Showing papers on "Distributed algorithm published in 1976"
07 Jun 1976
TL;DR: Examples of how distributed processing techniques are being used are provided, with comments on the advantages and disadvantages of the distribution of processing and databases in the current state-of-the-art.
Abstract: Distributed information systems represent an increasingly important trend to computer users. Distributed processing is a technique for implementing a single logical set of processing functions across a number of physical devices, so that each performs some part of the total processing required. Distributed processing is often accompanied by the formation of a distributed database. A distributed database exists when the data elements stored at multiple locations are interrelated, or if a process (program execution) at one location requires access to data stored at another location. Examples of how these techniques are being used are provided, with comments on the advantages and disadvantages of the distribution of processing and databases in the current state-of-the-art.
37 citations
01 Jun 1976
TL;DR: In this paper, a distributed algorithm for constructing minimal spanning trees in computer-communication networks is presented, which can be executed concurrently and asynchronously by the different computers of the network.
Abstract: This paper presents a distributed algorithm for constructing minimal spanning trees in computer-communication networks. The algorithm can be executed concurrently and asynchronously by the different computers of the network. This algorithm is also suitable for constructing minimal spanning trees using a multiprocessor computer system. There are many reasons for constructing minimal spanning trees in computer-communication networks since minimal spanning tree routing is useful in distributed operating systems for performing broadcast, in adaptive routing algorithms for transmitting delay estimates, and in other networks like the Packet Radio Network.
35 citations
01 Jul 1976
TL;DR: The algorithm embodies distributed control and can function effectively in the presence of communication and data base site outages and the correctness of the algorithm is demonstrated and the cost of using it is analyzed.
Abstract: : A majority consensus algorithm which represents a new solution to the update synchronization problem for multiple copy data bases is presented. The algorithm embodies distributed control and can function effectively in the presence of communication and data base site outages. The correctness of the algorithm is demonstrated and the cost of using it is analyzed. Several examples that illustrate aspects of the algorithm operation are included in an appendix.
33 citations
TL;DR: A review of the hardware and software structures that can be utilized in designing distributed computing systems by enphasizing two major arguments: - the usefulness of such structures in order to realize systems based on mini and microcomputers and their related features.
16 citations
01 May 1976
TL;DR: A heuristic design procedure for hierarchical computer systems is described and an experimental interactive configurator for distributed computer system design is implemented in APL.
Abstract: A model of a distributed computer system for transaction processing is described. The system configuration problem is formulated as a problem of deciding transaction allocation, routing, processor allocation, and line allocation to satisfy certain performance requirements and design constraints. A heuristic design procedure for hierarchical computer systems is described. Based upon this design procedure, an experimental interactive configurator for distributed computer system design is implemented in APL. Topics for further investigation are discussed.
14 citations
2 citations
09 Aug 1976
TL;DR: The transparency concept and some others currently being investigated may help to build efficient distributed architectures that may have to be run on distributed architectures.
Abstract: In this paper, synchronization and communication tools designed to operate in a distributed environment have been described. Good insight into their behavior has been made possible through simulation studies. Future Operating Systems may have to be run on distributed architectures and may need to include that kind of mechanisms. Moreover, another class of problems has been reported which deal with the internal control and the non-centralized allocation of resources into such distributed systems. The transparency concept and some others currently being investigated may help to build efficient distributed architectures.
1 citations
13 Oct 1976
TL;DR: This paper is an attempt to categorize distributed systems so that one can examine the generic characteristics and problems associated with each category.
Abstract: Phrases such as 'distributed processing' and 'distributed operating systems' are currently very much in vogue and are being applied to many systems that seem to be entirely different in nature. What used to be a system with a separate Input-Output channel or a multiprocessor system or a network without load balancing is now a distributed system. The common feature seems to be a multiplicity; i. e., more than one, of clearly distinguishable modules, as determined by the beholder, operating simultaneously. This paper is an attempt to categorize distributed systems so that one can examine the generic characteristics and problems associated with each category.The first step is to realize that distribution involves the apportioning of a set of tasks among a set of entities that can perform the tasks.
1 citations
01 Jan 1976
TL;DR: In this paper a formal model of process coordination in distributed computer systems is introduced and deadlock conditions, that can arise owing to message-transfer activity, are analized and a procedure for statically detect if a system is deadlock free is given.
Abstract: In this paper a formal model of process coordination in distributed computer systems is introduced. Properties of a message-transfer mechanism are analized from a graph theoretical viewpoint. In particular deadlock conditions, that can arise owing to message-transfer activity, are analized and a procedure for statically detect if a system is deadlock free is given. Optimal message-buffer dimensions are determined with respect to the system computational speed and to the message-buffer cost.