Billion-Scale Similarity Search with GPUs

Novel Design for Inline-Formula and k-Selection

This paper proposes a novel design for an inline-formula that enables the construction of a high accuracy brute-force. A paper that proposes a design for k-selection that enables faster and more accurate similarity search on GPUs. This paper proposes a design for k-selection that operates at up to 55 of theoretical peak performance enabling a nearest neighbor.

A review of a paper that proposes a GPU-based k-selection algorithm and a near-optimal design for exact and.

Request PDF

Similarity search finds application in database systems.