Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200552
C. Lee, H. Lam, S. Su
The design and implementation of a database computer architecture performance evaluation system (DACPES) are presented. DACPES is a simulation tool which can be configured to evaluate a class of parallel database computers (DBCs), which have shared-nothing architectures, use data flow query processing strategies, and support object-oriented databases. DACPES can be used to simulate concurrent multiple query processing in a parallel DBC under varying conditions. The functions and design issues for each of the modules of DACPES are discussed and a case study of the evaluation of an object flow computer using DACPES is presented.<>
{"title":"A Database Computer Architectures Performance Evaluation System (DACPES)","authors":"C. Lee, H. Lam, S. Su","doi":"10.1109/PCCC.1992.200552","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200552","url":null,"abstract":"The design and implementation of a database computer architecture performance evaluation system (DACPES) are presented. DACPES is a simulation tool which can be configured to evaluate a class of parallel database computers (DBCs), which have shared-nothing architectures, use data flow query processing strategies, and support object-oriented databases. DACPES can be used to simulate concurrent multiple query processing in a parallel DBC under varying conditions. The functions and design issues for each of the modules of DACPES are discussed and a case study of the evaluation of an object flow computer using DACPES is presented.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115695831","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200534
J. Liu, W. Hsu
Distributed routing and broadcasting algorithms for the Fibonacci cube are presented. The routing algorithm is shown to find shortest and deadlock-free paths. Two communication models are considered for the broadcasting. It is shown that the all-port broadcasting algorithm is optimal in terms of minimized routing steps. An upper bound is obtained for the one-port broadcasting algorithm, which is shown to be optimal for certain cases. The time complexities of the all- and one-port broadcasting algorithms are examined.<>
{"title":"Distributed algorithms for shortest-path, deadlock-free routing and broadcasting in Fibonacci cubes","authors":"J. Liu, W. Hsu","doi":"10.1109/PCCC.1992.200534","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200534","url":null,"abstract":"Distributed routing and broadcasting algorithms for the Fibonacci cube are presented. The routing algorithm is shown to find shortest and deadlock-free paths. Two communication models are considered for the broadcasting. It is shown that the all-port broadcasting algorithm is optimal in terms of minimized routing steps. An upper bound is obtained for the one-port broadcasting algorithm, which is shown to be optimal for certain cases. The time complexities of the all- and one-port broadcasting algorithms are examined.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124413379","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200508
G. Mansfield, M. Murata, K. Higuchi, K. Jayanthi, B. Chakraborty, Y. Nemoto, S. Noguchi
The authors examine the design issues of a practical network management system using the simple network management protocol (SNMP) in the context of a large-scale open systems interconnection (OSI)-based campus-network called TAINS. Various design aspects are examined and the importance of time-management is examined. In the proposed design, intelligent, time-synchronized agents are deployed to collect information about the network segments to which they are attached. The manager talks to the agents and gathers relevant network information. This information is used by the expert network manager, in conjunction with a network knowledge base, to reconstruct the overall network-traffic characteristic, to evaluate the status of the network and to take/suggest some action. The introduction of time-labeled composite objects in the MIB provides a means of reducing the load of management-related traffic on the network.<>
{"title":"An SNMP-based expert network management system for a large-scale OSI-based campus network","authors":"G. Mansfield, M. Murata, K. Higuchi, K. Jayanthi, B. Chakraborty, Y. Nemoto, S. Noguchi","doi":"10.1109/PCCC.1992.200508","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200508","url":null,"abstract":"The authors examine the design issues of a practical network management system using the simple network management protocol (SNMP) in the context of a large-scale open systems interconnection (OSI)-based campus-network called TAINS. Various design aspects are examined and the importance of time-management is examined. In the proposed design, intelligent, time-synchronized agents are deployed to collect information about the network segments to which they are attached. The manager talks to the agents and gathers relevant network information. This information is used by the expert network manager, in conjunction with a network knowledge base, to reconstruct the overall network-traffic characteristic, to evaluate the status of the network and to take/suggest some action. The introduction of time-labeled composite objects in the MIB provides a means of reducing the load of management-related traffic on the network.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122124689","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200564
K. Wakai, J. Li, T. Komastu, H. Ikeda, J.I. Satoh
The authors describe a new system for multiplexing digital codes onto the AM radio signal at medium wave frequency, and also analyze the interference of the digital codes with the AM radio signal. This type of phase shift keying (PSK) system was actualized by using the phase modulation of a narrowband phase shift. The phase modulation of the narrowband phase shift suppressed the required spectrum band energy under 10 dB compared with that in the normal BPSK the QPSK system and the interference of the PSK signal with the AM signal was improved by approximately 15 dB compared with that in the normal BPSK or QPSK system. The experimental results agree with the results of the computer simulation. Up to 99% of the transmitted signal energy was designed to fall into a bandwidth of +or-7.5 kHz around a center frequency of 1 MHz when the system was operated at a data rate of 1200 b/s or 2400 b/s, when the total angle of phase shift was 90 degrees in 2 phi PSK and when the total angle of phase shift was 150 degrees at 4 phi PSK.<>
