File IndexIVFPQFastScan.h

namespace faiss

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.

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.

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. 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.

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

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. 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.

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

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

Variables

FAISS_API IVFFastScanStats IVFFastScan_stats
struct IndexIVFPQFastScan : public faiss::IndexIVF
#include <IndexIVFPQFastScan.h>

Fast scan version of IVFPQ. Works for 4-bit PQ for now.

The codes in the inverted lists are not stored sequentially but grouped in blocks of size bbs. This makes it possible to very quickly compute distances with SIMD instructions.

Implementations (implem): 0: auto-select implementation (default) 1: orig’s search, re-implemented 2: orig’s search, re-ordered by invlist 10: optimizer int16 search, collect results in heap, no qbs 11: idem, collect results in reservoir 12: optimizer int16 search, collect results in heap, uses qbs 13: idem, collect results in reservoir

Public Functions

IndexIVFPQFastScan(Index *quantizer, size_t d, size_t nlist, size_t M, size_t nbits_per_idx, MetricType metric = METRIC_L2, int bbs = 32)
IndexIVFPQFastScan()
explicit IndexIVFPQFastScan(const IndexIVFPQ &orig, int bbs = 32)
virtual void train_residual(idx_t n, const float *x) override

Sub-classes that encode the residuals can train their encoders here does nothing by default

void precompute_table()

build precomputed table, possibly updating use_precomputed_table

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

same as the regular IVFPQ encoder. The codes are not reorganized by blocks a that point

virtual void add_with_ids(idx_t n, const float *x, const idx_t *xids) override

default implementation that calls encode_vectors

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

assign the vectors, then call search_preassign

void compute_LUT(size_t n, const float *x, const idx_t *coarse_ids, const float *coarse_dis, AlignedTable<float> &dis_tables, AlignedTable<float> &biases) const
void compute_LUT_uint8(size_t n, const float *x, const idx_t *coarse_ids, const float *coarse_dis, AlignedTable<uint8_t> &dis_tables, AlignedTable<uint16_t> &biases, float *normalizers) const
template<bool is_max>
void search_dispatch_implem(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels) const
template<class C>
void search_implem_1(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels) const
template<class C>
void search_implem_2(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels) const
template<class C>
void search_implem_10(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels, int impl, size_t *ndis_out, size_t *nlist_out) const
template<class C>
void search_implem_12(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels, int impl, size_t *ndis_out, size_t *nlist_out) const

Public Members

bool by_residual

Encode residual or plain vector?

ProductQuantizer pq

produces the codes

int bbs
size_t M2
int use_precomputed_table = 0

precomputed tables management

AlignedTable<float> precomputed_table

if use_precompute_table size (nlist, pq.M, pq.ksub)

int implem = 0
int skip = 0
int qbs = 0
size_t qbs2 = 0
InvertedLists *orig_invlists = nullptr

orig’s inverted lists (for debugging)

struct IVFFastScanStats

Public Functions

inline double Mcy_at(int i)
inline double Mcy_reservoir_at(int i)
inline IVFFastScanStats()
inline void reset()

Public Members

uint64_t times[10]
uint64_t t_compute_distance_tables
uint64_t t_round
uint64_t t_copy_pack
uint64_t t_scan
uint64_t t_to_flat
uint64_t reservoir_times[4]