A Storage-Computation-Communication Tradeoff for Distributed Computing

05/26/2018

∙

by   Qifa Yan, et al.

∙

0

∙

share

This paper investigates distributed computing systems where computations are split into "Map" and "Reduce" functions. A new coded scheme distributed computing and coded communication (D3C) is proposed, and its communication load is analyzed in function of the available storage space and the number of intermediate values (IVA) to be computed. D3C achieves smallest possible communication load for given storage space, where less IVAs need to be computed than in Li et al.'s coded distributed computing (CDC). More generally, our scheme can flexibly assign available storage space and the number of IVAs to be computed. Communication load is then analyzed for any given assignment.