Skip to Main content Skip to Navigation
Journal articles

Hypergraph partitioning for multiple communication cost metrics: Model and methods

Abstract : We investigate hypergraph partitioning-based methods for efficient paralleliza-tion of communicating tasks. A good partitioning method should divide the load among the processors as evenly as possible and minimize the inter-processor communication overhead. The total communication volume is the most popular communication overhead metric which is reduced by the existing state-of-the-art hypergraph partitioners. However, other metrics such as the total number of messages, the maximum amount of data transferred by a processor, or a combination of them are equally, if not more, important. Existing hypergraph-based solutions use a two phase approach to minimize such metrics where in each phase, they minimize a different metric, sometimes at the expense of others. We propose a one-phase approach where all the communication cost metrics can be effectively minimized in a multi-objective setting and reductions can be achieved for all metrics together. For an accurate modeling of the maximum volume and the number of messages sent and received by a processor, we propose the use of directed hypergraphs. The directions on hyperedges necessitate revisiting the standard partitioning heuristics. We do so and propose a multi-objective, multi-level hypergraph partitioner called UMPa. The partitioner takes various prioritized communication metrics into account, and optimizes all of them together in the same phase. Compared to the state-of-the-art methods which only minimize the total communication volume, we show on a large number of problem instances that UMPa produces better partitions in terms of several communication metrics.
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download
Contributor : Equipe Roma Connect in order to contact the contributor
Submitted on : Wednesday, June 3, 2015 - 3:20:28 PM
Last modification on : Friday, September 30, 2022 - 4:12:09 AM
Long-term archiving on: : Monday, April 24, 2017 - 11:29:26 PM


Files produced by the author(s)




Mehmet Deveci, Kamer Kaya, Bora Uçar, Umit V. Catalyurek. Hypergraph partitioning for multiple communication cost metrics: Model and methods. Journal of Parallel and Distributed Computing, Elsevier, 2015, 77, pp.69--83. ⟨10.1016/j.jpdc.2014.12.002⟩. ⟨hal-01159676⟩



Record views


Files downloads