:double) -> 15:bigint, FuncRandNoSeed -> 16:double, FuncRand -> 17:double, FuncExpDoubleToDouble(col 18:double)(children: FuncLnDoubleToDouble(col 5:double) -> 18:double) -> 19:double, FuncLnDoubleToDouble(col 5:double) -> 18:double, FuncLnDoubleToDouble(col 4:float) -> 20:double, FuncLog10DoubleToDouble(col 5:double) -> 21:double, FuncLog2DoubleToDouble(col 5:double) -> 22:double, FuncLog2DoubleToDouble(col 23:double)(children: DoubleColSubtractDoubleScalar(col 5:double, val 15601.0) -> 23:double) -> 24:double, FuncLog2DoubleToDouble(col 4:float) -> 23:double, FuncLog2LongToDouble(col 3:bigint) -> 25:double, FuncLog2LongToDouble(col 2:int) -> 26:double, FuncLog2LongToDouble(col 1:smallint) -> 27:double, FuncLog2LongToDouble(col 0:tinyint) -> 28:double, FuncLogWithBaseDoubleToDouble(col 5:double) ->
29:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 5:double) -> 30:double) -> 31:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 5:double) -> 30:double) -> 32:double, FuncSqrtDoubleToDouble(col 5:double) -> 30:double, FuncSqrtLongToDouble(col 3:bigint) -> 33:double, FuncBin(col 3:bigint) -> 34:string, VectorUDFAdaptor(hex(cdouble)) -> 35:string, VectorUDFAdaptor(conv(cbigint, 10, 16)) -> 36:string, FuncAbsDoubleToDouble(col 5:double) -> 37:double, FuncAbsLongToLong(col 0:tinyint) -> 38:int, PosModLongToLong(col 2, divisor 3) -> 39:int, FuncSinDoubleToDouble(col 5:double) -> 40:double, FuncASinDoubleToDouble(col 5:double) -> 41:double, FuncCosDoubleToDouble(col 5:double) -> 42:double, FuncACosDoubleToDouble(col 5:double) -> 43:double, FuncATanDoubleToDouble(col 5:double) -> 44:double, FuncDegreesDoubleToDouble(col 5:double) -> 45:double, FuncRadiansDoubleToDouble(col 5:double) -> 46:double, DoubleColUnaryMinus(co
l 5:double) -> 47:double, FuncSignDoubleToDouble(col 5:double) -> 48:double, FuncSignLongToDouble(col 3:bigint) -> 49:double, FuncCosDoubleToDouble(col 51:double)(children: DoubleColAddDoubleScalar(col 50:double, val 3.14159)(children: DoubleColUnaryMinus(col 51:double)(children: FuncSinDoubleToDouble(col 50:double)(children: FuncLnDoubleToDouble(col 5:double) -> 50:double) -> 51:double) -> 50:double) -> 51:double) -> 50:double
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out
index 1fe360f..389a2ce 100644
--- a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out
@@ -22,34 +22,34 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: t2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Vectorization:
enabled: false
enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false
@@ -65,11 +65,11 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2)
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out
index 51f3d5b..77a91b9 100644
--- a/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out
@@ -56,17 +56,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (((cbigint % 237) = 0) and (cstring1 like '%') and (length(substr(cstring1, 1, 2)) <= 2)) (type: boolean)
- Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: substr(cstring1, 1, 2) (type: string), substr(cstring1, 2) (type: string), lower(cstring1) (type: string), upper(cstring1) (type: string), upper(cstring1) (type: string), length(cstring1) (type: int), trim(cstring1) (type: string), ltrim(cstring1) (type: string), rtrim(cstring1) (type: string), concat(cstring1, cstring2) (type: string), concat('>', cstring1) (type: string), concat(cstring1, '<') (type: string), concat(substr(cstring1, 1, 2), substr(cstring2, 1, 2)) (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out
index fd9fd38..f12a2b6 100644
--- a/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out
@@ -48,7 +48,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -57,7 +57,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 250) -> 13:bigint)
predicate: ((cbigint % 250) = 0) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -66,13 +66,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [15, 17, 19, 21, 22, 23, 25, 27, 8, 28, 30]
selectExpressions: CastMillisecondsLongToTimestamp(col 0:tinyint) -> 15:timestamp, CastMillisecondsLongToTimestamp(col 1:smallint) -> 17:timestamp, CastMillisecondsLongToTimestamp(col 2:int) -> 19:timestamp, CastMillisecondsLongToTimestamp(col 3:bigint) -> 21:timestamp, CastDoubleToTimestamp(col 4:float) -> 22:timestamp, CastDoubleToTimestamp(col 5:double) -> 23:timestamp, CastMillisecondsLongToTimestamp(col 10:boolean) -> 25:timestamp, CastMillisecondsLongToTimestamp(col 13:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 13:bigint) -> 27:timestamp, VectorUDFAdaptor(CAST( cstring1 AS TIMESTAMP)) -> 28:timestamp, VectorUDFAdaptor(CAST( substr(cstring1, 1, 1) AS TIMESTAMP))(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 29:string) -> 30:timestamp
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -208,7 +208,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -217,7 +217,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 250) -> 13:bigint)
predicate: ((cbigint % 250) = 0) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -226,13 +226,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [14, 15, 16, 17, 18, 19, 20, 21, 8, 22, 24]
selectExpressions: CastLongToTimestamp(col 0:tinyint) -> 14:timestamp, CastLongToTimestamp(col 1:smallint) -> 15:timestamp, CastLongToTimestamp(col 2:int) -> 16:timestamp, CastLongToTimestamp(col 3:bigint) -> 17:timestamp, CastDoubleToTimestamp(col 4:float) -> 18:timestamp, CastDoubleToTimestamp(col 5:double) -> 19:timestamp, CastLongToTimestamp(col 10:boolean) -> 20:timestamp, CastLongToTimestamp(col 13:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 13:bigint) -> 21:timestamp, VectorUDFAdaptor(CAST( cstring1 AS TIMESTAMP)) -> 22:timestamp, VectorUDFAdaptor(CAST( substr(cstring1, 1, 1) AS TIMESTAMP))(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 23:string) -> 24:timestamp
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/windowing_gby2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/windowing_gby2.q.out b/ql/src/test/results/clientpositive/windowing_gby2.q.out
index be790bc..1bbdb9d 100644
--- a/ql/src/test/results/clientpositive/windowing_gby2.q.out
+++ b/ql/src/test/results/clientpositive/windowing_gby2.q.out
@@ -522,19 +522,19 @@ STAGE PLANS:
value expressions: _col1 (type: int), _col2 (type: boolean)
TableScan
alias: wr
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cstring1 is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cstring1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Reduce Operator Tree:
Join Operator
@@ -544,13 +544,13 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col1 (type: string)
outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col3), sum(_col1)
keys: _col2 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -566,7 +566,7 @@ STAGE PLANS:
key expressions: _col0 (type: boolean)
sort order: +
Map-reduce partition columns: _col0 (type: boolean)
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -575,11 +575,11 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -595,14 +595,14 @@ STAGE PLANS:
key expressions: 0 (type: int), (UDFToDouble(_col1) / UDFToDouble(_col2)) (type: double)
sort order: ++
Map-reduce partition columns: 0 (type: int)
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: VALUE._col1 (type: bigint), VALUE._col2 (type: bigint)
outputColumnNames: _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
@@ -623,14 +623,14 @@ STAGE PLANS:
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: rank_window_0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/windowing_streaming.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/windowing_streaming.q.out b/ql/src/test/results/clientpositive/windowing_streaming.q.out
index a8b0e6a..54deed0 100644
--- a/ql/src/test/results/clientpositive/windowing_streaming.q.out
+++ b/ql/src/test/results/clientpositive/windowing_streaming.q.out
@@ -334,18 +334,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: ctinyint (type: tinyint), cdouble (type: double)
sort order: ++
Map-reduce partition columns: ctinyint (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.8
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col5
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
Input definition
@@ -366,17 +366,17 @@ STAGE PLANS:
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (rank_window_0 < 5) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: tinyint), _col5 (type: double), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[04/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
index 58e295d..7f10b90 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
@@ -51,7 +51,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -61,7 +61,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:smallint, val 418), FilterLongColEqualLongScalar(col 1:smallint, val 12205), FilterLongColEqualLongScalar(col 1:smallint, val 10583))
predicate: ((csmallint = 10583S) or (csmallint = 12205S) or (csmallint = 418S)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -70,13 +70,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 17, 21]
selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 16:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprStringScalarStringScalar(col 15:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean) -> 16:string) -> 17:string, IfExprColumnCondExpr(col 15:boolean, col 18:stringcol 20:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 15:boolean, ConstantVectorExpression(val a) -> 18:string, IfExprStringScalarStringScalar(col 19:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 19:boolean) -> 20:string) -> 21:string
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -199,7 +199,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -209,7 +209,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:smallint, val 418), FilterLongColEqualLongScalar(col 1:smallint, val 12205), FilterLongColEqualLongScalar(col 1:smallint, val 10583))
predicate: ((csmallint = 10583S) or (csmallint = 12205S) or (csmallint = 418S)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN (null) ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -218,13 +218,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 18, 24]
selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 17:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprColumnNull(col 15:boolean, col 16:string, null)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean, ConstantVectorExpression(val b) -> 16:string) -> 17:string) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 23:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 19:boolean, ConstantVectorExpression(val a) -> 20:string, IfExprNullColumn(col 21:boolean, null, col 22)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 21:boolean, ConstantVectorExpression(val c) -> 22:string) -> 23:string) -> 24:string
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -283,7 +283,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -295,7 +295,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 14]
selectExpressions: IfExprLongScalarLongScalar(col 14:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongScalarLongScalar(col 15:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), sum(_col1)
Group By Vectorization:
@@ -425,7 +425,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -437,7 +437,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 14]
selectExpressions: IfExprLongColumnLongScalar(col 14:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongColumnLongScalar(col 15:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), sum(_col1)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
index 5104c80..4a80422 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
@@ -24,7 +24,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -33,7 +33,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
@@ -41,7 +41,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
Spark Hash Table Sink Vectorization:
className: VectorSparkHashTableSinkOperator
@@ -72,7 +72,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -81,7 +81,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
@@ -89,7 +89,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -103,7 +103,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int)
outputColumnNames: _col0, _col1, _col2
@@ -112,7 +112,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 2, 13]
selectExpressions: LongColAddLongColumn(col 2:int, col 2:int) -> 13:int
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorized_math_funcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_math_funcs.q.out b/ql/src/test/results/clientpositive/spark/vectorized_math_funcs.q.out
index 0cfc14b..4fbdd2e 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_math_funcs.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_math_funcs.q.out
@@ -119,7 +119,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -128,7 +128,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 500) -> 13:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 14:double, val -1.0)(children: FuncSinDoubleToDouble(col 4:float) -> 14:double))
predicate: (((cbigint % 500) = 0) and (sin(cfloat) >= -1.0D)) (type: boolean)
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double), round(cdouble, 2) (type: double), floor(cdouble) (type: bigint), ceil(cdouble) (type: bigint), rand() (type: double), rand(98007) (type: double), exp(ln(cdouble)) (type: double), ln(cdouble) (type: double), ln(cfloat) (type: double), log10(cdouble) (type: double), log2(cdouble) (type: double), log2((cdouble - 15601.0D)) (type: double), log2(cfloat) (type: double), log2(cbigint) (type: double), log2(cint) (type: double), log2(csmallint) (type: double), log2(ctinyint) (type: double), log(2, cdouble) (type: double), power(log2(cdouble), 2) (type: double), power(log2(cdouble), 2) (type: double), sqrt(cdouble) (type: double), sqrt(cbigint) (type: double), bin(cbigint) (type: string), hex(cdouble) (type: string), conv(cbigint, 10, 16) (type: string), abs(cdouble) (type: double), abs(ctinyint) (type: int), (cint pmod 3) (type: int), sin(cdouble) (type: double), asin(cdouble) (type: double), cos(cdouble) (type: double), acos(cdouble
) (type: double), atan(cdouble) (type: double), degrees(cdouble) (type: double), radians(cdouble) (type: double), cdouble (type: double), cbigint (type: bigint), (- cdouble) (type: double), sign(cdouble) (type: double), sign(cbigint) (type: double), cos(((- sin(log(cdouble))) + 3.14159D)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40
@@ -137,13 +137,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 14, 13, 15, 16, 17, 19, 18, 20, 21, 22, 24, 23, 25, 26, 27, 28, 29, 31, 32, 30, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 5, 3, 47, 48, 49, 50]
selectExpressions: RoundWithNumDigitsDoubleToDouble(col 5, decimalPlaces 2) -> 14:double, FuncFloorDoubleToLong(col 5:double) -> 13:bigint, FuncCeilDoubleToLong(col 5:double) -> 15:bigint, FuncRandNoSeed -> 16:double, FuncRand -> 17:double, FuncExpDoubleToDouble(col 18:double)(children: FuncLnDoubleToDouble(col 5:double) -> 18:double) -> 19:double, FuncLnDoubleToDouble(col 5:double) -> 18:double, FuncLnDoubleToDouble(col 4:float) -> 20:double, FuncLog10DoubleToDouble(col 5:double) -> 21:double, FuncLog2DoubleToDouble(col 5:double) -> 22:double, FuncLog2DoubleToDouble(col 23:double)(children: DoubleColSubtractDoubleScalar(col 5:double, val 15601.0) -> 23:double) -> 24:double, FuncLog2DoubleToDouble(col 4:float) -> 23:double, FuncLog2LongToDouble(col 3:bigint) -> 25:double, FuncLog2LongToDouble(col 2:int) -> 26:double, FuncLog2LongToDouble(col 1:smallint) -> 27:double, FuncLog2LongToDouble(col 0:tinyint) -> 28:double, FuncLogWithBaseDoubleToDouble(col 5:doubl
e) -> 29:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 5:double) -> 30:double) -> 31:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 5:double) -> 30:double) -> 32:double, FuncSqrtDoubleToDouble(col 5:double) -> 30:double, FuncSqrtLongToDouble(col 3:bigint) -> 33:double, FuncBin(col 3:bigint) -> 34:string, VectorUDFAdaptor(hex(cdouble)) -> 35:string, VectorUDFAdaptor(conv(cbigint, 10, 16)) -> 36:string, FuncAbsDoubleToDouble(col 5:double) -> 37:double, FuncAbsLongToLong(col 0:tinyint) -> 38:int, PosModLongToLong(col 2, divisor 3) -> 39:int, FuncSinDoubleToDouble(col 5:double) -> 40:double, FuncASinDoubleToDouble(col 5:double) -> 41:double, FuncCosDoubleToDouble(col 5:double) -> 42:double, FuncACosDoubleToDouble(col 5:double) -> 43:double, FuncATanDoubleToDouble(col 5:double) -> 44:double, FuncDegreesDoubleToDouble(col 5:double) -> 45:double, FuncRadiansDoubleToDouble(col 5:double) -> 46:double, DoubleColUnaryMi
nus(col 5:double) -> 47:double, FuncSignDoubleToDouble(col 5:double) -> 48:double, FuncSignLongToDouble(col 3:bigint) -> 49:double, FuncCosDoubleToDouble(col 51:double)(children: DoubleColAddDoubleScalar(col 50:double, val 3.14159)(children: DoubleColUnaryMinus(col 51:double)(children: FuncSinDoubleToDouble(col 50:double)(children: FuncLnDoubleToDouble(col 5:double) -> 50:double) -> 51:double) -> 50:double) -> 51:double) -> 50:double
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
index 09f2a1a..3abce03 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
@@ -20,14 +20,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: v1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (csmallint is not null and ctinyint is not null) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: tinyint)
@@ -48,14 +48,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: v3
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: csmallint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: smallint)
@@ -83,14 +83,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: v2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -100,11 +100,11 @@ STAGE PLANS:
outputColumnNames: _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: smallint), _col3 (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -114,7 +114,7 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 4
- Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14867 Data size: 3518672 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1)
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorized_shufflejoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/spark/vectorized_shufflejoin.q.out
index 417575a..3cbcf2c 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_shufflejoin.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_shufflejoin.q.out
@@ -27,7 +27,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -36,7 +36,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
@@ -44,7 +44,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -53,7 +53,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -68,7 +68,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -77,7 +77,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
@@ -85,7 +85,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -94,7 +94,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -119,11 +119,11 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2)
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorized_string_funcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_string_funcs.q.out b/ql/src/test/results/clientpositive/spark/vectorized_string_funcs.q.out
index 2fa9016..2a229d2 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_string_funcs.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_string_funcs.q.out
@@ -59,17 +59,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (((cbigint % 237) = 0) and (cstring1 like '%') and (length(substr(cstring1, 1, 2)) <= 2)) (type: boolean)
- Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: substr(cstring1, 1, 2) (type: string), substr(cstring1, 2) (type: string), lower(cstring1) (type: string), upper(cstring1) (type: string), upper(cstring1) (type: string), length(cstring1) (type: int), trim(cstring1) (type: string), ltrim(cstring1) (type: string), rtrim(cstring1) (type: string), concat(cstring1, cstring2) (type: string), concat('>', cstring1) (type: string), concat(cstring1, '<') (type: string), concat(substr(cstring1, 1, 2), substr(cstring2, 1, 2)) (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out
index 3b7e2a3..5c17512 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out
@@ -333,29 +333,29 @@ Stage-0
Stage-1
Reducer 3
File Output Operator [FS_12]
- Select Operator [SEL_11] (rows=1501/10 width=215)
+ Select Operator [SEL_11] (rows=1501/10 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_10]
- Map Join Operator [MAPJOIN_17] (rows=1501/10 width=215)
+ Map Join Operator [MAPJOIN_17] (rows=1501/10 width=236)
Conds:RS_6.KEY.reducesinkkey0=RS_7.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"]
<-Map 4 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_7]
PartitionCols:_col2
- Select Operator [SEL_5] (rows=1365/10 width=215)
+ Select Operator [SEL_5] (rows=1365/10 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
- Filter Operator [FIL_16] (rows=1365/10 width=215)
+ Filter Operator [FIL_16] (rows=1365/10 width=236)
predicate:(cbigint is not null and cint BETWEEN 1000000 AND 3000000)
- TableScan [TS_3] (rows=12288/12288 width=215)
+ TableScan [TS_3] (rows=12288/12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"]
<-Map 1 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_6]
PartitionCols:_col2
- Select Operator [SEL_2] (rows=1365/10 width=215)
+ Select Operator [SEL_2] (rows=1365/10 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
- Filter Operator [FIL_15] (rows=1365/10 width=215)
+ Filter Operator [FIL_15] (rows=1365/10 width=236)
predicate:cint BETWEEN 1000000 AND 3000000
- TableScan [TS_0] (rows=12288/12288 width=215)
+ TableScan [TS_0] (rows=12288/12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"]
PREHOOK: query: select
@@ -432,25 +432,25 @@ Stage-0
Output:["_col0"],aggregations:["count()"]
<-Reducer 2 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_10]
- Map Join Operator [MAPJOIN_18] (rows=1501/10 width=215)
+ Map Join Operator [MAPJOIN_18] (rows=1501/10 width=236)
Conds:RS_6.KEY.reducesinkkey0=RS_7.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true
<-Map 4 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_7]
PartitionCols:_col0
- Select Operator [SEL_5] (rows=1365/10 width=215)
+ Select Operator [SEL_5] (rows=1365/10 width=236)
Output:["_col0"]
- Filter Operator [FIL_17] (rows=1365/10 width=215)
+ Filter Operator [FIL_17] (rows=1365/10 width=236)
predicate:(cbigint is not null and cint BETWEEN 1000000 AND 3000000)
- TableScan [TS_3] (rows=12288/12288 width=215)
+ TableScan [TS_3] (rows=12288/12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"]
<-Map 1 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_6]
PartitionCols:_col0
- Select Operator [SEL_2] (rows=1365/10 width=215)
+ Select Operator [SEL_2] (rows=1365/10 width=236)
Output:["_col0"]
- Filter Operator [FIL_16] (rows=1365/10 width=215)
+ Filter Operator [FIL_16] (rows=1365/10 width=236)
predicate:cint BETWEEN 1000000 AND 3000000
- TableScan [TS_0] (rows=12288/12288 width=215)
+ TableScan [TS_0] (rows=12288/12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint"]
PREHOOK: query: select
@@ -521,34 +521,34 @@ Stage-0
Stage-1
Reducer 4
File Output Operator [FS_15]
- Select Operator [SEL_14] (rows=750/5 width=215)
+ Select Operator [SEL_14] (rows=750/5 width=236)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_13]
- Group By Operator [GBY_11] (rows=750/5 width=215)
+ Group By Operator [GBY_11] (rows=750/5 width=236)
Output:["_col0","_col1"],aggregations:["count()"],keys:KEY._col0
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_10]
PartitionCols:_col0
- Map Join Operator [MAPJOIN_20] (rows=1501/10 width=215)
+ Map Join Operator [MAPJOIN_20] (rows=1501/10 width=236)
Conds:RS_6.KEY.reducesinkkey0=RS_7.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true,Output:["_col0"]
<-Map 5 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_7]
PartitionCols:_col0
- Select Operator [SEL_5] (rows=1365/10 width=215)
+ Select Operator [SEL_5] (rows=1365/10 width=236)
Output:["_col0"]
- Filter Operator [FIL_19] (rows=1365/10 width=215)
+ Filter Operator [FIL_19] (rows=1365/10 width=236)
predicate:(cbigint is not null and cint BETWEEN 1000000 AND 3000000)
- TableScan [TS_3] (rows=12288/12288 width=215)
+ TableScan [TS_3] (rows=12288/12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"]
<-Map 1 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_6]
PartitionCols:_col1
- Select Operator [SEL_2] (rows=1365/10 width=215)
+ Select Operator [SEL_2] (rows=1365/10 width=236)
Output:["_col0","_col1"]
- Filter Operator [FIL_18] (rows=1365/10 width=215)
+ Filter Operator [FIL_18] (rows=1365/10 width=236)
predicate:cint BETWEEN 1000000 AND 3000000
- TableScan [TS_0] (rows=12288/12288 width=215)
+ TableScan [TS_0] (rows=12288/12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["csmallint","cint"]
PREHOOK: query: select
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out b/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out
index c9449e6..f2de761 100644
--- a/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out
+++ b/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out
@@ -44,17 +44,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((cbigint % 250) = 0) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -177,17 +177,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((cbigint % 250) = 0) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_decimal_cast.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_decimal_cast.q.out b/ql/src/test/results/clientpositive/vector_decimal_cast.q.out
