Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Statistics
  • Help & Advice
University of Warwick

The Library

  • Login

Predictive performance analysis of a parallel pipelined synchronous wavefront application for commodity processor cluster systems

Tools
- Tools
+ Tools

Mudalige, Gihan R., Jarvis, Stephan A., Spooner, Daniel P. and Nudd, Graham R. (2006) Predictive performance analysis of a parallel pipelined synchronous wavefront application for commodity processor cluster systems. In: IEEE International Conference on Cluster Computing, Barcelona, SPAIN, SEP 25-28, 2006. Published in: 2006 IEEE International Conference on Cluster Computing, Vols 1 and 2 pp. 467-478.

Full text not available from this repository.

Abstract

This paper details the development and application of a model for predictive performance analysis of a pipelined synchronous wavefront application running on commodity processor cluster systems. The performance model builds on existing work [1] by including extensions for modern commodity processor architectures. These extensions, including coarser hardware benchmarking, prove to be essential in countering the effects of modern superscalar processors (e.g. multiple operation pipelines and on-the-fly optimisations), complex memory hierarchies, and the impact of applying modern optimising compilers. The process of application modelling is also extended, combining static source code analysis with run-time profiling results for increased accuracy. The model is validated on several high performance SMP systems and the results show a high predictive accuracy (<= 10% error). Additionally, the use of the performance model to speculate on the performance and scalability of this application on a hypothetical cluster with two different problem sizes is demonstrated. It is shown that such speculative techniques can be used to support system procurement, run-time verification and system maintenance and upgrading.

Item Type: Conference Item (UNSPECIFIED)
Subjects: Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Journal or Publication Title: 2006 IEEE International Conference on Cluster Computing, Vols 1 and 2
Publisher: IEEE
ISBN: 978-1-4244-0327-1
Date: 2006
Number of Pages: 12
Page Range: pp. 467-478
Identification Number: 10.1109/CLUSTR.2006.311888
Publication Status: Published
Title of Event: IEEE International Conference on Cluster Computing
Location of Event: Barcelona, SPAIN
Date(s) of Event: SEP 25-28, 2006
URI: http://wrap.warwick.ac.uk/id/eprint/30961

Data sourced from Thomson Reuters' Web of Knowledge

Request changes to a record

Actions (login required)

View Item View Item
twitter

Email us: publications@warwick.ac.uk
Contact Details
About Us