File IndexScalarQuantizer.h

namespace faiss

Implementation of k-means clustering with many variants.

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree.

IDSelector is intended to define a subset of vectors to handle (for removal or as subset to search)

PQ4 SIMD packing and accumulation functions

The basic kernel accumulates nq query vectors with bbs = nb * 2 * 16 vectors and produces an output matrix for that. It is interesting for nq * nb <= 4, otherwise register spilling becomes too large.

The implementation of these functions is spread over 3 cpp files to reduce parallel compile times. Templates are instantiated explicitly.

This file contains callbacks for kernels that compute distances.

Throughout the library, vectors are provided as float * pointers. Most algorithms can be optimized when several vectors are processed (added/searched) together in a batch. In this case, they are passed in as a matrix. When n vectors of size d are provided as float * x, component j of vector i is

x[ i * d + j ]

where 0 <= i < n and 0 <= j < d. In other words, matrices are always compact. When specifying the size of the matrix, we call it an n*d matrix, which implies a row-major storage.

I/O functions can read/write to a filename, a file handle or to an object that abstracts the medium.

The read functions return objects that should be deallocated with delete. All references within these objectes are owned by the object.

Definition of inverted lists + a few common classes that implement the interface.

Since IVF (inverted file) indexes are of so much use for large-scale use cases, we group a few functions related to them in this small library. Most functions work both on IndexIVFs and IndexIVFs embedded within an IndexPreTransform.

In this file are the implementations of extra metrics beyond L2 and inner product

Implements a few neural net layers, mainly to support QINCo

Defines a few objects that apply transformations to a set of vectors Often these are pre-processing steps.

struct IndexScalarQuantizer : public faiss::IndexFlatCodes
#include <IndexScalarQuantizer.h>

Flat index built on a scalar quantizer.

Public Functions

IndexScalarQuantizer(int d, ScalarQuantizer::QuantizerType qtype, MetricType metric = METRIC_L2)

Constructor.

Parameters:

  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

IndexScalarQuantizer()
virtual void train(idx_t n, const float *x) override

Perform training on a representative set of vectors

Parameters:

  • n – nb of training vectors

  • x – training vecors, size n * d

virtual void search(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels, const SearchParameters *params = nullptr) const override

Search implemented by decoding

virtual FlatCodesDistanceComputer *get_FlatCodesDistanceComputer() const override

a FlatCodesDistanceComputer offers a distance_to_code method

The default implementation explicitly decodes the vector with sa_decode.

virtual void sa_encode(idx_t n, const float *x, uint8_t *bytes) const override

encode a set of vectors

Parameters:

  • n – number of vectors

  • x – input vectors, size n * d

  • bytes – output encoded vectors, size n * sa_code_size()

virtual void sa_decode(idx_t n, const uint8_t *bytes, float *x) const override

decode a set of vectors

Parameters:

  • n – number of vectors

  • bytes – input encoded vectors, size n * sa_code_size()

  • x – output vectors, size n * d

Public Members

ScalarQuantizer sq

Used to encode the vectors.

struct IndexIVFScalarQuantizer : public faiss::IndexIVF
#include <IndexScalarQuantizer.h>

An IVF implementation where the components of the residuals are encoded with a scalar quantizer. All distance computations are asymmetric, so the encoded vectors are decoded and approximate distances are computed.

Public Functions

IndexIVFScalarQuantizer(Index *quantizer, size_t d, size_t nlist, ScalarQuantizer::QuantizerType qtype, MetricType metric = METRIC_L2, bool by_residual = true)
IndexIVFScalarQuantizer()
virtual void train_encoder(idx_t n, const float *x, const idx_t *assign) override

Train the encoder for the vectors.

If by_residual then it is called with residuals and corresponding assign array, otherwise x is the raw training vectors and assign=nullptr

virtual idx_t train_encoder_num_vectors() const override

can be redefined by subclasses to indicate how many training vectors they need

virtual void encode_vectors(idx_t n, const float *x, const idx_t *list_nos, uint8_t *codes, bool include_listnos = false) const override

Encodes a set of vectors as they would appear in the inverted lists

Parameters:

  • list_nos – inverted list ids as returned by the quantizer (size n). -1s are ignored.

  • codes – output codes, size n * code_size

  • include_listno – include the list ids in the code (in this case add ceil(log8(nlist)) to the code size)

virtual void add_core(idx_t n, const float *x, const idx_t *xids, const idx_t *precomputed_idx, void *inverted_list_context = nullptr) override

Implementation of vector addition where the vector assignments are predefined. The default implementation hands over the code extraction to encode_vectors.

Parameters:

precomputed_idx – quantization indices for the input vectors (size n)

virtual InvertedListScanner *get_InvertedListScanner(bool store_pairs, const IDSelector *sel) const override

Get a scanner for this index (store_pairs means ignore labels)

The default search implementation uses this to compute the distances

virtual void reconstruct_from_offset(int64_t list_no, int64_t offset, float *recons) const override

Reconstruct a vector given the location in terms of (inv list index + inv list offset) instead of the id.

Useful for reconstructing when the direct_map is not maintained and the inv list offset is computed by search_preassigned() with store_pairs set.

virtual void sa_decode(idx_t n, const uint8_t *bytes, float *x) const override

decode a set of vectors

Parameters:

  • n – number of vectors

  • bytes – input encoded vectors, size n * sa_code_size()

  • x – output vectors, size n * d

Public Members

ScalarQuantizer sq