index 7bd2af4..0850648 100644
--- a/ql/src/test/results/clientpositive/vector_decimal_cast.q.out
+++ b/ql/src/test/results/clientpositive/vector_decimal_cast.q.out
@@ -16,7 +16,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -26,7 +26,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 5:double), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 10:boolean), SelectColumnIsNotNull(col 8:timestamp))
predicate: (cboolean1 is not null and cdouble is not null and cint is not null and ctimestamp1 is not null) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
@@ -35,19 +35,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 2, 10, 8, 13, 14, 15, 16]
selectExpressions: CastDoubleToDecimal(col 5:double) -> 13:decimal(20,10), CastLongToDecimal(col 2:int) -> 14:decimal(23,14), CastLongToDecimal(col 10:boolean) -> 15:decimal(5,2), CastTimestampToDecimal(col 8:timestamp) -> 16:decimal(15,0)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_elt.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_elt.q.out b/ql/src/test/results/clientpositive/vector_elt.q.out
index 474efb5..1b3e856 100644
--- a/ql/src/test/results/clientpositive/vector_elt.q.out
+++ b/ql/src/test/results/clientpositive/vector_elt.q.out
@@ -20,7 +20,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -29,7 +29,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColGreaterLongScalar(col 0:tinyint, val 0)
predicate: (ctinyint > 0Y) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -38,19 +38,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [14, 6, 2, 17]
selectExpressions: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 14:int, VectorElt(columns [15, 6, 16])(children: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 15:int, col 6:string, CastLongToString(col 2:int) -> 16:string) -> 17:string
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -134,7 +134,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_empty_where.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_empty_where.q.out b/ql/src/test/results/clientpositive/vector_empty_where.q.out
index 6b2c7fe..a77f55f 100644
--- a/ql/src/test/results/clientpositive/vector_empty_where.q.out
+++ b/ql/src/test/results/clientpositive/vector_empty_where.q.out
@@ -19,7 +19,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -28,7 +28,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastStringToBoolean(col 6) -> 13:boolean)
predicate: cstring1 (type: string)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: cint
@@ -36,7 +36,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -48,7 +48,7 @@ STAGE PLANS:
keys: cint (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -58,7 +58,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -78,7 +78,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: partial2
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0)
mode: partial2
@@ -170,7 +170,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -179,7 +179,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastLongToBooleanViaLongToLong(col 2:int) -> 13:boolean)
predicate: cint (type: int)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -191,7 +191,7 @@ STAGE PLANS:
keys: cint (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -201,7 +201,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -221,7 +221,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: partial2
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0)
mode: partial2
@@ -313,7 +313,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -322,7 +322,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastDoubleToBooleanViaDoubleToLong(col 4:float) -> 13:boolean)
predicate: cfloat (type: float)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: cint
@@ -330,7 +330,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -342,7 +342,7 @@ STAGE PLANS:
keys: cint (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -352,7 +352,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -372,7 +372,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: partial2
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0)
mode: partial2
@@ -464,7 +464,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -473,7 +473,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastTimestampToBoolean(col 8:timestamp) -> 13:boolean)
predicate: ctimestamp1 (type: timestamp)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: cint
@@ -481,7 +481,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -493,7 +493,7 @@ STAGE PLANS:
keys: cint (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -503,7 +503,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -523,7 +523,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: partial2
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0)
mode: partial2
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_if_expr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_if_expr.q.out b/ql/src/test/results/clientpositive/vector_if_expr.q.out
index c4d196c..c948ea8 100644
--- a/ql/src/test/results/clientpositive/vector_if_expr.q.out
+++ b/ql/src/test/results/clientpositive/vector_if_expr.q.out
@@ -18,7 +18,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -27,7 +27,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsTrue(col 10:boolean), SelectColumnIsNotNull(col 10:boolean))
predicate: (cboolean1 and cboolean1 is not null) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), if(cboolean1, 'first', 'second') (type: string)
outputColumnNames: _col0, _col1
@@ -36,7 +36,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 13]
selectExpressions: IfExprStringScalarStringScalar(col 10:boolean, val first, val second) -> 13:string
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -45,7 +45,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Execution mode: vectorized
Map Vectorization:
@@ -65,10 +65,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_left_outer_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out
index 2e0b82d..f3ddcd0 100644
--- a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out
+++ b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out
@@ -39,11 +39,11 @@ STAGE PLANS:
$hdt$_1:cd
TableScan
alias: cd
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col1 (type: int)
@@ -51,11 +51,11 @@ STAGE PLANS:
$hdt$_2:hd
TableScan
alias: hd
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: tinyint)
@@ -66,11 +66,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -78,14 +78,14 @@ STAGE PLANS:
0 _col1 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
- Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14867 Data size: 3518672 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out b/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
index 2e792f1..33c09b2 100644
--- a/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
+++ b/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
@@ -16,17 +16,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cint) IN (UDFToInteger(ctinyint), UDFToInteger(cbigint)) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_nvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_nvl.q.out b/ql/src/test/results/clientpositive/vector_nvl.q.out
index 467dc7f..c6eb842 100644
--- a/ql/src/test/results/clientpositive/vector_nvl.q.out
+++ b/ql/src/test/results/clientpositive/vector_nvl.q.out
@@ -22,7 +22,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -31,7 +31,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNull(col 5:double)
predicate: cdouble is null (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: null (type: double), 100.0D (type: double)
outputColumnNames: _col0, _col1
@@ -40,19 +40,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 14]
selectExpressions: ConstantVectorExpression(val null) -> 13:double, ConstantVectorExpression(val 100.0) -> 14:double
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -120,7 +120,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Select Operator
@@ -131,19 +131,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 14]
selectExpressions: VectorCoalesce(columns [4, 13])(children: col 4:float, ConstantVectorExpression(val 1.0) -> 13:float) -> 14:float
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -209,7 +209,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -298,7 +298,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_tablesample_rows.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_tablesample_rows.q.out b/ql/src/test/results/clientpositive/vector_tablesample_rows.q.out
index 5eff6be..b1dce4e 100644
--- a/ql/src/test/results/clientpositive/vector_tablesample_rows.q.out
+++ b/ql/src/test/results/clientpositive/vector_tablesample_rows.q.out
@@ -20,7 +20,7 @@ STAGE PLANS:
TableScan
alias: alltypesorc
Row Limit Per Split: 1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -114,7 +114,7 @@ STAGE PLANS:
TableScan
alias: alltypesorc
Row Limit Per Split: 1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_udf3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_udf3.q.out b/ql/src/test/results/clientpositive/vector_udf3.q.out
index a10b07e..e230c0e 100644
--- a/ql/src/test/results/clientpositive/vector_udf3.q.out
+++ b/ql/src/test/results/clientpositive/vector_udf3.q.out
@@ -22,7 +22,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Select Operator
@@ -33,13 +33,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13]
selectExpressions: VectorStringRot13(col 6:string) -> 13:string
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[10/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
HIVE-19339: Regenerate alltypesorc file with latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/95d6d9b3
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/95d6d9b3
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/95d6d9b3
Branch: refs/heads/master
Commit: 95d6d9b3dcf1ade54928043c69accdc529ae3412
Parents: 6953b67
Author: Jesus Camacho Rodriguez <jc...@apache.org>
Authored: Sun Apr 29 12:05:16 2018 -0700
Committer: Jesus Camacho Rodriguez <jc...@apache.org>
Committed: Mon Apr 30 13:04:43 2018 -0700
----------------------------------------------------------------------
data/files/alltypesorc | Bin 377237 -> 295616 bytes
data/files/alltypesorcold | Bin 0 -> 377237 bytes
.../clientpositive/orc_merge_incompat3.q | 8 +-
.../clientpositive/autoColumnStats_4.q.out | 20 +-
ql/src/test/results/clientpositive/foldts.q.out | 24 +-
.../clientpositive/groupby_join_pushdown.q.out | 282 +++++++++----------
.../clientpositive/llap/explainuser_4.q.out | 60 ++--
.../clientpositive/llap/orc_merge9.q.out | 6 +-
.../llap/orc_merge_incompat3.q.out | 16 +-
.../clientpositive/llap/orc_ppd_basic.q.out | 6 +-
.../llap/tez_dynpart_hashjoin_1.q.out | 72 ++---
.../llap/tez_vector_dynpart_hashjoin_1.q.out | 72 ++---
.../clientpositive/llap/vector_elt.q.out | 2 +-
.../clientpositive/llap/vector_nvl.q.out | 4 +-
.../clientpositive/llap/vectorization_0.q.out | 44 +--
.../clientpositive/llap/vectorization_not.q.out | 2 +-
.../llap/vectorization_short_regress.q.out | 6 +-
.../results/clientpositive/orc_merge9.q.out | 6 +-
.../clientpositive/orc_merge_incompat3.q.out | 16 +-
.../clientpositive/spark/limit_pushdown.q.out | 60 ++--
.../clientpositive/spark/orc_merge9.q.out | 17 +-
.../clientpositive/spark/vector_elt.q.out | 12 +-
.../spark/vector_left_outer_join.q.out | 16 +-
.../clientpositive/spark/vectorization_0.q.out | 134 ++++-----
.../clientpositive/spark/vectorization_1.q.out | 6 +-
.../clientpositive/spark/vectorization_10.q.out | 8 +-
.../clientpositive/spark/vectorization_11.q.out | 8 +-
.../clientpositive/spark/vectorization_12.q.out | 20 +-
.../clientpositive/spark/vectorization_13.q.out | 44 +--
.../clientpositive/spark/vectorization_14.q.out | 20 +-
.../clientpositive/spark/vectorization_15.q.out | 20 +-
.../clientpositive/spark/vectorization_16.q.out | 16 +-
.../clientpositive/spark/vectorization_17.q.out | 12 +-
.../clientpositive/spark/vectorization_2.q.out | 6 +-
.../clientpositive/spark/vectorization_3.q.out | 6 +-
.../clientpositive/spark/vectorization_4.q.out | 6 +-
.../clientpositive/spark/vectorization_5.q.out | 6 +-
.../clientpositive/spark/vectorization_6.q.out | 8 +-
.../clientpositive/spark/vectorization_9.q.out | 16 +-
.../spark/vectorization_div0.q.out | 54 ++--
.../spark/vectorization_nested_udf.q.out | 4 +-
.../spark/vectorization_not.q.out | 2 +-
.../spark/vectorization_pushdown.q.out | 6 +-
.../spark/vectorization_short_regress.q.out | 172 +++++------
.../clientpositive/spark/vectorized_case.q.out | 24 +-
.../spark/vectorized_mapjoin.q.out | 16 +-
.../spark/vectorized_math_funcs.q.out | 8 +-
.../spark/vectorized_nested_mapjoin.q.out | 24 +-
.../spark/vectorized_shufflejoin.q.out | 20 +-
.../spark/vectorized_string_funcs.q.out | 8 +-
.../clientpositive/tez/explainanalyze_4.q.out | 48 ++--
.../clientpositive/timestamp_ints_casts.q.out | 16 +-
.../clientpositive/vector_decimal_cast.q.out | 10 +-
.../results/clientpositive/vector_elt.q.out | 12 +-
.../clientpositive/vector_empty_where.q.out | 46 +--
.../results/clientpositive/vector_if_expr.q.out | 12 +-
.../clientpositive/vector_left_outer_join.q.out | 16 +-
.../vector_non_constant_in_expr.q.out | 8 +-
.../results/clientpositive/vector_nvl.q.out | 22 +-
.../vector_tablesample_rows.q.out | 4 +-
.../results/clientpositive/vector_udf3.q.out | 6 +-
.../clientpositive/vector_varchar_simple.q.out | 16 +-
.../clientpositive/vectorization_1.q.out | 6 +-
.../clientpositive/vectorization_10.q.out | 8 +-
.../clientpositive/vectorization_11.q.out | 8 +-
.../clientpositive/vectorization_12.q.out | 20 +-
.../clientpositive/vectorization_13.q.out | 44 +--
.../clientpositive/vectorization_14.q.out | 20 +-
.../clientpositive/vectorization_15.q.out | 20 +-
.../clientpositive/vectorization_16.q.out | 16 +-
.../clientpositive/vectorization_17.q.out | 12 +-
.../clientpositive/vectorization_2.q.out | 6 +-
.../clientpositive/vectorization_3.q.out | 6 +-
.../clientpositive/vectorization_4.q.out | 6 +-
.../clientpositive/vectorization_5.q.out | 6 +-
.../clientpositive/vectorization_6.q.out | 8 +-
.../clientpositive/vectorization_7.q.out | 28 +-
.../clientpositive/vectorization_8.q.out | 28 +-
.../clientpositive/vectorization_9.q.out | 16 +-
.../clientpositive/vectorization_limit.q.out | 98 +++----
.../vectorization_nested_udf.q.out | 4 +-
.../clientpositive/vectorization_not.q.out | 2 +-
.../vectorization_offset_limit.q.out | 24 +-
.../clientpositive/vectorization_pushdown.q.out | 6 +-
.../clientpositive/vectorized_case.q.out | 24 +-
.../clientpositive/vectorized_casts.q.out | 8 +-
.../vectorized_distinct_gby.q.out | 8 +-
.../clientpositive/vectorized_mapjoin.q.out | 16 +-
.../clientpositive/vectorized_math_funcs.q.out | 8 +-
.../clientpositive/vectorized_shufflejoin.q.out | 20 +-
.../vectorized_string_funcs.q.out | 8 +-
.../vectorized_timestamp_ints_casts.q.out | 16 +-
.../results/clientpositive/windowing_gby2.q.out | 28 +-
.../clientpositive/windowing_streaming.q.out | 14 +-
94 files changed, 1090 insertions(+), 1093 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/data/files/alltypesorc
----------------------------------------------------------------------
diff --git a/data/files/alltypesorc b/data/files/alltypesorc
index 95c68ca..4526030 100644
Binary files a/data/files/alltypesorc and b/data/files/alltypesorc differ
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/data/files/alltypesorcold
----------------------------------------------------------------------
diff --git a/data/files/alltypesorcold b/data/files/alltypesorcold
new file mode 100644
index 0000000..95c68ca
Binary files /dev/null and b/data/files/alltypesorcold differ
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/queries/clientpositive/orc_merge_incompat3.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge_incompat3.q b/ql/src/test/queries/clientpositive/orc_merge_incompat3.q
index c3d1a49..fd9ead9 100644
--- a/ql/src/test/queries/clientpositive/orc_merge_incompat3.q
+++ b/ql/src/test/queries/clientpositive/orc_merge_incompat3.q
@@ -4,10 +4,10 @@ set hive.vectorized.execution.enabled=false;
create table concat_incompat like alltypesorc;
-load data local inpath '../../data/files/alltypesorc' into table concat_incompat;
-load data local inpath '../../data/files/alltypesorc' into table concat_incompat;
-load data local inpath '../../data/files/alltypesorc' into table concat_incompat;
-load data local inpath '../../data/files/alltypesorc' into table concat_incompat;
+load data local inpath '../../data/files/alltypesorcold' into table concat_incompat;
+load data local inpath '../../data/files/alltypesorcold' into table concat_incompat;
+load data local inpath '../../data/files/alltypesorcold' into table concat_incompat;
+load data local inpath '../../data/files/alltypesorcold' into table concat_incompat;
dfs -ls ${hiveconf:hive.metastore.warehouse.dir}/concat_incompat/;
select count(*) from concat_incompat;
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
index 3fa59c7..5be906e 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
@@ -60,28 +60,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), CAST( cstring1 AS varchar(128)) (type: varchar(128))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: varchar(128))
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(128))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -96,17 +96,17 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: varchar(128))
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: int), VALUE._col1 (type: varchar(128))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -116,7 +116,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: varchar(128))
outputColumnNames: a, b
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll')
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/foldts.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/foldts.q.out b/ql/src/test/results/clientpositive/foldts.q.out
index 4c78495..2a82b9a 100644
--- a/ql/src/test/results/clientpositive/foldts.q.out
+++ b/ql/src/test/results/clientpositive/foldts.q.out
@@ -14,17 +14,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), to_unix_timestamp(ctimestamp1) (type: bigint), to_unix_timestamp(ctimestamp1) (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 1
- Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -72,17 +72,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: from_unixtime(to_unix_timestamp(ctimestamp1), 'EEEE') (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 1
- Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -120,17 +120,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: from_unixtime(to_unix_timestamp(ctimestamp1), 'EEEE') (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 1
- Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out b/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out
index d02d7c2..e7d958a 100644
--- a/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out
@@ -557,35 +557,35 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int), cbigint (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col2 (type: bigint)
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint)
Reduce Operator Tree:
Join Operator
@@ -595,13 +595,13 @@ STAGE PLANS:
0 _col1 (type: int)
1 _col1 (type: int)
outputColumnNames: _col0, _col2, _col3
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col2)
keys: _col0 (type: tinyint), _col3 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -617,7 +617,7 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint), _col1 (type: tinyint)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: tinyint)
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -626,10 +626,10 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -663,25 +663,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cbigint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cbigint (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col0)
keys: _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Execution mode: vectorized
Reduce Operator Tree:
@@ -690,7 +690,7 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -706,14 +706,14 @@ STAGE PLANS:
key expressions: _col0 (type: bigint)
sort order: +
Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
TableScan
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -722,14 +722,14 @@ STAGE PLANS:
0 _col0 (type: bigint)
1 _col0 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: bigint), _col2 (type: bigint), _col1 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -740,31 +740,31 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cbigint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: bigint)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: bigint)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -800,25 +800,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(_col0)
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: tinyint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -827,7 +827,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -843,14 +843,14 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: tinyint)
TableScan
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -859,14 +859,14 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: tinyint), _col2 (type: tinyint), _col1 (type: tinyint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -877,31 +877,31 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -937,25 +937,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(_col1)
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Execution mode: vectorized
Reduce Operator Tree:
@@ -964,7 +964,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -980,14 +980,14 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
TableScan
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -996,14 +996,14 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col1
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1014,31 +1014,31 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1074,25 +1074,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0)
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1101,7 +1101,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1117,14 +1117,14 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
TableScan
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reduce Operator Tree:
Join Operator
@@ -1134,14 +1134,14 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col1, _col3
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col1 * _col3) (type: bigint)
outputColumnNames: _col0
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1152,25 +1152,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1179,7 +1179,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1215,25 +1215,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1)
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1242,7 +1242,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1258,14 +1258,14 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
TableScan
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reduce Operator Tree:
Join Operator
@@ -1275,14 +1275,14 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col1 * _col3) (type: bigint), _col0 (type: tinyint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1293,25 +1293,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1320,7 +1320,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1356,25 +1356,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1)
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1383,7 +1383,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1399,14 +1399,14 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
TableScan
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reduce Operator Tree:
Join Operator
@@ -1416,14 +1416,14 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col1 * _col3) (type: bigint), _col0 (type: tinyint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1434,25 +1434,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1461,7 +1461,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1500,29 +1500,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -1531,13 +1531,13 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1)
keys: _col0 (type: tinyint), _col2 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1553,7 +1553,7 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint), _col1 (type: tinyint)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: tinyint)
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1562,14 +1562,14 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: bigint), _col0 (type: tinyint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1610,35 +1610,35 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: f
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
TableScan
alias: g
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -1647,13 +1647,13 @@ STAGE PLANS:
0 _col0 (type: tinyint)
1 _col0 (type: tinyint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1)
keys: _col0 (type: tinyint), _col2 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1669,7 +1669,7 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint), _col1 (type: tinyint)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: tinyint)
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -1678,14 +1678,14 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: bigint), _col0 (type: tinyint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
index 44f078b..26d858c 100644
--- a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
@@ -265,29 +265,29 @@ Stage-0
Stage-1
Reducer 3 vectorized, llap
File Output Operator [FS_28]
- Select Operator [SEL_27] (rows=1501 width=215)
+ Select Operator [SEL_27] (rows=1501 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"]
<-Reducer 2 [SIMPLE_EDGE] vectorized, llap
SHUFFLE [RS_26]
- Map Join Operator [MAPJOIN_25] (rows=1501 width=215)
+ Map Join Operator [MAPJOIN_25] (rows=1501 width=236)
Conds:RS_21.KEY.reducesinkkey0=RS_24.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"]
<-Map 4 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_24]
PartitionCols:_col2
- Select Operator [SEL_23] (rows=1365 width=215)
+ Select Operator [SEL_23] (rows=1365 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
- Filter Operator [FIL_22] (rows=1365 width=215)
+ Filter Operator [FIL_22] (rows=1365 width=236)
predicate:(cbigint is not null and cint BETWEEN 1000000 AND 3000000)
- TableScan [TS_3] (rows=12288 width=215)
+ TableScan [TS_3] (rows=12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_21]
PartitionCols:_col2
- Select Operator [SEL_20] (rows=1365 width=215)
+ Select Operator [SEL_20] (rows=1365 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
- Filter Operator [FIL_19] (rows=1365 width=215)
+ Filter Operator [FIL_19] (rows=1365 width=236)
predicate:cint BETWEEN 1000000 AND 3000000
- TableScan [TS_0] (rows=12288 width=215)
+ TableScan [TS_0] (rows=12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"]
PREHOOK: query: select
@@ -350,25 +350,25 @@ Stage-0
PARTITION_ONLY_SHUFFLE [RS_29]
Group By Operator [GBY_28] (rows=1 width=8)
Output:["_col0"],aggregations:["count()"]
- Map Join Operator [MAPJOIN_27] (rows=1501 width=215)
+ Map Join Operator [MAPJOIN_27] (rows=1501 width=236)
Conds:RS_23.KEY.reducesinkkey0=RS_26.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true
<-Map 4 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_26]
PartitionCols:_col0
- Select Operator [SEL_25] (rows=1365 width=215)
+ Select Operator [SEL_25] (rows=1365 width=236)
Output:["_col0"]
- Filter Operator [FIL_24] (rows=1365 width=215)
+ Filter Operator [FIL_24] (rows=1365 width=236)
predicate:(cbigint is not null and cint BETWEEN 1000000 AND 3000000)
- TableScan [TS_3] (rows=12288 width=215)
+ TableScan [TS_3] (rows=12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_23]
PartitionCols:_col0
- Select Operator [SEL_22] (rows=1365 width=215)
+ Select Operator [SEL_22] (rows=1365 width=236)
Output:["_col0"]
- Filter Operator [FIL_21] (rows=1365 width=215)
+ Filter Operator [FIL_21] (rows=1365 width=236)
predicate:cint BETWEEN 1000000 AND 3000000
- TableScan [TS_0] (rows=12288 width=215)
+ TableScan [TS_0] (rows=12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint"]
PREHOOK: query: select
@@ -419,36 +419,36 @@ Stage-0
Stage-1
Reducer 4 vectorized, llap
File Output Operator [FS_35]
- Select Operator [SEL_34] (rows=750 width=215)
+ Select Operator [SEL_34] (rows=750 width=236)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE] vectorized, llap
SHUFFLE [RS_33]
- Group By Operator [GBY_32] (rows=750 width=215)
+ Group By Operator [GBY_32] (rows=750 width=236)
Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0
<-Reducer 2 [SIMPLE_EDGE] vectorized, llap
SHUFFLE [RS_31]
PartitionCols:_col0
- Group By Operator [GBY_30] (rows=1501 width=215)
+ Group By Operator [GBY_30] (rows=1501 width=236)
Output:["_col0","_col1"],aggregations:["count()"],keys:_col0
- Map Join Operator [MAPJOIN_29] (rows=1501 width=215)
+ Map Join Operator [MAPJOIN_29] (rows=1501 width=236)
Conds:RS_25.KEY.reducesinkkey0=RS_28.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true,Output:["_col0"]
<-Map 5 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_28]
PartitionCols:_col0
- Select Operator [SEL_27] (rows=1365 width=215)
+ Select Operator [SEL_27] (rows=1365 width=236)
Output:["_col0"]
- Filter Operator [FIL_26] (rows=1365 width=215)
+ Filter Operator [FIL_26] (rows=1365 width=236)
predicate:(cbigint is not null and cint BETWEEN 1000000 AND 3000000)
- TableScan [TS_3] (rows=12288 width=215)
+ TableScan [TS_3] (rows=12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_25]
PartitionCols:_col1
- Select Operator [SEL_24] (rows=1365 width=215)
+ Select Operator [SEL_24] (rows=1365 width=236)
Output:["_col0","_col1"]
- Filter Operator [FIL_23] (rows=1365 width=215)
+ Filter Operator [FIL_23] (rows=1365 width=236)
predicate:cint BETWEEN 1000000 AND 3000000
- TableScan [TS_0] (rows=12288 width=215)
+ TableScan [TS_0] (rows=12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["csmallint","cint"]
PREHOOK: query: select
@@ -498,18 +498,18 @@ Stage-0
Stage-1
Reducer 2 llap
File Output Operator [FS_8]
- Merge Join Operator [MERGEJOIN_9] (rows=150994944 width=431)
+ Merge Join Operator [MERGEJOIN_9] (rows=150994944 width=474)
Conds:(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"],residual filter predicates:{((_col2 = _col14) or UDFToInteger(_col1) BETWEEN 1 AND 10)}
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_11]
- Select Operator [SEL_10] (rows=12288 width=215)
+ Select Operator [SEL_10] (rows=12288 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
- TableScan [TS_0] (rows=12288 width=215)
+ TableScan [TS_0] (rows=12288 width=236)
default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"]
<-Map 3 [CUSTOM_SIMPLE_EDGE] vectorized, llap
PARTITION_ONLY_SHUFFLE [RS_13]
- Select Operator [SEL_12] (rows=12288 width=215)
+ Select Operator [SEL_12] (rows=12288 width=236)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
- TableScan [TS_2] (rows=12288 width=215)
+ TableScan [TS_2] (rows=12288 width=236)
default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"]
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/orc_merge9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_merge9.q.out b/ql/src/test/results/clientpositive/llap/orc_merge9.q.out
index 28e51b2..d925e03 100644
--- a/ql/src/test/results/clientpositive/llap/orc_merge9.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_merge9.q.out
@@ -128,7 +128,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@a_merge
#### A masked pattern was here ####
24576
-Found 2 items
+Found 1 items
#### A masked pattern was here ####
PREHOOK: query: insert into table a_merge select * from alltypesorc
PREHOOK: type: QUERY
@@ -150,7 +150,7 @@ POSTHOOK: Lineage: a_merge.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema
POSTHOOK: Lineage: a_merge.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ]
POSTHOOK: Lineage: a_merge.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ]
POSTHOOK: Lineage: a_merge.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ]
-Found 3 items
+Found 2 items
#### A masked pattern was here ####
PREHOOK: query: select count(*) from a_merge
PREHOOK: type: QUERY
@@ -178,5 +178,5 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@a_merge
#### A masked pattern was here ####
36864
-Found 2 items
+Found 1 items
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/orc_merge_incompat3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_merge_incompat3.q.out b/ql/src/test/results/clientpositive/llap/orc_merge_incompat3.q.out
index e34492b..d4b9cf1 100644
--- a/ql/src/test/results/clientpositive/llap/orc_merge_incompat3.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_merge_incompat3.q.out
@@ -6,35 +6,35 @@ POSTHOOK: query: create table concat_incompat like alltypesorc
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/orc_ppd_basic.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_ppd_basic.q.out b/ql/src/test/results/clientpositive/llap/orc_ppd_basic.q.out
index 70b9844..96819f4 100644
--- a/ql/src/test/results/clientpositive/llap/orc_ppd_basic.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_ppd_basic.q.out
@@ -2057,7 +2057,7 @@ PREHOOK: Input: default@alltypesorc
PREHOOK: Output: database:default
PREHOOK: Output: default@tmp_orcppd
Stage-1 LLAP IO COUNTERS:
- SELECTED_ROWGROUPS: 3
+ SELECTED_ROWGROUPS: 2
PREHOOK: query: insert into table tmp_orcppd
values(null, null, null, null, null,
null, null, null, null, null)
@@ -2089,7 +2089,7 @@ PREHOOK: Input: default@alltypesorc
PREHOOK: Output: database:default
PREHOOK: Output: default@tmp_orcppd
Stage-1 LLAP IO COUNTERS:
- SELECTED_ROWGROUPS: 3
+ SELECTED_ROWGROUPS: 2
PREHOOK: query: insert into table tmp_orcppd
values(null, null)
PREHOOK: type: QUERY
@@ -2134,4 +2134,4 @@ PREHOOK: Input: default@tmp_orcppd
PREHOOK: Output: database:default
PREHOOK: Output: default@tbl_orcppd_3_1
Stage-1 LLAP IO COUNTERS:
- SELECTED_ROWGROUPS: 4
+ SELECTED_ROWGROUPS: 3
[09/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out
index 32cf0b5..e9c6771 100644
--- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out
@@ -442,19 +442,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint BETWEEN 1000000 AND 3000000 (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -462,19 +462,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -490,12 +490,12 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
input vertices:
1 Map 4
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: tinyint), _col13 (type: smallint), _col14 (type: int), _col15 (type: bigint), _col16 (type: float), _col17 (type: double), _col18 (type: string), _col19 (type: string), _col20 (type: timestamp), _col21 (type: timestamp), _col22 (type: boolean), _col23 (type: boolean)
Reducer 3
Execution mode: vectorized, llap
@@ -503,10 +503,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: tinyint), VALUE._col12 (type: smallint), VALUE._col13 (type: int), VALUE._col14 (type: bigint), VALUE._col15 (type: float), VALUE._col16 (type: double), VALUE._col17 (type: string), VALUE._col18 (type: string), VALUE._col19 (type: timestamp), VALUE._col20 (type: timestamp), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -577,38 +577,38 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint BETWEEN 1000000 AND 3000000 (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -622,7 +622,7 @@ STAGE PLANS:
1 KEY.reducesinkkey0 (type: int)
input vertices:
1 Map 4
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Group By Operator
aggregations: count()
@@ -708,19 +708,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint BETWEEN 1000000 AND 3000000 (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: smallint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -728,19 +728,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -755,19 +755,19 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 5
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Group By Operator
aggregations: count()
keys: _col0 (type: smallint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
Map-reduce partition columns: _col0 (type: smallint)
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -777,11 +777,11 @@ STAGE PLANS:
keys: KEY._col0 (type: smallint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -789,10 +789,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out
index 55e1ccb..33ce299 100644
--- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out
@@ -442,19 +442,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint BETWEEN 1000000 AND 3000000 (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -462,19 +462,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -490,12 +490,12 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
input vertices:
1 Map 4
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: tinyint), _col13 (type: smallint), _col14 (type: int), _col15 (type: bigint), _col16 (type: float), _col17 (type: double), _col18 (type: string), _col19 (type: string), _col20 (type: timestamp), _col21 (type: timestamp), _col22 (type: boolean), _col23 (type: boolean)
Reducer 3
Execution mode: vectorized, llap
@@ -503,10 +503,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: tinyint), VALUE._col12 (type: smallint), VALUE._col13 (type: int), VALUE._col14 (type: bigint), VALUE._col15 (type: float), VALUE._col16 (type: double), VALUE._col17 (type: string), VALUE._col18 (type: string), VALUE._col19 (type: timestamp), VALUE._col20 (type: timestamp), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -577,38 +577,38 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint BETWEEN 1000000 AND 3000000 (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -622,7 +622,7 @@ STAGE PLANS:
1 KEY.reducesinkkey0 (type: int)
input vertices:
1 Map 4
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Group By Operator
aggregations: count()
@@ -708,19 +708,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: cint BETWEEN 1000000 AND 3000000 (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: smallint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -728,19 +728,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -755,19 +755,19 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 5
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
HybridGraceHashJoin: true
Group By Operator
aggregations: count()
keys: _col0 (type: smallint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
Map-reduce partition columns: _col0 (type: smallint)
- Statistics: Num rows: 1501 Data size: 322826 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1501 Data size: 355334 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -777,11 +777,11 @@ STAGE PLANS:
keys: KEY._col0 (type: smallint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: bigint)
sort order: +
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: smallint)
Reducer 4
Execution mode: vectorized, llap
@@ -789,10 +789,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 750 Data size: 161305 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 750 Data size: 177548 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/vector_elt.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_elt.q.out b/ql/src/test/results/clientpositive/llap/vector_elt.q.out
index 98db7da..7303886 100644
--- a/ql/src/test/results/clientpositive/llap/vector_elt.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_elt.q.out
@@ -141,7 +141,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/vector_nvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_nvl.q.out b/ql/src/test/results/clientpositive/llap/vector_nvl.q.out
index 5a312fc..dbcb770 100644
--- a/ql/src/test/results/clientpositive/llap/vector_nvl.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_nvl.q.out
@@ -220,7 +220,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -313,7 +313,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
index 80da5a9..4ea490c 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
@@ -1021,7 +1021,7 @@ ORDER BY c1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--1.8515862077935246E8 2.07689300543070106E18 2.07689300543070106E18 2.07711944383076992E18 1.441142951074147E9 1.441142951074147E9 1.441142951074147E9 1.441221511021387E9
+-1.8515862077935246E8 2.07689300543077965E18 2.07689300543077965E18 2.07711944383084851E18 1.4411429510741742E9 1.4411429510741742E9 1.4411429510741742E9 1.4412215110214143E9
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT MIN(cfloat) as c1,
MAX(cfloat),
@@ -1779,7 +1779,7 @@ WHERE (((cstring2 LIKE '%b%')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64
+-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593823E9 3.875716535945533E8 0.0 2.06347151720199526E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0517100101050656E9 -2.06347151720199526E18 1.5020929380914048E17 -64 64
PREHOOK: query: EXPLAIN extended
select count(*) from alltypesorc
where (((cstring1 LIKE 'a%') or ((cstring1 like 'b%') or (cstring1 like 'c%'))) or
@@ -1848,11 +1848,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -1870,11 +1870,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30671,11 +30671,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -30693,11 +30693,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30788,11 +30788,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -30810,11 +30810,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30905,11 +30905,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -30927,11 +30927,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -31013,11 +31013,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -31035,11 +31035,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/vectorization_not.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_not.q.out b/ql/src/test/results/clientpositive/llap/vectorization_not.q.out
index cf92a6f..6dec19c 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_not.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_not.q.out
@@ -55,4 +55,4 @@ WHERE (((cstring2 LIKE '%b%')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64
+-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593823E9 3.875716535945533E8 0.0 2.06347151720199526E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0517100101050656E9 -2.06347151720199526E18 1.5020929380914048E17 -64 64
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
index 3a5c272..a6a0371 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
@@ -265,7 +265,7 @@ WHERE ((762 = cbigint)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-1.6000018929276082E8 1.5999646129276082E8 -1.5999646129276082E8 1.5999646129276082E8 2.5598867626205912E16 -8706342.964000002 -1.6000018929276082E8 5.481251832900251E8 4.095728233294762E24 8549.657499338193 -5.481251832900251E8 3.8812872199726427E8 2.12743126884873664E17 3.0054786945574982E17 -5.700752675298234 -3.0054786945574982E17 3.0054786945574982E17 973579.3664121227 5.482224634724026E8 -973579.3664121227 -18.377427808018613 -64 2044 -6.573680812059072E-5 18.377427808018613
+1.6000018929276082E8 1.5999646129276082E8 -1.5999646129276082E8 1.5999646129276082E8 2.5598867626205912E16 -8706342.964000002 -1.6000018929276082E8 5.481251832900263E8 4.095728233294762E24 8549.657499338193 -5.481251832900263E8 3.8812872199726546E8 2.12743126884874784E17 3.0054786945575117E17 -5.700752675298234 -3.0054786945575117E17 3.0054786945575117E17 973579.3664121248 5.482224634724039E8 -973579.3664121248 -18.377427808018613 -64 2044 -6.573680812059058E-5 18.377427808018613
PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
SELECT MAX(cint),
(MAX(cint) / -3728),
@@ -987,7 +987,7 @@ WHERE (((ctimestamp2 <= ctimestamp1)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--0.5934409161894847 6980.406559083811 6979.813118167622 2141851355 -11761.597368421053 -6980.406559083811 1.5852855222070777E8 -0.5934409161894847 2.5099887741857176E16 1.52140608502098611E18 -2141851355 -13.510823917814225 79.553 -3.998255191435152E19
+-0.5934409161894847 6980.406559083811 6979.813118167622 2141851355 -11761.597368421053 -6980.406559083811 1.5852855222071928E8 -0.5934409161894847 2.5099887741860824E16 1.52140608502098611E18 -2141851355 -13.510823917813244 79.553 -3.998255191435152E19
PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
SELECT cint,
cdouble,
@@ -3389,7 +3389,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
false 11.0 -11.0 -2.389090909090909 -17881597706 -17881597716.175 3.8953387713327046E17 1.0 -0.8249998 -2454.8879999999995 3.8953385925167277E17 -2145884705 1.66288903197104486E18 0.8249998 4.7840233756130287E-17 3.8687857663039107E-17 0.8249998 -1051696618 28.692556844886425 2980633855.245 -4032330473.245 85.79562278396776 4032330473.245 -3983699.3106060605 3983699.3106060605 4.1896430920933255E15
-true 79.553 -79.553 -0.33034580136836733 -401322621137 -401322621147.175 7.9255373737242976E16 23.552490234375 -69.378 4856.6352637899645 7.9254972414621824E16 -2130544867 2.30133924842409984E18 69.378 3.456813247089751E-17 5.788274192367441E-19 69.378 2182477964777 34.65496805050828 2959326820.263 2179518637956.737 9461.197516216063 -2179518637956.737 4.592756659884259E8 -4.592756659884259E8 1.002359020778021E21
+true 79.553 -79.553 -0.33034580136836733 -401322621137 -401322621147.175 7.9255373737245296E16 36.51544952392578 -69.378 4856.6352637899645 7.9254972414624144E16 -2130544867 2.30133924842409984E18 69.378 3.456813247089751E-17 8.984773630290127E-18 69.378 2182477964777 34.65496805050828 2959326820.263 2179518637956.737 9461.197516216063 -2179518637956.737 4.592756659884259E8 -4.592756659884259E8 1.002359020778021E21
PREHOOK: query: create table test_count(i int) stored as orc
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/orc_merge9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_merge9.q.out b/ql/src/test/results/clientpositive/orc_merge9.q.out
index 28e51b2..d925e03 100644
--- a/ql/src/test/results/clientpositive/orc_merge9.q.out
+++ b/ql/src/test/results/clientpositive/orc_merge9.q.out
@@ -128,7 +128,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@a_merge
#### A masked pattern was here ####
24576
-Found 2 items
+Found 1 items
#### A masked pattern was here ####
PREHOOK: query: insert into table a_merge select * from alltypesorc
PREHOOK: type: QUERY
@@ -150,7 +150,7 @@ POSTHOOK: Lineage: a_merge.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema
POSTHOOK: Lineage: a_merge.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ]
POSTHOOK: Lineage: a_merge.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ]
POSTHOOK: Lineage: a_merge.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ]
-Found 3 items
+Found 2 items
#### A masked pattern was here ####
PREHOOK: query: select count(*) from a_merge
PREHOOK: type: QUERY
@@ -178,5 +178,5 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@a_merge
#### A masked pattern was here ####
36864
-Found 2 items
+Found 1 items
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/orc_merge_incompat3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_merge_incompat3.q.out b/ql/src/test/results/clientpositive/orc_merge_incompat3.q.out
index e34492b..d4b9cf1 100644
--- a/ql/src/test/results/clientpositive/orc_merge_incompat3.q.out
+++ b/ql/src/test/results/clientpositive/orc_merge_incompat3.q.out
@@ -6,35 +6,35 @@ POSTHOOK: query: create table concat_incompat like alltypesorc
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
-PREHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+PREHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@concat_incompat
-POSTHOOK: query: load data local inpath '../../data/files/alltypesorc' into table concat_incompat
+POSTHOOK: query: load data local inpath '../../data/files/alltypesorcold' into table concat_incompat
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@concat_incompat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
index eb66d23..2087587 100644
--- a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
@@ -381,21 +381,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double)
outputColumnNames: cdouble
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: cdouble (type: double)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized
Reducer 2
@@ -405,13 +405,13 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -472,21 +472,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cdouble (type: double)
outputColumnNames: ctinyint, cdouble
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: ctinyint (type: tinyint), cdouble (type: double)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reducer 2
Execution mode: vectorized
@@ -495,19 +495,19 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1)
keys: _col0 (type: tinyint)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -568,21 +568,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cdouble (type: double)
outputColumnNames: ctinyint, cdouble
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: ctinyint (type: tinyint), cdouble (type: double)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reducer 2
Execution mode: vectorized
@@ -591,19 +591,19 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1)
keys: _col0 (type: tinyint)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -664,22 +664,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string)
outputColumnNames: ctinyint, cstring1, cstring2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2)
keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Reducer 2
Reduce Operator Tree:
@@ -688,13 +688,13 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/orc_merge9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/orc_merge9.q.out b/ql/src/test/results/clientpositive/spark/orc_merge9.q.out
index e5db512..31bcd90 100644
--- a/ql/src/test/results/clientpositive/spark/orc_merge9.q.out
+++ b/ql/src/test/results/clientpositive/spark/orc_merge9.q.out
@@ -103,7 +103,7 @@ POSTHOOK: type: LOAD
POSTHOOK: Output: default@a_merge
Found 2 items
-rw-r--r-- 3 ### USER ### ### GROUP ### 295616 ### HDFS DATE ### hdfs://### HDFS PATH ###
--rw-r--r-- 3 ### USER ### ### GROUP ### 377237 ### HDFS DATE ### hdfs://### HDFS PATH ###
+-rw-r--r-- 3 ### USER ### ### GROUP ### 295616 ### HDFS DATE ### hdfs://### HDFS PATH ###
PREHOOK: query: select count(*) from a_merge
PREHOOK: type: QUERY
PREHOOK: Input: default@a_merge
@@ -130,9 +130,8 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@a_merge
POSTHOOK: Output: hdfs://### HDFS PATH ###
24576
-Found 2 items
--rw-r--r-- 3 ### USER ### ### GROUP ### 295616 ### HDFS DATE ### hdfs://### HDFS PATH ###
--rw-r--r-- 3 ### USER ### ### GROUP ### 377237 ### HDFS DATE ### hdfs://### HDFS PATH ###
+Found 1 items
+-rw-r--r-- 3 ### USER ### ### GROUP ### 590506 ### HDFS DATE ### hdfs://### HDFS PATH ###
PREHOOK: query: insert into table a_merge select * from alltypesorc
PREHOOK: type: QUERY
PREHOOK: Input: default@alltypesorc
@@ -153,9 +152,8 @@ POSTHOOK: Lineage: a_merge.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema
POSTHOOK: Lineage: a_merge.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ]
POSTHOOK: Lineage: a_merge.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ]
POSTHOOK: Lineage: a_merge.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ]
-Found 3 items
--rw-r--r-- 3 ### USER ### ### GROUP ### 295616 ### HDFS DATE ### hdfs://### HDFS PATH ###
--rw-r--r-- 3 ### USER ### ### GROUP ### 377237 ### HDFS DATE ### hdfs://### HDFS PATH ###
+Found 2 items
+-rw-r--r-- 3 ### USER ### ### GROUP ### 590506 ### HDFS DATE ### hdfs://### HDFS PATH ###
-rw-r--r-- 3 ### USER ### ### GROUP ### 295616 ### HDFS DATE ### hdfs://### HDFS PATH ###
PREHOOK: query: select count(*) from a_merge
PREHOOK: type: QUERY
@@ -183,6 +181,5 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@a_merge
POSTHOOK: Output: hdfs://### HDFS PATH ###
36864
-Found 2 items
--rw-r--r-- 3 ### USER ### ### GROUP ### 590506 ### HDFS DATE ### hdfs://### HDFS PATH ###
--rw-r--r-- 3 ### USER ### ### GROUP ### 377237 ### HDFS DATE ### hdfs://### HDFS PATH ###
+Found 1 items
+-rw-r--r-- 3 ### USER ### ### GROUP ### 885395 ### HDFS DATE ### hdfs://### HDFS PATH ###
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vector_elt.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_elt.q.out b/ql/src/test/results/clientpositive/spark/vector_elt.q.out
index f70863a..b938d8c 100644
--- a/ql/src/test/results/clientpositive/spark/vector_elt.q.out
+++ b/ql/src/test/results/clientpositive/spark/vector_elt.q.out
@@ -23,7 +23,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -32,7 +32,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColGreaterLongScalar(col 0:tinyint, val 0)
predicate: (ctinyint > 0Y) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -41,19 +41,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [14, 6, 2, 17]
selectExpressions: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 14:int, VectorElt(columns [15, 6, 16])(children: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 15:int, col 6:string, CastLongToString(col 2:int) -> 16:string) -> 17:string
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -140,7 +140,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vector_left_outer_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/spark/vector_left_outer_join.q.out
index ac7c821..858edfa 100644
--- a/ql/src/test/results/clientpositive/spark/vector_left_outer_join.q.out
+++ b/ql/src/test/results/clientpositive/spark/vector_left_outer_join.q.out
@@ -34,11 +34,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cd
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col1 (type: int)
@@ -59,11 +59,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: hd
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: tinyint)
@@ -91,11 +91,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -105,7 +105,7 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 3
- Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -114,7 +114,7 @@ STAGE PLANS:
1 _col0 (type: tinyint)
input vertices:
1 Map 4
- Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14867 Data size: 3518672 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
[08/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
index 8b73ef2..19bc439 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
@@ -34,7 +34,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -45,7 +45,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(ctinyint), max(ctinyint), count(ctinyint), count()
Group By Vectorization:
@@ -213,7 +213,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -224,7 +224,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ctinyint)
Group By Vectorization:
@@ -401,11 +401,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1)
mode: hash
@@ -540,7 +540,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -551,7 +551,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(cbigint), max(cbigint), count(cbigint), count()
Group By Vectorization:
@@ -719,7 +719,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -730,7 +730,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(cbigint)
Group By Vectorization:
@@ -907,11 +907,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1)
mode: hash
@@ -1009,7 +1009,7 @@ ORDER BY c1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--1.8515862077935246E8 2.07689300543070106E18 2.07689300543070106E18 2.07711944383076992E18 1.441142951074147E9 1.441142951074147E9 1.441142951074147E9 1.441221511021387E9
+-1.8515862077935246E8 2.07689300543082035E18 2.07689300543082035E18 2.07711944383088922E18 1.4411429510741882E9 1.4411429510741882E9 1.4411429510741882E9 1.4412215110214283E9
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT MIN(cfloat) as c1,
MAX(cfloat),
@@ -1046,7 +1046,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1057,7 +1057,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [4]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(cfloat), max(cfloat), count(cfloat), count()
Group By Vectorization:
@@ -1225,7 +1225,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1236,7 +1236,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [4]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(cfloat)
Group By Vectorization:
@@ -1413,11 +1413,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cfloat (type: float), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1)
mode: hash
@@ -1590,7 +1590,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1600,7 +1600,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterDecimalColNotEqualDecimalScalar(col 13:decimal(13,3), val 79.553)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)), FilterDoubleColLessDoubleColumn(col 14:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterLongColEqualLongScalar(col 11:boolean, val 1), FilterLongColEqualLongScalar(col 0:int, val 3569)(children: col 0:tinyint)))
predicate: (((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (UDFToInteger(ctinyint) = 3569)) or (CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -1609,7 +1609,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 4, 0, 14, 17]
selectExpressions: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 3:bigint) -> 15:double, CastLongToDouble(col 3:bigint) -> 16:double) -> 17:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col4), sum(_col3), count(), sum(_col1), min(_col2)
Group By Vectorization:
@@ -1759,7 +1759,7 @@ WHERE (((cstring2 LIKE '%b%')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64
+-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593987E9 3.875716535945533E8 0.0 2.06347151720204262E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.051733737257113E9 -2.06347151720204262E18 1.5020929380914048E17 -64 64
PREHOOK: query: EXPLAIN extended
select count(*) from alltypesorc
where (((cstring1 LIKE 'a%') or ((cstring1 like 'b%') or (cstring1 like 'c%'))) or
@@ -1785,14 +1785,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0)) or (cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%')) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1826,11 +1826,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -1848,11 +1848,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30595,22 +30595,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (((cint = 45) and (cfloat = 3.02)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 49) and (cfloat = 3.5))) (type: boolean)
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -30648,11 +30648,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -30670,11 +30670,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30711,22 +30711,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean)
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -30763,11 +30763,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -30785,11 +30785,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30826,22 +30826,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (((cint = 45) or (cfloat = 3.02)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 49) or (cfloat = 3.5))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -30879,11 +30879,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -30901,11 +30901,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -30943,24 +30943,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (cstring1) IN ('biology', 'history', 'topology') (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: cstring1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col1 (type: bigint)
auto parallelism: false
@@ -30985,11 +30985,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
@@ -31007,11 +31007,11 @@ STAGE PLANS:
name default.alltypesorc
numFiles 1
numRows 12288
- rawDataSize 2641964
+ rawDataSize 2907994
serialization.ddl struct alltypesorc { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
- totalSize 377237
+ totalSize 295616
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.alltypesorc
@@ -31027,16 +31027,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
null sort order: a
sort order: +
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: bigint)
auto parallelism: false
@@ -31047,13 +31047,13 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 726998 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_1.q.out b/ql/src/test/results/clientpositive/spark/vectorization_1.q.out
index 71625e0..5303fe4 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_1.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_1.q.out
@@ -59,7 +59,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -69,7 +69,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0)), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColLessLongScalar(col 10:boolean, val 0))
predicate: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (UDFToLong(cint) > cbigint) or (cbigint < UDFToLong(ctinyint)) or (cboolean1 < 0)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -78,7 +78,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 4, 2, 5, 13, 16, 14]
selectExpressions: CastLongToDouble(col 0:tinyint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_10.q.out b/ql/src/test/results/clientpositive/spark/vectorization_10.q.out
index 8ff6e48..a2e5786 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_10.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_10.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a))))
predicate: (((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a'))) or (cstring2 <= '10')) (type: boolean)
- Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -82,13 +82,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 8, 0, 10, 6, 13, 17, 16, 18, 20, 21, 19, 23, 24, 26]
selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 18:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 18:double) -> 16:double, DoubleColUnaryMinus(col 5:double) -> 18:double, DoubleColModuloDoubleColumn(col 19:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 21:smallint, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColMultiplyLongColumn(col 3:bigint, col 22:bigint)(children: col 22:smallint) -> 23:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 25:double)(children: DoubleColAddDoubleColumn(col 5:double, col 24:double)(children: CastLongToDouble(col
1:smallint) -> 24:double) -> 25:double) -> 24:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 5:double) -> 25:double) -> 26:double
- Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_11.q.out b/ql/src/test/results/clientpositive/spark/vectorization_11.q.out
index ef029b2..dcf7c3e 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_11.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_11.q.out
@@ -45,7 +45,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -55,7 +55,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string), FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a)))
predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean)
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -64,13 +64,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 16]
selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 16:double
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
index 24cfa4e..1c302e1 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out
@@ -82,7 +82,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -92,7 +92,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint))))
predicate: (((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ctimestamp1 is null) (type: boolean)
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -101,7 +101,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 14]
selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6)
Group By Vectorization:
@@ -115,7 +115,7 @@ STAGE PLANS:
keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean)
sort order: ++++
@@ -126,7 +126,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -173,7 +173,7 @@ STAGE PLANS:
keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19
@@ -182,7 +182,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 2, 0, 11, 12, 4, 13, 14, 19, 15, 20, 22, 24, 9, 26, 25, 21, 27]
selectExpressions: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 11:double, LongColUnaryMinus(col 1:bigint) -> 12:bigint, LongColMultiplyLongColumn(col 1:bigint, col 4:bigint) -> 13:bigint, FuncPowerDoubleToDouble(col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 14:double) -> 15:double) -> 14:double, IfExprNullCondExpr(col 16:boolean, null, col 17:bigint)(children: LongColEqualLongScalar(col 4:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 4:bigint, val 1) -> 17:bigint) -> 18:bigint) -> 15:double) -> 14:double, DoubleColDivideDoubleScalar(col 15:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 15:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(ch
ildren: DoubleColDivideDoubleScalar(col 15:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 15:double) -> 20:double) -> 15:double, DoubleColDivideLongColumn(col 7:double, col 8:bigint) -> 20:double, DoubleColUnaryMinus(col 21:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 22:double, DecimalScalarAddDecimalColumn(val -5638.15, col 23:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 23:decimal(19,0)) -> 24:decimal(22,2), DoubleColDivideDoubleColumn(col 21:double, col 25:double)(children: DoubleColDivideLongColumn(col 7:double, col 8:bigint) -> 21:double, DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 25:double) -> 26:double, DoubleColUnaryMinus(col 21:double)(children: DoubleColUnaryMinus(col 25:double)(children: DoubleColDivideDoubleScalar(col 21:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 25:double) ->
21:double) -> 25:double, DoubleColAddDoubleColumn(col 27:double, col 28:double)(children: DoubleColDivideDoubleScalar(col 21:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 27:double, DoubleColUnaryMinus(col 21:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 21:double) -> 28:double) -> 21:double, FuncPowerDoubleToDouble(col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 8:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 8:bigint)(children: DoubleColMultiplyDoubleColumn(col 7:double, col 7:double) -> 27:double) -> 28:double) -> 27:double) -> 28:double) -> 27:double
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string)
sort order: +++
@@ -192,7 +192,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [3, 11, 12, 4, 13, 14, 19, 15, 20, 22, 24, 9, 26, 25, 21, 27]
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double)
Reducer 3
Execution mode: vectorized
@@ -218,13 +218,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 2, 19, 0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 11, 16, 17, 18]
selectExpressions: ConstantVectorExpression(val null) -> 19:timestamp
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
index c2a8006..0f1b228 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out
@@ -84,7 +84,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -94,7 +94,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val 11.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 12.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4))))
predicate: (((UDFToDouble(ctimestamp1) > 11.0D) and (UDFToDouble(ctimestamp2) <> 12.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean)
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -103,7 +103,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18]
selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1)
Group By Vectorization:
@@ -117,7 +117,7 @@ STAGE PLANS:
keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
sort order: +++++
@@ -128,7 +128,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [5, 6, 7, 8, 9, 10, 11, 12, 13, 14]
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint)
Execution mode: vectorized
Map Vectorization:
@@ -175,7 +175,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
@@ -184,7 +184,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 15, 5, 17, 6, 20, 19, 21, 22, 23, 24, 27, 28, 25, 13, 31, 14]
selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 19:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 6:double) -> 19:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 21:float, FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 22:double) -> 23:double) -> 22:double) -> 23:double) -> 22:double, DoubleColUnar
yMinus(col 6:double) -> 23:double, FuncPowerDoubleToDouble(col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 24:double) -> 25:double) -> 24:double) -> 25:double) -> 24:double, DecimalColSubtractDecimalScalar(col 26:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 26:decimal(3,0)) -> 27:decimal(7,3), DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 28:double, DoubleScalarDivideDoubleColumn(val -26.28, col 29:double)(children: DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 29:double) -> 25:double, D
oubleColDivideDoubleColumn(col 30:double, col 29:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 29:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 29:double) -> 30:double, CastLongToDouble(col 1:tinyint) -> 29:double) -> 31:double
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint)
sort order: +++++++++++++++++++++
@@ -194,7 +194,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: []
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized
@@ -219,19 +219,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20]
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 40
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -437,7 +437,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -446,7 +446,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -1.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -1.3359999999999999)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4))))
predicate: (((UDFToDouble(ctimestamp1) > -1.388D) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean)
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -455,7 +455,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18]
selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1)
Group By Vectorization:
@@ -469,7 +469,7 @@ STAGE PLANS:
keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
sort order: +++++
@@ -478,7 +478,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint)
Execution mode: vectorized
Map Vectorization:
@@ -512,7 +512,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
@@ -521,7 +521,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 15, 5, 17, 6, 20, 19, 21, 22, 23, 24, 27, 28, 25, 13, 31, 14]
selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 19:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 6:double) -> 19:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 21:float, FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 22:double) -> 23:double) -> 22:double) -> 23:double) -> 22:double, DoubleColUnar
yMinus(col 6:double) -> 23:double, FuncPowerDoubleToDouble(col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 24:double) -> 25:double) -> 24:double) -> 25:double) -> 24:double, DecimalColSubtractDecimalScalar(col 26:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 26:decimal(3,0)) -> 27:decimal(7,3), DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 28:double, DoubleScalarDivideDoubleColumn(val -26.28, col 29:double)(children: DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 6:double) -> 25:double) -> 29:double) -> 25:double, D
oubleColDivideDoubleColumn(col 30:double, col 29:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 29:double)(children: CastLongToDouble(col 18:tinyint)(children: LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 18:tinyint) -> 29:double) -> 30:double, CastLongToDouble(col 1:tinyint) -> 29:double) -> 31:double
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint)
sort order: +++++++++++++++++++++
@@ -529,7 +529,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized
@@ -547,19 +547,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20]
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 40
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[03/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vector_varchar_simple.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out
index 0a144d2..b880838 100644
--- a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out
+++ b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out
@@ -285,7 +285,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Select Operator
@@ -295,13 +295,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -309,7 +309,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int)
Execution mode: vectorized
@@ -330,17 +330,17 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: CAST( _col0 AS varchar(25)) (type: varchar(25))
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_1.q.out b/ql/src/test/results/clientpositive/vectorization_1.q.out
index bb8e483..767db3c 100644
--- a/ql/src/test/results/clientpositive/vectorization_1.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_1.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -64,7 +64,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0)), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColLessLongScalar(col 10:boolean, val 0))
predicate: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (UDFToLong(cint) > cbigint) or (cbigint < UDFToLong(ctinyint)) or (cboolean1 < 0)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 4, 2, 5, 13, 16, 14]
selectExpressions: CastLongToDouble(col 0:tinyint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_10.q.out b/ql/src/test/results/clientpositive/vectorization_10.q.out
index 2c35fd9..57a6fe9 100644
--- a/ql/src/test/results/clientpositive/vectorization_10.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_10.q.out
@@ -60,7 +60,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -70,7 +70,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a))))
predicate: (((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a'))) or (cstring2 <= '10')) (type: boolean)
- Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -79,13 +79,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 8, 0, 10, 6, 13, 17, 16, 18, 20, 21, 19, 23, 24, 26]
selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 18:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 18:double) -> 16:double, DoubleColUnaryMinus(col 5:double) -> 18:double, DoubleColModuloDoubleColumn(col 19:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 21:smallint, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColMultiplyLongColumn(col 3:bigint, col 22:bigint)(children: col 22:smallint) -> 23:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 25:double)(children: DoubleColAddDoubleColumn(col 5:double, col 24:double)(children: CastLongToDouble(col 1:smal
lint) -> 24:double) -> 25:double) -> 24:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 5:double) -> 25:double) -> 26:double
- Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9557 Data size: 2054789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_11.q.out b/ql/src/test/results/clientpositive/vectorization_11.q.out
index b378343..5792d0d 100644
--- a/ql/src/test/results/clientpositive/vectorization_11.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_11.q.out
@@ -42,7 +42,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -52,7 +52,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string), FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a)))
predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean)
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -61,13 +61,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 16]
selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 16:double
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_12.q.out b/ql/src/test/results/clientpositive/vectorization_12.q.out
index e129730..39c3476 100644
--- a/ql/src/test/results/clientpositive/vectorization_12.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_12.q.out
@@ -77,7 +77,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -87,7 +87,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint))))
predicate: (((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ctimestamp1 is null) (type: boolean)
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -96,7 +96,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 14]
selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6)
Group By Vectorization:
@@ -110,7 +110,7 @@ STAGE PLANS:
keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean)
sort order: ++++
@@ -120,7 +120,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 3754 Data size: 807123 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -148,11 +148,11 @@ STAGE PLANS:
keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -175,7 +175,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -201,10 +201,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1877 Data size: 403561 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out
index 96eda74..1cf64a3 100644
--- a/ql/src/test/results/clientpositive/vectorization_13.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_13.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -89,7 +89,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val 11.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 12.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4))))
predicate: (((UDFToDouble(ctimestamp1) > 11.0D) and (UDFToDouble(ctimestamp2) <> 12.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean)
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -98,7 +98,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18]
selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1)
Group By Vectorization:
@@ -112,7 +112,7 @@ STAGE PLANS:
keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
sort order: +++++
@@ -122,7 +122,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint)
Execution mode: vectorized
Map Vectorization:
@@ -150,11 +150,11 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -177,7 +177,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -203,13 +203,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 40
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -410,7 +410,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -419,7 +419,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -1.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -1.3359999999999999)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4))))
predicate: (((UDFToDouble(ctimestamp1) > -1.388D) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean)
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -428,7 +428,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18]
selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1)
Group By Vectorization:
@@ -442,7 +442,7 @@ STAGE PLANS:
keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string)
sort order: +++++
@@ -452,7 +452,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint)
Execution mode: vectorized
Map Vectorization:
@@ -474,11 +474,11 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -500,7 +500,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -520,13 +520,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 40
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_14.q.out b/ql/src/test/results/clientpositive/vectorization_14.q.out
index 7a7a817..9dbc20c 100644
--- a/ql/src/test/results/clientpositive/vectorization_14.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_14.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -89,7 +89,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 13:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp)), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float)))
predicate: (((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and (UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint))) (type: boolean)
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -98,7 +98,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 4, 6, 10, 5, 14, 13, 4, 15]
selectExpressions: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 15:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 16:double) -> 13:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 15:double
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1)
Group By Vectorization:
@@ -112,7 +112,7 @@ STAGE PLANS:
keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean)
sort order: +++++
@@ -122,7 +122,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -150,11 +150,11 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _
col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -177,7 +177,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -203,10 +203,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_15.q.out b/ql/src/test/results/clientpositive/vectorization_15.q.out
index dbef3e7..589b8f5 100644
--- a/ql/src/test/results/clientpositive/vectorization_15.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_15.q.out
@@ -75,7 +75,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -85,7 +85,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0)))
predicate: (((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D)) or (cstring1 like '10%') or (cstring2 like '%ss%')) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
@@ -94,7 +94,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 15, 19]
selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 18:double) -> 19:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5)
Group By Vectorization:
@@ -108,7 +108,7 @@ STAGE PLANS:
keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp)
sort order: +++++++
@@ -118,7 +118,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -145,11 +145,11 @@ STAGE PLANS:
keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), pow
er(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -172,7 +172,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -197,10 +197,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_16.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out
index 571eae0..18120f2 100644
--- a/ql/src/test/results/clientpositive/vectorization_16.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_16.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -62,7 +62,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a)))
predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -71,7 +71,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6, 5, 8, 13]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1)
Group By Vectorization:
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
sort order: +++
@@ -95,7 +95,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -123,14 +123,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_17.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_17.q.out b/ql/src/test/results/clientpositive/vectorization_17.q.out
index 3f9b947..6c9212f 100644
--- a/ql/src/test/results/clientpositive/vectorization_17.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_17.q.out
@@ -60,7 +60,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -70,7 +70,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)))
predicate: (((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and (cbigint > -23L)) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
@@ -79,7 +79,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 14, 17, 19, 20, 22, 18]
selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 14:double, DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 17:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double) -> 17:double, DoubleColDivideDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 20:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 21:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 23:double)(children: DoubleColUna
ryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 23:double) -> 18:double
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col5 (type: bigint), _col0 (type: float)
sort order: ++
@@ -88,7 +88,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -114,10 +114,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_2.q.out b/ql/src/test/results/clientpositive/vectorization_2.q.out
index e3d6ad0..05f22bb 100644
--- a/ql/src/test/results/clientpositive/vectorization_2.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_2.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -68,7 +68,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375)), FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 13:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterLongColLessLongScalar(col 2:int, val 359))))
predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean)
- Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -77,7 +77,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 4, 3, 0, 5, 13, 16]
selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double
- Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_3.q.out b/ql/src/test/results/clientpositive/vectorization_3.q.out
index bb6c014..b5ee0fb 100644
--- a/ql/src/test/results/clientpositive/vectorization_3.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_3.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 13:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 13:double), FilterDecimalColGreaterEqualDecimalScalar(col 15:decimal(8,3), val 79.553)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(8,3)), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp)))
predicate: (((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2)) or ((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D))) (type: boolean)
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
@@ -82,7 +82,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 0, 4, 2, 13, 18, 16, 20, 4, 17, 19, 23]
selectExpressions: CastLongToDouble(col 1:smallint) -> 13:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 16:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, CastLongToDouble(col 0:tinyint) -> 16:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 17:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 17:double, CastLongToDouble(col 2:int) -> 19:double, DoubleColMultiplyDoubleColumn(col 21:double, col 22:double)(children: CastLongToDouble(col 2:int) -> 21:double, CastLongToDouble(col 2:int) -> 22:double) -> 23:double
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10)
Group By Vectorization:
[02/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_4.q.out b/ql/src/test/results/clientpositive/vectorization_4.q.out
index 395431c..6dd398d 100644
--- a/ql/src/test/results/clientpositive/vectorization_4.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_4.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -68,7 +68,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553)), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0))))
predicate: (((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or (UDFToInteger(csmallint) >= cint)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -77,7 +77,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 5, 0, 13]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_5.q.out b/ql/src/test/results/clientpositive/vectorization_5.q.out
index dfe9715..dc539e0 100644
--- a/ql/src/test/results/clientpositive/vectorization_5.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_5.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -62,7 +62,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11:boolean), FilterStringColLikeStringScalar(col 6:string, pattern %b%)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), SelectColumnIsNotNull(col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern a)))
predicate: (((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a')) or (cboolean2 is not null and (cstring1 like '%b%'))) (type: boolean)
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int)
outputColumnNames: ctinyint, csmallint, cint
@@ -70,7 +70,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_6.q.out b/ql/src/test/results/clientpositive/vectorization_6.q.out
index 857cb31..6d17130 100644
--- a/ql/src/test/results/clientpositive/vectorization_6.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_6.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -64,7 +64,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: SelectColumnIsNotNull(col 3:bigint), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0)))))
predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257)))) and (ctinyint <> 0Y)) (type: boolean)
- Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
@@ -73,13 +73,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22]
selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int
- Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_7.q.out b/ql/src/test/results/clientpositive/vectorization_7.q.out
index 64c6fd8..3999bf2 100644
--- a/ql/src/test/results/clientpositive/vectorization_7.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_7.q.out
@@ -66,7 +66,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -76,7 +76,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -15.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))))
predicate: (((UDFToDouble(ctimestamp1) <= 0.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -15.0D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean)
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -85,7 +85,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23]
selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: col 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: col 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint)
sort order: +++++++++++++++
@@ -94,7 +94,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -120,13 +120,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 25
- Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -287,7 +287,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -296,7 +296,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val 7.6850000000000005)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))))
predicate: (((UDFToDouble(ctimestamp1) <= 0.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean)
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -305,7 +305,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23]
selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: col 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: col 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint)
sort order: +++++++++++++++
@@ -314,7 +314,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -334,13 +334,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 25
- Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_8.q.out b/ql/src/test/results/clientpositive/vectorization_8.q.out
index 80fdb0b..f658f80 100644
--- a/ql/src/test/results/clientpositive/vectorization_8.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_8.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -72,7 +72,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 10.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 16.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0)))
predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
@@ -81,7 +81,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22]
selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, col 23:float) -> 22:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double)
sort order: ++++++++++++++
@@ -90,7 +90,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -116,13 +116,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -270,7 +270,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -279,7 +279,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 12.503)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 11.998)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0)))
predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
@@ -288,7 +288,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22]
selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, col 23:float) -> 22:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double)
sort order: ++++++++++++++
@@ -297,7 +297,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -317,13 +317,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out
index 571eae0..18120f2 100644
--- a/ql/src/test/results/clientpositive/vectorization_9.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_9.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -62,7 +62,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a)))
predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -71,7 +71,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6, 5, 8, 13]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1)
Group By Vectorization:
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
sort order: +++
@@ -95,7 +95,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -123,14 +123,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_limit.q.out b/ql/src/test/results/clientpositive/vectorization_limit.q.out
index 7474547..438c060 100644
--- a/ql/src/test/results/clientpositive/vectorization_limit.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_limit.q.out
@@ -19,18 +19,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), cdouble (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: bigint), _col1 (type: double)
sort order: ++
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -50,13 +50,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 7
- Statistics: Num rows: 7 Data size: 1505 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 7 Data size: 1505 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -104,7 +104,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -114,7 +114,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:tinyint)
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint)
outputColumnNames: _col0, _col1, _col2
@@ -122,7 +122,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 5, 1]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: double), _col2 (type: smallint)
sort order: +++
@@ -131,7 +131,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized
Map Vectorization:
@@ -157,13 +157,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: smallint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -224,7 +224,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -236,7 +236,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 13]
selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col1)
Group By Vectorization:
@@ -250,7 +250,7 @@ STAGE PLANS:
keys: _col0 (type: tinyint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
@@ -260,7 +260,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double), _col2 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -288,11 +288,11 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: tinyint), (_col1 / _col2) (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -315,7 +315,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized
Map Vectorization:
@@ -341,13 +341,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -407,7 +407,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -418,7 +418,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -430,7 +430,7 @@ STAGE PLANS:
keys: ctinyint (type: tinyint)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
@@ -440,7 +440,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized
Map Vectorization:
@@ -467,13 +467,13 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -534,22 +534,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cdouble (type: double)
outputColumnNames: ctinyint, cdouble
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(DISTINCT cdouble)
keys: ctinyint (type: tinyint), cdouble (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
@@ -566,7 +566,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -589,7 +589,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized
Map Vectorization:
@@ -615,13 +615,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -710,7 +710,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -720,7 +720,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:tinyint)
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ctinyint)
Group By Vectorization:
@@ -734,7 +734,7 @@ STAGE PLANS:
keys: cdouble (type: double)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -744,7 +744,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -772,7 +772,7 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -795,7 +795,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized
Map Vectorization:
@@ -821,13 +821,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out b/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out
index 2c4fa69..c0677bd 100644
--- a/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out
@@ -18,7 +18,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -30,7 +30,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13]
selectExpressions: FuncAbsLongToLong(col 0:tinyint) -> 13:int
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_not.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_not.q.out b/ql/src/test/results/clientpositive/vectorization_not.q.out
index cf92a6f..5d9a1ef 100644
--- a/ql/src/test/results/clientpositive/vectorization_not.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_not.q.out
@@ -55,4 +55,4 @@ WHERE (((cstring2 LIKE '%b%')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64
+-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593987E9 3.875716535945533E8 0.0 2.06347151720204262E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.051733737257113E9 -2.06347151720204262E18 1.5020929380914048E17 -64 64
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out
index 0bdbd97..18d236c 100644
--- a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out
@@ -17,21 +17,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), cdouble (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 2
Offset of rows: 3
- Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -84,7 +84,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -93,7 +93,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:tinyint)
predicate: ctinyint is not null (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint)
outputColumnNames: _col0, _col1, _col2
@@ -101,7 +101,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 5, 1]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
@@ -110,7 +110,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: smallint)
Execution mode: vectorized
@@ -131,14 +131,14 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 3
Offset of rows: 10
- Statistics: Num rows: 3 Data size: 645 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 708 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 645 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 708 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorization_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out
index d8a5b08..6216581 100644
--- a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out
@@ -18,14 +18,14 @@ STAGE PLANS:
TableScan
alias: alltypesorc
filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint)
outputColumnNames: cbigint
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(cbigint), count(cbigint)
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/vectorized_case.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_case.q.out b/ql/src/test/results/clientpositive/vectorized_case.q.out
index 31dcd37..d4cb176 100644
--- a/ql/src/test/results/clientpositive/vectorized_case.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_case.q.out
@@ -48,7 +48,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -58,7 +58,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:smallint, val 418), FilterLongColEqualLongScalar(col 1:smallint, val 12205), FilterLongColEqualLongScalar(col 1:smallint, val 10583))
predicate: ((csmallint = 10583S) or (csmallint = 12205S) or (csmallint = 418S)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -67,13 +67,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 17, 21]
selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 16:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprStringScalarStringScalar(col 15:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean) -> 16:string) -> 17:string, IfExprColumnCondExpr(col 15:boolean, col 18:stringcol 20:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 15:boolean, ConstantVectorExpression(val a) -> 18:string, IfExprStringScalarStringScalar(col 19:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 19:boolean) -> 20:string) -> 21:string
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -193,7 +193,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -203,7 +203,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:smallint, val 418), FilterLongColEqualLongScalar(col 1:smallint, val 12205), FilterLongColEqualLongScalar(col 1:smallint, val 10583))
predicate: ((csmallint = 10583S) or (csmallint = 12205S) or (csmallint = 418S)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN (null) ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -212,13 +212,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 18, 24]
selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 17:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprColumnNull(col 15:boolean, col 16:string, null)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean, ConstantVectorExpression(val b) -> 16:string) -> 17:string) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 23:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 19:boolean, ConstantVectorExpression(val a) -> 20:string, IfExprNullColumn(col 21:boolean, null, col 22)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 21:boolean, ConstantVectorExpression(val c) -> 22:string) -> 23:string) -> 24:string
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -272,7 +272,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -284,7 +284,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 14]
selectExpressions: IfExprLongScalarLongScalar(col 14:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongScalarLongScalar(col 15:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), sum(_col1)
Group By Vectorization:
@@ -387,7 +387,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -399,7 +399,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 14]
