Numerical methods and programming
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Num. Meth. Prog.:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Numerical methods and programming, 2014, Volume 15, Issue 4, Pages 697–711 (Mi vmp285)  

An approach to the comparison of parallel program scalability

A. M. Teplov

M.V. Lomonosov Moscow State University, Research Computing Center
Abstract: An approach to the scalability analysis of parallel programs is proposed. The introduced definition of scalability allows one to take into account the effect of startup parameters on the program execution quality. A concept of the scalability metric and scalability mark for parallel programs is also introduced. An approach to the comparison of parallel program scalability based on the use of the scalability mark as a part of the parallel program scalability metric is described. Some comparative results of scalability study using this approach are discussed by several examples of parallel programs.
Keywords: scalability, parallel computing, scalability analysis, comparison of scalability, scalability metrics, scalability mark, efficiency of parallel programs.
Received: 02.11.2014
Document Type: Article
UDC: 004.021
Language: Russian
Citation: A. M. Teplov, “An approach to the comparison of parallel program scalability”, Num. Meth. Prog., 15:4 (2014), 697–711
Citation in format AMSBIB
\Bibitem{Tep14}
\by A.~M.~Teplov
\paper An approach to the comparison of parallel program scalability
\jour Num. Meth. Prog.
\yr 2014
\vol 15
\issue 4
\pages 697--711
\mathnet{http://mi.mathnet.ru/vmp285}
Linking options:
  • https://www.mathnet.ru/eng/vmp285
  • https://www.mathnet.ru/eng/vmp/v15/i4/p697
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Numerical methods and programming
    Statistics & downloads:
    Abstract page:158
    Full-text PDF :69
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024