Managing resources dynamically in hybrid photonic-electronic networks-on-chip

• Published in: Concurrency and computation 2014-10, Vol.26 (15), p.2530-2550
• Main Authors: García-Guirado, Antonio, Fernández-Pascual, Ricardo, García, José M., Bartolini, Sandro
• Format: Article
• Language: English
• Subjects: cache coherence; Decisions; Energy consumption; Messages; Microprocessors; Nanostructure; Networks; on-chip photonics; Photonics; Policies
• ISSN: 1532-0626; 1532-0634
• DOI: 10.1002/cpe.3332

SUMMARYNanophotonics promises to solve the scalability problems of current electrical interconnects thanks to its low sensitivity to distance in terms of latency and energy consumption. Before this technology reaches maturity, hybrid photonic‐electronic networks will be a viable alternative. Ideally, ordinary electrical meshes and ring‐based photonic networks should cooperate to minimize overall latency and energy consumption, but currently, we lack mechanisms to do this efficiently. In this paper, we present novel fine‐grain policies to manage the photonic resources in a tiled chip multiprocessor (CMP) scenario. Our policies are dynamic and base their decisions on parameters such as message size, ring availability, and distance between endpoints, at the message level. The resulting network behavior is also fairer to all cores, reducing processor idle time thanks to faster thread synchronization. All these policies improve performance when compared to the same CMP without the photonic ring, and the most elaborate ones reduce the overall network latency by 50%, execution time by 36%, and network energy consumption by 52% on average, in a 16‐core CMP for the PARSEC benchmark suite. Larger hybrid networks with 64 endpoints for 256‐core CMPs, based on Corona and Firefly designs, also show far superior throughput and lower latency if managed by one of the proposed policies. Copyright © 2014 John Wiley & Sons, Ltd.