Abstract

This study presents simulation studies on the execution time and energy consumption of optical multi-socket boards with on-chip, all-to-all, and contention-less arrayed waveguide grating routers-based interconnection. This study considers throughput and energy-efficiency optimizations based on dynamic voltage and frequency scaling under realistic, shared memory, and cache-coherent PARSEC benchmarking traffic. The benchmark results show how a low-latency, optical inter-socket interconnection can provide significant execution time reduction, and up to 3× energy savings when using dynamic variable bandwidth communication techniques when compared to an electronic baseline. The proposed architecture can be used as “building block” for future energy-aware large-scale systems.

© 2015 IEEE

Enabling Scalable Disintegrated Computing Systems With AWGR-Based 2.5D Interconnection Networks

Pouya Fotouhi, Sebastian Werner, Roberto Proietti, Xian Xiao, and S. J. Ben Yoo
J. Opt. Commun. Netw. 11(7) 333-346 (2019)

AWGR-Based Optical Topologies for Scalable and Efficient Global Communications in Large-Scale Multi-Processor Systems

Xiaohui Ye, S. J. B. Yoo, and Venkatesh Akella
J. Opt. Commun. Netw. 4(9) 651-662 (2012)

Hi-LION: Hierarchical Large-Scale Interconnection Optical Network With AWGRs [Invited]

Zheng Cao, Roberto Proietti, and S. J. B. Yoo
J. Opt. Commun. Netw. 7(1) A97-A105 (2015)

OPSquare: A Flat DCN Architecture Based on Flow-Controlled Optical Packet Switches

Fulong Yan, Wang Miao, Oded Raz, and Nicola Calabretta
J. Opt. Commun. Netw. 9(4) 291-303 (2017)

SYMNET: an optical interconnection network for scalable high-performance symmetric multiprocessors

Ahmed Louri and Avinash Karanth Kodi
Appl. Opt. 42(17) 3407-3417 (2003)