selectExpressions: IfExprLongColumnLongScalar(col 14:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongColumnLongScalar(col 15:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), sum(_col1)
Group By Vectorization:
[07/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
index 95bf29b..5266764 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out
@@ -84,7 +84,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -94,7 +94,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 13:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp)), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float)))
predicate: (((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and (UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint))) (type: boolean)
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -103,7 +103,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 4, 6, 10, 5, 14, 13, 4, 15]
selectExpressions: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 15:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 16:double) -> 13:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 15:double
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1)
Group By Vectorization:
@@ -117,7 +117,7 @@ STAGE PLANS:
keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean)
sort order: +++++
@@ -128,7 +128,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -175,7 +175,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col
10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
@@ -184,7 +184,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 1, 0, 4, 2, 12, 14, 13, 15, 8, 19, 20, 21, 22, 11, 24, 25, 23, 29, 28, 31, 34]
selectExpressions: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 12:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 13:double) -> 14:double, FuncPowerDoubleToDouble(col 15:double)(children: DoubleColDivideLongColumn(col 13:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 15:double)(children: DoubleColDivideLongColumn(col 13:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 13:double) -> 15:double) -> 13:double, IfExprNullCondExpr(col 16:boolean, null, col 17:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 17:bigint) -> 18:bigint) -> 15:double) -> 13:double, DoubleColMultiplyDoubleScalar(col 1:float, val -26.280000686645508) -> 15:float, DoubleColUnaryMinus(col 1:float) -> 19:float, DoubleColUnaryMinus(col 8:float) -> 20:float, DoubleColDi
videDoubleScalar(col 22:double, val 10.175)(children: DoubleColUnaryMinus(col 21:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 21:double) -> 22:double) -> 21:double, FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 22:double) -> 23:double) -> 22:double) -> 23:double) -> 22:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColDivideDoubleScalar(col 24:double, val 10.175)(children: DoubleColUnaryMinus(col 23:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 23:double) -> 24:double) -> 23:double) -> 24:double, DoubleScalarModuloDoubleColumn(val -1.389, col 23:double)(children: FuncPowerDoubleToDouble(col 25:double)(children: DoubleColDivideLongColumn(col 23:double,
col 27:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 25:double)(children: DoubleColDivideLongColumn(col 23:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 23:double) -> 25:double) -> 23:double, IfExprNullCondExpr(col 18:boolean, null, col 26:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 18:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 26:bigint) -> 27:bigint) -> 25:double) -> 23:double) -> 25:double, DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 23:double, DoubleColDivideLongColumn(col 28:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 29:double)(children: DoubleColDivideLongColumn(col 28:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 28:double) -> 29:double) -> 28:double) -> 29:double, DoubleColModuloDoubleScalar(col 30:double, val 10.175)(children: DoubleColDivideLon
gColumn(col 28:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 30:double)(children: DoubleColDivideLongColumn(col 28:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 28:double) -> 30:double) -> 28:double) -> 30:double) -> 28:double, DoubleColDivideLongColumn(col 30:double, col 33:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 30:double) -> 31:double) -> 30:double, IfExprNullCondExpr(col 27:boolean, null, col 32:bigint)(children: LongColEqualLongScalar(col 11:bigint, val 1) -> 27:boolean, LongColSubtractLongScalar(col 11:bigint, val 1) -> 32:bigint) -> 33:bigint) -> 31:double, DoubleColUnaryMinus(col 30:double)(children: DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 30:double) -> 34:double
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp)
sort order: ++++
@@ -194,7 +194,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [4, 12, 14, 13, 15, 8, 19, 20, 21, 22, 11, 24, 25, 23, 29, 28, 31, 34]
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double)
Reducer 3
Execution mode: vectorized
@@ -219,13 +219,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3, 1, 0, 4, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21]
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out
index d0b03b3..5d51c87 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out
@@ -80,7 +80,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -90,7 +90,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0)))
predicate: (((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D)) or (cstring1 like '10%') or (cstring2 like '%ss%')) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
@@ -99,7 +99,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 15, 19]
selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 18:double) -> 19:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5)
Group By Vectorization:
@@ -113,7 +113,7 @@ STAGE PLANS:
keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp)
sort order: +++++++
@@ -124,7 +124,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [7, 8, 9, 10, 11, 12, 13, 14, 15, 16]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -153,15 +153,15 @@ STAGE PLANS:
keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)
), power(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp)
sort order: +++++++
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double)
Reducer 3
Reduce Vectorization:
@@ -172,10 +172,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
index 8798ebe..56bbb89 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -67,7 +67,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a)))
predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -76,7 +76,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6, 5, 8, 13]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1)
Group By Vectorization:
@@ -90,7 +90,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
sort order: +++
@@ -101,7 +101,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [3, 4, 5, 6]
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -148,7 +148,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
@@ -157,13 +157,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 7, 9, 3, 8, 14, 20, 6, 10, 22, 17]
selectExpressions: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 7:double, DoubleColUnaryMinus(col 8:double)(children: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 8:double) -> 9:double, FuncPowerDoubleToDouble(col 10:double)(children: DoubleColDivideLongColumn(col 8:double, col 13:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 10:double)(children: DoubleColDivideLongColumn(col 8:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 8:double) -> 10:double) -> 8:double, IfExprNullCondExpr(col 11:boolean, null, col 12:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 11:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 12:bigint) -> 13:bigint) -> 10:double) -> 8:double, DoubleColUnaryMinus(col 10:double)(children: FuncPowerDoubleToDouble(col 14:double)(children: DoubleColDivideLongColumn(col 10:double, col 16:bigint)(children: DoubleColSubtract
DoubleColumn(col 4:double, col 14:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 14:double) -> 10:double, IfExprNullCondExpr(col 13:boolean, null, col 15:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 15:bigint) -> 16:bigint) -> 14:double) -> 10:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 10:double, col 17:double)(children: FuncPowerDoubleToDouble(col 17:double)(children: DoubleColDivideLongColumn(col 10:double, col 19:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 17:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 17:double) -> 10:double, IfExprNullCondExpr(col 16:boolean, null, col 18:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 16:boo
lean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 18:bigint) -> 19:bigint) -> 17:double) -> 10:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 20:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 1:double) -> 10:double, DecimalColDivideDecimalScalar(col 21:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(28,6), FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 17:double, col 25:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 23:double)(children: DoubleColDivideLongColumn(col 17:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 17:double) -> 23:double) -> 17:double, IfExprNullCondExpr(col 19:boolean, null, col 24:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 19:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 24:bigint) -> 25:bigint) -> 23:double) -> 17:double
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_17.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_17.q.out b/ql/src/test/results/clientpositive/spark/vectorization_17.q.out
index c333ab1..1877fb3 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_17.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_17.q.out
@@ -65,7 +65,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -75,7 +75,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)))
predicate: (((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and (cbigint > -23L)) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
@@ -84,7 +84,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 14, 17, 19, 20, 22, 18]
selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 14:double, DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 17:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double) -> 17:double, DoubleColDivideDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 20:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 21:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 23:double)(children: Double
ColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 23:double) -> 18:double
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col5 (type: bigint), _col0 (type: float)
sort order: ++
@@ -94,7 +94,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [6, 2, 8, 5, 15, 16, 14, 17, 19, 20, 22, 18]
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -135,13 +135,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1, 2, 3, 4, 5, 0, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_2.q.out b/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
index 99afc2b..1af403a 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_2.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375)), FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 13:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterLongColLessLongScalar(col 2:int, val 359))))
predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean)
- Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -82,7 +82,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 4, 3, 0, 5, 13, 16]
selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double
- Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_3.q.out b/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
index 2bccf64..51d04cc 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_3.q.out
@@ -68,7 +68,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -78,7 +78,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 13:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 13:double), FilterDecimalColGreaterEqualDecimalScalar(col 15:decimal(8,3), val 79.553)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(8,3)), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp)))
predicate: (((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2)) or ((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D))) (type: boolean)
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
@@ -87,7 +87,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 0, 4, 2, 13, 18, 16, 20, 4, 17, 19, 23]
selectExpressions: CastLongToDouble(col 1:smallint) -> 13:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 16:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, CastLongToDouble(col 0:tinyint) -> 16:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 17:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 17:double, CastLongToDouble(col 2:int) -> 19:double, DoubleColMultiplyDoubleColumn(col 21:double, col 22:double)(children: CastLongToDouble(col 2:int) -> 21:double, CastLongToDouble(col 2:int) -> 22:double) -> 23:double
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_4.q.out b/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
index 922eb90..07d30cf 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_4.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553)), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0))))
predicate: (((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or (UDFToInteger(csmallint) >= cint)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -82,7 +82,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 5, 0, 13]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_5.q.out b/ql/src/test/results/clientpositive/spark/vectorization_5.q.out
index 4cf4548..0fb430e 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_5.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_5.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -67,7 +67,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11:boolean), FilterStringColLikeStringScalar(col 6:string, pattern %b%)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), SelectColumnIsNotNull(col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern a)))
predicate: (((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a')) or (cboolean2 is not null and (cstring1 like '%b%'))) (type: boolean)
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int)
outputColumnNames: ctinyint, csmallint, cint
@@ -75,7 +75,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_6.q.out b/ql/src/test/results/clientpositive/spark/vectorization_6.q.out
index ebf4849..bdb014c 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_6.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_6.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -67,7 +67,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: SelectColumnIsNotNull(col 3:bigint), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0)))))
predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257)))) and (ctinyint <> 0Y)) (type: boolean)
- Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
@@ -76,13 +76,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22]
selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int
- Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
index 8798ebe..56bbb89 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_9.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -67,7 +67,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a)))
predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -76,7 +76,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6, 5, 8, 13]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1)
Group By Vectorization:
@@ -90,7 +90,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp)
sort order: +++
@@ -101,7 +101,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumnNums: [3, 4, 5, 6]
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -148,7 +148,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
@@ -157,13 +157,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 7, 9, 3, 8, 14, 20, 6, 10, 22, 17]
selectExpressions: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 7:double, DoubleColUnaryMinus(col 8:double)(children: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 8:double) -> 9:double, FuncPowerDoubleToDouble(col 10:double)(children: DoubleColDivideLongColumn(col 8:double, col 13:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 10:double)(children: DoubleColDivideLongColumn(col 8:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 8:double) -> 10:double) -> 8:double, IfExprNullCondExpr(col 11:boolean, null, col 12:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 11:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 12:bigint) -> 13:bigint) -> 10:double) -> 8:double, DoubleColUnaryMinus(col 10:double)(children: FuncPowerDoubleToDouble(col 14:double)(children: DoubleColDivideLongColumn(col 10:double, col 16:bigint)(children: DoubleColSubtract
DoubleColumn(col 4:double, col 14:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 14:double) -> 10:double, IfExprNullCondExpr(col 13:boolean, null, col 15:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 15:bigint) -> 16:bigint) -> 14:double) -> 10:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 10:double, col 17:double)(children: FuncPowerDoubleToDouble(col 17:double)(children: DoubleColDivideLongColumn(col 10:double, col 19:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 17:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 17:double) -> 10:double, IfExprNullCondExpr(col 16:boolean, null, col 18:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 16:boo
lean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 18:bigint) -> 19:bigint) -> 17:double) -> 10:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 20:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 1:double) -> 10:double, DecimalColDivideDecimalScalar(col 21:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(28,6), FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col 17:double, col 25:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 23:double)(children: DoubleColDivideLongColumn(col 17:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 17:double) -> 23:double) -> 17:double, IfExprNullCondExpr(col 19:boolean, null, col 24:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 19:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 24:bigint) -> 25:bigint) -> 23:double) -> 17:double
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[05/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
index 6215906..0336982 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
@@ -91,7 +91,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -100,7 +100,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 762), FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 1:smallint) -> 13:float), FilterDoubleColGreaterDoubleScalar(col 13:double, val -5.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 2:int) -> 13:double)), FilterStringGroupColEqualStringScalar(col 6:string, val a), FilterExprAndExpr(children: FilterDecimalColLessEqualDecimalScalar(col 14:decimal(22,3), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterStringGroupColNotEqualStringScalar(col 7:string, val a), FilterDecimalColNotEqualDecimalScalar(col 15:decimal(13,3), val 79.553)(children: CastLongToDecimal(col 2:int) -> 15:decimal(13,3)), FilterLongColNotEqualLongColumn(col 11:boolean, co
l 10:boolean)))
predicate: (((CAST( cbigint AS decimal(22,3)) <= -1.389) and (cstring2 <> 'a') and (CAST( cint AS decimal(13,3)) <> 79.553) and (cboolean2 <> cboolean1)) or ((UDFToFloat(csmallint) < cfloat) and (UDFToDouble(ctimestamp2) > -5.0D) and (cdouble <> UDFToDouble(cint))) or (cbigint = 762L) or (cstring1 = 'a')) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -109,7 +109,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 5, 1, 4, 0, 13, 18, 16, 20]
selectExpressions: CastLongToDouble(col 2:int) -> 13:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 17:double) -> 18:double, CastLongToDouble(col 1:smallint) -> 16:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 1:smallint) -> 17:double, CastLongToDouble(col 1:smallint) -> 19:double) -> 20:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), sum(_col8), sum(_col7), count(_col2), sum(_col3), count(_col3), min(_col4)
Group By Vectorization:
@@ -263,7 +263,7 @@ WHERE ((762 = cbigint)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-1.6000018929276082E8 1.5999646129276082E8 -1.5999646129276082E8 1.5999646129276082E8 2.5598867626205912E16 -8706342.964000002 -1.6000018929276082E8 5.481251832900251E8 4.095728233294762E24 8549.657499338193 -5.481251832900251E8 3.8812872199726427E8 2.12743126884873664E17 3.0054786945574982E17 -5.700752675298234 -3.0054786945574982E17 3.0054786945574982E17 973579.3664121227 5.482224634724026E8 -973579.3664121227 -18.377427808018613 -64 2044 -6.573680812059072E-5 18.377427808018613
+1.6000018929276082E8 1.5999646129276082E8 -1.5999646129276082E8 1.5999646129276082E8 2.5598867626205912E16 -8706342.964000002 -1.6000018929276082E8 5.481251832900263E8 4.095728233294762E24 8549.657499338193 -5.481251832900263E8 3.8812872199726546E8 2.12743126884874784E17 3.0054786945575117E17 -5.700752675298234 -3.0054786945575117E17 3.0054786945575117E17 973579.3664121248 5.482224634724039E8 -973579.3664121248 -18.377427808018613 -64 2044 -6.573680812059058E-5 18.377427808018613
PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
SELECT MAX(cint),
(MAX(cint) / -3728),
@@ -351,7 +351,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -360,7 +360,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 3:bigint, val 197), FilterLongColLessLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int)), FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -26.28), FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 1:smallint) -> 13:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 0:tinyint) -> 13:float), FilterStringColRegExpStringScalar(col 6:string, pattern .*ss.*)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 4:float, val 79.5530014038086), FilterStringColLikeStringScalar(col 7:string, pattern 10%)))
predicate: (((UDFToFloat(ctinyint) > cfloat) and cstring1 regexp '.*ss.*') or ((cbigint <= 197L) and (UDFToLong(cint) < cbigint)) or ((cdouble >= -26.28D) and (UDFToDouble(csmallint) > cdouble)) or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean)
- Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6826 Data size: 1615394 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -369,7 +369,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 3, 1, 5, 0, 13, 16, 14, 18, 15, 20]
selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, CastLongToDouble(col 1:smallint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 15:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 2:int) -> 17:double, CastLongToDouble(col 2:int) -> 19:double) -> 20:double
- Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6826 Data size: 1615394 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(_col0), sum(_col6), sum(_col5), count(_col1), sum(_col8), sum(_col7), count(_col2), max(_col3), sum(_col4), count(_col4), min(_col0), min(_col3), sum(_col10), sum(_col9), count(_col0)
Group By Vectorization:
@@ -603,7 +603,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -612,7 +612,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterTimestampColEqualTimestampColumn(col 8:timestamp, col 9:timestamp), FilterDoubleColEqualDoubleScalar(col 4:float, val 762.0), FilterStringGroupColEqualStringScalar(col 6:string, val ss), FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterLongColEqualLongScalar(col 11:boolean, val 1)), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), SelectColumnIsNotNull(col 9:timestamp), FilterStringGroupColGreaterStringScalar(col 7:string, val a)))
predicate: (((UDFToLong(csmallint) <= cbigint) and (cboolean2 = 1)) or (cboolean1 is not null and ctimestamp2 is not null and (cstring2 > 'a')) or (cfloat = 762) or (cstring1 = 'ss') or (ctimestamp1 = ctimestamp2)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
@@ -621,7 +621,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 0, 1, 2, 5, 13, 16, 14, 18, 15]
selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, CastLongToDouble(col 1:smallint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 15:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 15:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col6), sum(_col5), count(_col0), count(), max(_col1), sum(_col8), sum(_col7), count(_col2), max(_col3), sum(_col9), sum(_col4), count(_col4), count(_col1), sum(_col1)
Group By Vectorization:
@@ -767,7 +767,7 @@ WHERE ((ctimestamp1 = ctimestamp2)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-2.5109214708344376E18 -2.5109214708344376E18 5.0218429416688753E18 2780 75.198 62 2.5109214708344402E18 2.5109214708344376E18 -1.0 2780 -2780 9460.675803068356 -2.5109214708344376E18 -2118360 1072872630 -2118298 -2.5109214697615652E18 185935.34910862715 0 758 -1.733509234828496 -3728
+2.5109214708345605E18 -2.5109214708345605E18 5.021842941669121E18 2780 75.198 62 2.5109214708345631E18 2.5109214708345605E18 -1.0 2780 -2780 9460.675803068356 -2.5109214708345605E18 -2118360 1072872630 -2118298 -2.5109214697616881E18 185935.34910862715 0 758 -1.733509234828496 -3728
WARNING: Comparing a bigint and a double may result in a loss of precision.
PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
SELECT AVG(ctinyint),
@@ -834,7 +834,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -843,7 +843,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessEqualTimestampColumn(col 9:timestamp, col 8:timestamp), FilterDoubleColNotEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 13:double), FilterStringGroupColGreaterEqualStringScalar(col 6:string, val ss)), FilterExprAndExpr(children: FilterLongColLessLongColumn(col 1:smallint, col 0:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double)), FilterDoubleColEqualDoubleScalar(col 4:float, val 17.0))
predicate: (((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0D)) or ((ctimestamp2 <= ctimestamp1) and (UDFToDouble(cbigint) <> cdouble) and (cstring1 >= 'ss')) or (cfloat = 17)) (type: boolean)
- Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8874 Data size: 2100060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
@@ -852,7 +852,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 2, 4, 13, 16, 14, 18]
selectExpressions: CastLongToDouble(col 2:int) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 2:int) -> 14:double, CastLongToDouble(col 2:int) -> 15:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 15:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 18:double
- Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8874 Data size: 2100060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0), count(_col0), max(_col1), sum(_col5), sum(_col4), count(_col2), sum(_col7), sum(_col6), count(_col1), max(_col3)
Group By Vectorization:
@@ -979,7 +979,7 @@ WHERE (((ctimestamp2 <= ctimestamp1)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--0.5934409161894847 6980.406559083811 6979.813118167622 2141851355 -11761.597368421053 -6980.406559083811 1.5852855222070777E8 -0.5934409161894847 2.5099887741857176E16 1.52140608502098611E18 -2141851355 -13.510823917814225 79.553 -3.998255191435152E19
+-0.5934409161894847 6980.406559083811 6979.813118167622 2141851355 -11761.597368421053 -6980.406559083811 1.5852855222071928E8 -0.5934409161894847 2.5099887741860824E16 1.52140608502098611E18 -2141851355 -13.510823917813244 79.553 -3.998255191435152E19
PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
SELECT cint,
cdouble,
@@ -1073,7 +1073,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -1082,7 +1082,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterStringColRegExpStringScalar(col 6:string, pattern a.*), FilterStringColLikeStringScalar(col 7:string, pattern %ss%)), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 11:boolean, val 1), FilterDecimalColLessDecimalScalar(col 13:decimal(8,3), val 79.553)(children: CastLongToDecimal(col 1:smallint) -> 13:decimal(8,3)), FilterLongColNotEqualLongScalar(col 0:int, val -257)(children: col 0:tinyint)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 14:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double), FilterDoubleColGreaterEqualDoubleColumn(col 4:float, col 14:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 14:float)), FilterExprAndExpr(children: FilterLongColLessLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColGreaterLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint)))
predicate: (((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint)) or ((cboolean2 <> 1) and (CAST( csmallint AS decimal(8,3)) < 79.553) and (UDFToInteger(ctinyint) <> -257)) or ((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or (cstring1 regexp 'a.*' and (cstring2 like '%ss%'))) (type: boolean)
- Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2342392 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728L * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - CAST( cint AS decimal(10,0))) (type: decimal(14,3)), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - CAST( cint AS decimal(10,0))) - -26.28) (type: decimal(15,3)), (- cfloat) (type: float), (cdouble * -89010.0D) (type: double), (UDFToDouble(ctinyint) / 988888.0D) (type: double), (- ctinyint) (type: tinyint), (79.553 / CAST( ctinyint AS decimal(3,0))) (type: decimal(9,7))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22
@@ -1091,7 +1091,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 5, 9, 6, 11, 0, 4, 8, 1, 3, 15, 16, 18, 19, 21, 23, 25, 27, 14, 24, 29, 20, 31]
selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 3:bigint) -> 15:bigint, LongColUnaryMinus(col 2:int) -> 16:int, DecimalScalarSubtractDecimalColumn(val -863.257, col 17:decimal(10,0))(children: CastLongToDecimal(col 2:int) -> 17:decimal(10,0)) -> 18:decimal(14,3), LongColUnaryMinus(col 1:smallint) -> 19:smallint, LongColSubtractLongColumn(col 1:smallint, col 20:smallint)(children: LongColUnaryMinus(col 1:smallint) -> 20:smallint) -> 21:smallint, LongColAddLongColumn(col 22:smallint, col 20:smallint)(children: LongColSubtractLongColumn(col 1:smallint, col 20:smallint)(children: LongColUnaryMinus(col 1:smallint) -> 20:smallint) -> 22:smallint, LongColUnaryMinus(col 1:smallint) -> 20:smallint) -> 23:smallint, DoubleColDivideDoubleColumn(col 14:double, col 24:double)(children: CastLongToDouble(col 2:int) -> 14:double, CastLongToDouble(col 2:int) -> 24:double) -> 25:double, DecimalColSubtractDecimalScalar(col 26:decimal(14,3), val -26.28)(children:
DecimalScalarSubtractDecimalColumn(val -863.257, col 17:decimal(10,0))(children: CastLongToDecimal(col 2:int) -> 17:decimal(10,0)) -> 26:decimal(14,3)) -> 27:decimal(15,3), DoubleColUnaryMinus(col 4:float) -> 14:float, DoubleColMultiplyDoubleScalar(col 5:double, val -89010.0) -> 24:double, DoubleColDivideDoubleScalar(col 28:double, val 988888.0)(children: CastLongToDouble(col 0:tinyint) -> 28:double) -> 29:double, LongColUnaryMinus(col 0:tinyint) -> 20:tinyint, DecimalScalarDivideDecimalColumn(val 79.553, col 30:decimal(3,0))(children: CastLongToDecimal(col 0:tinyint) -> 30:decimal(3,0)) -> 31:decimal(9,7)
- Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2342392 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: decimal(14,3)), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: decimal(15,3)), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: decimal(9,7))
sort order: +++++++++++++++++++++++
@@ -1099,7 +1099,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2342392 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -1127,19 +1127,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22]
- Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2342392 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 50
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 11800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 11800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1368,7 +1368,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -1377,7 +1377,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessLongScalar(col 0:int, val 197)(children: col 0:tinyint), FilterLongColEqualLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int)), FilterLongColEqualLongScalar(col 3:bigint, val 359), FilterLongColLessLongScalar(col 10:boolean, val 0), FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %ss), FilterDoubleColLessEqualDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 0:tinyint) -> 13:float)))
predicate: (((UDFToInteger(ctinyint) < 197) and (UDFToLong(cint) = cbigint)) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint))) or (cbigint = 359L) or (cboolean1 < 0)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (CAST( cbigint AS decimal(19,0)) % 79.553) (type: decimal(5,3)), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % cfloat) (type: float), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569L % cbigint) (type: bigint), (359.0D - cdouble) (type: double), (- csmallint) (type: smallint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
@@ -1386,7 +1386,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 3, 6, 10, 4, 5, 9, 1, 7, 11, 15, 17, 13, 14, 18, 20, 19, 22, 21, 23, 24, 27, 28, 25, 29]
selectExpressions: DoubleColDivideDoubleColumn(col 13:double, col 14:double)(children: CastLongToDouble(col 2:int) -> 13:double, CastLongToDouble(col 3:bigint) -> 14:double) -> 15:double, DecimalColModuloDecimalScalar(col 16:decimal(19,0), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 16:decimal(19,0)) -> 17:decimal(5,3), DoubleColUnaryMinus(col 18:double)(children: DoubleColDivideDoubleColumn(col 13:double, col 14:double)(children: CastLongToDouble(col 2:int) -> 13:double, CastLongToDouble(col 3:bigint) -> 14:double) -> 18:double) -> 13:double, DoubleScalarModuloDoubleColumn(val 10.175000190734863, col 4:float) -> 14:float, DoubleColUnaryMinus(col 4:float) -> 18:float, DoubleColSubtractDoubleColumn(col 4:float, col 19:float)(children: DoubleColUnaryMinus(col 4:float) -> 19:float) -> 20:float, DoubleColModuloDoubleScalar(col 21:float, val -6432.0)(children: DoubleColSubtractDoubleColumn(col 4:float, col 19:float)(children: DoubleColUnaryMinus(col
4:float) -> 19:float) -> 21:float) -> 19:float, DoubleColMultiplyDoubleColumn(col 5:double, col 21:double)(children: CastLongToDouble(col 1:smallint) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 5:double) -> 21:double, LongColUnaryMinus(col 3:bigint) -> 23:bigint, DoubleColSubtractDoubleColumn(col 4:double, col 26:double)(children: col 4:float, DoubleColDivideDoubleColumn(col 24:double, col 25:double)(children: CastLongToDouble(col 2:int) -> 24:double, CastLongToDouble(col 3:bigint) -> 25:double) -> 26:double) -> 24:double, LongColUnaryMinus(col 1:smallint) -> 27:smallint, LongScalarModuloLongColumn(val 3569, col 3:bigint) -> 28:bigint, DoubleScalarSubtractDoubleColumn(val 359.0, col 5:double) -> 25:double, LongColUnaryMinus(col 1:smallint) -> 29:smallint
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean), _col10 (type: double), _col11 (type: decimal(5,3)), _col12 (type: double), _col13 (type: float), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double), _col24 (type: smallint)
sort order: +++++++++++++++++++++++++
@@ -1394,7 +1394,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -1422,19 +1422,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 21]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1612,7 +1612,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -1621,7 +1621,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDecimalColGreaterDecimalScalar(col 13:decimal(7,2), val -26.28)(children: CastLongToDecimal(col 1:smallint) -> 13:decimal(7,2)), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5:double, col 14:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterStringGroupColGreaterEqualStringScalar(col 6:string, val ss), FilterDoubleColNotEqualDoubleColumn(col 14:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 14:double)), FilterLongColEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 14:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 3:bigint) -> 14:float), FilterDecimalColGreaterEqualDecimalScalar(col 13:decimal(7,2), val -26.28)(children: CastLongToDecimal(col 1:smallint) -> 13:d
ecimal(7,2))))
predicate: (((CAST( csmallint AS decimal(7,2)) > -26.28) and (cstring2 like 'ss')) or ((UDFToFloat(cbigint) <= cfloat) and (CAST( csmallint AS decimal(7,2)) >= -26.28)) or ((cdouble <= UDFToDouble(cbigint)) and (cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble)) or (UDFToInteger(ctinyint) = -89010)) (type: boolean)
- Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2584725 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / CAST( ctinyint AS decimal(3,0))) (type: decimal(8,7)), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
@@ -1630,7 +1630,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 6, 11, 9, 5, 4, 3, 1, 10, 15, 16, 17, 14, 19, 20, 21, 23, 26, 28, 25, 18, 29]
selectExpressions: LongColAddLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 15:int, LongColSubtractLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint) -> 16:bigint, LongColUnaryMinus(col 3:bigint) -> 17:bigint, DoubleColUnaryMinus(col 4:float) -> 14:float, LongColAddLongColumn(col 18:bigint, col 3:bigint)(children: LongColSubtractLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint) -> 18:bigint) -> 19:bigint, DoubleColDivideDoubleColumn(col 5:double, col 5:double) -> 20:double, DoubleColUnaryMinus(col 5:double) -> 21:double, LongColMultiplyLongColumn(col 18:bigint, col 22:bigint)(children: col 18:int, LongColUnaryMinus(col 3:bigint) -> 22:bigint) -> 23:bigint, DoubleColAddDoubleColumn(col 24:double, col 25:double)(children: DoubleColUnaryMinus(col 5:double) -> 24:double, CastLongToDouble(col 3:bigint) -> 25:double) -> 26:double, DecimalScalarDivideDecimalColumn(val -1.389, col 27:decimal(3,0))(children: CastLongToDecima
l(col 0:tinyint) -> 27:decimal(3,0)) -> 28:decimal(8,7), DoubleColModuloDoubleColumn(col 24:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 24:double) -> 25:double, LongColUnaryMinus(col 1:smallint) -> 18:smallint, LongColAddLongColumn(col 1:int, col 22:int)(children: col 1:smallint, LongColAddLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 22:int) -> 29:int
- Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2584725 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: decimal(8,7)), _col19 (type: double), _col20 (type: smallint), _col21 (type: int)
sort order: +++++++++++++++++++++
@@ -1638,7 +1638,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2584725 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: boolean)
Execution mode: vectorized
@@ -1667,19 +1667,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [6, 1, 21, 2, 5, 3, 4, 7, 0, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20]
- Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2584725 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 75
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 75 Data size: 17700 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 75 Data size: 17700 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1914,7 +1914,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -1923,7 +1923,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDecimalColLessEqualDecimalScalar(col 13:decimal(13,3), val -1.389)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)), FilterLongColLessLongColumn(col 1:smallint, col 0:smallint)(children: col 0:tinyint), FilterLongColLessLongScalar(col 1:int, val -6432)(children: col 1:smallint)), FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleColumn(col 5:double, col 4:double)(children: col 4:float), FilterStringGroupColLessEqualStringScalar(col 7:string, val a)), FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern ss%), FilterDecimalColLessDecimalScalar(col 14:decimal(22,3), val 10.175)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3))))
predicate: (((CAST( cint AS decimal(13,3)) <= -1.389) and (csmallint < UDFToShort(ctinyint)) and (UDFToInteger(csmallint) < -6432)) or ((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (CAST( cbigint AS decimal(22,3)) < 10.175))) (type: boolean)
- Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 915374 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0D) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double), (cdouble * 10.175D) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (- cdouble) (type: double), (cdouble * (- cdouble)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
@@ -1932,7 +1932,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 7, 5, 4, 3, 1, 16, 17, 15, 18, 19, 21, 20, 22, 23, 25]
selectExpressions: DoubleColDivideDoubleScalar(col 15:double, val 3569.0)(children: CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, LongScalarSubtractLongColumn(val -257, col 1:int)(children: col 1:smallint) -> 17:int, DoubleScalarMultiplyDoubleColumn(val -6432.0, col 4:float) -> 15:float, DoubleColUnaryMinus(col 5:double) -> 18:double, DoubleColMultiplyDoubleScalar(col 5:double, val 10.175) -> 19:double, DoubleColDivideDoubleColumn(col 20:double, col 4:double)(children: col 20:float, col 4:float) -> 21:double, DoubleColUnaryMinus(col 4:float) -> 20:float, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 22:int, DoubleColUnaryMinus(col 5:double) -> 23:double, DoubleColMultiplyDoubleColumn(col 5:double, col 24:double)(children: DoubleColUnaryMinus(col 5:double) -> 24:double) -> 25:double
- Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 915374 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col14 (type: double), _col15 (type: double)
sort order: +++++++++++++++
@@ -1940,7 +1940,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 915374 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: timestamp)
Execution mode: vectorized
@@ -1969,19 +1969,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [15, 1, 2, 3, 4, 0, 5, 6, 7, 8, 9, 10, 11, 12, 8, 14]
- Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 915374 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 45
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 45 Data size: 10620 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 45 Data size: 10620 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2158,7 +2158,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -2167,7 +2167,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 1:int, val -257)(children: col 1:smallint), FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1:int, val -6432)(children: col 1:smallint), FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 13:double), FilterLongColLessEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint))))
predicate: (((UDFToInteger(csmallint) = -6432) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint))) and (UDFToInteger(csmallint) >= -257)) (type: boolean)
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -2176,7 +2176,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 0, 13, 16, 14, 18]
selectExpressions: CastLongToDouble(col 1:smallint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 1:smallint) -> 14:double, CastLongToDouble(col 1:smallint) -> 15:double) -> 16:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col4), sum(_col3), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count()
Group By Vectorization:
@@ -2190,7 +2190,7 @@ STAGE PLANS:
keys: _col0 (type: smallint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
@@ -2199,7 +2199,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -2233,7 +2233,7 @@ STAGE PLANS:
keys: KEY._col0 (type: smallint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 296052 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), power(((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (-1.389 / CAST( _col0 AS decimal(5,0))) (type: decimal(10,9)), _col4 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col4)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), ((_col5 - ((_col6 * _col6) / _col7)) / _col7) (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col8 (type: bigint), (_col8 - -89010L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -2242,7 +2242,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 9, 10, 16, 4, 18, 19, 17, 14, 8, 20]
selectExpressions: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 9:int, FuncPowerDoubleToDouble(col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 14:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 10:double) -> 11:double) -> 10:double, IfExprNullCondExpr(col 12:boolean, null, col 13:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 12:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 13:bigint) -> 14:bigint) -> 11:double) -> 10:double, DecimalScalarDivideDecimalColumn(val -1.389, col 15:decimal(5,0))(children: CastLongToDecimal(col 0:smallint) -> 15:decimal(5,0)) -> 16:decimal(10,9), DoubleColDivideDoubleColumn(col 11:double, col 17:double)(children: CastLongToDouble(col 14:int)(children: LongColModuloLongScalar(col 0:int, val -7
5)(children: col 0:smallint) -> 14:int) -> 11:double, CastLongToDouble(col 4:bigint) -> 17:double) -> 18:double, LongColUnaryMinus(col 14:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 14:int) -> 19:int, DoubleColDivideLongColumn(col 11:double, col 7:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 17:double)(children: DoubleColDivideLongColumn(col 11:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 11:double) -> 17:double) -> 11:double) -> 17:double, LongColUnaryMinus(col 20:int)(children: LongColUnaryMinus(col 14:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 14:int) -> 20:int) -> 14:int, LongColSubtractLongScalar(col 8:bigint, val -89010) -> 20:bigint
- Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 296052 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(10,9)), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint)
sort order: +++++++++++
@@ -2250,7 +2250,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 296052 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized
@@ -2268,19 +2268,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 296052 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2433,7 +2433,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -2442,7 +2442,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 2563.58), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 3:bigint, col 2:bigint)(children: col 2:int), FilterLongColLessLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterDoubleColLessDoubleScalar(col 4:float, val -5638.14990234375)), FilterDecimalColEqualDecimalScalar(col 13:decimal(6,2), val 2563.58)(children: CastLongToDecimal(col 0:tinyint) -> 13:decimal(6,2)), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5:double, col 14:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(21,2), val -5638.15)(children: CastLongToDecimal(col 3:bigint) -> 15:decimal(21,2)))))
predicate: ((((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (cfloat < -5638.15)) or (CAST( ctinyint AS decimal(6,2)) = 2563.58) or ((cdouble <= UDFToDouble(cbigint)) and (CAST( cbigint AS decimal(21,2)) < -5638.15))) and (cdouble > 2563.58D)) (type: boolean)
- Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 628077 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cdouble (type: double), cfloat (type: float), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2
@@ -2451,7 +2451,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 4, 14]
selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double
- Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 628077 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col2), sum(_col0), count(_col0), count(_col1), sum(_col1)
Group By Vectorization:
