Default CPU benchmark estimators to max parallelism#8025
Draft
dantegd wants to merge 12 commits intorapidsai:mainfrom
Draft
Default CPU benchmark estimators to max parallelism#8025dantegd wants to merge 12 commits intorapidsai:mainfrom
dantegd wants to merge 12 commits intorapidsai:mainfrom
Conversation
dantegd
added
improvement
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
github-actions
Bot
added
conda
5 tasks
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR updates the cuML benchmark harness so CPU-side estimators use maximum available parallelism by default when the underlying estimator supports it. In practice, sklearn/UMAP-style estimators now default to n_jobs=-1 unless the benchmark config or CLI explicitly provides a different value. This should avoid users or anyone in general to get a false picture of the speed of execution of libraries.
HDBSCAN is handled explicitly through its CPU-specific parallelism parameter, core_dist_n_jobs=-1. Explicit user-provided values are preserved, so benchmarks can still constrain CPU parallelism when needed.
Builds on top of #7980