Fan Li, Jinyuan Chen, Zhiying Wang · 2018
Motivated by mobile edge computing and wireless data centers, we study a wireless distributed computing framework where the distributed nodes exchange information over a wireless interference network. Our framework follows the structure of MapReduce. This framework consists of Map, Shuffle, and Reduce phases, where Map and Reduce are computation phases and Shuffle is a data transmission phase. In our setting, we assume that the transmission is operated over a wireless interference network. We demonstrate that, by duplicating the computation work at a cluster of distributed nodes in the Map phase, one can reduce the amount of transmission load required for the Shuffle phase. In this work, we characterize the fundamental tradeoff between computation load and communication load, under the assumption of one-shot linear schemes. The proposed scheme is based on side information cancellation and zero-forcing, and we prove that it is optimal in terms of computation-communication tradeoff. The proposed scheme outperforms the naive TDMA scheme with single node transmission at a time, as well as the coded TDMA scheme that allows coding across data, in terms of the computation-communication tradeoff.
Cited by 19
Jennifer L. Welch · ACM SIGACT News · 2014
No abstract available.
Cited by 0
Sergio Rajsbaum · ACM SIGACT News · 2004
No abstract available.
Cited by 0
Joan Feigenbaum, Michael Merritt · DIMACS series in discrete mathematics and theoretical computer science · 1991
Cited by 39
David Whalley · 2005
No abstract available.
Cited by 0
Salim Hariri, Dongmin Kim, Chongam Kim et al. · 2000
Abstract : The next generation of network-centric applications will utilize a large number of computing and storage systems that are connected by global high speed networks. We refer to the environment that provides transparent computing and communication services for large scale parallel and distributed applications as Metacomputing environment. In this report, we present the design and the experimental results with the Virtual Distribute Computing Environment (VDCE) and the Adaptive Distributed Virtual Computing Environment (ADViCE) being developed at the University of Arizona and Syracuse University.
Cited by 1
Vassil Furnadjiev · Scholar Electronic Repository of the New Bulgarian University (New Bulgarian University) · 2011
After a short overview of the most known ideas about the distributed computing as clustering and grids, the paper describes a new approach for it. The application programs are presented with their structure, called skeleton. The skeleton is sent throughout the network to find the “volunteers” for the execution of the different components of the program. \n
Cited by 0
Sergio Rajsbaum November, Sergio Rajsbaum · 2007
The Distributed Computing Column covers the theory of systems that are composed of a number of interacting computing elements. These include problems of communication and networking, databases, distributed shared memory, multiprocessor architectures, operating systems, veri cation, internet, and the web.
Cited by 0
Nicolas Nisse, Ivan Rapaport, Karol Suchan · 2012
Efficient algorithms for computing routing tables should take advantage of the particular properties arising in large scale networks. There are in fact at least two properties that any routing scheme must consider: low (logarithmic) diameter and high clustering coefficient. High clustering coefficient implies the existence of few large induced cycles. Therefore, we propose a routing scheme that computes short routes in the class of k-chordal graphs, i.e., graphs with no chordless cycles of length more than k. We study the tradeoff between the length of routes and the time complexity for computing them. In the class of k-chordal graphs, our routing scheme achieves an additive stretch of at most k − 1, i.e., for all pairs of nodes, the length of the route never exceeds their distance plus k − 1. In order to compute the routing tables of any n-node graph with diameter D we propose a distributed algorithm which uses O(log n)-bit messages and takes O(D) time. We then propose a slightly modified version of the algorithm for computing routing tables in time O(min{∆D, n}), where ∆ is the the maximum degree of the graph. Using these tables, our routing scheme achieves a better additive stretch of 1 in chordal graphs (notice that chordal graphs are 3-chordal graphs). The routing scheme uses addresses of size log n bits and local memory of size 2(d − 1)log n bits in a node of degree d.
Cited by 0
Jiří Karel Novák · Digital Repository (National Repository of Grey Literature) · 2009
This thesis is about solving problems using systems for distributed computing. In the beginning, it provides the reader brief introduction to the area of systems for distributed computing and introduces some of the existing systems. Further there is a proposal of a new distributed computing system. Design of this system is described thoroughly including the processes, network connections and messages which are used for communication between the processes. The system is then compared to existing implementations. Advantages and disadvantages are discussed. At the end there are some ideas how the system can be improved in the future.
Cited by 0
Past Year Exam Question, · Andalas University Repository (Andalas University) · 2013
Cited by 0Open access
Past Year Exam Question, · HRB National Drugs Library (Health Research Board) · 2012
Cited by 0
Barbara Sımons · Lecture notes in computer science · 1990
Cited by 62
David J. Kuck · 1985
Multiprocessor supercomputers and distributed systems share many common properties in a logical sense. The physical implementation of these systems may be quite different, particularly with respect to timing considerations. Some of the recent work on supercomputer hardware and software may be of use in the distributed processing community. We discuss some aspects of how to relate program and data structures to architectural models.
Cited by 1
Hirozumi Yamaguchi, Khaled El-fakih, Gregor Von Bochmann et al. · 2008
(will be inserted by the editor) Protocol synthesis and re-synthesis with optimal allocation of resources based on extended Petri nets
Cited by 0
Ling Jia · 2000
This paper introduces the Parallel Virtual Machine (PVM) system which supports the distributed computation.PVM can implement parallel processing by using the present computer network.It not only makes full use of network resources,but also provides a powerful parallel processing tool for many ordinary users
Cited by 0
E. Luppi · 2020
Cited by 11
Michael F. Goodchild, Douglas M. Johnston, David Maguire et al. · 2004
This chapter addresses the nature of computing, proposing that it is best understood as a form of communication. It reviews the history of computing from a locational perspective, and the changes that have led to substantial Itinerant, distributed, and ubiquitous computing (IDU) capabilities. The chapter discusses the technologies of IDU computing, including hardware, software, and communications and examines IDU computing within an economic framework, to address questions of costs and benefits. It focuses on distributed computing from the perspectives of libraries and central facilities location theory, in an effort to cast IDU computing within the framework of traditional arrangements for the production and dissemination of information. The chapter also focuses on locational history has already hinted at how the location of computing might be placed within an economic framework. It argues that theme, and presents a basis for research on the costs, benefits, and economic value of distributed and mobile computing.
Cited by 3
Eth Zürich · 2003
Cited by 0
Dyalog Apl, Andreas Geyer-schulz, T. Kolarik · 1992
Recent market surveys quote UNIX as the operating system of the 1990s and as the computer industry 's fastest growing market segment. In the next few years we expect the emergence of large UNIX-based workstation networks in both universities and industry. In these rapidly growing environments we envision distributed super-computing on off-the-shelf hardware as an economic alternative to special hardware based technologies. By distributed super-computing we mean treating a network of workstations as a loosely coupled multi-processor system. For fast prototyping and debugging of distributed applications we suggest APL as the language of choice. We base our vision of distributed super-computing on APL's familiar shared variable construct which has been extended to allow for distributed, mixed-language applications in large, heterogenous computer networks. With the help of shared variables we implement several other distributed programming constructs, namely message-passing, clientserver n...
Cited by 0