Mark RunningWindowFunction as supported in Qual tool (#1465)

Signed-off-by: Ahmed Hussein (amahussein) <[email protected]> Fix #1460 `RunningWindowFunction` should be marked as supported by the qualification tool.
NVIDIA · Dec 16, 2024 · 9564d0b · 9564d0b
1 parent a1f866f
commit 9564d0b
Show file tree

Hide file tree

Showing 15 changed files with 17 additions and 3 deletions.
diff --git a/core/src/main/resources/operatorsScore-databricks-aws-a10G.csv b/core/src/main/resources/operatorsScore-databricks-aws-a10G.csv
@@ -305,3 +305,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-databricks-aws-t4.csv b/core/src/main/resources/operatorsScore-databricks-aws-t4.csv
@@ -305,3 +305,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-databricks-azure-t4.csv b/core/src/main/resources/operatorsScore-databricks-azure-t4.csv
@@ -293,3 +293,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-dataproc-gke-l4.csv b/core/src/main/resources/operatorsScore-dataproc-gke-l4.csv
@@ -287,3 +287,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-dataproc-gke-t4.csv b/core/src/main/resources/operatorsScore-dataproc-gke-t4.csv
@@ -287,3 +287,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-dataproc-l4.csv b/core/src/main/resources/operatorsScore-dataproc-l4.csv
@@ -293,3 +293,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-dataproc-serverless-l4.csv b/core/src/main/resources/operatorsScore-dataproc-serverless-l4.csv
@@ -287,3 +287,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-dataproc-t4.csv b/core/src/main/resources/operatorsScore-dataproc-t4.csv
@@ -293,3 +293,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-emr-a10.csv b/core/src/main/resources/operatorsScore-emr-a10.csv
@@ -293,3 +293,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-emr-a10G.csv b/core/src/main/resources/operatorsScore-emr-a10G.csv
@@ -293,3 +293,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-emr-t4.csv b/core/src/main/resources/operatorsScore-emr-t4.csv
@@ -293,3 +293,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/operatorsScore-onprem-a100.csv b/core/src/main/resources/operatorsScore-onprem-a100.csv
@@ -305,3 +305,4 @@ DecimalSum,1.5
 MaxBy,1.5
 MinBy,1.5
 ArrayJoin,1.5
+RunningWindowFunctionExec,1.5
diff --git a/core/src/main/resources/supportedExecs.csv b/core/src/main/resources/supportedExecs.csv
@@ -57,3 +57,4 @@ WriteFilesExec,S,None,Input/Output,S,S,S,S,S,S,S,S,PS,S,S,S,S,S,PS,PS,PS,S,S,S
 CustomShuffleReaderExec,S,None,Input/Output,S,S,S,S,S,S,S,S,PS,S,S,S,S,NS,PS,PS,PS,NS,NS,NS
 WindowGroupLimitExec,S,None,Input/Output,S,S,S,S,S,S,S,S,PS,S,S,S,NS,NS,PS,PS,PS,NS,NS,NS
 MapInArrowExec,S,None,Input/Output,S,S,S,S,S,S,S,S,PS,S,NS,NS,NS,NS,PS,NS,PS,NS,NS,NS
+RunningWindowFunctionExec,S,None,Input/Output,S,S,S,S,S,S,S,S,PS,S,S,S,NS,NS,PS,PS,PS,NS,NS,NS
diff --git a/core/src/main/scala/com/nvidia/spark/rapids/tool/planparser/GenericExecParser.scala b/core/src/main/scala/com/nvidia/spark/rapids/tool/planparser/GenericExecParser.scala
@@ -91,7 +91,8 @@ class GenericExecParser(
     ExecInfo(
       node,
       sqlID,
-      node.name,
+      // Remove trailing spaces from node name if any
+      node.name.trim,
       "",
       speedupFactor,
       duration,

diff --git a/core/src/main/scala/com/nvidia/spark/rapids/tool/planparser/SQLPlanParser.scala b/core/src/main/scala/com/nvidia/spark/rapids/tool/planparser/SQLPlanParser.scala
@@ -483,8 +483,8 @@ object SQLPlanParser extends Logging {
       case "AggregateInPandas" | "ArrowEvalPython" | "AQEShuffleRead" | "CartesianProduct"
            | "Coalesce" | "CollectLimit" | "CustomShuffleReader" | "FlatMapGroupsInPandas"
            | "GlobalLimit" | "LocalLimit" | "InMemoryTableScan" | "MapInPandas"
-           | "PythonMapInArrow" | "MapInArrow" | "Range" | "Sample" | "Union"
-           | "WindowInPandas" =>
+           | "PythonMapInArrow" | "MapInArrow" | "Range" | "RunningWindowFunction"
+           | "Sample" | "Union" | "WindowInPandas" =>
         GenericExecParser(node, checker, sqlID, app = Some(app)).parse
       case "BatchScan" =>
         BatchScanExecParser(node, checker, sqlID, app).parse