Add clustering_chunk_size to bound assign_iclust memory - #1037
Open
grahamfindlay wants to merge 1 commit into
Open
Add clustering_chunk_size to bound assign_iclust memory#1037grahamfindlay wants to merge 1 commit into
grahamfindlay wants to merge 1 commit into
Conversation
The graph-clustering step builds a dense (n_spikes x n_clusters) assignment matrix. For very long recordings (tens of millions of spikes per clustering center) this can exhaust GPU memory. Added an optional `clustering_chunk_size` setting that computes the assignment in row chunks, bounding peak memory to roughly one (chunk x n_clusters) tile. No row is split across a chunk boundary and each spike's argmax depends only on its own neighbors, so the result is identical to the unchunked path.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The graph-clustering step builds a dense (n_spikes x n_clusters) assignment matrix. For very long recordings (tens of millions of spikes per clustering center) this can exhaust GPU memory.
Added an optional
clustering_chunk_sizesetting that computes the assignment in row chunks, bounding peak memory to roughly one (chunk x n_clusters) tile. No row is split across a chunk boundary and each spike's argmax depends only on its own neighbors, so the result is identical to the unchunked path.