Document Actions
Featured Joint Conferences Tutorial
| Heterogeneous Parallel and Distributed Computing: Model, Resource Management, and Robustness
Prof. H. J. Siegel, Colorado State University, USA Date: June 27, 2006 Time: 6:00 - 9:30 PM Room: 1 |
ABSTRACT
In heterogeneous parallel and distributed computing environments, a network of different machines is interconnected and provides a variety of computational capabilities. These capabilities can be used to execute a collection of different types of applications, each of which may consist of multiple tasks, where the tasks have diverse computational requirements. The execution times of a task may vary from one machine to the next, and tasks must share the computing and communication resources of the system. Furthermore, there can be inter-task data dependencies.
An important research problem for heterogeneous computing is how to assign tasks to machines and schedule the order of their execution to maximize some given performance criterion. Factors that must be considered include machine and network loading, how well the execution needs of a task match the computational capabilities of a machine, any inter-task communications, and the performance criterion to be optimized. Example resource management heuristics for assigning and scheduling tasks in different types of heterogeneous computing environments will be presented. Methods for evaluating and comparing heuristics will be demonstrated.
The issue of robust resource allocations will be explored. Allocation decisions and associated performance prediction are often based on estimated values of task and system parameters. The actual values of these parameters may differ from the estimates; for example, the estimates may represent only average values, the models used to generate the estimates may have limited accuracy, and there may be changes in the environment. To address this problem, we have designed a technique for deriving the degree of robustness of a resource allocation — the maximum amount of collective uncertainty in system parameters within which a user-specified level of system performance (QoS) can be guaranteed. The technique, its significance, and its use in resource allocation heuristics will be examined.
Open problems in the field of heterogeneous parallel and distributed computing will be discussed. “Alligators” that make heterogeneous computing challenging will be shown. The tutorial material is applicable to various types of heterogeneous computing and communication environments, including parallel, distributed, cluster, grid, Internet, embedded, and wireless.
OBJECTIVES
-
This course will enable you to:
Understand the potential advantages of using heterogeneous parallel and distributed computing systems
Analyze some of the factors that must be considered when designing resource management systems for heterogeneous environments
Be familiar with a variety of resource management techniques for assigning tasks to machines and scheduling their execution to optimize some performance criterion
Determine how to evaluate the potential performance of a heterogeneous computing system for a particular workload environment
Examine the robustness of a resource allocation and incorporate robustness into the design of resource management heuristics
Be aware of the open research problems in heterogeneous computing that are important areas for future research and development
This course is intended for faculty, engineers, scientists, and graduate students who want an introduction to the use of heterogeneous suites of computers (including clusters and certain types of grids) to execute applications in a way that will optimize some performance criterion.
H. J. Siegel is the George T. Abell Endowed Chair Distinguished Professor of Electrical and Computer Engineering at Colorado State University (CSU), where he is also a Professor of Computer Science. He is the Director of the CSU Information Science and Technology Center (ISTeC), a university-wide organization for promoting, facilitating, and enhancing CSU’s research, education, and outreach activities pertaining to the design and innovative application of computer, communication, and information systems. From 1976 to 2001, he was a professor in the School of Electrical and Computer Engineering at Purdue University. He received two B.S. degrees from the Massachusetts Institute of Technology (MIT), and the M.A., M.S.E., and Ph.D. degrees from Princeton University. He is a Fellow of the IEEE and a Fellow of the ACM. Prof. Siegel has co-authored over 300 published technical papers in the areas of parallel and distributed computing and communications. He was a Coeditor-in-Chief of the Journal of Parallel and Distributed Computing, and was on the Editorial Boards of the IEEE Transactions on Parallel and Distributed Systems and the IEEE Transactions on Computers.
Professor H. J. Siegel
Department of Electrical and Computer Engineering and Department of Computer Science
Colorado State University
Fort Collins, CO 80523-1373
Office: (970) 491-7982
Fax: (970) 491-2249
E-mail: hj@colostate.edu
www.engr.colostate.edu/~hj
