Abstract
This paper presents the most significant results of the investigation project aimed to implement a parallel application for simulating nonlinear optic systems. A new scalability analysis of parallel algorithm-architecture combinations (parallel systems) is proposed. The execution time and parallel efficiency are the parameters that the parallel system must preserve as it is scaled. These parameters are studied considering the physical phenomena that the scientific application is simulating. The goal in scaling a parallel system is to reduce the overall simulation error in the scientific application so that the simulation reflects the physical phenomena more accurately. Consequently, all the error sources, and not only the problem size, should be scaled simultaneously. The realistic scaling improves the operation count and scalability of common iterative methods to solve systems of equations. The execution time, performance and scalability of a d-dimensional full multigrid algorithm on a d-dimensional mesh of processors are analytically determined. The analytical results are experimentally verified using the parallel simulator of optic systems.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
