update expected plans for Spark 4.0

apache · Jan 19, 2025 · 9ddf582 · 9ddf582
1 parent 9d84407
commit 9ddf582
Show file tree

Hide file tree

Showing 2 changed files with 104 additions and 104 deletions.
diff --git a/spark/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark4_0/q9/explain.txt b/spark/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark4_0/q9/explain.txt
@@ -1,6 +1,6 @@
 == Physical Plan ==
-* CometColumnarToRow (4)
-+- CometProject (3)
+* Project (4)
++- * CometColumnarToRow (3)
    +- CometFilter (2)
       +- CometScan parquet spark_catalog.default.reason (1)
 
@@ -16,16 +16,16 @@ ReadSchema: struct<r_reason_sk:int>
 Input [1]: [r_reason_sk#1]
 Condition : (isnotnull(r_reason_sk#1) AND (r_reason_sk#1 = 1))
 
-(3) CometProject
+(3) CometColumnarToRow [codegen id : 1]
 Input [1]: [r_reason_sk#1]
-Arguments: [bucket1#2, bucket2#3, bucket3#4, bucket4#5, bucket5#6], [CASE WHEN (Subquery scalar-subquery#7, [id=#8].count(1) > 62316685) THEN ReusedSubquery Subquery scalar-subquery#7, [id=#8].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#7, [id=#8].avg(ss_net_paid) END AS bucket1#2, CASE WHEN (Subquery scalar-subquery#9, [id=#10].count(1) > 19045798) THEN ReusedSubquery Subquery scalar-subquery#9, [id=#10].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#9, [id=#10].avg(ss_net_paid) END AS bucket2#3, CASE WHEN (Subquery scalar-subquery#11, [id=#12].count(1) > 365541424) THEN ReusedSubquery Subquery scalar-subquery#11, [id=#12].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#11, [id=#12].avg(ss_net_paid) END AS bucket3#4, CASE WHEN (Subquery scalar-subquery#13, [id=#14].count(1) > 216357808) THEN ReusedSubquery Subquery scalar-subquery#13, [id=#14].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#13, [id=#14].avg(ss_net_paid) END AS bucket4#5, CASE WHEN (Subquery scalar-subquery#15, [id=#16].count(1) > 184483884) THEN ReusedSubquery Subquery scalar-subquery#15, [id=#16].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#15, [id=#16].avg(ss_net_paid) END AS bucket5#6]
 
-(4) CometColumnarToRow [codegen id : 1]
-Input [5]: [bucket1#2, bucket2#3, bucket3#4, bucket4#5, bucket5#6]
+(4) Project [codegen id : 1]
+Output [5]: [CASE WHEN (Subquery scalar-subquery#2, [id=#3].count(1) > 62316685) THEN ReusedSubquery Subquery scalar-subquery#2, [id=#3].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#2, [id=#3].avg(ss_net_paid) END AS bucket1#4, CASE WHEN (Subquery scalar-subquery#5, [id=#6].count(1) > 19045798) THEN ReusedSubquery Subquery scalar-subquery#5, [id=#6].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#5, [id=#6].avg(ss_net_paid) END AS bucket2#7, CASE WHEN (Subquery scalar-subquery#8, [id=#9].count(1) > 365541424) THEN ReusedSubquery Subquery scalar-subquery#8, [id=#9].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#8, [id=#9].avg(ss_net_paid) END AS bucket3#10, CASE WHEN (Subquery scalar-subquery#11, [id=#12].count(1) > 216357808) THEN ReusedSubquery Subquery scalar-subquery#11, [id=#12].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#11, [id=#12].avg(ss_net_paid) END AS bucket4#13, CASE WHEN (Subquery scalar-subquery#14, [id=#15].count(1) > 184483884) THEN ReusedSubquery Subquery scalar-subquery#14, [id=#15].avg(ss_ext_discount_amt) ELSE ReusedSubquery Subquery scalar-subquery#14, [id=#15].avg(ss_net_paid) END AS bucket5#16]
+Input [1]: [r_reason_sk#1]
 
