Task Assignment With Link Contention On Distributed Memory Systems
Download Task Assignment With Link Contention On Distributed Memory Systems full books in PDF, epub, and Kindle. Read online free Task Assignment With Link Contention On Distributed Memory Systems ebook anywhere anytime directly on your device. Fast Download speed and no annoying ads. We cannot guarantee that every ebooks is available!
Author | : Vibha A. Dixit-Radiya |
Publisher | : |
Total Pages | : 25 |
Release | : 1993 |
Genre | : Parallel programming (Computer science) |
ISBN | : |
Abstract: "Assignment of tasks of a parallel program onto processors of a distributed-memory architecture determines the completion time of the program. The problem is to determine an assignment which minimizes communication overhead leading to minimal completion time. This paper presents assignment heuristics by taking into account two major factors that determine interprocessor communication overhead, temporal link contention and unequal distances between processors on a given topology. We use a new Temporal Communication Graph (TCG) to model task graphs. Using this model, we identify communication steps that conflict both temporally and spatially. Further, this model is strong enough to identify critical communication edges which make the completion time longer. Assignment heuristics are developed to reduce contention on critical communication edges. An iterative heuristic derives optimal assignment by pair-wise exchanging of processors, involved with the critical communication edge, within d-hops. The goodness of our heuristics are verified through simulation experiments by applying them to random task graphs with a variety of topologies (hypercubes and meshes) using wormhole e-cube routing. The heuristics are general and can be applied to programs with regular/irregular communication and any host system exhibiting message transfer over minimal distance."
Author | : Vibha A. Dixit-Radiya |
Publisher | : |
Total Pages | : 22 |
Release | : 1993 |
Genre | : Multiprocessors |
ISBN | : |
Abstract: "Assignment of tasks of a parallel program onto processors of a distributed-memory system is critical to obtain minimal program completion time by minimizing communication overhead. Wormhole- routing switching technique, with various adaptive routing strategies, is increasingly becoming the trend to build scalable distributed-memory systems. This paper presents task assignment heuristics for such wormhole- routed systems and analyzes the effect of adaptive routing. A Temporal Communication Graph (TCG) is used to model task graphs and to identify communication steps that conflict both temporally and spatially. Heuristics are proposed to capture temporal link contention and derive optimal assignment in an iterative manner by pairwise exchanging of processors, associated with the critical communication edges, within d hops. The interplay between degree of routing adaptivity, topology, application characteristics, and optimal task assignment are studied through simulation experiments using random task graphs. The study indicates that even for systems supporting fully adaptive routing, optimal task assignment is necessary to reduce program completion time for communication bound applications. The proposed heuristics are general and can be applied to programs with regular/irregular communication and to any distributed-memory host system supporting message communication over minimal path."
Author | : Costas Halatsis |
Publisher | : Springer Science & Business Media |
Total Pages | : 860 |
Release | : 1994-06-08 |
Genre | : Computers |
ISBN | : 9783540581840 |
This volume presents the proceedings of the 5th International Conference Parallel Architectures and Languages Europe (PARLE '94), held in Athens, Greece in July 1994. PARLE is the main Europe-based event on parallel processing. Parallel processing is now well established within the high-performance computing technology and of stategic importance not only to the computer industry, but also for a wide range of applications affecting the whole economy. The 60 full papers and 24 poster presentations accepted for this proceedings were selected from some 200 submissions by the international program committee; they cover the whole field and give a timely state-of-the-art report on research and advanced applications in parallel computing.
Author | : Virginia Mary Lo |
Publisher | : |
Total Pages | : 150 |
Release | : 1983 |
Genre | : Electronic data processing |
ISBN | : |
Author | : Wesley W. Chu |
Publisher | : Artech House Publishers |
Total Pages | : 320 |
Release | : 1986 |
Genre | : Computers |
ISBN | : |
Author | : Ginnie Lo |
Publisher | : |
Total Pages | : |
Release | : 1983 |
Genre | : |
ISBN | : |
Author | : Michael H. Barton |
Publisher | : North Holland |
Total Pages | : 664 |
Release | : 1988 |
Genre | : Computers |
ISBN | : |
Author | : Scott Small |
Publisher | : |
Total Pages | : 58 |
Release | : 1985 |
Genre | : Electronic data processing |
ISBN | : |
Author | : Bashir M. Al-Hashimi |
Publisher | : IET |
Total Pages | : 940 |
Release | : 2006-01-31 |
Genre | : Technology & Engineering |
ISBN | : 0863415520 |
This book highlights both the key achievements of electronic systems design targeting SoC implementation style, and the future challenges presented by the continuing scaling of CMOS technology.
Author | : Oliver Sinnen |
Publisher | : John Wiley & Sons |
Total Pages | : 302 |
Release | : 2007-05-18 |
Genre | : Computers |
ISBN | : 0470121165 |
A new model for task scheduling that dramatically improves the efficiency of parallel systems Task scheduling for parallel systems can become a quagmire of heuristics, models, and methods that have been developed over the past decades. The author of this innovative text cuts through the confusion and complexity by presenting a consistent and comprehensive theoretical framework along with realistic parallel system models. These new models, based on an investigation of the concepts and principles underlying task scheduling, take into account heterogeneity, contention for communication resources, and the involvement of the processor in communications. For readers who may be new to task scheduling, the first chapters are essential. They serve as an excellent introduction to programming parallel systems, and they place task scheduling within the context of the program parallelization process. The author then reviews the basics of graph theory, discussing the major graph models used to represent parallel programs. Next, the author introduces his task scheduling framework. He carefully explains the theoretical background of this framework and provides several examples to enable readers to fully understand how it greatly simplifies and, at the same time, enhances the ability to schedule. The second half of the text examines both basic and advanced scheduling techniques, offering readers a thorough understanding of the principles underlying scheduling algorithms. The final two chapters address communication contention in scheduling and processor involvement in communications. Each chapter features exercises that help readers put their new skills into practice. An extensive bibliography leads to additional information for further research. Finally, the use of figures and examples helps readers better visualize and understand complex concepts and processes. Researchers and students in distributed and parallel computer systems will find that this text dramatically improves their ability to schedule tasks accurately and efficiently.