Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications最新文献

{"title":"Recursively scalable fat-trees as interconnection networks","authors":"M. Valerio, L. Moser, P. Melliar-Smith","doi":"10.1109/PCCC.1994.504091","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504091","url":null,"abstract":"We introduce orthogonal fat-trees as a type of interconnection network for parallel computers, and show how they can be used to maximize the number of processors in a massively parallel computer when the degree of the internal nodes and the diameter of the network are physically constrained. The basic building block of these orthogonal fat-trees is a two-level fat-tree that is obtained from a complete set of mutually orthogonal Latin Squares. As a practical application of orthogonal fat-trees, we propose a new interconnection network for a massively parallel computer based on the QROOOl Data Stream Controller Interface, an integrated circuit produced by National Semiconductor, which can sustain a throughput of up to 180 MBytes/sec. The network consists of multiple interconnected rings and is constrained to have at most 16 nodes per ring and a maximum diameter of four. Our solution yields a maximum of 51,984 processors.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134025100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parallel Program Visualisation for a Message-Passing System","authors":"Gaurav Marwaha, Kang Zhang","doi":"10.1109/PCCC.1994.504115","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504115","url":null,"abstract":"Designing parallel programs for message-passing systems is not an easy task. Difficulties arise largely due to human limitations in identifying relationships between simultaneously executed program components, or processes, and between the data computed by these processes. This paper presents a parallel program visualisation tool, Visputer, that provides the ability to graphically design and edit messagepassing programs, configure parallel processes onto a multiprocessor network and visualise the execution of programs. The textual versions of programs and network configurations are automatically generated by Visputer based on program and network graphs. Animation of program execution is achieved by instrumenting the original program with event collecting code. The event collecting method maintains program behaviour and imposes little performance impact on he original program. views. Wagner et al. developed an environment, known as TIPS [18], which integrates a performance monitoring tool, a process to processor mapping tool, a graphical interface and the capability to analyse the resource requirements of an application. The visual abstraction method proposed by Ritchie [13] attempts to capture the major characteristics of the Occam language. It is, however, more textual than graphical. Zernik et al. evaluated a visualisation methodology using causality graphs to replay interprocess communication and process creation on a network of 256 transputers [19]. This paper presents Visputer, a visualisation tool for developing Occam programs. Section 2 briefly describes an overview of Visputer. Section 3 presents the visual abstraction methods for Occam program construction and for network configuration, followed by a description of the visualisation methods for the execution behaviour in Section 4. Section 5 covers the instrumentation techniques used.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134602294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IF1-Viewer : A Visual Tool for Graphical Display and Execution of SISAL Programs","authors":"Hsing-bung Chen, B. Shirazi, S. Thrane, J. Marquis","doi":"10.1109/PCCC.1994.504116","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504116","url":null,"abstract":"Efficient visualization tools to explore the internal hierarchical task structures of parallel programs have gained a prominent role in the parallel programming community. As such, the IF1 -Viewer is a visual, graphical parallel programming tool developed to aid in the understanding and interpretation of SISAL and IF1 programs. IF1-Viewer consists of two sub-tools: the IF1-Grapher and the IF1-Interpreter. The IF1-Grapher graphically displays the hierarchical directed acyclic task graphs of the IF1 code and the IF1Interpreter visually shows the execution behavior the IF1 code. IF1 ( Intermediate Form) is a machine independent graphical language generated from the SISALS compiler. The IF1-Viewer is a generalpurpose parallel software and with the aid of graphical interfaces, provides a unique way to assist programmers in (1) gaining insight into internal task structures of application programs, (2) alleviating the shortcomings in parallel program implementation, (3) detecting the degree of parallelism in the applications, and (4) understanding the parallel program executing behaviors.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115902630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance & Reliability Oriented Combined File, Capacity Allocation on Distributed Systems","authors":"A. Kumar, S. Ahuja","doi":"10.1109/PCCC.1994.504127","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504127","url":null,"abstract":"Distributed Computing Systems (DCSs) have the potential for high reliability. When the topology of a DCS is fixed, the DCS reliability depends mainly on the allocation of various resources. One of the important resources to be allocated on a DCS are various files. Another problem of significance deals with the allocation of capacities to the links of a DCS such that the performance (throughput) is maximized and a cost constraint is satisfied. In this paper, we have developed a performance based reliability oriented file and capacity allocation scheme for distributed systems. In this scheme capacities are allocated to the links of the DCS and the files are allocated to the nodes of the DCS such that the overall effectiveness of executing a program which requires files from remote node(s) is maximized. A Genetic Algorithm (GA) based approach is used to solve this problem. The effectiveness of the GA based approach is demonstrated by comparing the results with the results obtained using exhaustive search of the problem state space. The paper also studies the impact of the Probability of Crossover (Pc) and the Probability of Mutation (Pm) on the results obtained using the GA. 1. The File and Capacity Allocation Problem The reliability of executing various applications (programs) in a Distributed Computing System (DCS) depends on the topology of the DCS, the program locations, and the allocation of files on the DCS [l]. The system reliability can also be improved by introducing redundancy in the system [2,3]. If the topology of a DCS is fixed then the overall reliability of executing various applications depends mainly on the file allocation on the DCS [2]. If there are n processing nodes and m data files in the DCS, then the total number of possible assignments are nm. Thus the optimal allocation of files on the processing nodes is a problem of exponential complexity [2]. The file allocation problem is formulated in terms of cost factors and constraints, the objective being to allocate files such that the cost factor@) are minimized/maximized and all the constraints are satisfied [2]/ The cost factor(s) are represented by a cost funciton. The nature of a cost function and the constraints is problem dependent. For example, system reliability or htroughoput are important in communication networks, while response time is extremely important in real time systems. *This research is in part supported by the President’s Grant at the University of Louisville. 