Repository: hive Updated Branches: refs/heads/branch-1.0 301de8353 -> 9eb95813a
http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/vectorization_short_regress.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out index 34394c5..ffb1401 100644 --- a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out @@ -141,14 +141,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((762 = cbigint) or ((csmallint < cfloat) and ((ctimestamp2 > -5) and (cdouble <> cint)))) or (cstring1 = 'a')) or ((cbigint <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> cint) and (cboolean2 <> cboolean1))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) outputColumnNames: cint, cdouble, csmallint, cfloat, ctinyint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) mode: hash @@ -347,14 +347,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((cbigint <= 197) and (cint < cbigint)) or ((cdouble >= -26.28) and (csmallint > cdouble))) or ((ctinyint > cfloat) and (cstring1 rlike '.*ss.*'))) or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean) - Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) outputColumnNames: cint, cbigint, csmallint, cdouble, ctinyint - Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) mode: hash @@ -544,14 +544,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((ctimestamp1 = ctimestamp2) or (762.0 = cfloat)) or (cstring1 = 'ss')) or ((csmallint <= cbigint) and (1 = cboolean2))) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a')))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) outputColumnNames: cbigint, ctinyint, csmallint, cint, cdouble - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) mode: hash @@ -720,14 +720,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((ctimestamp2 <= ctimestamp1) and ((cbigint <> cdouble) and ('ss' <= cstring1))) or ((csmallint < ctinyint) and (ctimestamp1 >= 0))) or (cfloat = 17.0)) (type: boolean) - Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) outputColumnNames: ctinyint, cbigint, cint, cfloat - Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) mode: hash @@ -902,20 +902,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or ((1 <> cboolean2) and ((csmallint < 79.553) and (-257 <> ctinyint)))) or ((cdouble > ctinyint) and (cfloat >= cint))) or ((cint < cbigint) and (ctinyint > cbigint))) (type: boolean) - Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 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), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - cint) (type: double), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (cint / cint) (type: double), ((-863.257 - cint) - -26.28) (type: double), (- cfloat) (type: float), (cdouble * -89010) (type: double), (ctinyint / 988888) (type: double), (- ctinyint) (type: tinyint), (79.553 / ctinyint) (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 - Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1140,20 +1140,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((197.0 > ctinyint) and (cint = cbigint)) or (cbigint = 359)) or (cboolean1 < 0)) or ((cstring1 like '%ss') and (cfloat <= ctinyint))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 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), (cint / cbigint) (type: double), (cbigint % 79.553) (type: double), (- (cint / cbigint)) (type: double), (10.175 % cfloat) (type: double), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432) (type: float), (cdouble * csmallint) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (cfloat - (cint / cbigint)) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359 - 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 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1329,31 +1329,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((csmallint > -26.28) and (cstring2 like 'ss')) or ((cdouble <= cbigint) and ((cstring1 >= 'ss') and (cint <> cdouble)))) or (ctinyint = -89010)) or ((cbigint <= cfloat) and (-26.28 <= csmallint))) (type: boolean) - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 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 + csmallint) (type: int), (cbigint - ctinyint) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - ctinyint) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), ((cint + csmallint) * (- cbigint)) (type: bigint), ((- cdouble) + cbigint) (type: double), (-1.389 / ctinyint) (type: double), (cbigint % cdouble) (type: double), (- csmallint) (type: smallint), (csmallint + (cint + 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 - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 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), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double) sort order: ++++++++++ - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: boolean), _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: double), _col19 (type: double), _col20 (type: smallint), _col21 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey7 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey0 (type: boolean), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: bigint), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: smallint), VALUE._col13 (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 - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 75 - Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1588,31 +1588,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((-1.389 >= cint) and ((csmallint < ctinyint) and (-6432 > csmallint))) or ((cdouble >= cfloat) and (cstring2 <= 'a'))) or ((cstring1 like 'ss%') and (10.175 > cbigint))) (type: boolean) - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), ((-6432 * cfloat) / cfloat) (type: double), (- cfloat) (type: float), (cint % csmallint) (type: int), (cdouble * (- cdouble)) (type: double), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (cbigint / 3569) (type: double), (-257 - csmallint) (type: int), (-6432 * cfloat) (type: float), (- cdouble) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col15, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double) sort order: +++ - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: timestamp), _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), _col15 