Abstract
An important challenge in parallel computing is the mapping of parallel algorithms to parallel computing platforms. This requires several activities such as the analysis of the parallel algorithm, the definition of the logical configuration of the platform and the implementation and deployment of the algorithm to the computing platform. However, in current parallel computing approaches very often only conceptual and idiosyncratic models are used which fall short in supporting the communication and analysis of the design decisions. In this article, we present ParDSL, a domain-specific language framework for providing explicit models to support the activities for mapping parallel algorithms to parallel computing platforms. The language framework includes four coherent set of domain-specific languages each of which focuses on an activity of the mapping process. We use the domain-specific languages for modeling the design as well as for generating the required platform-specific models and the code of the selected parallel algorithm. In addition to the languages, a library is defined to support systematic reuse. We discuss the overall architecture of the language framework, the separate DSLs, the corresponding model transformations and the toolset. The framework is illustrated for four different parallel computing algorithms.
Highlights
It is increasingly acknowledged that the processing power of a single processor has reached the physical limitations, and serial computing has reached its limits
To model the particular concerns of parallel computing and to support the automation of the activities, we propose ParDSL, a domain-specific language framework consisting of four coherent set of domain-specific languages (DSLs) each of which focuses on a different aspect of the mapping process
The DSLs are used in the generation of platform-specific models and the code of selected parallel algorithms that needs to be mapped on parallel computing platforms
Summary
It is increasingly acknowledged that the processing power of a single processor has reached the physical limitations, and serial computing has reached its limits. Models are not mere documentation but become “code” that are executable and that can be further used to generate even more refined models or code This contrasts with model-based software development in which models are used as blueprints at the most [2]. Developing domain-specific languages (DSLs) is an important approach for supporting model-driven software development and the application of executable models. The DSLs are used in the generation of platform-specific models and the code of selected parallel algorithms that needs to be mapped on parallel computing platforms. Both the languages and the transformations are implemented using the Epsilon language.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
