search

zilliztech / knowhere

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.
Apache License 2.0
156 stars 64 forks source link

todo: merge AVX-512 version of PQFastScan #511

Open alexanderguzhva opened 2 months ago

alexanderguzhva commented 2 months ago

Faiss PR https://github.com/facebookresearch/faiss/pull/3276

AVX-512 implementation for PQFastScan for QBS.
For local benchmarks on 4th gen Xeon, the QPS is up to 10% higher, mostly for a single query case. But as far as I remember, production cases would show higher performance improvements.

It cannot be cherry-picked or copy-pasted, because Faiss baseline uses #ifdef mechanism for deciding whether to use AVX-512, and Knowhere uses dynamic hooks. Some additional code is needed.

github-actions[bot] commented 1 month ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. Rotten issues close after 30d of inactivity. Reopen the issue with /reopen.

alexanderguzhva commented 1 month ago

/reopen

sre-ci-robot commented 1 month ago

@alexanderguzhva: Reopened this issue.

In response to [this](https://github.com/zilliztech/knowhere/issues/511#issuecomment-2132422349): >/reopen > Instructions for interacting with me using PR comments are available [here](https://git.k8s.io/community/contributors/guide/pull-requests.md). If you have questions or suggestions related to my behavior, please file an issue against the [kubernetes/test-infra](https://github.com/kubernetes/test-infra/issues/new?title=Prow%20issue:) repository.
github-actions[bot] commented 3 weeks ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. Rotten issues close after 30d of inactivity. Reopen the issue with /reopen.

alexanderguzhva commented 3 weeks ago

/reopen