Exploiting accelerators for efficient high dimensional similarity search

Abstract

Similarity search finds the most similar matches in an object collection for a given query; making it an important problem across a wide range of disciplines such as web search, image recognition and protein sequencing. Practical implementations of High Dimensional Similarity Search (HDSS) search across billions of possible solutions for multiple queries in real time, making its performance and efficiency a significant challenge. Existing clusters and datacenters use commercial multicore hardware to perform search, which may not provide the optimal performance and performance per Watt. This work explores the performance, power and cost benefits of using throughput accelerators like GPUs to perform similarity search for query cohorts even under tight deadlines. We propose optimized implementations of similarity search for both the host and the accelerator. Augmenting existing Xeon servers with accelerators results in a 3× improvement in throughput per machine, resulting in a more than 2.5× reduction in cost of ownership, even for discounted Xeon servers. Replacing a Xeon based cluster with an accelerator based cluster for similarity search reduces the total cost of ownership by more than 6× to 16× while consuming significantly less power than an ARM based cluster.

POSTER: Application-Driven Near-Data Processing for Similarity Search

“…Their design tightly integrates a k-nearest neighbor accelerator engine and microarchitecturally shares common elements with our design. Agrawal et al [100] exploit accelerators to reduce the total cost of ownership of high-dimensional similarity search. Yu et al [101] optimize all-pairs nearest neighbors by fusing neighbor selection with distance computations.…”

Performance optimization, modeling and analysis of sparse matrix-matrix products on multi-core and many-core processors

“…Multiplication of two sparse matrices (SpGEMM) is a recurrent kernel in many algorithms in machine learning, data analysis, and graph analysis. For example, bulk of the computation in multi-source breadth-first search [1], betweenness centrality [2], Markov clustering [3], label propagation [4], peer pressure clustering [5], clustering coefficients [6], high-dimensional similarity search [7], and topological similarity search [8] can be expressed as SpGEMM. Similarly, numerical applications such as scientific simulations also use SpGEMM as a subroutine.…”