This is an automated email from the ASF dual-hosted git repository.
englefly pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 051b9aca6ed [fix](cost model) scale group-by-less global agg cost by
BE number when partitioned (#66354)
051b9aca6ed is described below
commit 051b9aca6ed256573608a8457b42f58b0b432fdf
Author: foxtail463 <[email protected]>
AuthorDate: Thu Aug 6 13:54:03 2026 +0800
[fix](cost model) scale group-by-less global agg cost by BE number when
partitioned (#66354)
Problem Summary:
A scalar count(distinct) runs its global aggregate hash-shuffled by the
distinct
key (non-empty partitionExpressions), i.e. in parallel across BEs. But
the cost
model set the parallelism factor from group-by keys alone, so with no
group by it
used factor = 1, costing the aggregate as single-point. This
overestimated the
parallel plan and made CBO reject it.
Solution:
Treat a global aggregate as partitioned when it has group by keys or
non-empty
partitionExpressions, and scale its cost by beNumber accordingly.
---------
Co-authored-by: yangtao555 <[email protected]>
---
.../org/apache/doris/nereids/cost/CostModel.java | 4 +-
.../apache/doris/nereids/cost/CostModelV1Test.java | 51 ++++++++++++++++++++++
.../tpcds_sf100/noStatsRfPrune/query16.out | 42 +++++++++---------
.../tpcds_sf100/noStatsRfPrune/query94.out | 42 +++++++++---------
.../tpcds_sf100/noStatsRfPrune/query95.out | 44 +++++++++----------
.../tpcds_sf100/no_stats_shape/query16.out | 42 +++++++++---------
.../tpcds_sf100/no_stats_shape/query94.out | 42 +++++++++---------
.../tpcds_sf100/no_stats_shape/query95.out | 44 +++++++++----------
.../shape_check/tpcds_sf100/rf_prune/query16.out | 44 +++++++++----------
.../shape_check/tpcds_sf100/rf_prune/query94.out | 44 +++++++++----------
.../shape_check/tpcds_sf100/rf_prune/query95.out | 44 +++++++++----------
.../data/shape_check/tpcds_sf100/shape/query16.out | 44 +++++++++----------
.../data/shape_check/tpcds_sf100/shape/query94.out | 44 +++++++++----------
.../data/shape_check/tpcds_sf100/shape/query95.out | 44 +++++++++----------
.../tpcds_sf1000/bs_downgrade_shape/query95.out | 44 +++++++++----------
.../data/shape_check/tpcds_sf1000/hint/query16.out | 42 +++++++++---------
.../data/shape_check/tpcds_sf1000/hint/query94.out | 42 +++++++++---------
.../data/shape_check/tpcds_sf1000/hint/query95.out | 44 +++++++++----------
.../shape_check/tpcds_sf1000/shape/query16.out | 42 +++++++++---------
.../shape_check/tpcds_sf1000/shape/query94.out | 42 +++++++++---------
.../shape_check/tpcds_sf1000/shape/query95.out | 44 +++++++++----------
.../tpcds_sf1000_nopkfk/shape/query16.out | 42 +++++++++---------
.../tpcds_sf1000_nopkfk/shape/query94.out | 42 +++++++++---------
.../tpcds_sf1000_nopkfk/shape/query95.out | 44 +++++++++----------
.../shape_check/tpcds_sf10t_orc/shape/query16.out | 42 +++++++++---------
.../shape_check/tpcds_sf10t_orc/shape/query94.out | 38 ++++++++--------
.../shape_check/tpcds_sf10t_orc/shape/query95.out | 44 +++++++++----------
27 files changed, 565 insertions(+), 562 deletions(-)
diff --git
a/fe/fe-core/src/main/java/org/apache/doris/nereids/cost/CostModel.java
b/fe/fe-core/src/main/java/org/apache/doris/nereids/cost/CostModel.java
index 28485173376..e21832b00bc 100644
--- a/fe/fe-core/src/main/java/org/apache/doris/nereids/cost/CostModel.java
+++ b/fe/fe-core/src/main/java/org/apache/doris/nereids/cost/CostModel.java
@@ -360,7 +360,9 @@ class CostModel extends PlanVisitor<Cost, PlanContext> {
exprCost / 100 + inputStatistics.getRowCount() / beNumber,
inputStatistics.getRowCount() / beNumber, 0);
} else {
- int factor = aggregate.getGroupByExpressions().isEmpty() ? 1 :
beNumber;
+ boolean isPartitioned =
!aggregate.getGroupByExpressions().isEmpty()
+ || aggregate.getPartitionExpressions().filter(expressions
-> !expressions.isEmpty()).isPresent();
+ int factor = isPartitioned ? beNumber : 1;
// global
return Cost.of(context.getSessionVariable(),
exprCost / 100 + inputStatistics.getRowCount() / factor,
diff --git
a/fe/fe-core/src/test/java/org/apache/doris/nereids/cost/CostModelV1Test.java
b/fe/fe-core/src/test/java/org/apache/doris/nereids/cost/CostModelV1Test.java
index 9ebd933d46c..c81e136ad7c 100644
---
a/fe/fe-core/src/test/java/org/apache/doris/nereids/cost/CostModelV1Test.java
+++
b/fe/fe-core/src/test/java/org/apache/doris/nereids/cost/CostModelV1Test.java
@@ -17,12 +17,26 @@
package org.apache.doris.nereids.cost;
+import org.apache.doris.nereids.PlanContext;
import org.apache.doris.nereids.sqltest.SqlTestBase;
+import org.apache.doris.nereids.trees.expressions.Slot;
+import org.apache.doris.nereids.trees.expressions.functions.agg.AggregateParam;
+import org.apache.doris.nereids.trees.plans.AggMode;
+import org.apache.doris.nereids.trees.plans.AggPhase;
import org.apache.doris.nereids.trees.plans.Plan;
+import org.apache.doris.nereids.trees.plans.physical.PhysicalHashAggregate;
import org.apache.doris.nereids.trees.plans.physical.PhysicalHashJoin;
import org.apache.doris.nereids.util.PlanChecker;
+import org.apache.doris.nereids.util.PlanConstructor;
+import org.apache.doris.statistics.Statistics;
+import org.apache.doris.statistics.StatisticsBuilder;
+import com.google.common.collect.ImmutableList;
+import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.Test;
+import org.mockito.Mockito;
+
+import java.util.Optional;
class CostModelV1Test extends SqlTestBase {
@@ -39,4 +53,41 @@ class CostModelV1Test extends SqlTestBase {
.getBestPlanTree();
p.anyMatch(j -> j instanceof PhysicalHashJoin && ((PhysicalHashJoin<?,
?>) j).getJoinType().isRightJoin());
}
+
+ @Test
+ void testPartitionedScalarAggregateCostUsesClusterScale() {
+ int originBeNumberForTest =
connectContext.getSessionVariable().getBeNumberForTest();
+ connectContext.getSessionVariable().setBeNumberForTest(4);
+ try {
+ Plan child = PlanConstructor.newLogicalOlapScan(101,
"partitioned_scalar_agg_t", 0);
+ Slot partitionKey = child.getOutput().get(0);
+ PhysicalHashAggregate<Plan> aggregate = new
PhysicalHashAggregate<Plan>(
+ ImmutableList.of(), ImmutableList.of(partitionKey),
Optional.of(ImmutableList.of(partitionKey)),
+ new AggregateParam(AggPhase.GLOBAL,
AggMode.INPUT_TO_RESULT), false, null, false, child);
+ PhysicalHashAggregate<Plan> singlePointAggregate = new
PhysicalHashAggregate<Plan>(
+ ImmutableList.of(), ImmutableList.of(partitionKey),
Optional.empty(),
+ new AggregateParam(AggPhase.GLOBAL,
AggMode.INPUT_TO_RESULT), false, null, false, child);
+ PhysicalHashAggregate<Plan> groupByAggregate = new
PhysicalHashAggregate<Plan>(
+ ImmutableList.of(partitionKey),
ImmutableList.of(partitionKey), Optional.empty(),
+ new AggregateParam(AggPhase.GLOBAL,
AggMode.INPUT_TO_RESULT), false, null, false, child);
+ Statistics childStats = new
StatisticsBuilder().setRowCount(1000).build();
+ PlanContext context = Mockito.mock(PlanContext.class);
+ Mockito.when(context.getChildStatistics(0)).thenReturn(childStats);
+
Mockito.when(context.getSessionVariable()).thenReturn(connectContext.getSessionVariable());
+
+ Cost cost = new
CostModel(connectContext).visitPhysicalHashAggregate(aggregate, context);
+ Cost singlePointCost = new
CostModel(connectContext).visitPhysicalHashAggregate(singlePointAggregate,
+ context);
+ Cost groupByCost = new
CostModel(connectContext).visitPhysicalHashAggregate(groupByAggregate, context);
+
+ Assertions.assertEquals(250, cost.getCpuCost(), 1e-9);
+ Assertions.assertEquals(250, cost.getMemoryCost(), 1e-9);
