Data Structures and Algorithms for Domain Decomposition and Distributed Sparse Matrices

Although Domain Decomposition (DD) techniques constitute an important class of methods few actual general purpose codes based on these techniques have been developed so far. It is important to develop algorithms as well as software libraries and tools to facilitate parallel implementations of such techniques. In this paper we explore these ideas and propose a data structure for implementing`distributed sparse matrices', which is a broader concept than that of domain decomposition. We also give an overview of how the data structure can be exploited when implementing a parallel sparse matrix iterative solver.