File GpuIndexIVF.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.

namespace gpu
struct GpuIndexIVFConfig : public faiss::gpu::GpuIndexConfig

Subclassed by faiss::gpu::GpuIndexIVFFlatConfig, faiss::gpu::GpuIndexIVFPQConfig, faiss::gpu::GpuIndexIVFScalarQuantizerConfig

Public Functions

inline GpuIndexIVFConfig()

Public Members

IndicesOptions indicesOptions

Index storage options for the GPU.

GpuIndexFlatConfig flatConfig

Configuration for the coarse quantizer object.

class GpuIndexIVF : public faiss::gpu::GpuIndex
#include <GpuIndexIVF.h>

Base class of all GPU IVF index types. This (for now) deliberately does not inherit from IndexIVF, as many of the public data members and functionality in IndexIVF is not supported in the same manner on the GPU.

Subclassed by faiss::gpu::GpuIndexIVFFlat, faiss::gpu::GpuIndexIVFPQ, faiss::gpu::GpuIndexIVFScalarQuantizer

Public Functions

GpuIndexIVF(GpuResourcesProvider *provider, int dims, faiss::MetricType metric, float metricArg, int nlist, GpuIndexIVFConfig config = GpuIndexIVFConfig())

Version that auto-constructs a flat coarse quantizer based on the desired metric

GpuIndexIVF(GpuResourcesProvider *provider, Index *coarseQuantizer, int dims, faiss::MetricType metric, float metricArg, int nlist, GpuIndexIVFConfig config = GpuIndexIVFConfig())

Version that takes a coarse quantizer instance. The GpuIndexIVF does not own the coarseQuantizer instance by default (functions like IndexIVF).

~GpuIndexIVF() override
void copyFrom(const faiss::IndexIVF *index)

Copy what we need from the CPU equivalent.

void copyTo(faiss::IndexIVF *index) const

Copy what we have to the CPU equivalent.

virtual void updateQuantizer() = 0

Should be called if the user ever changes the state of the IVF coarse quantizer manually (e.g., substitutes a new instance or changes vectors in the coarse quantizer outside the scope of training)

int getNumLists() const

Returns the number of inverted lists we’re managing.

int getListLength(int listId) const

Returns the number of vectors present in a particular inverted list.

std::vector<uint8_t> getListVectorData(int listId, bool gpuFormat = false) const

Return the encoded vector data contained in a particular inverted list, for debugging purposes. If gpuFormat is true, the data is returned as it is encoded in the GPU-side representation. Otherwise, it is converted to the CPU format. compliant format, while the native GPU format may differ.

std::vector<idx_t> getListIndices(int listId) const

Return the vector indices contained in a particular inverted list, for debugging purposes.

void setNumProbes(int nprobe)

Sets the number of list probes per query.

int getNumProbes() const

Returns our current number of list probes per query.

void search_preassigned(idx_t n, const float *x, idx_t k, const idx_t *assign, const float *centroid_dis, float *distances, idx_t *labels, bool store_pairs, const SearchParametersIVF *params = nullptr) const

Same interface as faiss::IndexIVF, in order to search a set of vectors pre-quantized by the IVF quantizer. Does not include IndexIVFStats as that can only be obtained on the host via a GPU d2h copy.

Parameters:
  • n – nb of vectors to query

  • x – query vectors, size nx * d

  • assign – coarse quantization indices, size nx * nprobe

  • centroid_dis – distances to coarse centroids, size nx * nprobe

  • distance – output distances, size n * k

  • labels – output labels, size n * k

  • store_pairs – store inv list index + inv list offset instead in upper/lower 32 bit of result, instead of ids (used for reranking).

  • params – used to override the object’s search parameters

Public Members

ClusteringParameters cp

Exposing this like the CPU version for manipulation.

int nlist

Exposing this like the CPU version for query.

int nprobe

Exposing this like the CPU version for manipulation.

Index *quantizer

A user-pluggable coarse quantizer.

bool own_fields

Whether or not we own the coarse quantizer.

Protected Functions

void verifyIVFSettings_() const
virtual bool addImplRequiresIDs_() const override

Does addImpl_ require IDs? If so, and no IDs are provided, we will generate them sequentially based on the order in which the IDs are added

void trainQuantizer_(idx_t n, const float *x)
virtual void addImpl_(int n, const float *x, const idx_t *ids) override

Called from GpuIndex for add/add_with_ids.

virtual void searchImpl_(int n, const float *x, int k, float *distances, idx_t *labels, const SearchParameters *params) const override

Called from GpuIndex for search.

Protected Attributes

const GpuIndexIVFConfig ivfConfig_

Our configuration options.

std::shared_ptr<IVFBase> baseIndex_

For a trained/initialized index, this is a reference to the base class.

Private Functions

void init_()

Shared initialization functions.