+ Assertions.assertEquals(1000, singlePointCost.getCpuCost(), 1e-9);
+ Assertions.assertEquals(1000, singlePointCost.getMemoryCost(),
1e-9);
+ Assertions.assertEquals(250, groupByCost.getCpuCost(), 1e-9);
+ Assertions.assertEquals(250, groupByCost.getMemoryCost(), 1e-9);
+ } finally {
+
connectContext.getSessionVariable().setBeNumberForTest(originBeNumberForTest);
+ }
+ }
}
diff --git
a/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query16.out
b/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query16.out
index c5ddb58c3b1..a0c674ff8eb 100644
--- a/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF3 cc_call_center_sk->cs_call_center_sk
----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF3 cc_call_center_sk->cs_call_center_sk
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->cs_ship_addr_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->cs_ship_addr_sk
-------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
-----------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+--------------------------PhysicalProject
+----------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF0
cs_order_number->cs_order_number
------------------------------PhysicalProject
---------------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF0
cs_order_number->cs_order_number
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs2)] apply
RFs: RF0
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF1 RF2 RF3
+--------------------------------PhysicalOlapScan[catalog_sales(cs2)] apply
RFs: RF0
------------------------------PhysicalProject
---------------------------------PhysicalOlapScan[catalog_returns(cr1)]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
---------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF1 RF2 RF3
+--------------------------PhysicalProject
+----------------------------PhysicalOlapScan[catalog_returns(cr1)]
------------------------PhysicalProject
---------------------------filter((customer_address.ca_state = 'WV'))
-----------------------------PhysicalOlapScan[customer_address]
+--------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+----------------------------PhysicalOlapScan[date_dim]
--------------------PhysicalProject
-----------------------filter(call_center.cc_county IN ('Barrow County',
'Daviess County', 'Luce County', 'Richland County', 'Ziebach County'))
-------------------------PhysicalOlapScan[call_center]
+----------------------filter((customer_address.ca_state = 'WV'))
+------------------------PhysicalOlapScan[customer_address]
+----------------PhysicalProject
+------------------filter(call_center.cc_county IN ('Barrow County', 'Daviess
County', 'Luce County', 'Richland County', 'Ziebach County'))
+--------------------PhysicalOlapScan[call_center]
diff --git
a/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query94.out
b/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query94.out
index 1abd7ec2887..44f99c94442 100644
--- a/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->ws_ship_addr_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->ws_ship_addr_sk
-------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
-----------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+--------------------------PhysicalProject
+----------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF0
ws_order_number->ws_order_number
------------------------------PhysicalProject
---------------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF0
ws_order_number->ws_order_number
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws2)] apply
RFs: RF0
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
+--------------------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF0
------------------------------PhysicalProject
---------------------------------PhysicalOlapScan[web_returns(wr1)]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
---------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
+--------------------------PhysicalProject
+----------------------------PhysicalOlapScan[web_returns(wr1)]
------------------------PhysicalProject
---------------------------filter((customer_address.ca_state = 'OK'))
-----------------------------PhysicalOlapScan[customer_address]
+--------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
+----------------------------PhysicalOlapScan[date_dim]
--------------------PhysicalProject
-----------------------filter((web_site.web_company_name = 'pri'))
-------------------------PhysicalOlapScan[web_site]
+----------------------filter((customer_address.ca_state = 'OK'))
+------------------------PhysicalOlapScan[customer_address]
+----------------PhysicalProject
+------------------filter((web_site.web_company_name = 'pri'))
+--------------------PhysicalOlapScan[web_site]
diff --git
a/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query95.out
b/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query95.out
index 0e0514695e2..e6a3d47ea15 100644
--- a/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf100/noStatsRfPrune/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
+------------hashAgg[GLOBAL]
+--------------PhysicalProject
+----------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF7 web_site_sk->ws_web_site_sk
------------------PhysicalProject
---------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF7 web_site_sk->ws_web_site_sk
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF6 ca_address_sk->ws_ship_addr_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF6 ca_address_sk->ws_ship_addr_sk
---------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF5 d_date_sk->ws_ship_date_sk
-------------------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF4 ws_order_number->ws_order_number
---------------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply
RFs: RF4
---------------------------------hashJoin[RIGHT_SEMI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF2 ws_order_number->wr_order_number;RF8
ws_order_number->ws_order_number;RF9 ws_order_number->ws_order_number
-----------------------------------PhysicalProject
-------------------------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF1 wr_order_number->ws_order_number
---------------------------------------PhysicalCteConsumer ( cteId=CTEId#0 )
apply RFs: RF1
---------------------------------------PhysicalProject
-----------------------------------------PhysicalOlapScan[web_returns] apply
RFs: RF2
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF5 d_date_sk->ws_ship_date_sk
+--------------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF4 ws_order_number->ws_order_number
+----------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs:
RF4
+----------------------------hashJoin[RIGHT_SEMI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF2 ws_order_number->wr_order_number;RF8
ws_order_number->ws_order_number;RF9 ws_order_number->ws_order_number
+------------------------------PhysicalProject
+--------------------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF1 wr_order_number->ws_order_number
+----------------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply
RFs: RF1
----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF5 RF6 RF7
+------------------------------------PhysicalOlapScan[web_returns] apply RFs:
RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF5 RF6 RF7
--------------------------PhysicalProject