 ===== Subqueries =====
 
-Subquery:1 Hosting operator id = 3 Hosting Expression = Subquery scalar-subquery#7, [id=#8]
+Subquery:1 Hosting operator id = 4 Hosting Expression = Subquery scalar-subquery#2, [id=#3]
 * Project (13)
 +- * HashAggregate (12)
    +- * CometColumnarToRow (11)
@@ -80,11 +80,11 @@ Results [3]: [count(1)#31 AS count(1)#34, cast((avg(UnscaledValue(ss_ext_discoun
 Output [1]: [named_struct(count(1), count(1)#34, avg(ss_ext_discount_amt), avg(ss_ext_discount_amt)#35, avg(ss_net_paid), avg(ss_net_paid)#36) AS mergedValue#37]
 Input [3]: [count(1)#34, avg(ss_ext_discount_amt)#35, avg(ss_net_paid)#36]
 
-Subquery:2 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#7, [id=#8]
+Subquery:2 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#2, [id=#3]
 
-Subquery:3 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#7, [id=#8]
+Subquery:3 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#2, [id=#3]
 
-Subquery:4 Hosting operator id = 3 Hosting Expression = Subquery scalar-subquery#9, [id=#10]
+Subquery:4 Hosting operator id = 4 Hosting Expression = Subquery scalar-subquery#5, [id=#6]
 * Project (22)
 +- * HashAggregate (21)
    +- * CometColumnarToRow (20)
@@ -139,11 +139,11 @@ Results [3]: [count(1)#52 AS count(1)#55, cast((avg(UnscaledValue(ss_ext_discoun
 Output [1]: [named_struct(count(1), count(1)#55, avg(ss_ext_discount_amt), avg(ss_ext_discount_amt)#56, avg(ss_net_paid), avg(ss_net_paid)#57) AS mergedValue#58]
 Input [3]: [count(1)#55, avg(ss_ext_discount_amt)#56, avg(ss_net_paid)#57]
 
-Subquery:5 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#9, [id=#10]
+Subquery:5 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#5, [id=#6]
 
-Subquery:6 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#9, [id=#10]
+Subquery:6 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#5, [id=#6]
 
-Subquery:7 Hosting operator id = 3 Hosting Expression = Subquery scalar-subquery#11, [id=#12]
+Subquery:7 Hosting operator id = 4 Hosting Expression = Subquery scalar-subquery#8, [id=#9]
 * Project (31)
 +- * HashAggregate (30)
    +- * CometColumnarToRow (29)
@@ -198,11 +198,11 @@ Results [3]: [count(1)#73 AS count(1)#76, cast((avg(UnscaledValue(ss_ext_discoun
 Output [1]: [named_struct(count(1), count(1)#76, avg(ss_ext_discount_amt), avg(ss_ext_discount_amt)#77, avg(ss_net_paid), avg(ss_net_paid)#78) AS mergedValue#79]
 Input [3]: [count(1)#76, avg(ss_ext_discount_amt)#77, avg(ss_net_paid)#78]
 
-Subquery:8 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#11, [id=#12]
+Subquery:8 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#8, [id=#9]
 
-Subquery:9 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#11, [id=#12]
+Subquery:9 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#8, [id=#9]
 
-Subquery:10 Hosting operator id = 3 Hosting Expression = Subquery scalar-subquery#13, [id=#14]
+Subquery:10 Hosting operator id = 4 Hosting Expression = Subquery scalar-subquery#11, [id=#12]
 * Project (40)
 +- * HashAggregate (39)
    +- * CometColumnarToRow (38)
@@ -257,11 +257,11 @@ Results [3]: [count(1)#94 AS count(1)#97, cast((avg(UnscaledValue(ss_ext_discoun
 Output [1]: [named_struct(count(1), count(1)#97, avg(ss_ext_discount_amt), avg(ss_ext_discount_amt)#98, avg(ss_net_paid), avg(ss_net_paid)#99) AS mergedValue#100]
 Input [3]: [count(1)#97, avg(ss_ext_discount_amt)#98, avg(ss_net_paid)#99]
 
