Inheritance diagram for faiss::gpu::GpuIndexIVFPQConfig:

Public Attributes
bool	useFloat16LookupTables

bool	usePrecomputedTables

Public Attributes inherited from faiss::gpu::GpuIndexIVFConfig
IndicesOptions	indicesOptions
	Index storage options for the GPU.

GpuIndexFlatConfig	flatConfig
	Configuration for the coarse quantizer object.

Public Attributes inherited from faiss::gpu::GpuIndexConfig
int	device
	GPU device on which the index is resident.

MemorySpace	memorySpace

Detailed Description

Definition at line 23 of file GpuIndexIVFPQ.h.

Member Data Documentation

bool faiss::gpu::GpuIndexIVFPQConfig::useFloat16LookupTables

Whether or not float16 residual distance tables are used in the list scanning kernels. When subQuantizers * 2^bitsPerCode > 16384, this is required.

Definition at line 32 of file GpuIndexIVFPQ.h.

bool faiss::gpu::GpuIndexIVFPQConfig::usePrecomputedTables

Whether or not we enable the precomputed table option for search, which can substantially increase the memory requirement.

Definition at line 36 of file GpuIndexIVFPQ.h.

The documentation for this struct was generated from the following file: