Heterogeneity Considered Harmful to Algorithm Designers

Olivier Beaumont 1 Vincent Boudet 1 Arnaud Legrand 1 Fabrice Rastello 1 Yves Robert 1
1 REMAP - Regularity and massive parallel computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : In this paper, we deal with algorithmic issues on heterogeneous platforms. We show that static scheduling and load-balancing strategies are absolutely needed to achieve good performances, in contrast to situation for homogeneous parallel machines where dynamic schemes often turn out to be very satisfactory. However, we also show that static strategies targeted to heterogeneous platforms are difficult to design and implement: intuitively, data distribution must obey a much more refined model than standard block-cyclic distributions to equally balance the load between processors of different speeds. Technically, we state several NP-completeness results that demonstrate the intrinsic difficulty of static load-balancing on heterogeneous platforms.
Complete list of metadatas

https://hal.inria.fr/hal-00789464
Contributor : Arnaud Legrand <>
Submitted on : Monday, February 18, 2013 - 11:52:06 AM
Last modification on : Friday, November 23, 2018 - 1:40:03 PM

Identifiers

  • HAL Id : hal-00789464, version 1

Collections

Citation

Olivier Beaumont, Vincent Boudet, Arnaud Legrand, Fabrice Rastello, Yves Robert. Heterogeneity Considered Harmful to Algorithm Designers. Cluster'2000, 2000, Unknown, pp.403―404. ⟨hal-00789464⟩

Share

Metrics

Record views

203