Design and implementation of a parallel programming environment based on distributed shared arrays

We have developed a parallel programming environment called the "Distributed Shared Array" (DSA), which provides a shared global array abstract across different machines connected by a network. The DSA provides array-specific operations and fine-grained data consistency based on arrays. It allows a user to explicitly manage array area allocation, replication, and migration. This paper also describes the use of our model for gene cluster analysis, multiple alignment, and molecular dynamics simulation. Global arrays are used in these applications for storing the distance matrix, alignment matrix and atom coordinates, respectively. Large array areas, which cannot be stored in the memory of individual machines, are made available by the DSA. Scalable performance of DSA was obtained and compared to that of conventional parallel programs written in MPI.