-----------------------------filter((customer_address.ca_state = 'NC'))
-------------------------------PhysicalOlapScan[customer_address]
+----------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
+------------------------------PhysicalOlapScan[date_dim]
----------------------PhysicalProject
-------------------------filter((web_site.web_company_name = 'pri'))
---------------------------PhysicalOlapScan[web_site]
+------------------------filter((customer_address.ca_state = 'NC'))
+--------------------------PhysicalOlapScan[customer_address]
+------------------PhysicalProject
+--------------------filter((web_site.web_company_name = 'pri'))
+----------------------PhysicalOlapScan[web_site]
diff --git
a/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query16.out
b/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query16.out
index c5ddb58c3b1..a0c674ff8eb 100644
--- a/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF3 cc_call_center_sk->cs_call_center_sk
----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF3 cc_call_center_sk->cs_call_center_sk
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->cs_ship_addr_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->cs_ship_addr_sk
-------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
-----------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+--------------------------PhysicalProject
+----------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF0
cs_order_number->cs_order_number
------------------------------PhysicalProject
---------------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF0
cs_order_number->cs_order_number
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs2)] apply
RFs: RF0
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF1 RF2 RF3
+--------------------------------PhysicalOlapScan[catalog_sales(cs2)] apply
RFs: RF0
------------------------------PhysicalProject
---------------------------------PhysicalOlapScan[catalog_returns(cr1)]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
---------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF1 RF2 RF3
+--------------------------PhysicalProject
+----------------------------PhysicalOlapScan[catalog_returns(cr1)]
------------------------PhysicalProject
---------------------------filter((customer_address.ca_state = 'WV'))
-----------------------------PhysicalOlapScan[customer_address]
+--------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+----------------------------PhysicalOlapScan[date_dim]
--------------------PhysicalProject
-----------------------filter(call_center.cc_county IN ('Barrow County',
'Daviess County', 'Luce County', 'Richland County', 'Ziebach County'))
-------------------------PhysicalOlapScan[call_center]
+----------------------filter((customer_address.ca_state = 'WV'))
+------------------------PhysicalOlapScan[customer_address]
+----------------PhysicalProject
+------------------filter(call_center.cc_county IN ('Barrow County', 'Daviess
County', 'Luce County', 'Richland County', 'Ziebach County'))
+--------------------PhysicalOlapScan[call_center]
diff --git
a/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query94.out
b/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query94.out
index 1abd7ec2887..44f99c94442 100644
--- a/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->ws_ship_addr_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->ws_ship_addr_sk
-------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
-----------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+--------------------------PhysicalProject
+----------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF0
ws_order_number->ws_order_number
------------------------------PhysicalProject
---------------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF0
ws_order_number->ws_order_number
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws2)] apply
RFs: RF0
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
+--------------------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF0
------------------------------PhysicalProject
---------------------------------PhysicalOlapScan[web_returns(wr1)]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
---------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
+--------------------------PhysicalProject
+----------------------------PhysicalOlapScan[web_returns(wr1)]
------------------------PhysicalProject
---------------------------filter((customer_address.ca_state = 'OK'))
-----------------------------PhysicalOlapScan[customer_address]
+--------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
+----------------------------PhysicalOlapScan[date_dim]
--------------------PhysicalProject
-----------------------filter((web_site.web_company_name = 'pri'))
-------------------------PhysicalOlapScan[web_site]
+----------------------filter((customer_address.ca_state = 'OK'))
+------------------------PhysicalOlapScan[customer_address]
+----------------PhysicalProject
+------------------filter((web_site.web_company_name = 'pri'))
+--------------------PhysicalOlapScan[web_site]
diff --git
a/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query95.out
b/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query95.out
index 0476c1e198f..7aef7d8be94 100644
--- a/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf100/no_stats_shape/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
+------------hashAgg[GLOBAL]
+--------------PhysicalProject
+----------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF14 web_site_sk->ws_web_site_sk;RF15 web_site_sk->ws_web_site_sk
------------------PhysicalProject
---------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF14 web_site_sk->ws_web_site_sk;RF15 web_site_sk->ws_web_site_sk
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF12 ca_address_sk->ws_ship_addr_sk;RF13
ca_address_sk->ws_ship_addr_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF12 ca_address_sk->ws_ship_addr_sk;RF13
ca_address_sk->ws_ship_addr_sk
---------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF10 d_date_sk->ws_ship_date_sk;RF11 d_date_sk->ws_ship_date_sk
-------------------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
---------------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply
RFs: RF8 RF9
---------------------------------hashJoin[RIGHT_SEMI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF4 ws_order_number->wr_order_number;RF6
ws_order_number->wr_order_number;RF16 ws_order_number->ws_order_number;RF17
ws_order_number->ws_order_number;RF18 ws_order_number->ws_order_number;RF19
ws_order_number->ws_order_number
-----------------------------------PhysicalProject
-------------------------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF2 wr_order_number->ws_order_number;RF3
wr_order_number->ws_order_number
---------------------------------------PhysicalCteConsumer ( cteId=CTEId#0 )
apply RFs: RF2 RF3
---------------------------------------PhysicalProject
-----------------------------------------PhysicalOlapScan[web_returns] apply
RFs: RF4 RF6
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF10 d_date_sk->ws_ship_date_sk;RF11 d_date_sk->ws_ship_date_sk
+--------------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
+----------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs:
RF8 RF9
+----------------------------hashJoin[RIGHT_SEMI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF4 ws_order_number->wr_order_number;RF6
