The Design , Implementation , and Evaluation of

Jade is a portable, implicitly parallel language designed for exploiting task-level concurrency. Jade programmers start with a program written in a standard serial, imperative language, then use Jade constructs to declare how parts of the program access data. The Jade implementation uses this data access information to automatically extract the concurrency and map the application onto the machine at hand. The resulting parallel execution preserves the semantics of the original serial program. We have implemented Jade as an extension to C, and Jade implementations exist for shared-memory multiprocessors, homogeneous message-passing machines, and heterogeneous networks of workstations. In this article we discuss the design goals and decisions that determined the nal form of Jade and present an overview of the Jade implementation. We also present our experience using Jade to implement several complete scientiic and engineering applications. We use this experience to evaluate how the diierent Jade language features were used in practice and how well Jade as a whole supports the process of developing parallel applications. We nd that the basic idea of preserving the serial semantics simpliies the program development process, and that the concept of using data access speciications to guide the parallelization ooers signiicant advantages over more traditional control-based approaches. We also nd that the Jade data model can interact poorly with concurrency patterns that write disjoint pieces of a single aggregate data structure, although this problem arises in only one of the applications. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proot or direct commercial advantage and that copies show this notice on the rst page or initial screen of a display along with the full citation. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, to redistribute to lists, or to use any component of this work in other works, requires prior speciic permission and/or a fee. Permissions may be requested from Publications 1. INTRODUCTION Programmers have traditionally developed software for parallel machines using explicitly parallel systems Lusk et al. 1987; Sunderam 1990]. These systems provide constructs that programmers use to create parallel tasks. On shared-memory machines the programmer synchronizes the tasks using low-level primitives such as locks, condition variables, and barriers. …