0-7803-1814-5194 $4.00 @ 1994 IEEE Sanjay P. Ahuja Department of Mathematical Sciences SUNY at Oneonta Oneonta, NY 13820 Conventional measures such as TR [4], survivability index [5], and computer network reliability (CNR) [6] compute fault tolerance of a DCS from a network component failure point of view only. The effect of file distribution on the DCS reliability is ignored. The parameters Distri-buted Program Reliability (DPR) [7] and Distributed System Reliability (DSR) [7] take into account the eff","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"05 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123275505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using Business Process Reengineering to Develop Information Service Project Plans","authors":"S. Passer","doi":"10.1109/PCCC.1994.504113","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504113","url":null,"abstract":"With the onslaught of Business Process Reengineering (BPR), an opportunity exists to improve the information system capabilities of corporations undertaking the reengineering effort with little change to the general techniques of BPR. A methodology is being outlined here to suggest a way to revamp the Information Service (IS) systems planning function, benejit from both the existing technology base and the legacy of sofware and hardware, plus strategize the future technology direction in IS . This, then, is a framework for augmenting general BPR techniques with little change to BPR methods, strategy or cost to develop a prioritized strategic plan for deployment of IS data assets","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121689138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Suspended Transition Paradigm within Complex Distributed Systems","authors":"N. Dowuona, L. E. Heindel","doi":"10.1109/PCCC.1994.504110","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504110","url":null,"abstract":"Development of distributed transaction promsing systems has emphasized issues of transaction consistency, synchronization, rollback and recovery. Comparatively little focus has been placed on humdtransaction interactions. In this paper, we introduce a new transaction paradigm, the Suspended Transaction Paradigm, that gracefully supports participation of humans in complex distributed systems, and presents a new way of viewing the role of the human in a complex distributed system. We also discuss how the suspended transaction paradigm could be used as a technique for gradually replacing the human expert with an embedded or external expert system within transaction processing systems. We conclude with several examples of the use of the suspended transaction paradigm in the context of automated Telecommunications Provisioning Systems.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122376665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimedia Collaborative Remote Consultation Tools via Gigabit Wide Area Networks in Teleradiology","authors":"W. Chimiak, R. Martinez","doi":"10.1109/PCCC.1994.504147","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504147","url":null,"abstract":"Many rural hospitals would like continuous coverage for radiology services. Some of these hospitals are, in fact, without a radiologist. This shortcoming can be addressed by developing a diagnostic-quality, cost-effective system for teleradiolgy. As deployment of wide area and local asynchronous transfer mode (ATM) networks continues, workstation performance accelerates and costs decrease, the availability of teleradiology systems becomes limited by upper-layer protocols, disk speed and the dynamic range of computer displays. If data base functionality of a picture archive and communications system (PACS) are ignored, teleradiology is becoming a reality. This paper deals with extending a University of Arizona teleradiolgy and teleconsultation application to the widest possible area by using high-performance-satellite communications and traditional telephone service.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128200852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance study of distributed rule evaluation algorithm in distributed active databases","authors":"I. Hsu, M. Singhal, M. Liu","doi":"10.1109/PCCC.1994.504089","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504089","url":null,"abstract":"Processing rules in a distributed active database involves evaluating distributed rules correctly. For databases whose rules are not changed very often, the performance of the distributed rule evaluation algorithm plays the key role in the overall performance of distributed active databases. In this paper, we study the performance of a distributed rule evaluation algorithm. An analytical model is developed to study the message count and the response time for triggering updates, which toggle the global status of a rule condition. Simulation results confirm the analytical data. Moreover, simulations are used to derive the total message count for the operation of this algorithm considering any updates which may or may not change the global status of a rule condition. Results from performance study suggest best ways to distribute a decomposed rule.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134631447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multicast protocol for high speed local area networks","authors":"I. E. Mbarki, J. Metzner","doi":"10.1109/PCCC.1994.504137","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504137","url":null,"abstract":"High speed local area networks encompass the new network generation based on fiber technology. Multicasting is common in computer communications and introduces several specific issues. Among them is the implosion problem which can severely degrade the network performance if no appropriate steps are taken. A protocol which reduces the implosion problem is presented. It is partially based on a negative acknowledgment policy. It responds to the needs of HSLN by being simple and not requiring out of bandwidth messages to coordinate among the destinations. The results show a large reduction of the implosion problem and hence improvement of overall network utilization.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132159066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative performance study of neural network paradigms for identifying computer users","authors":"M. Obaidat","doi":"10.1109/PCCC.1994.504108","DOIUrl":"https://doi.org/10.1109/PCCC.1994.504108","url":null,"abstract":"This paper presents a neural network system for identifying computer users. A comparative evaluation study of three neural networks paradigms as applied to the identification of computer users using keystroke intervals when typing a well known phrase is made. The input vectors were made up of the time intervals between successive keystrokes created by users while typing characters. Each input vector was classified into one of several classes, thereby identifying the user who typed the phrase. We investigated and compared the performance of the neural network paradigms as applied to this problem. These paradigms are: Adaptive Resonance Theory-2, (ART-2), Back Propagation, and Counterpropagation. The identification technique presented here is accurate, practical and novel.","PeriodicalId":203232,"journal":{"name":"Proceeding of 13th IEEE Annual International Phoenix Conference on Computers and Communications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128789898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}