Hits:

Indexed by:期刊论文

Date of Publication:2011-05-01

Journal:Journal of Computational Information Systems

Included Journals:EI、Scopus

Volume:7

Issue:5

Page Number:1691-1697

ISSN No.:15539105

Abstract:Traditional TAP (task allocation problem) aims mostly to minimize overall execution cost and inter-node or inter-processor communication cost. New TAP (NTAP) considering additive intra-node communication cost on emerging multi-core clusters is proposed. Solution to the NTAP is investigated. A 0-1 integer nonlinear programming formulation is presented for solving the NTAP. Furthermore, a 0-1 integer linear programming reformulation using linear programming relaxation technique and an optimization method for the reformulation are also presented. Computational experiment is carried out to demonstrate computational capabilities of the reformulation. Excellent results indicate that solution to the NTAP presented in this paper is more efficient and faster than existing approaches when a large number of tasks communicate. Copyright ? 2011 Binary Information Press.