Support MinBy and MaxBy for non-float ordering (#11371)

* Support minBy on GPU Signed-off-by: Firestarman <[email protected]> * Support minBy on GPU Signed-off-by: Firestarman <[email protected]> * max_by wip Signed-off-by: Haoyang Li <[email protected]> * wip Signed-off-by: Haoyang Li <[email protected]> * test wip Signed-off-by: Haoyang Li <[email protected]> * wip test Signed-off-by: Haoyang Li <[email protected]> * reverse order and value Signed-off-by: Haoyang Li <[email protected]> * use min instead of min_by Signed-off-by: Haoyang Li <[email protected]> * verify again Signed-off-by: Haoyang Li <[email protected]> * regenerate shim docs Signed-off-by: Haoyang Li <[email protected]> * refine reduction and limit float type Signed-off-by: Haoyang Li <[email protected]> * 400 doc Signed-off-by: Haoyang Li <[email protected]> * update tests Signed-off-by: Haoyang Li <[email protected]> * verify and address comments Signed-off-by: Haoyang Li <[email protected]> * fix IT on spark320 and combine tests Signed-off-by: Haoyang Li <[email protected]> * remove 311 docs Signed-off-by: Haoyang Li <[email protected]> * comment address Signed-off-by: Haoyang Li <[email protected]> --------- Signed-off-by: Firestarman <[email protected]> Signed-off-by: Haoyang Li <[email protected]> Co-authored-by: Firestarman <[email protected]>
NVIDIA · Aug 29, 2024 · dbd92d2 · dbd92d2
1 parent 61f0cca
commit dbd92d2
Show file tree

Hide file tree

Showing 48 changed files with 925 additions and 84 deletions.
diff --git a/docs/additional-functionality/advanced_configs.md b/docs/additional-functionality/advanced_configs.md
@@ -403,7 +403,9 @@ Name | SQL Function(s) | Description | Default Value | Notes
 <a name="sql.expression.First"></a>spark.rapids.sql.expression.First|`first_value`, `first`|first aggregate operator|true|None|
 <a name="sql.expression.Last"></a>spark.rapids.sql.expression.Last|`last_value`, `last`|last aggregate operator|true|None|
 <a name="sql.expression.Max"></a>spark.rapids.sql.expression.Max|`max`|Max aggregate operator|true|None|
+<a name="sql.expression.MaxBy"></a>spark.rapids.sql.expression.MaxBy|`max_by`|MaxBy aggregate operator. It may produce different results than CPU when multiple rows in a group have same minimum value in the ordering column and different associated values in the value column.|true|None|
 <a name="sql.expression.Min"></a>spark.rapids.sql.expression.Min|`min`|Min aggregate operator|true|None|
+<a name="sql.expression.MinBy"></a>spark.rapids.sql.expression.MinBy|`min_by`|MinBy aggregate operator. It may produce different results than CPU when multiple rows in a group have same minimum value in the ordering column and different associated values in the value column.|true|None|
 <a name="sql.expression.Percentile"></a>spark.rapids.sql.expression.Percentile|`percentile`|Aggregation computing exact percentile|true|None|
 <a name="sql.expression.PivotFirst"></a>spark.rapids.sql.expression.PivotFirst| |PivotFirst operator|true|None|
 <a name="sql.expression.StddevPop"></a>spark.rapids.sql.expression.StddevPop|`stddev_pop`|Aggregation computing population standard deviation|true|None|