forked from NVIDIA/spark-rapids
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Optimize unnecessary columnar->row->columnar transitions with AQE (NV…
…IDIA#2064) * Avoid transitions when writing columnar output from adaptive plan Signed-off-by: Andy Grove <andygrove@nvidia.com> * Implement unit test and code cleanup Signed-off-by: Andy Grove <andygrove@nvidia.com> * Remove debug println Signed-off-by: Andy Grove <andygrove@nvidia.com> * Move logic to GpuOverrides Signed-off-by: Andy Grove <andygrove@nvidia.com> * Add comments Signed-off-by: Andy Grove <andygrove@nvidia.com> * Update docs Signed-off-by: Andy Grove <andygrove@nvidia.com> * Update comment Signed-off-by: Andy Grove <andygrove@nvidia.com> * Move AvoidAdaptiveTransitionToRow logic to generic rule in GpuTransitionOverrides Signed-off-by: Andy Grove <andygrove@nvidia.com> * Add unit test for collect case Signed-off-by: Andy Grove <andygrove@nvidia.com> * Code simplification Signed-off-by: Andy Grove <andygrove@nvidia.com> * Use ExecutionPlanCaptureCallback instead of custom listener Signed-off-by: Andy Grove <andygrove@nvidia.com>
- Loading branch information
Showing
2 changed files
with
162 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters