File ResultHandler.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.

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. 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)

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. 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.

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. This file contains callbacks for kernels that compute distances.

The SIMDResultHandler object is intended to be templated and inlined. Methods:

  • handle(): called when 32 distances are computed and provided in two simd16uint16. (q, b) indicate which entry it is in the block.

  • set_block_origin(): set the sub-matrix that is being computed

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.

template<class C>
struct HeapResultHandler

Public Types

using T = typename C::T
using TI = typename C::TI

Public Functions

inline HeapResultHandler(size_t nq, T *heap_dis_tab, TI *heap_ids_tab, size_t k)
inline void begin_multiple(size_t i0, size_t i1)

begin

inline void add_results(size_t j0, size_t j1, const T *dis_tab)

add results for query i0..i1 and j0..j1

inline void end_multiple()

series of results for queries i0..i1 is done

Public Members

int nq
T *heap_dis_tab
TI *heap_ids_tab
int64_t k
size_t i0
size_t i1
struct SingleResultHandler

Public Functions

inline SingleResultHandler(HeapResultHandler &hr)
inline void begin(size_t i)

begin results for query # i

inline void add_result(T dis, TI idx)

add one result for query i

inline void end()

series of results for query i is done

Public Members

HeapResultHandler &hr
size_t k
T *heap_dis
TI *heap_ids
T thresh
template<class C>
struct ReservoirTopN
#include <ResultHandler.h>

Reservoir for a single query.

Public Types

using T = typename C::T
using TI = typename C::TI

Public Functions

inline ReservoirTopN()
inline ReservoirTopN(size_t n, size_t capacity, T *vals, TI *ids)
inline void add(T val, TI id)
inline void shrink_fuzzy()
inline void to_result(T *heap_dis, TI *heap_ids) const

Public Members

T *vals
TI *ids
size_t i
size_t n
size_t capacity
T threshold
template<class C>
struct ReservoirResultHandler

Public Types

using T = typename C::T
using TI = typename C::TI

Public Functions

inline ReservoirResultHandler(size_t nq, T *heap_dis_tab, TI *heap_ids_tab, size_t k)
inline void begin_multiple(size_t i0, size_t i1)

begin

inline void add_results(size_t j0, size_t j1, const T *dis_tab)

add results for query i0..i1 and j0..j1

inline void end_multiple()

series of results for queries i0..i1 is done

Public Members

int nq
T *heap_dis_tab
TI *heap_ids_tab
int64_t k
size_t capacity
size_t i0
size_t i1
std::vector<T> reservoir_dis
std::vector<TI> reservoir_ids
std::vector<ReservoirTopN<C>> reservoirs
struct SingleResultHandler

Public Functions

inline SingleResultHandler(ReservoirResultHandler &hr)
inline void begin(size_t i)

begin results for query # i

inline void add_result(T dis, TI idx)

add one result for query i

inline void end()

series of results for query i is done

Public Members

ReservoirResultHandler &hr
std::vector<T> reservoir_dis
std::vector<TI> reservoir_ids
ReservoirTopN<C> res1
size_t i
template<class C>
struct RangeSearchResultHandler

Public Types

using T = typename C::T
using TI = typename C::TI

Public Functions

inline RangeSearchResultHandler(RangeSearchResult *res, float radius)
inline void begin_multiple(size_t i0, size_t i1)

begin

inline void add_results(size_t j0, size_t j1, const T *dis_tab)

add results for query i0..i1 and j0..j1

inline void end_multiple()
inline ~RangeSearchResultHandler()

Public Members

RangeSearchResult *res
float radius
size_t i0
size_t i1
std::vector<RangeSearchPartialResult*> partial_results
std::vector<size_t> j0s
int pr = 0
struct SingleResultHandler

Public Functions

inline SingleResultHandler(RangeSearchResultHandler &rh)
inline void begin(size_t i)

begin results for query # i

inline void add_result(T dis, TI idx)

add one result for query i

inline void end()

series of results for query i is done

inline ~SingleResultHandler()

Public Members

RangeSearchPartialResult pres
float radius
RangeQueryResult *qr = nullptr
template<class C>
struct SingleBestResultHandler

Public Types

using T = typename C::T
using TI = typename C::TI

Public Functions

inline SingleBestResultHandler(size_t nq, T *dis_tab, TI *ids_tab)
inline void begin_multiple(size_t i0, size_t i1)

begin

inline void add_results(size_t j0, size_t j1, const T *dis_tab)

add results for query i0..i1 and j0..j1

inline void add_result(const size_t i, const T dis, const TI idx)
inline void end_multiple()

series of results for queries i0..i1 is done

Public Members

int nq
T *dis_tab
TI *ids_tab
size_t i0
size_t i1
struct SingleResultHandler

Public Functions

inline SingleResultHandler(SingleBestResultHandler &hr)
inline void begin(const size_t current_idx)

begin results for query # i

inline void add_result(T dis, TI idx)

add one result for query i

inline void end()

series of results for query i is done

Public Members

SingleBestResultHandler &hr
T min_dis
TI min_idx
size_t current_idx = 0