Alleviating Datapath Conflicts and Design Centralization in Graph Analytics Acceleration
TimeWednesday, July 13th5:10pm - 5:30pm PDT
Location3000, Level 3
Design of Cyber-physical Systems, Cloud Computing and IoT
DescriptionPrevious graph analytics accelerators have achieved great improvement on throughput by alleviating irregular off-chip memory accesses. However, on-chip side datapath conflicts and design centralization have become the critical issues hindering further improvement on throughput. In this paper, a general solution, Multiple-stage Decentralized Propagation network(MDP-network), is proposed to address these issues, inspired by the key idea of trading latency for throughput. Besides, a novel high throughput graph analytics accelerator, HiGraph, is proposed by deploying MDP-network to address each issue in practice. The experiment shows that compared with state-of-the-art accelerator, HiGraph achieves up to 2.2×speedup (1.47×on average) as well as better scalability.