Commit Graph

3 Commits (b32abc95c21de4b737e219b51223b8c44922988d)

Author SHA1 Message Date
Matthijs Douze c0052c1533 IndexFlatCodes: a single parent for all flat codecs (#2132)
Summary:
Pull Request resolved: https://github.com/facebookresearch/faiss/pull/2132

This diff adds the class IndexFlatCodes that becomes the parent of all "flat" encodings.
IndexPQ
IndexFlat
IndexAdditiveQuantizer
IndexScalarQuantizer
IndexLSH
Index2Layer

The other changes are:
- for IndexFlat, there is no vector<float> with the data anymore. It is replaced with a `get_xb()` function. This broke quite a few external codes, that this diff also attempts to fix.
- I/O functions needed to be adapted. This is done without changing the I/O format for any index.
- added a small contrib function to get the data from the IndexFlat
- the functionality has been made uniform, for example remove_ids and add are now in the parent class.

Eventually, we may support generic storage for flat indexes, similar to `InvertedLists`, eg to memmap the data, but this will again require a big change.

Reviewed By: wickedfoo

Differential Revision: D32646769

fbshipit-source-id: 04a1659173fd51b130ae45d345176b72183cae40
2021-12-07 01:31:07 -08:00
Matthijs Douze 760cce7f3a Support for additive quantizer search (#1961)
Summary:
Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1961

This diff implements LUT-based search for additive quantizers.
It also further merges code for LSQ and the RedisualQuantizer.

The documentation + evaluation is on github:

https://github.com/facebookresearch/faiss/wiki/Additive-quantizers

Reviewed By: wickedfoo

Differential Revision: D29395079

fbshipit-source-id: b8a24a647bbdc4cda2a699e791ffdb2a12bfa9c6
2021-08-20 01:00:10 -07:00
Matthijs Douze 6d0bc58db6 Implementation of PQ4 search with SIMD instructions (#1542)
Summary:
IndexPQ and IndexIVFPQ implementations with AVX shuffle instructions.

The training and computing of the codes does not change wrt. the original PQ versions but the code layout is "packed" so that it can be used efficiently by the SIMD computation kernels.

The main changes are:

- new IndexPQFastScan and IndexIVFPQFastScan objects

- simdib.h for an abstraction above the AVX2 intrinsics

- BlockInvertedLists for invlists that are 32-byte aligned and where codes are not sequential

- pq4_fast_scan.h/.cpp:  for packing codes and look-up tables + optmized distance comptuation kernels

- simd_result_hander.h: SIMD version of result collection in heaps / reservoirs

Misc changes:

- added contrib.inspect_tools to access fields in C++ objects

- moved .h and .cpp code for inverted lists to an invlists/ subdirectory, and made a .h/.cpp for InvertedListsIOHook

- added a new inverted lists type with 32-byte aligned codes (for consumption by SIMD)

- moved Windows-specific intrinsics to platfrom_macros.h

Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1542

Test Plan:
```
buck test mode/opt  -j 4  //faiss/tests/:test_fast_scan_ivf //faiss/tests/:test_fast_scan
buck test mode/opt  //faiss/manifold/...
```

Reviewed By: wickedfoo

Differential Revision: D25175439

Pulled By: mdouze

fbshipit-source-id: ad1a40c0df8c10f4b364bdec7172e43d71b56c34
2020-12-03 10:06:38 -08:00