PMF: A Multicore-Enabled Framework for the Construction of Metaheuristics for Single and Multiobjective Optimization
暂无分享,去创建一个
This paper describes the design and implementation of the Parallel Metaheuristics Framework (PMF), a C++ framework for the construction of single and multiobjective metaheuristics utilizing Intel's Threading Building Blocks library to allow easy parallelization of computationally intensive algorithms. The framework demonstrates a generic approach to the construction of metaheuristics, striving to provide a general representation of core operators and concepts, thus allowing users to more easily tailor the system for novel problems. The paper describes the overall implementation of the framework, demonstrates a case study for implementing a simple metaheuristic within the system, and discusses a range of possible enhancements.
[1] El-Ghazali Talbi,et al. ParadisEO: A Framework for the Reusable Design of Parallel and Distributed Metaheuristics , 2004, J. Heuristics.
[2] E. Talbi,et al. A Unified Model for Evolutionary Multiobjective Optimization and its Implementation in a General Purpose Software Framework: ParadisEO-MOEO , 2009, 0904.2987.
[3] James Reinders,et al. Intel® threading building blocks , 2008 .