Logo
    • English
    • Ελληνικά
    • Deutsch
    • français
    • italiano
    • español
  • English 
    • English
    • Ελληνικά
    • Deutsch
    • français
    • italiano
    • español
  • Login
View Item 
  •   University of Thessaly Institutional Repository
  • Επιστημονικές Δημοσιεύσεις Μελών ΠΘ (ΕΔΠΘ)
  • Δημοσιεύσεις σε περιοδικά, συνέδρια, κεφάλαια βιβλίων κλπ.
  • View Item
  •   University of Thessaly Institutional Repository
  • Επιστημονικές Δημοσιεύσεις Μελών ΠΘ (ΕΔΠΘ)
  • Δημοσιεύσεις σε περιοδικά, συνέδρια, κεφάλαια βιβλίων κλπ.
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.
Institutional repository
All of DSpace
  • Communities & Collections
  • By Issue Date
  • Authors
  • Titles
  • Subjects

IRaaS: A cloud implementation of an interface relaxation method for the solution of PDEs

Thumbnail
Author
Korfiati A., Sfika N., Daloukas K., Alexakos C., Tsompanopoulou P., Likothanassis S.
Date
2015
Language
en
Keyword
Cloud computing
Computers
Engineering
Industrial engineering
Efficient allocations
Inherent parallelism
Interface relaxations
Management mechanisms
Memory requirements
Multi domains
PDEs
Scientific applications
Computer science
Newswood Limited
Metadata display
Abstract
The solution of composite Partial Differential Equations is an indispensable step in numerous scientific applications. However, this is a computationally and memory demanding process for large-scale differential equations. This is especially true for multidomain/multiphysics problems, which require application of an interface relaxation (IR) methodology on the common boundaries between domains. In this paper, we present IRaaS, a cloud-based environment for the solution of multidomain/multiphysics problems. IRaaS efficiently exploits the inherent parallelism found in the solution step for the individual subdomains, thus significantly reducing computational and memory requirements. At the same time, its efficient allocation and management mechanism allocates the optimal number of resources (virtual machines), based on the total number of resources available, as well as the size of the problems for solution.
URI
http://hdl.handle.net/11615/75133
Collections
  • Δημοσιεύσεις σε περιοδικά, συνέδρια, κεφάλαια βιβλίων κλπ. [19735]
htmlmap 

 

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister (MyDspace)
Help Contact
DepositionAboutHelpContact Us
Choose LanguageAll of DSpace
EnglishΕλληνικά
htmlmap