NVIDIA / NVIDIA/cuvs

[FEA] Remove PqBits as a template of IVF-PQ code

Open
#1,770 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

Currently IVF-PQ is using PqBits as a template. Switching that to a run-time parameter could reduce compilation time and the total library size.
PR #1278 introduced a version of bitfield_ref_t and bitfield_view_t that doesn't require PqBits as a template so that can be re-used when needed in IVF-PQ.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the IVF-PQ implementation and PR #1278, especially the existing bitfield_ref_t and bitfield_view_t versions that do not require PqBits as a template. The work is done when IVF-PQ uses a run-time parameter instead of PqBits as a template and compilation time and total library size are reduced.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning, performance
Issue type
Refactor
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.