Analysis and evaluation of performance issues of parallel software on multi-core processors

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

Abstract

For decades, the processor manufacturers have attempted to achieve performance gains by increasing the clock frequency on single-core processors. But physical problems-such as the high power dissipation-lead to the release of the first multi-core processors on the market in 2005. To benefit from the multi-core architecture, parallel programming is required. However, this programming model requires a different approach and is associated with certain risks and pitfalls. This paper focuses on modelling of certain test scenarios for two common multi-core specific problems, namely oversubscription and false sharing. Various simulations and tests offered solutions and design patterns to avoid such problems. Results have shown that the problems have a fatal impact on the execution time, so that the performance gain on the multi-core system is nearly nonexistent. Thence, any software developer must have in-depth knowledge of the used hardware and software to benefit as much as possible from multi-core architectures.

Original languageEnglish
Title of host publication28th European Modeling and Simulation Symposium, EMSS 2016
EditorsAgostino G. Bruzzone, Emilio Jimenez, Loucas S. Louca, Lin Zhang, Francesco Longo
PublisherDIME UNIVERSITY OF GENOA
Pages256-262
Number of pages7
ISBN (Electronic)9788897999683
Publication statusPublished - 2016
Event28th European Modeling and Simulation Symposium, EMSS 2016 - Larnaca, Cyprus
Duration: 26 Sept 201628 Sept 2016

Publication series

Name28th European Modeling and Simulation Symposium, EMSS 2016

Conference

Conference28th European Modeling and Simulation Symposium, EMSS 2016
Country/TerritoryCyprus
CityLarnaca
Period26.09.201628.09.2016

Keywords

  • False sharing
  • Multi-core
  • Oversubscription
  • Parallel software
  • Performance analysis

Fingerprint

Dive into the research topics of 'Analysis and evaluation of performance issues of parallel software on multi-core processors'. Together they form a unique fingerprint.

Cite this