The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—Clustered or hierarchical interconnections demonstrate advantage in designing large scale multiprocessor systems. Earlier studies in literature have either focused on only flat interconnections or proposed hierarchical/clustered interconnections with limited packaging and demanded performance constraints. Large systems require several levels of packaging. Packaging technologies impose various physical constraints on bisection bandwidth and channel width of a system. Pinout technologies and capacity of packaging modules have been ignored in earlier studies, often leading to configurations that are not design-feasible. Similarly, the impact of processor and interconnect technologies on demanded performance has also not been considered. In this paper, we propose a new <it>supply-demand framework</it> for multiprocessor system design by considering packaging, processor, and interconnect technologies in an integrated manner. The elegance of this framework lies in its parameterized representation of different technologies. For a given set of technological parameters the framework derives the best configuration while considering practical design aspects like maximum board area, maximum available pinout, fixed channel width, and scalability. In order to build a scalable parallel system with a given number of processors, the framework explores the design space of flat <it>k</it>-ary <it>n</it>-cube topologies and their clustered variations (<it>k</it>-ary <it>n</it>-cube cluster-<it>c</it>) to derive design-feasible configurations with best system performance. The study identifies processor board area, supported channel width, board pinout density, and router pinout as critical parameters and analyzes their impact on deriving design-feasible and best configurations. For a wide range of parameters, it is shown that best configurations are achieved with cluster-based systems with up to 8 processors per cluster and 3D-5D intercluster interconnection.</p>
Multiprocessor systems, scalable systems, clustered architectures, hierarchical organization, k-ary n-cube interconnection, packaging constraints, parallel architectures, interconnection networks.

D. K. Panda and D. Basak, "Designing Clustered Multiprocessor Systems under Packaging and Technological Advancements," in IEEE Transactions on Parallel & Distributed Systems, vol. 7, no. , pp. 962-978, 1996.
96 ms
(Ver 3.3 (11022016))