Fast generation of large task network mappings

Abstract : In the context of networks of massively parallel execution models, optimizing the locality if inter-process communication is a major performance issue. We propose two heuristics to solve a dataflow process network mapping problem, where a network of communicating tasks is placed into a set of processors with limited resource capacities, while minimizing the overall communication bandwidth between processors. Those approaches are designed to tackle instances of over one hundred thousand tasks in acceptable time.
Document type :
Conference papers
Complete list of metadatas

https://hal-cea.archives-ouvertes.fr/cea-01839857
Contributor : Léna Le Roy <>
Submitted on : Monday, July 16, 2018 - 10:06:01 AM
Last modification on : Wednesday, January 23, 2019 - 2:39:33 PM

Identifiers

Collections

CEA | CNRS | PRISM | UVSQ | DRT | LIST

Citation

K.-E. Berger, F. Galea, B. Le Cun, R. Sirdey. Fast generation of large task network mappings. 2014 IEEE International Parallel & Distributed Processing Symposium Workshops, May 2014, Phoenix, United States. pp.1526-1530, ⟨10.1109/IPDPSW.2014.170⟩. ⟨cea-01839857⟩

Share

Metrics

Record views

54