ws_order_number->wr_order_number;RF16 ws_order_number->ws_order_number;RF17
ws_order_number->ws_order_number;RF18 ws_order_number->ws_order_number;RF19
ws_order_number->ws_order_number
+------------------------------PhysicalProject
+--------------------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF2 wr_order_number->ws_order_number;RF3
wr_order_number->ws_order_number
+----------------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply
RFs: RF2 RF3
----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF10 RF11 RF12 RF13 RF14 RF15
+------------------------------------PhysicalOlapScan[web_returns] apply RFs:
RF4 RF6
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF10 RF11 RF12 RF13 RF14 RF15
--------------------------PhysicalProject
-----------------------------filter((customer_address.ca_state = 'NC'))
-------------------------------PhysicalOlapScan[customer_address]
+----------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
+------------------------------PhysicalOlapScan[date_dim]
----------------------PhysicalProject
-------------------------filter((web_site.web_company_name = 'pri'))
---------------------------PhysicalOlapScan[web_site]
+------------------------filter((customer_address.ca_state = 'NC'))
+--------------------------PhysicalOlapScan[customer_address]
+------------------PhysicalProject
+--------------------filter((web_site.web_company_name = 'pri'))
+----------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf100/rf_prune/query16.out
b/regression-test/data/shape_check/tpcds_sf100/rf_prune/query16.out
index 1c4377348ab..50420bf11bc 100644
--- a/regression-test/data/shape_check/tpcds_sf100/rf_prune/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf100/rf_prune/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF3
cs_order_number->cs_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF3
cs_order_number->cs_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF3
+------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF3
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+--------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
+----------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[catalog_returns(cr1)]
----------------------------PhysicalProject
-------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
---------------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_returns(cr1)]
---------------------------------PhysicalProject
-----------------------------------filter((customer_address.ca_state = 'WV'))
-------------------------------------PhysicalOlapScan[customer_address]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
---------------------------------PhysicalOlapScan[date_dim]
+------------------------------filter((customer_address.ca_state = 'WV'))
+--------------------------------PhysicalOlapScan[customer_address]
------------------------PhysicalProject
---------------------------filter(call_center.cc_county IN ('Barrow County',
'Daviess County', 'Luce County', 'Richland County', 'Ziebach County'))
-----------------------------PhysicalOlapScan[call_center]
+--------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+----------------------------PhysicalOlapScan[date_dim]
+--------------------PhysicalProject
+----------------------filter(call_center.cc_county IN ('Barrow County',
'Daviess County', 'Luce County', 'Richland County', 'Ziebach County'))
+------------------------PhysicalOlapScan[call_center]
diff --git a/regression-test/data/shape_check/tpcds_sf100/rf_prune/query94.out
b/regression-test/data/shape_check/tpcds_sf100/rf_prune/query94.out
index 6be107b8333..e8957a1d790 100644
--- a/regression-test/data/shape_check/tpcds_sf100/rf_prune/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf100/rf_prune/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF3
ws_order_number->ws_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF3
ws_order_number->ws_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF3
+------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF3
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+--------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
+----------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF0 RF1 RF2
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[web_returns(wr1)]
----------------------------PhysicalProject
-------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
---------------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_returns(wr1)]
---------------------------------PhysicalProject
-----------------------------------filter((customer_address.ca_state = 'OK'))
-------------------------------------PhysicalOlapScan[customer_address]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
---------------------------------PhysicalOlapScan[date_dim]
+------------------------------filter((customer_address.ca_state = 'OK'))
+--------------------------------PhysicalOlapScan[customer_address]
------------------------PhysicalProject
---------------------------filter((web_site.web_company_name = 'pri'))
-----------------------------PhysicalOlapScan[web_site]
+--------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
+----------------------------PhysicalOlapScan[date_dim]
+--------------------PhysicalProject
+----------------------filter((web_site.web_company_name = 'pri'))
+------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf100/rf_prune/query95.out
b/regression-test/data/shape_check/tpcds_sf100/rf_prune/query95.out
index 67d5aa669c7..2fd73932d99 100644
--- a/regression-test/data/shape_check/tpcds_sf100/rf_prune/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf100/rf_prune/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5 RF7
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5
RF7
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns] apply RFs: RF6
---------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+----------------------PhysicalOlapScan[web_returns] apply RFs: RF6
+----------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
+------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'NC'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'NC'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf100/shape/query16.out
b/regression-test/data/shape_check/tpcds_sf100/shape/query16.out
index 1c4377348ab..50420bf11bc 100644
--- a/regression-test/data/shape_check/tpcds_sf100/shape/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf100/shape/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF3
cs_order_number->cs_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF3
cs_order_number->cs_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF3
+------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF3
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+--------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
+----------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[catalog_returns(cr1)]
----------------------------PhysicalProject
-------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
---------------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_returns(cr1)]
---------------------------------PhysicalProject
-----------------------------------filter((customer_address.ca_state = 'WV'))
-------------------------------------PhysicalOlapScan[customer_address]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
---------------------------------PhysicalOlapScan[date_dim]
