Large electromagnetic simulation by hybrid approach on large-scale parallel computing systems

摘要

This paper deals with the parallel computing and computation time prediction applied to computationalrnelectromagnetics based on rigorous methods for large and complex structures, such as tunnels andrnairplane cabins. The main objective of this work is represented by the electromagnetic computation ofrnan airplane cabin in order to characterize the propagation channel for a given frequency inside the structure.rnA well-known three-dimensional numerical method, transmission-line matrix, is adopted for this work.rnTransmission-line matrix modelling method is applied to volumes, using the symmetrical condensed node.rnThe planar structures are modelled with the mode matching approach. In order to analyse the electromagneticrnfield at high frequencies inside large structures as an airplane cabin, the transmission-line matrix meshrnstep is very small compared with the size of the physical structure. Thus, the total amount of data thatrnneed to be processed exceeds the RAM memory presented on a traditional computing machine. The implementationrnof the parallel transmission-line matrix algorithm is a viable solution to this problem taking fullrnadvantage of the parallel and distributed architectures, as clusters, grids and supercomputers. The resultsrnprove the benefits of the grid computing and supercomputer environments to solve electrically large structures.rnThe parallel hybrid approach, based on Message Passing Interface, is designed for Single ProgrammernMultiple Data programming model. The study highlights the role of parallelization scheme, grid versusrnsupercomputer, with respect to the size of the problem and its repartition. In order to access the computingrnresources available on different parallel computing platforms, users need to respect a charter containing timernand resource number restrictions when doing reservations. So, a time prediction model based on the profilernof the transmission-line matrix algorithm has been developed to allow safe reservations of the computingrnnodes on grid environment. To have a good agreement between the measured and the predicted values forrnthe computation time, the problem of the cache misses appearing during the simulation has been consideredrnin the profile-based prediction model of the transmission-line matrix/modal hybrid application, according tornthe processor cache memory size. The maximum error for the estimated values of the computation times isrnabout 6.09%. The relevance of this work is based on the fact that is given a complete tool to deal with thernlarge electromagnetic structures: a parallel transmission-line matrix implementation to take the advantage ofrnthe distributed architectures and a time prediction model in order to optimize the resource reservation andrnthe simulation execution on the computing nodes.