Accelerating Large-Scale Graph-based Nearest Neighbor Search on a Computational Storage Platform

07/12/2022
by   Ji-Hoon Kim, et al.
0

K-nearest neighbor search is one of the fundamental tasks in various applications and the hierarchical navigable small world (HNSW) has recently drawn attention in large-scale cloud services, as it easily scales up the database while offering fast search. On the other hand, a computational storage device (CSD) that combines programmable logic and storage modules on a single board becomes popular to address the data bandwidth bottleneck of modern computing systems. In this paper, we propose a computational storage platform that can accelerate a large-scale graph-based nearest neighbor search algorithm based on SmartSSD CSD. To this end, we modify the algorithm more amenable on the hardware and implement two types of accelerators using HLS- and RTL-based methodology with various optimization methods. In addition, we scale up the proposed platform to have 4 SmartSSDs and apply graph parallelism to boost the system performance further. As a result, the proposed computational storage platform achieves 75.59 query per second throughput for the SIFT1B dataset at 258.66W power dissipation, which is 12.83x and 17.91x faster and 10.43x and 24.33x more energy efficient than the conventional CPU-based and GPU-based server platform, respectively. With multi-terabyte storage and custom acceleration capability, we believe that the proposed computational storage platform is a promising solution for cost-sensitive cloud datacenters.

READ FULL TEXT

page 3

page 9

research
10/19/2020

LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System

Nearest neighbor search (NNS) has a wide range of applications in inform...
research
04/03/2019

Graph based Nearest Neighbor Search: Promises and Failures

Recently, graph based nearest neighbor search gets more and more popular...
research
08/29/2023

CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs

Approximate Nearest Neighbor Search (ANNS) plays a critical role in vari...
research
04/03/2019

A Comparative Study on Hierarchical Navigable Small World Graphs

Hierarchical navigable small world (HNSW) graphs get more and more popul...
research
01/17/2023

Custom 8-bit floating point value format for reducing shared memory bank conflict in approximate nearest neighbor search

The k-nearest neighbor search is used in various applications such as ma...
research
02/10/2018

A Continuation Method for Discrete Optimization and its Application to Nearest Neighbor Classification

The continuation method is a popular approach in non-convex optimization...
research
05/08/2022

Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search

Despite the broad range of algorithms for Approximate Nearest Neighbor S...

Please sign up or login with your details

Forgot password? Click here to reset