Verifying Memory Consistency Models for DSM System


Book Description

The parallelism of Distributed Shared Memory (DSM) system can be improved by data replication. A DSM system sends data from one node to another via a network. So for replication of data, maintenance of memory consistency is required. The maintenance of memory consistency can be done by a proper memory consistency model with the help of coherence protocol. Although a lot of research has been done for the maintenance of memory consistency using a consistency model, a specific memory model is not given in literature; but it has been taken randomly. However, in this paper, it is described in a unified framework. So this paper aims at analyzing some memory consistency models and finding the perfect model for DSM system architecture based on write-update coherence protocol.




Distributed Shared Memory Consistency Models


Book Description

This book talks about the Specification and Verification of Distributed Shared Memory Relaxed Consistency Models specifically Weak Consistency Models. For this, an abstract Distributed Shared Memory (DSM) has been designed and implemented using CADP (Construction and Analysis of Distributed Processes). In DSM, sequential consistency unnecessarily reduces the performance of the system because it does not allow reordering or pipelining the memory operations. Weak consistency allows the reordering of memory events and buffering or pipelining of memory accesses so weak consistency improves the performance of the DSM system. For any critical system, it is very important to develop methods that increase our confidence in the correctness of such systems. One such method for the correctness of critical systems is formal verification. For verification of the weak consistency model, the properties of weak consistency have been specified and verified on the Abstract DSM System using CADP Toolbox.




Automated Technology for Verification and Analysis


Book Description

This book constitutes the proceedings of the 12th International Symposium on Automated Technology for Verification and Analysis, ATVA 2014, held in Sydney, Australia, in November 2014. The 29 revised papers presented in this volume were carefully reviewed and selected from 76 submissions. They show current research on theoretical and practical aspects of automated analysis, verification and synthesis by providing an international forum for interaction among the researchers in academia and industry.




Comparative Study of Various Consistency Models in Distributed Shared Memory System


Book Description

Distributed Shared Memory (DSM) is a collection of nodes or clusters, each with its own memory connected by an interconnected network. The key issue in DSM is keeping the memory pages consistent. It refers to the degree of consistency that has to be maintained for the shared memory data. Maintaining perfect consistency is especially painful when the difference between the latency and/or throughput of memory accesses on the one hand, and the network connecting the machines on which these copies reside on the other, is big. The solution might be to accept less than perfect consistency as the price for better performance. This paper reviews various memory consistency models which are used in different DSM systems.




High Performance Computing Systems and Applications


Book Description

High Performance Computing Systems and Applications contains the fully refereed papers from the 13th Annual Symposium on High Performance Computing, held in Kingston, Canada, in June 1999. This book presents the latest research in HPC architectures, distributed and shared memory performance, algorithms and solvers, with special sessions on atmospheric science, computational chemistry and physics. High Performance Computing Systems and Applications is suitable as a secondary text for graduate level courses, and as a reference for researchers and practitioners in industry.







Application and Theory of Petri Nets 1998


Book Description

This volume contains the proceedings of the 19th annual International Conference on Application and Theory of Petri Nets. The aim of the Petri net conference is to create a forum for the dissemination of the latest results in the application and theory of Petri nets. It always takes place in the last week of June. Typically there are 150 - 200 participants. About one third of these come from industry while the rest are from universities and research institutions. The conferences and a number of other activities are coordinated by a steering committee with the following members: G. Balbo (Italy), J. Billington (Australia), G. DeMichelis(Italy),C. Girault(France),K. Jensen (Denmark), S. Kumagai (Japan), T. Murata (USA), C. A. Petri (Germany; honorary member), W. Reisig (Germany), G. Roucairol (France), G. Rozenberg (The Netherlands; chairman), M. Silva (Spain). The 19th conference has been organized for the rst time in Portugal, by the Department of Electrical Engineering of the Faculty of Sciences and Technology of the New University of Lisbon, together with the Center for Intelligent Robotics of UNINOVA. It takes place in Lisbon at the same time as EXPO’98, the last world exhibition of the 20th century.




Memory Consistency Models for Shared-Memory Multiprocessors


Book Description

We believe that the combined benefits in hardware and software will make relaxed models universal in future multiprocessors, as is already evidenced by their adoption in several commercial systems.