Abstract
A parallel processor network is called n-universal with slowdown s if it can simulate each computation of each constant-degree processor network with n processors with slowdown s. We prove the following lower bound tradeoff: for each constant-degree n-universal network of size m with slowdown s, \(m\cdot s=\Omega(n\log m)\) holds. Our tradeoff holds for a very general model of simulations. It covers all previously considered models and all known techniques for simulations among networks. For \(m\ge n\) , this improves a previous lower bound by a factor of \(\log\log n\) , proved for a weaker simulation model. For m < n, this is the first nontrivial lower bound for this problem. In this case this lower bound is asymptotically tight.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received November 6, 1995, and in final form November 12, 1996.
Rights and permissions
About this article
Cite this article
Meyer auf der Heide, F., Storch, M. & Wanka, R. Optimal Tradeoffs Between Size and Slowdown for Universal Parallel Networks. Theory Comput. Systems 30, 627–644 (1997). https://doi.org/10.1007/s002240000071
Published:
Issue Date:
DOI: https://doi.org/10.1007/s002240000071