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: float), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: smallint), VALUE._col3 (type: double), VALUE._col4 (type: int), VALUE._col5 (type: float), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: float), VALUE._col10 (type: int), VALUE._col6 (type: double), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 45 - Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1789,25 +1789,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((csmallint >= -257) and ((-6432 = csmallint) or ((cint >= cdouble) and (ctinyint <= cint)))) (type: boolean) - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) outputColumnNames: csmallint, cbigint, ctinyint - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 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: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1816,11 +1816,11 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: smallint), (_col0 % -75) (type: int), _col1 (type: double), (-1.389 / _col0) (type: double), _col2 (type: bigint), ((_col0 % -75) / _col2) (type: double), (- (_col0 % -75)) (type: int), _col3 (type: double), (- (- (_col0 % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1835,19 +1835,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: int), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: int), VALUE._col6 (type: double), VALUE._col7 (type: int), VALUE._col8 (type: bigint), VALUE._col9 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2000,25 +2000,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cdouble > 2563.58) and (((cbigint >= cint) and ((csmallint < cint) and (cfloat < -5638.15))) or ((cdouble <= cbigint) and (-5638.15 > cbigint)))) (type: boolean) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) outputColumnNames: cdouble, cfloat - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 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: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -2027,11 +2027,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2046,16 +2046,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 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) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2255,25 +2255,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((ctimestamp1 <> 0) and (((((((-257 <> ctinyint) and cboolean2 is not null) and ((cstring1 rlike '.*ss') and (-3 < ctimestamp1))) or (ctimestamp2 = -5)) or ((ctimestamp1 < 0) and (cstring2 like '%b%'))) or (cdouble = cint)) or (cboolean1 is null and (cfloat < cint)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 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) outputColumnNames: ctimestamp1, cstring1, cint, csmallint, ctinyint, cfloat, cdouble - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) keys: ctimestamp1 (type: timestamp), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,input:smallint>), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,input:int>), _col9 (type: struct<count:bigint,sum:double,variance:double>), _col10 (type: struct<count:bigint,sum:double,input:float>), _col11 (type: double), _col12 (type: struct<count:bigint,sum:double,variance:double>), _col13 (type: struct<count:bigint,sum:double,variance:double>), _col14 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -2282,17 +2282,17 @@ 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 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * (- _col4)) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) (type: double), (- (- _col2)) (type: double), ((- _col4) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) - (((-26.28 - _col2) * (- _col2)) * (- _col4))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) - (((-26.28 - _col2) * (- _col2)) * (- _col4))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / (- _col5)) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * (- _col4))) % -26.28) (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 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2568,25 +2568,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (cboolean1 is not null and (((((cdouble < csmallint) and ((cboolean2 = cboolean1) and (cbigint <= -863.257))) or ((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1)))) or (cstring2 rlike 'b')) or ((csmallint >= ctinyint) and ctimestamp2 is null))) (type: boolean) - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) outputColumnNames: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) keys: cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:double>), _col5 (type: bigint), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: bigint), _col8 (type: struct<count:bigint,sum:double,variance:double>), _col9 (type: struct<count:bigint,sum:double,variance:double>), _col10 (type: struct<count:bigint,sum:double,input:int>) Execution mode: vectorized Reduce Operator Tree: @@ -2595,11 +2595,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: float), ((_col2 - 10.175) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + (- _col1))) (type: double), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * _col5) (type: double), (- _col1) (type: float), (_col7 - (-1.389 * _col5)) (type: double), _col9 (type: double), (- (_col7 - (-1.389 * _col5))) (type: double), _col10 (type: double), (- _col10) (type: double), (_col10 * _col7) (type: double), (-26.28 / _col1) (type: double), _col2 (type: bigint), (_col2 - 10.175) (type: double), _col3 (type: double), (_col3 % _col1) (type: double), (10.175 + (- _col1)) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2614,16 +2614,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float), _col2 (type: float), _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: bigint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), 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._col12 (type: double), VALUE._col15 (type: bigint), VALUE._col16 (type: double), VALUE._col17 (type: double), VALUE._col18 (type: double), VALUE._col19 (type: double), VALUE._col20 (type: double), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (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 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 bec3de1..d65b5b3 100644 --- a/ql/src/test/results/clientpositive/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/vectorized_case.q.out @@ -44,17 +44,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((csmallint = 418) or (csmallint = 12205)) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 8ce937f..f47edff 100644 --- a/ql/src/test/results/clientpositive/vectorized_casts.q.out +++ b/ql/src/test/results/clientpositive/vectorized_casts.q.out @@ -156,17 +156,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 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 * 0)) (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), UDFToD ouble(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 * 0) 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 * 0)) (type: string), UDFToString(ctimestamp1) (type: string), cstring1 (type: string), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), UDFToString(sin(cfloat)) (type: string), (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 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 e19186f..d870f83 100644 --- a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out @@ -94,21 +94,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: cint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(DISTINCT cint), count(DISTINCT cint), avg(DISTINCT cint), std(DISTINCT cint) keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 da1a838..442361e 100644 --- a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out @@ -22,10 +22,10 @@ STAGE PLANS: t1 TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: 0 @@ -39,10 +39,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -53,11 +53,11 @@ STAGE PLANS: 0 cint (type: int) 1 cint (type: int) outputColumnNames: _col2, _col17 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col17 (type: int) outputColumnNames: _col2, _col17 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17)) mode: hash http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 99deb49..29f80f6 100644 --- a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out @@ -116,17 +116,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cbigint % 500) = 0) and (sin(cfloat) >= -1.0)) (type: boolean) - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 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 - 15601.0)) (type: double), log2(cfloat) (type: double), log2(cbigint) (type: double), log2(cint) (type: double), log2(csmallint) (type: double), log2(ctinyint) (type: double), log(2.0, cdouble) (type: double), power(log2(cdouble), 2.0) (type: double), power(log2(cdouble), 2.0) (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))) + 3.14159)) (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 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out index ed7e595..99c329d 100644 --- a/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out @@ -21,10 +21,10 @@ STAGE PLANS: t1:v1 TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ctinyint is not null and csmallint is not null) (type: boolean) - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: 0 {csmallint} {cdouble} @@ -35,10 +35,10 @@ STAGE PLANS: v3 TableScan alias: v3 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator condition expressions: 0 {_col1} @@ -52,10 +52,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: v2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -66,14 +66,14 @@ STAGE PLANS: 0 ctinyint (type: tinyint) 1 ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col5, _col15 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col0 = _col15) (type: boolean) - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3379 Data size: 726540 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col5 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3379 Data size: 103739 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3379 Data size: 726540 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -84,11 +84,11 @@ STAGE PLANS: 0 _col0 (type: smallint) 1 csmallint (type: smallint) outputColumnNames: _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: double) outputColumnNames: _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) mode: hash http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 f621927..155f5c4 100644 --- a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out @@ -17,26 +17,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: cint (type: int) sort order: + Map-reduce partition columns: cint (type: int) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: cint (type: int) sort order: + Map-reduce partition columns: cint (type: int) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Join Operator @@ -46,11 +46,11 @@ STAGE PLANS: 0 {KEY.reducesinkkey0} 1 {KEY.reducesinkkey0} outputColumnNames: _col2, _col17 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col17 (type: int) outputColumnNames: _col2, _col17 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17)) mode: hash http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 9ab5c1e..8a5925e 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: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((cbigint % 237) = 0) and (length(substr(cstring1, 1, 2)) <= 2)) and (cstring1 like '%')) (type: boolean) - Statistics: Num rows: 1024 Data size: 31436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 220163 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: 31436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 31436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/9eb95813/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 d43c699..883e7d5 100644 --- a/ql/src/test/results/clientpositive/windowing_streaming.q.out +++ b/ql/src/test/results/clientpositive/windowing_streaming.q.out @@ -305,29 +305,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 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: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.8 value expressions: ctinyint (type: tinyint), cdouble (type: double) Reduce Operator Tree: Extract - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE PTF Operator - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_wcol0 < 5) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), _col5 (type: double), _wcol0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat