2 Commits (ef7e945b4dfaa2fc5caecd923f924eeeb62471a7)

Author	SHA1	Message	Date
Matthijs Douze	291353c5a9	Generalize DistanceComputer for flat indexes (#2255) ... Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/2255 The `DistanceComputer` object is derived from an Index (obtained with `get_distance_computer()`). It maintains a current query and quickly computes distances from that query to any item in the database. This is useful, eg. for the IndexHNSW and IndexNSG that rely on query-to-point comparisons in the datasets. This diff introduces the `FlatCodesDistanceComputer`, that inherits from `DistanceComputer` for Flat indexes. In addition to the distance-to-item function, it adds a `distance_to_code` that computes the distance from any code to the current query, even if it is not stored in the index. This is implemented for all FlatCode indexes (IndexFlat, IndexPQ, IndexScalarQuantizer and IndexAdditiveQuantizer). In the process, the two classes were extracted to their own header file `impl/DistanceComputer.h` Reviewed By: beauby Differential Revision: D34863609 fbshipit-source-id: 39d8c66475e55c3223c4a6a210827aa48bca292d	2022-03-20 23:43:33 -07:00
Matthijs Douze	c5975cda72	PQ4 fast scan benchmarks (#1555) ... Summary: Code + scripts for Faiss benchmarks around the Fast scan codes. Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1555 Test Plan: buck test //faiss/tests/:test_refine Reviewed By: wickedfoo Differential Revision: D25546505 Pulled By: mdouze fbshipit-source-id: 902486b7f47e36221a2671d124df8c114f25db58	2020-12-16 01:18:58 -08:00