No abstract

A key issue of problem-oriented parallel programming is an appropriate concept for representing the spatial structures of an application and modelling local or global interactions operating on them. This paper advocates for the use of so-called index spaces as a unified and powerful expression tool. It discusses the interface between application modelling and programming abstractions, and presents their embeddings in the high-level, data parallel language PROMOTER

No abstract

No abstract

We present a new approach to the problem of dependence-free partitioning of structured domains, also known as alignment. The proposed method is based on a unified description of data and dependence structures with the help of abelian groups, and considers alignment as a factorization problem automatically driven by given crossed-and auto-dependences. We develop a mathematical framework and give some empirical results.