Introducing Aspects to the Implementation of a Java Fork/Join Framework

Authors:
Chrysoulis Zambas;Mikel Luján
Affiliations:
School of Computer Science, The University of Manchester, Manchester, United Kingdom M13 9PL;School of Computer Science, The University of Manchester, Manchester, United Kingdom M13 9PL
Venue:
ICA3PP '08 Proceedings of the 8th international conference on Algorithms and Architectures for Parallel Processing
Year:
2008

Citing 7
Cited 0

A Java fork/join framework

Proceedings of the ACM 2000 conference on Java Grande
Concurrent Programming in Java. Second Edition: Design Principles and Patterns

Concurrent Programming in Java. Second Edition: Design Principles and Patterns
Design pattern implementation in Java and aspectJ

OOPSLA '02 Proceedings of the 17th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications
Using AspectJ to separate concerns in parallel scientific Java code

Proceedings of the 3rd international conference on Aspect-oriented software development
Summarization of dynamic content in web collections

PKDD '04 Proceedings of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases
A join point for loops in AspectJ

Proceedings of the 5th international conference on Aspect-oriented software development
Reusable aspect-oriented implementations of concurrency patterns and mechanisms

Proceedings of the 5th international conference on Aspect-oriented software development

Quantified Score

Hi-index	0.00

Visualization

Abstract

When faced with the question of how will a program exploit the current and upcoming chip multiprocessors, many answers can be produced. Two of the most promising answers are: (1) frameworks or libraries where experts have encapsulated the parallelism, and (2) work stealing as a means of load balancing the work. This paper presents a study of whether aspect-oriented programming can benefit the implementation of a well-known Java framework for divide-and-conquer applications that relies on random work stealing. Despite different kinds of aspects being introduced, the performance evaluation shows no significant overhead due to their inclusion.