Reusable and Extensible High Level Data Distributions

This paper presents a reusable design of a data distribution frame-work for data parallel high performance applications. We are im-plementing the design in the context of the Chapel high productiv-ity programming language. Distributions in Chapel are a means to express locality in systems composed of large numbers of processor and memory components connected by a network. Since distribu-tions have a great effect on the performance of applications, it is important that the distribution strategy can be chosen by a user. At the same time, high productivity concerns require that the user is shielded from error-prone, tedious details such as communication and synchronization. We propose an approach to distributions that enables the user to re-fine a language-provided distribution type and adjust it to optimize the performance of the application. Additionally, we conceal from the user low-level communication and synchronization details to increase productivity. To emphasize the generality of our distribu-tion machinery, we present its abstract design in the form of a de-sign pattern, which is independent of a concrete implementation. To illustrate the applicability of our distribution framework design, we outline the implementation of data distributions in terms of the Chapel language