Skip to main content

Auto-Mobiles: Optimised Message-Passing

Brown, Neil C.C. (2009) Auto-Mobiles: Optimised Message-Passing. In: Welch, Peter H. and Roebbers, Herman W. and Broenink, Jan F. and Barnes, Frederick R.M. and Ritson, Carl G. and Sampson, Adam T. and Stiles, Gardiner S. and Vinter, Brian, eds. Communicating Process Architectures 2009. Concurrent Systems Engineering . IOS Press, Amsterdam, Netherlands, pp. 182-196. ISBN 978-1-60750-065-0. E-ISBN 978-1-60750-513-6. (doi:10.3233/978-1-60750-065-0-225) (KAR id:30582)

PDF Publisher pdf
Language: English
Download (212kB) Preview
[thumbnail of AutoMobiles.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL:
http://dx.doi.org/10.3233/978-1-60750-065-0-225

Abstract

Some message-passing concurrent systems, such as occam 2, prohibit aliasing of data objects. Communicated data must thus be copied, which can be time-intensive for large data packets such as video frames. We introduce automatic mobility, a compiler optimisation that performs communications by reference and deduces when these communications can be performed without copying. We discuss bounds for speed-up and memory use, and benchmark the automatic mobility optimisation. We show that in the best case it can transform an operation from being linear with respect to packet size into constant-time.

Item Type: Book section
DOI/Identification number: 10.3233/978-1-60750-065-0-225
Uncontrolled keywords: determinacy analysis, Craig interpolants
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Funders: [UNSPECIFIED] WoTUG
Depositing User: Neil Brown
Date Deposited: 21 Sep 2012 09:49 UTC
Last Modified: 16 Nov 2021 10:08 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/30582 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year