Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Sync supported operators with plugin changes and update default score #1020

Merged
merged 2 commits into from
May 17, 2024

Conversation

nartal1
Copy link
Collaborator

@nartal1 nartal1 commented May 16, 2024

This fixes #1007

Updated the supportedExprs.csv to include ArrayFilter and updated the notes section for json_tuple to be in sync with plugin changes.

  • Ran sync_operator_scores.py to update the scores for all platforms for newly added ArrayFilter operator. Increased the default score to 1.5( from the current 1.0)
  • Verified that filter in array works as intended. Did not add a test for this as it is just checking filter function. We have tests to check the function names.

Spark plan:

== Physical Plan ==
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[], functions=[sum(size(f#4, true))])
   +- Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=15]
      +- HashAggregate(keys=[], functions=[partial_sum(size(f#4, true))])
         +- Project [filter(array(id#0L, (id#0L + 1), (id#0L - 100), (id#0L + 3), (id#0L + 2)), lambdafunction(((lambda f#5L % 3) = 0), lambda f#5L, false)) AS f#4]
            +- Range (0, 1000, step=1, splits=64)

Before:

===================================================================================
|   App Name|             App ID|App Duration|SQL DF Duration|GPU Opportunity|Estimated GPU Duration|Estimated GPU Speedup|Estimated GPU Time Saved|      Recommendation|Unsupported Execs|Unsupported Expressions|Estimated Job Frequency (monthly)|
=====================================================================================================================================================================================================================================================
|Spark shell|local-1715892862056|       31861|           1346|           1010|              31103.44|                 1.02|                  757.55|     Not Recommended|          Project|                 filter|                               30|
=====================================================================================================================================================================================================================================================

After updating the supportedExprs.csv file:

=====================================================================================================================================================================================================================================================
|   App Name|             App ID|App Duration|SQL DF Duration|GPU Opportunity|Estimated GPU Duration|Estimated GPU Speedup|Estimated GPU Time Saved|      Recommendation|Unsupported Execs|Unsupported Expressions|Estimated Job Frequency (monthly)|
=====================================================================================================================================================================================================================================================
|Spark shell|local-1715892862056|       31861|           1346|           1346|               30831.7|                 1.03|                 1029.29|     Not Recommended|                 |                       |                               30|
=====================================================================================================================================================================================================================================================

Signed-off-by: Niranjan Artal <nartal@nvidia.com>
@nartal1 nartal1 added the core_tools Scope the core module (scala) label May 16, 2024
@nartal1 nartal1 self-assigned this May 16, 2024
Copy link
Collaborator

@amahussein amahussein left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @nartal1
just minor comment on extra added file.

core/src/main/resources/operatorsScore123.csv Outdated Show resolved Hide resolved
parthosa
parthosa previously approved these changes May 17, 2024
Copy link
Collaborator

@parthosa parthosa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @nartal1. Same comment as @amahussein.

Signed-off-by: Niranjan Artal <nartal@nvidia.com>
Copy link
Collaborator

@amahussein amahussein left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTME!
Thanks Niranjan!

@nartal1 nartal1 merged commit e9361a5 into NVIDIA:dev May 17, 2024
15 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
core_tools Scope the core module (scala)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[FEA] Sync supported operators with plugin changes
3 participants