On partitioning problems with complex objectives

Abstract : Hypergraph and graph partitioning tools are used to partition work for efficient parallelization of many sparse matrix computations. Most of the time, the objective function that is reduced by these tools relates to reducing the communication requirements, and the balancing constraints satisfied by these tools relate to balancing the work or memory requirements. Sometimes, the objective sought for having balance is a complex function of a partition. We mention some important class of parallel sparse matrix computations that have such balance objectives. For these cases, the current state of the art partitioning tools fall short of being adequate. To the best of our knowledge, there is only a single algorithmic framework in the literature to address such balance objectives. We propose another algorithmic framework to tackle complex objectives and experimentally investigate the proposed framework.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.inria.fr/hal-00763548
Contributor : Equipe Roma <>
Submitted on : Tuesday, December 11, 2012 - 9:57:43 AM
Last modification on : Friday, April 12, 2019 - 4:23:12 PM

Links full text

Identifiers

Citation

Kamer Kaya, Rouet François-Henry, Bora Uçar. On partitioning problems with complex objectives. Euro-Par 2011: Parallel Processing Workshops, Aug 2011, Bordeaux, France. pp.334-344, ⟨10.1007/978-3-642-29737-3_38⟩. ⟨hal-00763548⟩

Share

Metrics

Record views

159