Single-partition Dask executor for cuDF-Polars #17262
Merged
Conversation
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
rjzamora
added
5 - DO NOT MERGE
rjzamora
commented
Nov 7, 2024
rjzamora
commented
Nov 7, 2024
rjzamora
added
2 - In Progress
wence-
reviewed
Nov 7, 2024
…to cudf-polars-dask-simple
wence-
reviewed
Nov 11, 2024
rjzamora
changed the title
rjzamora
commented
Nov 21, 2024
wence-
approved these changes
Nov 25, 2024
Comment on lines
+74
to
+78
| # Return reconstructed node and partition-info dict | ||
| partition = PartitionInfo(count=1) | ||
| new_node = ir.reconstruct(children) | ||
| partition_info[new_node] = partition | ||
| return new_node, partition_info |
There was a problem hiding this comment.
nit: No need to address here, but just to note for a followup. This does "unnecessary" reconstruction if the children are unchanged. We could consider making reconstruct return self if the children match.
|
@rjzamora I've addressed Lawrence's comments on the code I've added, for now I left the others up to you but I can work on those too if you prefer. |
Thanks @pentschev! Hopefully I've addressed everything else now. |
jameslamb
approved these changes
Nov 25, 2024
rjzamora
added
5 - Ready to Merge
|
/merge |
3 tasks
rapids-bot bot
pushed a commit
that referenced
this pull request
Dec 3, 2024
Follow-up to #17262 Adds support for parallel `DataFrameScan` operations. Authors: - Richard (Rick) Zamora (https://github.com/rjzamora) Approvers: - Lawrence Mitchell (https://github.com/wence-) URL: #17441
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
The goal here is to lay down the initial foundation for dask-based evaluation of
IRgraphs in cudf-polars. The first pass will only support single-partition workloads. This functionality could be achieved with much less-complicated changes to cudf-polars. However, we do want to build multi-partition support on top of this.Checklist