+------------------------------filter((customer_address.ca_state = 'WV'))
+--------------------------------PhysicalOlapScan[customer_address]
------------------------PhysicalProject
---------------------------filter(call_center.cc_county IN ('Barrow County',
'Daviess County', 'Luce County', 'Richland County', 'Ziebach County'))
-----------------------------PhysicalOlapScan[call_center]
+--------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+----------------------------PhysicalOlapScan[date_dim]
+--------------------PhysicalProject
+----------------------filter(call_center.cc_county IN ('Barrow County',
'Daviess County', 'Luce County', 'Richland County', 'Ziebach County'))
+------------------------PhysicalOlapScan[call_center]
diff --git a/regression-test/data/shape_check/tpcds_sf100/shape/query94.out
b/regression-test/data/shape_check/tpcds_sf100/shape/query94.out
index 6be107b8333..e8957a1d790 100644
--- a/regression-test/data/shape_check/tpcds_sf100/shape/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf100/shape/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF3
ws_order_number->ws_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF3
ws_order_number->ws_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF3
+------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF3
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+--------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
+----------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF0 RF1 RF2
+------------------------------PhysicalProject
+--------------------------------PhysicalOlapScan[web_returns(wr1)]
----------------------------PhysicalProject
-------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
---------------------------------hashJoin[LEFT_ANTI_JOIN broadcast]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_returns(wr1)]
---------------------------------PhysicalProject
-----------------------------------filter((customer_address.ca_state = 'OK'))
-------------------------------------PhysicalOlapScan[customer_address]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
---------------------------------PhysicalOlapScan[date_dim]
+------------------------------filter((customer_address.ca_state = 'OK'))
+--------------------------------PhysicalOlapScan[customer_address]
------------------------PhysicalProject
---------------------------filter((web_site.web_company_name = 'pri'))
-----------------------------PhysicalOlapScan[web_site]
+--------------------------filter((date_dim.d_date <= '2000-04-01') and
(date_dim.d_date >= '2000-02-01'))
+----------------------------PhysicalOlapScan[date_dim]
+--------------------PhysicalProject
+----------------------filter((web_site.web_company_name = 'pri'))
+------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf100/shape/query95.out
b/regression-test/data/shape_check/tpcds_sf100/shape/query95.out
index b239bf8a16c..b8dbaed7fcb 100644
--- a/regression-test/data/shape_check/tpcds_sf100/shape/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf100/shape/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF12 ws_order_number->wr_order_number;RF13
ws_order_number->ws_order_number;RF14 ws_order_number->wr_order_number;RF15
ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF12 ws_order_number->wr_order_number;RF13
ws_order_number->ws_order_number;RF14 ws_order_number->wr_order_number;RF15
ws_order_number->ws_order_number
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF10 wr_order_number->ws_order_number;RF11
wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF10 RF11
RF13 RF15
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF10 wr_order_number->ws_order_number;RF11
wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF10
RF11 RF13 RF15
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns] apply RFs: RF12 RF14
---------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF16 ws_order_number->ws_order_number;RF17
ws_order_number->ws_order_number;RF18 ws_order_number->ws_order_number;RF19
ws_order_number->ws_order_number
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+----------------------PhysicalOlapScan[web_returns] apply RFs: RF12 RF14
+----------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF16 ws_order_number->ws_order_number;RF17
ws_order_number->ws_order_number;RF18 ws_order_number->ws_order_number;RF19
ws_order_number->ws_order_number
+------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF6 web_site_sk->ws_web_site_sk;RF7 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF6 web_site_sk->ws_web_site_sk;RF7 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF4 d_date_sk->ws_ship_date_sk;RF5 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF4 d_date_sk->ws_ship_date_sk;RF5 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->ws_ship_addr_sk;RF3
ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->ws_ship_addr_sk;RF3
ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF2 RF3 RF4 RF5 RF6 RF7
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'NC'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF2 RF3 RF4 RF5 RF6 RF7
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'NC'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '1999-04-02') and
(date_dim.d_date >= '1999-02-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git
a/regression-test/data/shape_check/tpcds_sf1000/bs_downgrade_shape/query95.out
b/regression-test/data/shape_check/tpcds_sf1000/bs_downgrade_shape/query95.out
index f0f5bc65c65..96877476635 100644
---
a/regression-test/data/shape_check/tpcds_sf1000/bs_downgrade_shape/query95.out
+++
b/regression-test/data/shape_check/tpcds_sf1000/bs_downgrade_shape/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5 RF7
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5
RF7
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns] apply RFs: RF6
---------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+----------------------PhysicalOlapScan[web_returns] apply RFs: RF6
+----------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
+------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'VA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'VA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf1000/hint/query16.out
b/regression-test/data/shape_check/tpcds_sf1000/hint/query16.out
index 34b03c22237..f5d89240d32 100644
--- a/regression-test/data/shape_check/tpcds_sf1000/hint/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf1000/hint/query16.out
@@ -3,35 +3,33 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF4
cs_order_number->cs_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF4
cs_order_number->cs_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF4
---------------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
build RFs:RF3 cs_order_number->cr_order_number
+------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF4
+----------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
build RFs:RF3 cs_order_number->cr_order_number
+------------------PhysicalProject
+--------------------PhysicalOlapScan[catalog_returns(cr1)] apply RFs: RF3
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
----------------------PhysicalProject
-------------------------PhysicalOlapScan[catalog_returns(cr1)] apply RFs: RF3
-----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'PA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'PA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((call_center.cc_county = 'Williamson
