Abstractions for portable, scalable parallel programming

In parallel programming, the need to manage communication, load imbalance, and irregular-ities in the computation puts substantial demands on the programmer. Key properties of the architecture, such as the number of processors and the cost of communication, must be exploited to achieve good performance, but coding these properties directly into a program compromises the portability and exibility of the code because signicant changes are then needed to port or enhance the program. We describe a parallel programming model that supports the con-cise, independent description of key aspects of a parallel program|including data distribution, communication, and boundary conditions|without reference to machine idiosyncrasies. The in-dependence of such components improves portability by allowing the components of a program to be tuned independently, and encourages reuse by supporting the composition of existing com-ponents. The isolation of architecture-sensitive aspects of a computation simplies the task of porting programs to new platforms. Moreover, the model is eective in exploiting both data parallelism and functional parallelism. This paper provides programming examples, compares this work to related languages, and presents performance results.