Advertisement

Implementation of the real-time functional language Erlang on a massively parallel platform, with applications to telecommunications services

  • Beshar Zuhdy
  • Peter Fritzson
  • Kent Engström
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 919)

Abstract

Many real-time systems need large amounts of computational power. This may soon provide a larger market for parallel computers than the scientific computing area where most of them are used today. Examples of new and interesting areas are telephone switching systems, image recognition, real-time databases, multi-media services and traffic guidance systems. Programming parallel computers for these new applications is often complex and error-phrone. To alleviate this condition, Ericsson has developed a new non-lazy functional programming language called Erlang. This new language, which has already been used in several large projects, was designed to provide a good environment for building large fault-tolerant real-time applications with explicit concurrency.

Existing Erlang implementations run on SISD computers. Together with Ericsson, we have developed a MIMD version of Erlang, initially for the Parsytec GC/PowerPlus. This is one of the first implementations of a functional language used in industry on a MIMD computer. To benchmark the parallel Erlang version, we are using a telecommunications application developed by Ericsson.

Keywords

Master Node Functional Language IEEE Communication Magazine Intelligent Network Parallel Platform 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Beshar Zuhdy
    • 1
  • Peter Fritzson
    • 1
  • Kent Engström
    • 1
  1. 1.PELAB, Dept. of Computer and InformationScience Linköping UniversityLinköpingSweden

Personalised recommendations