@@ -2465,7 +2465,7 @@ STAGE PLANS:
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 628077 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -2474,7 +2474,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 628077 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -2508,7 +2508,7 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 314038 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END) (type: double), (2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), _col4 (type: bigint), ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D) (type: double), ((- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) * ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D)) (type: double), _col5 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (_col0 - (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THE
N (null) ELSE ((_col3 - 1)) END))) (type: double), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (_col0 + ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (_col0 * 762.0D) (type: double), _col2 (type: double), (-863.257D % (_col0 * 762.0D)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -2517,7 +2517,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 7, 6, 11, 4, 17, 20, 5, 23, 26, 14, 29, 30, 2, 34]
selectExpressions: DoubleColDivideLongColumn(col 6:double, col 10:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 7:double)(children: DoubleColDivideLongColumn(col 6:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 6:double) -> 7:double) -> 6:double, IfExprNullCondExpr(col 8:boolean, null, col 9:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 8:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 9:bigint) -> 10:bigint) -> 7:double, DoubleScalarMultiplyDoubleColumn(val 2563.58, col 11:double)(children: DoubleColDivideLongColumn(col 6:double, col 13:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 11:double)(children: DoubleColDivideLongColumn(col 6:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 6:double) -> 11:double) -> 6:double, IfExprNullCondExpr(col 10:boolean, null, col 12:bigint)(children: LongColEqualLongScal
ar(col 3:bigint, val 1) -> 10:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 12:bigint) -> 13:bigint) -> 11:double) -> 6:double, DoubleColUnaryMinus(col 14:double)(children: DoubleColDivideLongColumn(col 11:double, col 16:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 14:double)(children: DoubleColDivideLongColumn(col 11:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 11:double) -> 14:double) -> 11:double, IfExprNullCondExpr(col 13:boolean, null, col 15:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 15:bigint) -> 16:bigint) -> 14:double) -> 11:double, DoubleColAddDoubleScalar(col 14:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 17:double)(children: DoubleColDivideLongColumn(col 14:double, col 19:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 17:double)(children: DoubleColDivi
deLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 17:double) -> 14:double, IfExprNullCondExpr(col 16:boolean, null, col 18:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 18:bigint) -> 19:bigint) -> 17:double) -> 14:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 14:double, col 23:double)(children: DoubleColUnaryMinus(col 20:double)(children: DoubleColDivideLongColumn(col 14:double, col 22:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 20:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 20:double) -> 14:double, IfExprNullCondExpr(col 19:boolean, null, col 21:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 19:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 21:bigint) ->
22:bigint) -> 20:double) -> 14:double, DoubleColAddDoubleScalar(col 20:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 23:double)(children: DoubleColDivideLongColumn(col 20:double, col 25:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 23:double)(children: DoubleColDivideLongColumn(col 20:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 20:double) -> 23:double) -> 20:double, IfExprNullCondExpr(col 22:boolean, null, col 24:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 22:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 24:bigint) -> 25:bigint) -> 23:double) -> 20:double) -> 23:double) -> 20:double, DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 23:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:dou
ble) -> 23:double) -> 14:double) -> 23:double, DoubleColSubtractDoubleColumn(col 0:double, col 14:double)(children: DoubleColUnaryMinus(col 26:double)(children: DoubleColDivideLongColumn(col 14:double, col 28:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 26:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 26:double) -> 14:double, IfExprNullCondExpr(col 25:boolean, null, col 27:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 25:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 27:bigint) -> 28:bigint) -> 26:double) -> 14:double) -> 26:double, FuncPowerDoubleToDouble(col 29:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 29:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, co
l 2:double) -> 14:double) -> 29:double) -> 14:double) -> 29:double) -> 14:double, DoubleColAddDoubleColumn(col 0:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 32:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 29:double) -> 30:double) -> 29:double, IfExprNullCondExpr(col 28:boolean, null, col 31:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 28:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 31:bigint) -> 32:bigint) -> 30:double) -> 29:double, DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 30:double, DoubleScalarModuloDoubleColumn(val -863.257, col 33:double)(children: DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 33:double) -> 34:double
- Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 314038 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -2525,7 +2525,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 314038 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double)
Reducer 3
Execution mode: vectorized
@@ -2543,13 +2543,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13]
- Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 314038 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 314038 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2752,7 +2752,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -2761,7 +2761,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDoubleColNotEqualDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:int, val -257)(children: col 0:tinyint), SelectColumnIsNotNull(col 11:boolean), FilterStringColRegExpStringScalar(col 6:string, pattern .*ss), FilterDoubleColGreaterDoubleScalar(col 13:double, val -3.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double)), FilterDoubleColEqualDoubleScalar(col 13:double, val -5.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 13:double, val 0.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterStringColLikeStringScalar(col 7:string, pattern %b%)), FilterDoubleColEqualDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 2:int) -> 13:do
uble), FilterExprAndExpr(children: SelectColumnIsNull(col 10:boolean), FilterDoubleColLessDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float))))
predicate: ((((UDFToInteger(ctinyint) <> -257) and cboolean2 is not null and cstring1 regexp '.*ss' and (UDFToDouble(ctimestamp1) > -3.0D)) or (UDFToDouble(ctimestamp2) = -5.0D) or ((UDFToDouble(ctimestamp1) < 0.0D) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint)))) and (UDFToDouble(ctimestamp1) <> 0.0D)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -2770,7 +2770,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 6, 2, 1, 0, 4, 5, 13, 16, 14, 18, 4, 15, 17, 21]
selectExpressions: CastLongToDouble(col 2:int) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 2:int) -> 14:double, CastLongToDouble(col 2:int) -> 15:double) -> 16:double, CastLongToDouble(col 1:smallint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 15:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 15:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 19:double, col 20:double)(children: CastLongToDouble(col 0:tinyint) -> 19:double, CastLongToDouble(col 0:tinyint) -> 20:double) -> 21:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col8), sum(_col7), count(_col2), sum(_col3), count(_col3), count(), min(_col4), sum(_col10), sum(_col9), sum(_col12), sum(_col11), count(_col5), sum(_col2), sum(_col5), min(_col6), sum(_col14), sum(_col13), count(_col4)
Group By Vectorization:
@@ -2784,7 +2784,7 @@ STAGE PLANS:
keys: _col0 (type: timestamp), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col1 (type: string)
sort order: ++
@@ -2793,7 +2793,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: tinyint), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -2827,7 +2827,7 @@ STAGE PLANS:
keys: KEY._col0 (type: timestamp), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: timestamp), _col1 (type: string), power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5) (type: double), (power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5) * 10.175D) (type: double), (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) (type: double), (_col5 / _col6) (type: double), (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) (type: double), (-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) (type: double), _col7 (type: bigint), (- _col7) (type: bigint), ((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) (type: double), _col8 (type: tinyint), (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7))) (type: double), (- (power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5) * 10.175D)) (type: do
uble), ((_col9 - ((_col10 * _col10) / _col6)) / CASE WHEN ((_col6 = 1L)) THEN (null) ELSE ((_col6 - 1)) END) (type: double), (((_col9 - ((_col10 * _col10) / _col6)) / CASE WHEN ((_col6 = 1L)) THEN (null) ELSE ((_col6 - 1)) END) + (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) (type: double), (- (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) (type: double), (UDFToDouble((- _col7)) / power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (10.175D / (_col5 / _col6)) (type: double), (_col14 / _col4) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END) (type: double), ((((_col9 - ((_col10 * _col10) / _col6)) / CASE WHEN ((_col6 = 1L)) THEN (null) ELSE ((_col6 - 1)) END) + (((-26.28D - power(((_col2 - ((_
col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) - (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) (type: double), (- (- (power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5) * 10.175D))) (type: double), (_col15 / _col13) (type: double), (((((_col9 - ((_col10 * _col10) / _col6)) / CASE WHEN ((_col6 = 1L)) THEN (null) ELSE ((_col6 - 1)) END) + (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) - (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) * 10.175D) (type: double), (10.175D % (10.175D / (_col5 / _col6))) (type: double), (- _col8) (type: tinyint), _col16 (
type: double), ((_col9 - ((_col10 * _col10) / _col6)) / _col6) (type: double), (- ((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)))) (type: double), ((- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) % (_col15 / _col13)) (type: double), (-26.28 / CAST( (- _col8) AS decimal(3,0))) (type: decimal(8,6)), power(((_col17 - ((_col18 * _col18) / _col19)) / _col19), 0.5) (type: double), _col14 (type: bigint), ((((_col9 - ((_col10 * _col10) / _col6)) / CASE WHEN ((_col6 = 1L)) THEN (null) ELSE ((_col6 - 1)) END) + (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) / ((_col11 - ((_col12 * _col12) / _col13)) / _col13)) (type: double), (- (- _col7)) (type: bigint), _col7 (type: bigint), ((((_col9 - ((_col10 * _col10) / _col6)) / CASE WHEN ((_col6 = 1L)) THEN (null) ELSE ((_col6 - 1)) END
) + (((-26.28D - power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) * (- power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5))) * UDFToDouble((- _col7)))) % -26.28D) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38
@@ -2836,7 +2836,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 20, 22, 23, 21, 25, 26, 7, 27, 24, 8, 30, 28, 32, 29, 35, 40, 39, 41, 38, 43, 46, 49, 42, 50, 51, 53, 16, 55, 56, 58, 61, 54, 14, 62, 67, 7, 65]
selectExpressions: FuncPowerDoubleToDouble(col 21:double)(children: DoubleColDivideLongColumn(col 20:double, col 4:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 21:double)(children: DoubleColDivideLongColumn(col 20:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 20:double) -> 21:double) -> 20:double) -> 21:double) -> 20:double, DoubleColMultiplyDoubleScalar(col 21:double, val 10.175)(children: FuncPowerDoubleToDouble(col 22:double)(children: DoubleColDivideLongColumn(col 21:double, col 4:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 22:double)(children: DoubleColDivideLongColumn(col 21:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 21:double) -> 22:double) -> 21:double) -> 22:double) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 21:double)(children: FuncPowerDoubleToDouble(col 23:double)(children: DoubleColDivideLongColumn(col
21:double, col 4:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 23:double)(children: DoubleColDivideLongColumn(col 21:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 21:double) -> 23:double) -> 21:double) -> 23:double) -> 21:double) -> 23:double, LongColDivideLongColumn(col 5:bigint, col 6:bigint) -> 21:double, DoubleColUnaryMinus(col 24:double)(children: FuncPowerDoubleToDouble(col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 24:double) -> 25:double) -> 24:double) -> 25:double) -> 24:double) -> 25:double, DoubleScalarSubtractDoubleColumn(val -26.28, col 24:double)(children: FuncPowerDoubleToDouble(col 26:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children:
DoubleColSubtractDoubleColumn(col 2:double, col 26:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 24:double) -> 26:double) -> 24:double) -> 26:double) -> 24:double) -> 26:double, LongColUnaryMinus(col 7:bigint) -> 27:bigint, DoubleColMultiplyDoubleColumn(col 28:double, col 29:double)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 24:double)(children: FuncPowerDoubleToDouble(col 28:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 28:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 24:double) -> 28:double) -> 24:double) -> 28:double) -> 24:double) -> 28:double, DoubleColUnaryMinus(col 24:double)(children: FuncPowerDoubleToDouble(col 29:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigi
nt)(children: DoubleColSubtractDoubleColumn(col 2:double, col 29:double)(children: DoubleColDivideLongColumn(col 24:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 24:double) -> 29:double) -> 24:double) -> 29:double) -> 24:double) -> 29:double) -> 24:double, DoubleColMultiplyDoubleColumn(col 28:double, col 29:double)(children: DoubleColMultiplyDoubleColumn(col 29:double, col 30:double)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 28:double)(children: FuncPowerDoubleToDouble(col 29:double)(children: DoubleColDivideLongColumn(col 28:double, col 4:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 29:double)(children: DoubleColDivideLongColumn(col 28:double, col 4:bigint)(children: DoubleColMu
<TRUNCATED>
[06/10] hive git commit: HIVE-19339: Regenerate alltypesorc file with
latest ORC (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out
index 504dfa7..e6a0b5c 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_div0.q.out
@@ -26,7 +26,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Select Operator
@@ -37,7 +37,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 14, 0, 15, 3, 16, 5, 13]
selectExpressions: DoubleColDivideDoubleScalar(col 13:double, val 0.0)(children: CastLongToDouble(col 2:int) -> 13:double) -> 14:double, DoubleColDivideDoubleScalar(col 13:double, val 0.0)(children: CastLongToDouble(col 0:tinyint) -> 13:double) -> 15:double, DoubleColDivideDoubleScalar(col 13:double, val 0.0)(children: CastLongToDouble(col 3:bigint) -> 13:double) -> 16:double, DoubleColDivideDoubleScalar(col 5:double, val 0.0) -> 13:double
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col2 (type: tinyint), _col4 (type: bigint), _col6 (type: double)
sort order: ++++
@@ -45,7 +45,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: double), _col3 (type: double), _col5 (type: double), _col7 (type: double)
Execution mode: vectorized
@@ -74,19 +74,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 4, 1, 5, 2, 6, 3, 7]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -237,7 +237,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -246,7 +246,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000))
predicate: ((cbigint < 100000000L) and (cbigint > 0L)) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / CAST( (cbigint - 988888) AS decimal(19,0))) (type: decimal(22,21))
outputColumnNames: _col0, _col1, _col2
@@ -255,7 +255,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 16, 18]
selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double, DecimalScalarDivideDecimalColumn(val 1.2, col 17:decimal(19,0))(children: CastLongToDecimal(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 17:decimal(19,0)) -> 18:decimal(22,21)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: decimal(22,21))
sort order: +++
@@ -263,7 +263,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -291,19 +291,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -454,7 +454,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -463,7 +463,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0))
predicate: ((cdouble < -199.0D) and (cdouble >= -500.0D)) (type: boolean)
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -472,7 +472,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13, 16, 17, 18, 15, 19]
selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 17:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 18:double, DoubleScalarDivideDoubleColumn(val 3.0, col 14:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double) -> 15:double, DoubleScalarDivideDoubleColumn(val 1.2, col 14:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double) -> 19:double
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double)
sort order: ++++++
@@ -480,7 +480,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -508,19 +508,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 1, 4, 5]
- Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -671,7 +671,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -680,7 +680,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 2:int, val 500000000), FilterDoubleColGreaterDoubleScalar(col 5:double, val 1.0E9), FilterLongColEqualLongScalar(col 0:tinyint, val 0))
predicate: ((cdouble > 1.0E9D) or (cint > 500000000) or (ctinyint = 0Y)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cbigint (type: bigint), ctinyint (type: tinyint), (UDFToDouble(cint) / UDFToDouble((cint - 528534767))) (type: double), (UDFToDouble(cbigint) / UDFToDouble((cbigint - 1018195815L))) (type: double), (UDFToDouble(ctinyint) / UDFToDouble(ctinyint)) (type: double), (cint % (cint - 528534767)) (type: int), (cbigint % (cbigint - 1018195815L)) (type: bigint), (ctinyint % ctinyint) (type: tinyint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -689,7 +689,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 3, 0, 16, 17, 18, 19, 20, 14]
selectExpressions: DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 2:int) -> 13:double, CastLongToDouble(col 14:int)(children: LongColSubtractLongScalar(col 2:int, val 528534767) -> 14:int) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 13:double, CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 1018195815) -> 14:bigint) -> 15:double) -> 17:double, DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 18:double, LongColModuloLongColumn(col 2:int, col 14:int)(children: LongColSubtractLongScalar(col 2:int, val 528534767) -> 14:int) -> 19:int, LongColModuloLongColumn(col 3:bigint, col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 1018195815) -> 14:bigint) -> 20:bigint, LongCol
ModuloLongColumn(col 0:tinyint, col 0:tinyint) -> 14:tinyint
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: tinyint), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: int), _col7 (type: bigint), _col8 (type: tinyint)
sort order: +++++++++
@@ -697,7 +697,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -725,19 +725,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8]
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 23600 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out b/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out
index c46fc03..7f81581 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_nested_udf.q.out
@@ -23,7 +23,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -35,7 +35,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [13]
selectExpressions: FuncAbsLongToLong(col 0:tinyint) -> 13:int
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_not.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_not.q.out b/ql/src/test/results/clientpositive/spark/vectorization_not.q.out
index cf92a6f..5d9a1ef 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_not.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_not.q.out
@@ -55,4 +55,4 @@ WHERE (((cstring2 LIKE '%b%')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593627E9 3.875716535945533E8 0.0 2.0634715172019392E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.0516820315185745E9 -2.0634715172019392E18 1.5020929380914048E17 -64 64
+-3.875652215945533E8 3.875652215945533E8 -3.875716535945533E8 1.4363874554593987E9 3.875716535945533E8 0.0 2.06347151720204262E18 3.875716535945533E8 3.875652215945533E8 3.875716535945533E8 1.0 10934 -37224.52399241924 1.051733737257113E9 -2.06347151720204262E18 1.5020929380914048E17 -64 64
http://git-wip-us.apache.org/repos/asf/hive/blob/95d6d9b3/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out
index 0cf6955..9001a2a 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_pushdown.q.out
@@ -23,14 +23,14 @@ STAGE PLANS:
TableScan
alias: alltypesorc
filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean)
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cbigint (type: bigint)
outputColumnNames: cbigint
- Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(cbigint), count(cbigint)
mode: hash