County'))
-------------------------------PhysicalOlapScan[call_center]
+----------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((call_center.cc_county = 'Williamson County'))
+--------------------------PhysicalOlapScan[call_center]
Hint log:
Used: leading(catalog_sales { cs1 customer_address date_dim call_center } )
diff --git a/regression-test/data/shape_check/tpcds_sf1000/hint/query94.out
b/regression-test/data/shape_check/tpcds_sf1000/hint/query94.out
index e9553b57d75..2aa3ca40f33 100644
--- a/regression-test/data/shape_check/tpcds_sf1000/hint/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf1000/hint/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF4
ws_order_number->ws_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF4
ws_order_number->ws_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF4
---------------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
build RFs:RF3 ws_order_number->wr_order_number
+------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF4
+----------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
build RFs:RF3 ws_order_number->wr_order_number
+------------------PhysicalProject
+--------------------PhysicalOlapScan[web_returns(wr1)] apply RFs: RF3
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------PhysicalOlapScan[web_returns(wr1)] apply RFs: RF3
-----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'OK'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF0 RF1 RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2002-06-30') and
(date_dim.d_date >= '2002-05-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'OK'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2002-06-30') and
(date_dim.d_date >= '2002-05-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf1000/hint/query95.out
b/regression-test/data/shape_check/tpcds_sf1000/hint/query95.out
index f0f5bc65c65..96877476635 100644
--- a/regression-test/data/shape_check/tpcds_sf1000/hint/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf1000/hint/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5 RF7
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5
RF7
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns] apply RFs: RF6
---------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+----------------------PhysicalOlapScan[web_returns] apply RFs: RF6
+----------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
+------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'VA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'VA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf1000/shape/query16.out
b/regression-test/data/shape_check/tpcds_sf1000/shape/query16.out
index 62ab186dfac..a40f6ef4508 100644
--- a/regression-test/data/shape_check/tpcds_sf1000/shape/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf1000/shape/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF4
cs_order_number->cs_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF4
cs_order_number->cs_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF4
---------------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
build RFs:RF3 cs_order_number->cr_order_number
+------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF4
+----------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
build RFs:RF3 cs_order_number->cr_order_number
+------------------PhysicalProject
+--------------------PhysicalOlapScan[catalog_returns(cr1)] apply RFs: RF3
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
----------------------PhysicalProject
-------------------------PhysicalOlapScan[catalog_returns(cr1)] apply RFs: RF3
-----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'PA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'PA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((call_center.cc_county = 'Williamson
County'))
-------------------------------PhysicalOlapScan[call_center]
+----------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((call_center.cc_county = 'Williamson County'))
+--------------------------PhysicalOlapScan[call_center]
diff --git a/regression-test/data/shape_check/tpcds_sf1000/shape/query94.out
b/regression-test/data/shape_check/tpcds_sf1000/shape/query94.out
index e9553b57d75..2aa3ca40f33 100644
--- a/regression-test/data/shape_check/tpcds_sf1000/shape/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf1000/shape/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF4
ws_order_number->ws_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF4
ws_order_number->ws_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF4
---------------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
build RFs:RF3 ws_order_number->wr_order_number
+------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF4
+----------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
build RFs:RF3 ws_order_number->wr_order_number
+------------------PhysicalProject
+--------------------PhysicalOlapScan[web_returns(wr1)] apply RFs: RF3
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------PhysicalOlapScan[web_returns(wr1)] apply RFs: RF3
-----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'OK'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF0 RF1 RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2002-06-30') and
(date_dim.d_date >= '2002-05-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'OK'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2002-06-30') and
(date_dim.d_date >= '2002-05-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf1000/shape/query95.out
b/regression-test/data/shape_check/tpcds_sf1000/shape/query95.out
index f0f5bc65c65..96877476635 100644
--- a/regression-test/data/shape_check/tpcds_sf1000/shape/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf1000/shape/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5 RF7
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5
RF7
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns] apply RFs: RF6
---------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+----------------------PhysicalOlapScan[web_returns] apply RFs: RF6
+----------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
+------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'VA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'VA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git
a/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query16.out
b/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query16.out
index 62ab186dfac..a40f6ef4508 100644
--- a/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF4
cs_order_number->cs_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF4
cs_order_number->cs_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF4
---------------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
build RFs:RF3 cs_order_number->cr_order_number
+------------------PhysicalOlapScan[catalog_sales(cs2)] apply RFs: RF4
+----------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
build RFs:RF3 cs_order_number->cr_order_number
+------------------PhysicalProject
+--------------------PhysicalOlapScan[catalog_returns(cr1)] apply RFs: RF3
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
----------------------PhysicalProject
-------------------------PhysicalOlapScan[catalog_returns(cr1)] apply RFs: RF3
