mirror of
https://github.com/facebookresearch/faiss.git
synced 2026-10-12 02:13:36 +00:00
Tom Jackson
a3a7627009
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/4735 `VisitedTable` accounts for a huge portion of `HNSW::search()` for unbatched searches of large indices. As demonstrated in the benchmarks shown below, the vector-based implementation is much faster for smaller `ntotal` values, but at ~2M and above, it becomes slower, often significantly so. E.g.: At 64M slots, without batching, a workload of 1000 `set()`/`get()`s is >100x slower. Even with batching, this workload is still 3x slower with vectors. This is a very likely explanation for the poor performance of HNSW in a 2023 USearch blog post (https://www.unum.cloud/blog/2023-11-07-scaling-vector-search-with-intel), which shows the same high throughput below 1M docs, and the same O(n) slowdown as the size grows beyond >2M: Reviewed By: mnorris11, mdouze Differential Revision: D89515309 fbshipit-source-id: 08bc4a54faa311eeb9946f2a43482ae52b61566e