ANN-benchmarks: avoid using the dataset during search when possible #1657
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
achirkin
added
3 - Ready for Review
improvement
tfeher
approved these changes
Jul 20, 2023
| if (!d_base_set_) { | ||
| base_set(); | ||
| RAFT_CUDA_TRY(cudaMalloc((void**)&d_base_set_, base_set_size_ * dim_ * sizeof(T))); | ||
| RAFT_CUDA_TRY(cudaMalloc((void**)&d_base_set_, base_set_size() * dim() * sizeof(T))); |
There was a problem hiding this comment.
I wonder why we are not using RMM allocator here? (I know it was not changed in this PR, and should be a separate task to fix that).
There was a problem hiding this comment.
I think that was a straight file copy from the separate ann benchmarks project.
There was a problem hiding this comment.
Yep, this has been on the TODO but we rushed this out in 23.04 and haven't gotten back to this.
There was a problem hiding this comment.
Relevant issue here: #1367. Item number 2
|
/merge |
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Outdated suggestions cannot be applied.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.
This PR changes the behavior of ANN benchmark
dataset.hto defer reading the data until it is definitely needed. This allows to avoid copying/reading huge datasets in search benchmarks when the database (index) is already built.