CaltechAUTHORS
  A Caltech Library Service

Performance of a high-level parallel programming layer defined on top of the Ada tasking model

Thornley, John (1995) Performance of a high-level parallel programming layer defined on top of the Ada tasking model. In: TRI-Ada '95 Proceedings of the conference on TRI-Ada '95: Ada's role in global markets: solutions for a changing complex world. ACM , New York, NY, pp. 252-262. ISBN 0-89791-705-7. https://resolver.caltech.edu/CaltechAUTHORS:20161222-113006091

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20161222-113006091

Abstract

In earlier work, we proposed extending Ada with a high-level parallel programming layer consisting of three pragmas that indicate where standard sequential constructs can be executed in parallel without changing the sequential semantics of a program. The three pragmas specify: {i) parallelizable sequences of statements, (ii) parallelizable for-loop statements, and (iii) single-assignment types for synchronization. A precise definition of these pragmas was given by means of transformations to standard Ada tasking constructs. In this paper, we improve our definition of the parallel programming layer and demonstrate that the pragmas can be implemented efficiently on top of an existing Ada compiler by straightforward preprocessing using the defining transformations. We present three simple parallel programs that exhibit good speedups over sequential programs, when executed on a multiprocessor computer. Development of these programs was considerably easier than the direct use of Ada tasking, because the parallel programs are identical to equivalent sequential programs except for the added pragmas.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1145/376503.376589DOIArticle
http://dl.acm.org/citation.cfm?doid=376503.376589PublisherArticle
Additional Information:© 1995 ACM. Thank you to the members of the Compositional Systems Group of the Computer Science Department at Caltech for their discussions and suggestions throughout this research. Thank you to the GNAT team and their sponsors for their timely work in providing a valuable resource to the entire computing community. Thanks also to the Ada group at SGI, particularly Tom Quiggle and Wes Embry, for making their compiler and multiprocessor computer available for these performance experiments.
Record Number:CaltechAUTHORS:20161222-113006091
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20161222-113006091
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:73153
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:22 Dec 2016 19:35
Last Modified:03 Oct 2019 16:25

Repository Staff Only: item control page