p-MEMPSODE: Parallel and irregular memetic global optimization

Description

p-MEMPSODE is a parallel implementation of a memetic global optimization algorithm suitable for shared memory multicore systems. The algorithm combines two well-known and widely used population-based stochastic algorithms, namely Particle Swarm Optimization and Differential Evolution, with two efficient and parallelizable local search procedures. The sequential version of the algorithm was first introduced as MEMPSODE (MEMetic Particle Swarm Optimization and Differential Evolution) and published in the CPC program library. We exploit the inherent and highly irregular parallelism of the memetic global optimization algorithm by means of a dynamic and multilevel approach based on the OpenMP tasking model. In our case, tasks correspond to local optimization procedures or simple function evaluations. Parallelization occurs at each iteration step of the memetic algorithm without affecting its searching efficiency. The proposed implementation, for the same random seed, reaches the same solution irrespectively of being executed sequentially or in parallel. Extensive experimental evaluation has been performed in order to illustrate the speedup achieved on a shared-memory multicore server.

p-MEMPSODE is described in the following article:

• p-MEMPSODE: Parallel and irregular memetic global optimization
  C. Voglis, P.E. Hadjidoukas, K.E. Parsopoulos, D.G. Papageorgiou, I.E. Lagaris, M.N. Vrahatis
  Comput. Phys. Commun. 197 (2015) 190.
  Associated software in the CPC Program Library: AEXJ_v1_0
  DOI: 10.1016/j.cpc.2015.07.011

Downloads