perf: fully building HNSW partitions in parallel #2117
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
before this, the previous partition building blocks the following ones if it hasn't been consumed from the stream Signed-off-by: BubbleCal <bubble-cal@outlook.com>
Signed-off-by: BubbleCal <bubble-cal@outlook.com>
eddyxu
approved these changes
Mar 28, 2024
eddyxu
reviewed
Mar 28, 2024
| @@ -293,6 +294,7 @@ pub(super) async fn write_hnsw_index_partitions( | |||
| let mut aux_part_files = Vec::with_capacity(ivf.num_partitions()); | |||
| let tmp_part_dir = Path::from_filesystem_path(TempDir::new()?)?; | |||
| let mut tasks = Vec::with_capacity(ivf.num_partitions()); | |||
| let sem = Arc::new(Semaphore::new(HNSW_PARTITIONS_BUILD_PARRALLEL)); | |||
There was a problem hiding this comment.
Maybe pass this as HnswBuildParameter?
There was a problem hiding this comment.
that's an idea! this actually depends on how large the dataset is
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Outdated suggestions cannot be applied.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.
improves 25% on 8.5M rows dataset (19 minutes)