Non Linear Divisible Loads: There is No Free Lunch - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Non Linear Divisible Loads: There is No Free Lunch


Divisible Load Theory (DLT) has received a lot of attention in the past decade. A divisible load is a perfect parallel task, that can be split arbitrarily and executed in parallel on a set of possibly heterogeneous resources. The success of DLT is strongly related to the existence of many optimal resource allocation and scheduling algorithms, what strongly differs from general scheduling theory. Moreover, recently, close relationships have been underlined between DLT, that provides a fruitful theoretical framework for scheduling jobs on heterogeneous platforms, and MapReduce, that provides a simple and efficient programming framework to deploy applications on large scale distributed platforms. The success of both have suggested to extend their framework to non-linear complexity tasks. In this paper, we show that both DLT and MapReduce are better suited to workloads with linear complexity. In particular, we prove that divisible load theory cannot directly be applied to quadratic workloads, such as it has been proposed recently. We precisely state the limits for classical DLT studies and we review and propose solutions based on a careful preparation of the dataset and clever data parti- tioning algorithms. In particular, through simulations, we show the possible impact of this approach on the volume of communications generated by MapReduce, in the context of Matrix Multiplication and Outer Product algorithms.
Fichier principal
Vignette du fichier
nofreelunch.pdf (146.01 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00771640 , version 1 (09-01-2013)


  • HAL Id : hal-00771640 , version 1


Olivier Beaumont, Hubert Larchevêque, Loris Marchal. Non Linear Divisible Loads: There is No Free Lunch. IPDPS 2013, 27th IEEE International Parallel & Distributed Processing Symposium, IEEE, May 2013, Boston, United States. ⟨hal-00771640⟩
499 View
216 Download


Gmail Facebook Twitter LinkedIn More