-Subquery:11 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#13, [id=#14]
+Subquery:11 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#11, [id=#12]
 
-Subquery:12 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#13, [id=#14]
+Subquery:12 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#11, [id=#12]
 
-Subquery:13 Hosting operator id = 3 Hosting Expression = Subquery scalar-subquery#15, [id=#16]
+Subquery:13 Hosting operator id = 4 Hosting Expression = Subquery scalar-subquery#14, [id=#15]
 * Project (49)
 +- * HashAggregate (48)
    +- * CometColumnarToRow (47)
@@ -316,8 +316,8 @@ Results [3]: [count(1)#115 AS count(1)#118, cast((avg(UnscaledValue(ss_ext_disco
 Output [1]: [named_struct(count(1), count(1)#118, avg(ss_ext_discount_amt), avg(ss_ext_discount_amt)#119, avg(ss_net_paid), avg(ss_net_paid)#120) AS mergedValue#121]
 Input [3]: [count(1)#118, avg(ss_ext_discount_amt)#119, avg(ss_net_paid)#120]
 
-Subquery:14 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#15, [id=#16]
+Subquery:14 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#14, [id=#15]
 
-Subquery:15 Hosting operator id = 3 Hosting Expression = ReusedSubquery Subquery scalar-subquery#15, [id=#16]
+Subquery:15 Hosting operator id = 4 Hosting Expression = ReusedSubquery Subquery scalar-subquery#14, [id=#15]
 
