Supporting adaptive and irregular parallelism for non-linear numerical optimization
作者：
Highlights：
• A global optimization framework for SMPs and multicore clusters is presented.
• It exploits hierarchal and dynamic task parallelism of the Multistart method.
• Gradient/Hessian calculations and Newton’s optimization method are parallelized.
• Several task distribution schemes are studied and evaluated.
• Our framework is applied successfully to the protein conformation problem.
摘要
•A global optimization framework for SMPs and multicore clusters is presented.•It exploits hierarchal and dynamic task parallelism of the Multistart method.•Gradient/Hessian calculations and Newton’s optimization method are parallelized.•Several task distribution schemes are studied and evaluated.•Our framework is applied successfully to the protein conformation problem.
论文关键词：Irregular and multilevel parallelism,Adaptive task parallelism,Multicore clusters,Message passing,Numerical differentiation,Numerical optimization,Protein conformation
论文评审过程：Available online 1 February 2014.
论文官网地址：https://doi.org/10.1016/j.amc.2013.12.092
