Reduce device memory usage for CAGRA's graph optimization process (reverse graph creation) #832
Conversation
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
anaruse
changed the title
cjnolet
added
improvement
|
/ok to test bfc45cd |
|
/ok to test b0f648b |
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Outdated suggestions cannot be applied.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.
Since CAGRA improves search accuracy by merging forward and reverse graphs, reverse graph is created as part of the graph optimization process. Currently, GPU is used to create the reverse graph at high speed, but when creating a graph for huge dataset, the amount of device memory may be insufficient to create the graph.
In this PR, as a countermeasure for the lack of device memory, we will add an implementation in which reverse graphs are created on the CPU.