 
diff --git a/spark/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark4_0/q9/simplified.txt b/spark/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark4_0/q9/simplified.txt
@@ -1,86 +1,86 @@
 WholeStageCodegen (1)
-  CometColumnarToRow
-    InputAdapter
-      CometProject [bucket1,bucket2,bucket3,bucket4,bucket5]
-        Subquery #1
-          WholeStageCodegen (2)
-            Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
-              HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
-                CometColumnarToRow
-                  InputAdapter
-                    CometColumnarExchange #1
-                      WholeStageCodegen (1)
-                        HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
-                          CometColumnarToRow
-                            InputAdapter
-                              CometProject [ss_ext_discount_amt,ss_net_paid]
-                                CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-                                  CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-        ReusedSubquery [mergedValue] #1
-        ReusedSubquery [mergedValue] #1
-        Subquery #2
-          WholeStageCodegen (2)
-            Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
-              HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
-                CometColumnarToRow
-                  InputAdapter
-                    CometColumnarExchange #2
-                      WholeStageCodegen (1)
-                        HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
-                          CometColumnarToRow
-                            InputAdapter
-                              CometProject [ss_ext_discount_amt,ss_net_paid]
-                                CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-                                  CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-        ReusedSubquery [mergedValue] #2
-        ReusedSubquery [mergedValue] #2
-        Subquery #3
-          WholeStageCodegen (2)
-            Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
-              HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
-                CometColumnarToRow
-                  InputAdapter
-                    CometColumnarExchange #3
-                      WholeStageCodegen (1)
-                        HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
-                          CometColumnarToRow
-                            InputAdapter
-                              CometProject [ss_ext_discount_amt,ss_net_paid]
-                                CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-                                  CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-        ReusedSubquery [mergedValue] #3
-        ReusedSubquery [mergedValue] #3
-        Subquery #4
-          WholeStageCodegen (2)
-            Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
-              HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
-                CometColumnarToRow
-                  InputAdapter
-                    CometColumnarExchange #4
-                      WholeStageCodegen (1)
-                        HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
-                          CometColumnarToRow
-                            InputAdapter
-                              CometProject [ss_ext_discount_amt,ss_net_paid]
-                                CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-                                  CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-        ReusedSubquery [mergedValue] #4
-        ReusedSubquery [mergedValue] #4
-        Subquery #5
-          WholeStageCodegen (2)
-            Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
-              HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
-                CometColumnarToRow
-                  InputAdapter
-                    CometColumnarExchange #5
-                      WholeStageCodegen (1)
-                        HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
-                          CometColumnarToRow
-                            InputAdapter
-                              CometProject [ss_ext_discount_amt,ss_net_paid]
-                                CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-                                  CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
-        ReusedSubquery [mergedValue] #5
-        ReusedSubquery [mergedValue] #5
+  Project
+    Subquery #1
+      WholeStageCodegen (2)
+        Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
+          HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
+            CometColumnarToRow
+              InputAdapter
+                CometColumnarExchange #1
+                  WholeStageCodegen (1)
+                    HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
+                      CometColumnarToRow
+                        InputAdapter
+                          CometProject [ss_ext_discount_amt,ss_net_paid]
+                            CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+                              CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+    ReusedSubquery [mergedValue] #1
+    ReusedSubquery [mergedValue] #1
+    Subquery #2
+      WholeStageCodegen (2)
+        Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
+          HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
+            CometColumnarToRow
+              InputAdapter
+                CometColumnarExchange #2
+                  WholeStageCodegen (1)
+                    HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
+                      CometColumnarToRow
+                        InputAdapter
+                          CometProject [ss_ext_discount_amt,ss_net_paid]
+                            CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+                              CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+    ReusedSubquery [mergedValue] #2
+    ReusedSubquery [mergedValue] #2
+    Subquery #3
+      WholeStageCodegen (2)
+        Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
+          HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
+            CometColumnarToRow
+              InputAdapter
+                CometColumnarExchange #3
+                  WholeStageCodegen (1)
+                    HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
+                      CometColumnarToRow
+                        InputAdapter
+                          CometProject [ss_ext_discount_amt,ss_net_paid]
+                            CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+                              CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+    ReusedSubquery [mergedValue] #3
+    ReusedSubquery [mergedValue] #3
+    Subquery #4
+      WholeStageCodegen (2)
+        Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
+          HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
+            CometColumnarToRow
+              InputAdapter
+                CometColumnarExchange #4
+                  WholeStageCodegen (1)
+                    HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
+                      CometColumnarToRow
+                        InputAdapter
+                          CometProject [ss_ext_discount_amt,ss_net_paid]
+                            CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+                              CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+    ReusedSubquery [mergedValue] #4
+    ReusedSubquery [mergedValue] #4
+    Subquery #5
+      WholeStageCodegen (2)
+        Project [count(1),avg(ss_ext_discount_amt),avg(ss_net_paid)]
+          HashAggregate [count,sum,count,sum,count] [count(1),avg(UnscaledValue(ss_ext_discount_amt)),avg(UnscaledValue(ss_net_paid)),count(1),avg(ss_ext_discount_amt),avg(ss_net_paid),count,sum,count,sum,count]
+            CometColumnarToRow
+              InputAdapter
+                CometColumnarExchange #5
+                  WholeStageCodegen (1)
+                    HashAggregate [ss_ext_discount_amt,ss_net_paid] [count,sum,count,sum,count,count,sum,count,sum,count]
+                      CometColumnarToRow
+                        InputAdapter
+                          CometProject [ss_ext_discount_amt,ss_net_paid]
+                            CometFilter [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+                              CometScan parquet spark_catalog.default.store_sales [ss_quantity,ss_ext_discount_amt,ss_net_paid,ss_sold_date_sk]
+    ReusedSubquery [mergedValue] #5
+    ReusedSubquery [mergedValue] #5
+    CometColumnarToRow
+      InputAdapter
         CometFilter [r_reason_sk]
           CometScan parquet spark_catalog.default.reason [r_reason_sk]