About This Special Issue
Parallel computing (Parallel computers and algorithms) has emerged as an indispensable tool for any scientific domains during last 25 years of intensive using of parallel principles (Parallelism). Using of parallel principles belongs nowadays to dominant ways of achieving the required performance, which should be higher than what is possible with only single computers. Performance driven studies have explored a wealth of alternatives with respect to all aspects of parallel computers and algorithms too aiming at improving the performance of the available parallel systems and their parallel algorithms by optimizing the whole performance of individual technical and program resources and their influences.
The best way how to optimize the whole performance in parallel computing is to apply performance evaluation tools (modeling) in parallel computing. The optimal resource allocation constitutes the problem of being able to understand and to predict modeled resource behavior. To this analysis we can use both analytical and simulation methods. Modeling and simulation are methods, which are commonly used by performance analysts to represent constraints and to optimize performance. Principally analytical methods represented by queuing theory and theory of complexity belong to the preferred methods in comparison to the simulation method, because of their potential ability of general analysis and also of their ability to potentially analyze also massive resources of parallel computers and algorithms too. In relation to it the suggested Special issue should by devoted to complex modeling in parallel computing in order to optimize the whole execution times including the minimization of coincident overheads in parallel computing. The idea of extended complex modeling then opens new possibilities to unify modeling and optimization in parallel computers based on queuing theory and in parallel algorithms using the extensions of theory of complexity to parallel algorithms including their overheads.