-----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF2 cc_call_center_sk->cs_call_center_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->cs_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'PA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF0 RF1 RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'PA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((call_center.cc_county = 'Williamson
County'))
-------------------------------PhysicalOlapScan[call_center]
+----------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((call_center.cc_county = 'Williamson County'))
+--------------------------PhysicalOlapScan[call_center]
diff --git
a/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query94.out
b/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query94.out
index e9553b57d75..2aa3ca40f33 100644
--- a/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF4
ws_order_number->ws_order_number
----------------PhysicalProject
-------------------hashJoin[RIGHT_SEMI_JOIN shuffleBucket]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF4
ws_order_number->ws_order_number
---------------------PhysicalProject
-----------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF4
---------------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
build RFs:RF3 ws_order_number->wr_order_number
+------------------PhysicalOlapScan[web_sales(ws2)] apply RFs: RF4
+----------------hashJoin[RIGHT_ANTI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
build RFs:RF3 ws_order_number->wr_order_number
+------------------PhysicalProject
+--------------------PhysicalOlapScan[web_returns(wr1)] apply RFs: RF3
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------PhysicalOlapScan[web_returns(wr1)] apply RFs: RF3
-----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF0 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF0 RF1 RF2
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'OK'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF0 RF1 RF2
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2002-06-30') and
(date_dim.d_date >= '2002-05-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'OK'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2002-06-30') and
(date_dim.d_date >= '2002-05-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git
a/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query95.out
b/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query95.out
index f0f5bc65c65..96877476635 100644
--- a/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf1000_nopkfk/shape/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[RIGHT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 ws_order_number->wr_order_number;RF7
ws_order_number->ws_order_number
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5 RF7
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF5 wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF5
RF7
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns] apply RFs: RF6
---------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+----------------------PhysicalOlapScan[web_returns] apply RFs: RF6
+----------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF8 ws_order_number->ws_order_number;RF9
ws_order_number->ws_order_number
+------------------PhysicalCteConsumer ( cteId=CTEId#0 )
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF3 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF1 RF2 RF3
-----------------------------------PhysicalProject
-------------------------------------filter((customer_address.ca_state = 'VA'))
---------------------------------------PhysicalOlapScan[customer_address]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF1 RF2 RF3
------------------------------PhysicalProject
---------------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
-----------------------------------PhysicalOlapScan[date_dim]
+--------------------------------filter((customer_address.ca_state = 'VA'))
+----------------------------------PhysicalOlapScan[customer_address]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((date_dim.d_date <= '2001-05-31') and
(date_dim.d_date >= '2001-04-01'))
+------------------------------PhysicalOlapScan[date_dim]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
diff --git a/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query16.out
b/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query16.out
index 1317473b732..996e38668c1 100644
--- a/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query16.out
+++ b/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query16.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
+----------hashAgg[GLOBAL]
+------------PhysicalProject
+--------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF3 cc_call_center_sk->cs_call_center_sk
----------------PhysicalProject
-------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_call_center_sk = call_center.cc_call_center_sk))
otherCondition=() build RFs:RF3 cc_call_center_sk->cs_call_center_sk
+------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->cs_ship_addr_sk
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF2 ca_address_sk->cs_ship_addr_sk
-------------------------PhysicalProject
---------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
-----------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+----------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((cs1.cs_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF1 d_date_sk->cs_ship_date_sk
+------------------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((cs1.cs_order_number = cr1.cr_order_number)) otherCondition=()
+--------------------------PhysicalProject
+----------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF0
cs_order_number->cs_order_number
------------------------------PhysicalProject
---------------------------------hashJoin[RIGHT_SEMI_JOIN shuffle]
hashCondition=((cs1.cs_order_number = cs2.cs_order_number)) otherCondition=((
not (cs1.cs_warehouse_sk = cs2.cs_warehouse_sk))) build RFs:RF0
cs_order_number->cs_order_number
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs2)] apply
RFs: RF0
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF1 RF2 RF3
+--------------------------------PhysicalOlapScan[catalog_sales(cs2)] apply
RFs: RF0
------------------------------PhysicalProject
---------------------------------PhysicalOlapScan[catalog_returns(cr1)]
-----------------------------PhysicalProject
-------------------------------filter((date_dim.d_date <= '1999-05-31') and
(date_dim.d_date >= '1999-04-01'))
---------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[catalog_sales(cs1)] apply
RFs: RF1 RF2 RF3
+--------------------------PhysicalProject
+----------------------------PhysicalOlapScan[catalog_returns(cr1)]
------------------------PhysicalProject
---------------------------filter((customer_address.ca_state = 'IL'))
-----------------------------PhysicalOlapScan[customer_address]
+--------------------------filter((date_dim.d_date <= '1999-05-31') and
(date_dim.d_date >= '1999-04-01'))
+----------------------------PhysicalOlapScan[date_dim]
--------------------PhysicalProject
-----------------------filter(call_center.cc_county IN ('Bronx County',
'Maverick County', 'Mesa County', 'Raleigh County', 'Richland County'))
-------------------------PhysicalOlapScan[call_center]
+----------------------filter((customer_address.ca_state = 'IL'))
+------------------------PhysicalOlapScan[customer_address]
+----------------PhysicalProject
+------------------filter(call_center.cc_county IN ('Bronx County', 'Maverick
