On a Hybrid MPI-Pthread Approach for Simplicial Branch-and-Bound
| Autor: | Juan F. R. Herrera, Eligius M. T. Hendrix, Leocadio G. Casado, Julius Zilinskas, Remigijus Paulavičius |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Multi-core processor
POSIX Threads 021103 operations research Branch and bound Computer science Computation Message passing 0211 other engineering and technologies 02 engineering and technology Parallel computing Software_PROGRAMMINGTECHNIQUES Lipschitz continuity Computer Science::Performance Multithreading 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Global optimization Computer Science::Distributed Parallel and Cluster Computing |
| Zdroj: | IPDPS Workshops |
| DOI: | 10.1109/ipdpsw.2013.178 |
| Popis: | We investigate models that efficiently map branch-and-bound algorithms on a distributed computer architecture using a case of multidimensional Lipschitz Global Optimization. A combination of MPI and Pthreads is studied: MPI for distributed computation (inter-node) and Pthreads for multicore computation (intra-node). That model adapts the algorithm to the characteristics of the architecture at hand with an increasing number of nodes. Dynamic load balancing is performed in intra-node space through dynamic generation of threads. Results show performance improvements compared to OpenMP and MPI versions used in previous work. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|