Customized message passing and scheduling for parallel and distributed applications
Islam, Nayeem
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/23636
Description
Title
Customized message passing and scheduling for parallel and distributed applications
Author(s)
Islam, Nayeem
Issue Date
1994
Doctoral Committee Chair(s)
Campbell, Roy H.
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Computer Science
Language
eng
Abstract
Replacing traditional operating systems communication and scheduling implementations with customized implementations increases the performance of parallel and distributed applications. In this thesis, I discuss the design and implementation of customizable message passing and scheduling systems. Both the message passing and scheduling systems have been implemented on a bus-based shared-memory multiprocessor and a distributed system.
The customized systems are generated using application-specific information such as the profile of an application's communication pattern. I use FFT, Simplex, Cholesky and adaptive quadrature as example parallel applications. The customized systems improve the execution times and scalability of these applications.
The message passing system has also been customized for different types of distributed system services including a nameservice and a distributed scheduling facility. The customized message passing system likewise improves the performance of these facilities and enhances their scalability.
Similarly, the scheduling system can be customized to provide support for particular types of applications. This thesis describes results from a novel implementation of distributed gang scheduling for running parallel applications on distributed systems.
As a practical concern, as there are a large number of possible optimizations, object-oriented frameworks are employed to organize the implementations and to facilitate the choice of optimizations. Object-oriented frameworks allow the easy porting of the message passing system code, allow easy incremental development of optimizations and, lastly, allow easy experimentation.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
