NCAM: Near-Data Processing for Nearest Neighbor Search

Abstract

Emerging classes of computer vision applications demand unprecedented computational resources and operate on large amounts of data. In particular, k-nearest neighbors (kNN), a cornerstone algorithm in these applications, incurs significant data movement. To address this challenge, the underlying architecture and memory subsystems must vertically evolve to address memory bandwidth and compute demands. To enable large-scale computer vision, we propose a new class of associative memories called NCAMs which encapsulate logic with memory to accelerate k-nearest neighbors. We estimate that NCAMs can improve the performance of kNN by orders of magnitude over the best off-the-shelf software libraries (e.g., FLANN) and commodity platforms (e.g., GPUs).