Activity Graphs: A Model-independent Intermediate Layer for Skeletal Coordination

Murray Cole, Andrea Zavanella

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Activity Graphs are introduced as a simple and practical means of capturing model independent aspects of the operational semantics of structured (and in particular, skeletal) parallel programs. AGs provide a notion of parallel activities, dependencies between activities, and the process groupings within which these take place. They are independent of low level details of parallel implementation and so can act as an intermediate layer for compilation to diverse underlying models. The paper introduces Activity Graphs and gives a compilation scheme from a simple skeletal language into them. The compilation process uses a set of graph generators (templates) to derive the Activity Graph. We then describe a simple scheme to transform Activity Graphs to message passing programs.
Original languageEnglish
Title of host publicationSAC '00 Proceedings of the 2000 ACM Symposium on Applied Computing - Volume 1
Place of PublicationNew York, NY, USA
PublisherACM
Pages255-261
Number of pages7
Volume1
ISBN (Print)1-58113-240-9
DOIs
Publication statusPublished - 2000

Fingerprint

Dive into the research topics of 'Activity Graphs: A Model-independent Intermediate Layer for Skeletal Coordination'. Together they form a unique fingerprint.

Cite this