Skip to content

Update score calculation for CAGRA-Q instance selection #938

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 27, 2025
Merged

Update score calculation for CAGRA-Q instance selection #938

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6e39ca7
Update score calculation for CAGRA-Q instance selection
enp1s0 May 27, 2025
33d4555
Merge branch 'branch-25.06' into cagra-q-auto-team-size
enp1s0 May 27, 2025
9e262da
Merge branch 'branch-25.06' into cagra-q-auto-team-size
enp1s0 May 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion cpp/src/neighbors/detail/cagra/compute_distance_vpq.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,11 @@ struct vpq_descriptor_spec : public instance_spec<DataT, IndexT, DistanceT> {
if (dataset.pq_bits() != PqBits) { return -1.0; }
if (dataset.pq_len() != PqLen) { return -1.0; }
// Otherwise, favor the closest dataset dimensionality.
return 1.0 / (0.1 + std::abs(double(dataset.dim()) - double(DatasetBlockDim)));
constexpr std::uint32_t preferred_load_elmes_per_thread =
16; /*magic number that is good based on experiments.*/
return 1.0 / (0.1 + std::abs(double(dataset.dim()) - double(DatasetBlockDim))) * TeamSize +
1.0 / (0.1 + std::abs(double(dataset.dim()) / TeamSize / PqLen -
preferred_load_elmes_per_thread));
}

private:
Expand Down