County', 'Mesa County', 'Raleigh County', 'Richland County'))
+--------------------PhysicalOlapScan[call_center]
diff --git a/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query94.out
b/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query94.out
index ba778eeca79..32c583ce7c2 100644
--- a/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query94.out
+++ b/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query94.out
@@ -3,33 +3,31 @@
PhysicalResultSink
--PhysicalLimit[GLOBAL]
----PhysicalLimit[LOCAL]
-------hashAgg[DISTINCT_GLOBAL]
+------hashAgg[GLOBAL]
--------PhysicalDistribute[DistributionSpecGather]
-----------hashAgg[DISTINCT_LOCAL]
-------------hashAgg[GLOBAL]
---------------hashAgg[LOCAL]
-----------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+----------hashAgg[GLOBAL]
+------------hashJoin[LEFT_ANTI_JOIN bucketShuffle]
hashCondition=((ws1.ws_order_number = wr1.wr_order_number)) otherCondition=()
+--------------PhysicalProject
+----------------hashJoin[LEFT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF3
ws_order_number->ws_order_number
------------------PhysicalProject
---------------------hashJoin[LEFT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws2.ws_order_number)) otherCondition=((
not (ws1.ws_warehouse_sk = ws2.ws_warehouse_sk))) build RFs:RF3
ws_order_number->ws_order_number
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF2 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF1 ca_address_sk->ws_ship_addr_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF0 d_date_sk->ws_ship_date_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF0 d_date_sk->ws_ship_date_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF0 RF1 RF2 RF3
-----------------------------------PhysicalProject
-------------------------------------filter((date_dim.d_date <= '1999-05-31')
and (date_dim.d_date >= '1999-04-01'))
---------------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF0 RF1 RF2 RF3
------------------------------PhysicalProject
---------------------------------filter((customer_address.ca_state = 'NE'))
-----------------------------------PhysicalOlapScan[customer_address]
+--------------------------------filter((date_dim.d_date <= '1999-05-31') and
(date_dim.d_date >= '1999-04-01'))
+----------------------------------PhysicalOlapScan[date_dim]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
+----------------------------filter((customer_address.ca_state = 'NE'))
+------------------------------PhysicalOlapScan[customer_address]
----------------------PhysicalProject
-------------------------PhysicalOlapScan[web_sales(ws2)]
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
------------------PhysicalProject
---------------------PhysicalOlapScan[web_returns(wr1)]
+--------------------PhysicalOlapScan[web_sales(ws2)]
+--------------PhysicalProject
+----------------PhysicalOlapScan[web_returns(wr1)]
diff --git a/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query95.out
b/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query95.out
index b725fd3e801..0e412839e7c 100644
--- a/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query95.out
+++ b/regression-test/data/shape_check/tpcds_sf10t_orc/shape/query95.out
@@ -11,34 +11,32 @@ PhysicalCteAnchor ( cteId=CTEId#0 )
--PhysicalResultSink
----PhysicalLimit[GLOBAL]
------PhysicalLimit[LOCAL]
---------hashAgg[DISTINCT_GLOBAL]
+--------hashAgg[GLOBAL]
----------PhysicalDistribute[DistributionSpecGather]
-------------hashAgg[DISTINCT_LOCAL]
---------------hashAgg[GLOBAL]
-----------------hashAgg[LOCAL]
-------------------hashJoin[LEFT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 wr_order_number->ws_order_number;RF7
wr_order_number->ws_order_number
---------------------hashJoin[LEFT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF5 ws_order_number->ws_order_number
+------------hashAgg[GLOBAL]
+--------------hashJoin[LEFT_SEMI_JOIN colocated]
hashCondition=((ws1.ws_order_number = web_returns.wr_order_number))
otherCondition=() build RFs:RF6 wr_order_number->ws_order_number;RF7
wr_order_number->ws_order_number
+----------------hashJoin[LEFT_SEMI_JOIN shuffle]
hashCondition=((ws1.ws_order_number = ws_wh.ws_order_number)) otherCondition=()
build RFs:RF5 ws_order_number->ws_order_number
+------------------PhysicalProject
+--------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF4 web_site_sk->ws_web_site_sk
----------------------PhysicalProject
-------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_web_site_sk = web_site.web_site_sk)) otherCondition=()
build RFs:RF4 web_site_sk->ws_web_site_sk
+------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF3 ca_address_sk->ws_ship_addr_sk
--------------------------PhysicalProject
-----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_addr_sk = customer_address.ca_address_sk))
otherCondition=() build RFs:RF3 ca_address_sk->ws_ship_addr_sk
+----------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
------------------------------PhysicalProject
---------------------------------hashJoin[INNER_JOIN broadcast]
hashCondition=((ws1.ws_ship_date_sk = date_dim.d_date_sk)) otherCondition=()
build RFs:RF2 d_date_sk->ws_ship_date_sk
-----------------------------------PhysicalProject
-------------------------------------PhysicalOlapScan[web_sales(ws1)] apply
RFs: RF2 RF3 RF4 RF5 RF6
-----------------------------------PhysicalProject
-------------------------------------filter((date_dim.d_date <= '2002-05-31')
and (date_dim.d_date >= '2002-04-01'))
---------------------------------------PhysicalOlapScan[date_dim]
+--------------------------------PhysicalOlapScan[web_sales(ws1)] apply RFs:
RF2 RF3 RF4 RF5 RF6
------------------------------PhysicalProject
---------------------------------filter((customer_address.ca_state = 'AL'))
-----------------------------------PhysicalOlapScan[customer_address]
+--------------------------------filter((date_dim.d_date <= '2002-05-31') and
(date_dim.d_date >= '2002-04-01'))
+----------------------------------PhysicalOlapScan[date_dim]
--------------------------PhysicalProject
-----------------------------filter((web_site.web_company_name = 'pri'))
-------------------------------PhysicalOlapScan[web_site]
-----------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF7
+----------------------------filter((customer_address.ca_state = 'AL'))
+------------------------------PhysicalOlapScan[customer_address]
+----------------------PhysicalProject
+------------------------filter((web_site.web_company_name = 'pri'))
+--------------------------PhysicalOlapScan[web_site]
+------------------PhysicalCteConsumer ( cteId=CTEId#0 ) apply RFs: RF7
+----------------PhysicalProject
+------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF8 wr_order_number->ws_order_number;RF9
wr_order_number->ws_order_number
+--------------------PhysicalCteConsumer ( cteId=CTEId#0 )
--------------------PhysicalProject
-----------------------hashJoin[INNER_JOIN shuffle]
hashCondition=((web_returns.wr_order_number = ws_wh.ws_order_number))
otherCondition=() build RFs:RF8 wr_order_number->ws_order_number;RF9
wr_order_number->ws_order_number
-------------------------PhysicalCteConsumer ( cteId=CTEId#0 )
-------------------------PhysicalProject
---------------------------PhysicalOlapScan[web_returns]
+----------------------PhysicalOlapScan[web_returns]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
