Scheduling Strategies for Master-Slave Tasking on Heterogeneous Processor Grids

Abstract

International audienceIn this paper, we consider the problem of allocating a large number of independent, equal-sized tasks to a heterogeneous "grid" computing platform. We use a non-oriented graph to model a grid, where resources can have different speeds of computation and communication, as well as different overlap capabilities. We show how to determine the optimal steady-state scheduling strategy for each processor. Because spanning trees are easier to deal with in practice, a natural question arises: how to extract the best spanning tree, i.e. the one with optimal steady-state throughput, out of a general interconnection graph? We show that this problem is NP-Complete. Still, we introduce and compare several low-complexity heuristics to determine a sub-optimal spanning tree

Toward understanding heterogeneity in computing

“…In 1994, the first author noted the need for better understanding of the scheduling implications of heterogeneity via rigorous analyses [23]. There has since been an impressive amount of first-rate work on this topic-focusing largely on collective communication [3,4,8,15,17,22,24], but also studying important scheduling issues [1,5,6,7,13,18]. That said, sources such as [1] show that there is still much to learn about this important topic-including the questions in the abstract.…”

“…0.216 0.116 0.060 Table 2: HECR values for sample competing heterogeneous clusters 4 Because we use the value of ρ to calibrate a heterogeneous cluster's power, we must violate our normalization convention and allow ρ to assume any value ≤ 1.…”

Load-balancing scatter operations for grid computing

“…Another difference is in the produced schedule: we constrain that for each slave all the data are sent before starting the computation, whereas they allow communications between different slaves to be interleaved. The same authors, in association with Banino, have studied in [3] more general tree-structured networks where, rather than searching an optimal solution to the problem, they characterize the best steady-state for various operation models.…”

Improving Metaheuristics for Mapping Independent Tasks into Heterogeneous Memory-Constrained Systems

“…The master-slave scheme is one of the most popular parallel algorithmic schemes [1], [2]. There are publications about optimal mapping master-slave schemes in parallel systems [3], [4], [5], but in those works the optimal mappings are obtained only under certain restrictions, and memory constraints are not considered.…”