Abstract

The ways in which photonic and optoelectronic technologies could play an important role in future highly scalable and flexible interconnects for multicomputer parallel processing systems are discussed. For electronic interconnect implementation, the primary limitations arise from transmission drive power requirements, limited bandwidth, and the crosstalk-limited length. It is shown that photonic interconnects can relieve these bottlenecks in order to allow systems to scale to large numbers of nodes without degrading the interconnect performance. As an example, a network architecture capable of interconnecting thousands of processors with multigigabit average access rate per user, and peak access rates an order of magnitude higher is presented. The network topology is a shuffle-exchange, multihop, multipath, wraparound direct interconnect that utilizes self-routing and a deflection flow control technique to simplify and speed the processing. An experimental 2*2 photonic switching node based on the presented techniques is described.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.