File GpuCloner.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.

namespace gpu

Functions

faiss::Index *index_gpu_to_cpu(const faiss::Index *gpu_index): converts any GPU index inside gpu_index to a CPU index

faiss::Index *index_cpu_to_gpu(GpuResourcesProvider *provider, int device, const faiss::Index *index, const GpuClonerOptions *options = nullptr): converts any CPU index that can be converted to GPU

faiss::Index *index_cpu_to_gpu_multiple(std::vector<GpuResourcesProvider*> &provider, std::vector<int> &devices, const faiss::Index *index, const GpuMultipleClonerOptions *options = nullptr)

faiss::IndexBinary *index_binary_gpu_to_cpu(const faiss::IndexBinary *gpu_index)

faiss::IndexBinary *index_binary_cpu_to_gpu(GpuResourcesProvider *provider, int device, const faiss::IndexBinary *index, const GpuClonerOptions *options = nullptr): converts any CPU index that can be converted to GPU

faiss::IndexBinary *index_binary_cpu_to_gpu_multiple(std::vector<GpuResourcesProvider*> &provider, std::vector<int> &devices, const faiss::IndexBinary *index, const GpuMultipleClonerOptions *options = nullptr)

struct ToCPUCloner : public faiss::Cloner 

#include <GpuCloner.h>

Cloner specialized for GPU -> CPU.

Public Functions

void merge_index(Index *dst, Index *src, bool successive_ids)

virtual Index *clone_Index(const Index *index) override

struct ToGpuCloner : public faiss::Cloner, public faiss::gpu::GpuClonerOptions 

#include <GpuCloner.h>

Cloner specialized for CPU -> 1 GPU.

Public Functions

ToGpuCloner(GpuResourcesProvider *prov, int device, const GpuClonerOptions &options)

virtual Index *clone_Index(const Index *index) override

Public Members

GpuResourcesProvider *provider

int device

struct ToGpuClonerMultiple : public faiss::Cloner, public faiss::gpu::GpuMultipleClonerOptions 

#include <GpuCloner.h>

Cloner specialized for CPU -> multiple GPUs.

Public Functions

ToGpuClonerMultiple(std::vector<GpuResourcesProvider*> &provider, std::vector<int> &devices, const GpuMultipleClonerOptions &options)

ToGpuClonerMultiple(const std::vector<ToGpuCloner> &sub_cloners, const GpuMultipleClonerOptions &options)

void copy_ivf_shard(const IndexIVF *index_ivf, IndexIVF *idx2, idx_t n, idx_t i)

Index *clone_Index_to_shards(const Index *index)

virtual Index *clone_Index(const Index *index) override: main function

Public Members

std::vector<ToGpuCloner> sub_cloners

struct GpuProgressiveDimIndexFactory : public faiss::ProgressiveDimIndexFactory 

#include <GpuCloner.h>

index factory for the ProgressiveDimClustering object

Public Functions

explicit GpuProgressiveDimIndexFactory(int ngpu)

virtual Index *operator()(int dim) override: ownership transferred to caller

virtual ~GpuProgressiveDimIndexFactory() override

Public Members

GpuMultipleClonerOptions options

std::vector<GpuResourcesProvider*> vres

std::vector<int> devices

int ncall