Abstract
As the number of cores in a multicore chip increases, the kilo-core processor will be a trend in Network-on-Chip development. For such case, the network topology needs to scale effectively. In this paper, we propose a new scalable topology for kilo-core-oriented processors named CSquare, a cluster-formed structure, in which each cluster is a variation of the butterfly-tree. For each cluster, the routers adopt parallel-level structure to obtain efficient global connections. With the global interconnections between clusters, the topology scale can be extended at a much faster rate than with only one cluster. For such characters, we propose a deadlock-free routing algorithm for CSquare, called GNCA. Compared with 2D-Mesh and Torus, CSquare employs fewer routers and links. The simulation results indicate that CSquare greatly improves the average latency and throughput under various traffic patterns and consumes less power and area.
Sign-in/Register to access full text options 
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 callDisclaimer: 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.