{"title":"Digital code transmission with medium wave AM radio transmitter","authors":"K. Wakai, J. Li, T. Komastu, H. Ikeda, J.I. Satoh","doi":"10.1109/PCCC.1992.200564","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200564","url":null,"abstract":"The authors describe a new system for multiplexing digital codes onto the AM radio signal at medium wave frequency, and also analyze the interference of the digital codes with the AM radio signal. This type of phase shift keying (PSK) system was actualized by using the phase modulation of a narrowband phase shift. The phase modulation of the narrowband phase shift suppressed the required spectrum band energy under 10 dB compared with that in the normal BPSK the QPSK system and the interference of the PSK signal with the AM signal was improved by approximately 15 dB compared with that in the normal BPSK or QPSK system. The experimental results agree with the results of the computer simulation. Up to 99% of the transmitted signal energy was designed to fall into a bandwidth of +or-7.5 kHz around a center frequency of 1 MHz when the system was operated at a data rate of 1200 b/s or 2400 b/s, when the total angle of phase shift was 90 degrees in 2 phi PSK and when the total angle of phase shift was 150 degrees at 4 phi PSK.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123968588","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200537
M. Hu, R. Ammar
The time costs of several parallel computation structures are analyzed. These analyses are based on assumptions that the processes communicate implicitly via the shared memory and that a locking mechanism is imposed on the access to shared variables. In previous work, an approach to estimating a set of special parallel computation structures has been developed. The authors expand this approach and propose a new technique for covering more general parallel computation structures.<>
{"title":"Time cost analysis of parallel structures with multi-communication nodes in a shared memory","authors":"M. Hu, R. Ammar","doi":"10.1109/PCCC.1992.200537","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200537","url":null,"abstract":"The time costs of several parallel computation structures are analyzed. These analyses are based on assumptions that the processes communicate implicitly via the shared memory and that a locking mechanism is imposed on the access to shared variables. In previous work, an approach to estimating a set of special parallel computation structures has been developed. The authors expand this approach and propose a new technique for covering more general parallel computation structures.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125021875","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200588
Thou-Ho Chen, Liang-Gee Chen, Yeu-Shen Jehng
An alternative fault-tolerant design in VLSI-based arithmetic arrays using the partitioning technique is presented. The basic concept is that the arithmetic array can be divided into m parts and its operation can be completed through m iterative calculations with some one part. By taking three such parts with a majority-voting technique at each iteration, error correction can be achieved through m-step computations. This leads to the same fault tolerance capability as triple modular redundancy (TMR). The overheads of chip area and operation time are only introduced by multiplexers, latches, and voters and can be reduced by selecting an appropriate value of m. Based on the AT/sup 2/ (where A is the chip area and T is the operation time) measure of VLSI performance, the proposed design is shown to be superior to the general TMR method. Some application-specified tradeoffs between speed performance and area cost are also presented.<>
{"title":"A partitioning approach to design fault-tolerant arithmetic arrays","authors":"Thou-Ho Chen, Liang-Gee Chen, Yeu-Shen Jehng","doi":"10.1109/PCCC.1992.200588","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200588","url":null,"abstract":"An alternative fault-tolerant design in VLSI-based arithmetic arrays using the partitioning technique is presented. The basic concept is that the arithmetic array can be divided into m parts and its operation can be completed through m iterative calculations with some one part. By taking three such parts with a majority-voting technique at each iteration, error correction can be achieved through m-step computations. This leads to the same fault tolerance capability as triple modular redundancy (TMR). The overheads of chip area and operation time are only introduced by multiplexers, latches, and voters and can be reduced by selecting an appropriate value of m. Based on the AT/sup 2/ (where A is the chip area and T is the operation time) measure of VLSI performance, the proposed design is shown to be superior to the general TMR method. Some application-specified tradeoffs between speed performance and area cost are also presented.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129453062","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200511
P. J. Zievers, C. Wu
An architecture for tightly coupled network computing is presented. The system was created to provide a scalable processing environment for computationally intensive applications. The system consists of a digital data switch surrounded by computing elements. The switch is composed of a back-to-back baseline multistage interconnection network, plus the ISDN protocol suite with an asynchronous transfer mode (ATM) sublayer. The key to the sources of the Star network computer is the cooperation between the application under execution and the network. Application of memory to each switch element allows the network to schedule topologies without loss of modularity, and improves system throughput significantly. The modularity of the interconnection network makes the system scalable at a low level. The Livermore test kernels were run on a network computer simulator. The worst-case communications overhead for the simulated cases was 8.5% of total run time.<>
{"title":"The Star network computer: a heterogeneous computing system","authors":"P. J. Zievers, C. Wu","doi":"10.1109/PCCC.1992.200511","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200511","url":null,"abstract":"An architecture for tightly coupled network computing is presented. The system was created to provide a scalable processing environment for computationally intensive applications. The system consists of a digital data switch surrounded by computing elements. The switch is composed of a back-to-back baseline multistage interconnection network, plus the ISDN protocol suite with an asynchronous transfer mode (ATM) sublayer. The key to the sources of the Star network computer is the cooperation between the application under execution and the network. Application of memory to each switch element allows the network to schedule topologies without loss of modularity, and improves system throughput significantly. The modularity of the interconnection network makes the system scalable at a low level. The Livermore test kernels were run on a network computer simulator. The worst-case communications overhead for the simulated cases was 8.5% of total run time.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125417340","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200547
E. Debenedictis, J. M. D. Del Rosario
Describes input/output (I/O) system software that makes I/O on a massively parallel computer as scalable as computing. The analysis is centered around mapping functions, which form an intellectual framework from which to understand parallel I/O. The I/O system not only provides the raw capability of doing parallel I/O, but is also convenient to use and compatible with Unix. These features are in release 3 of the nCUBE system software. This system will transfer data in parallel between scalable programs and/or I/O devices with any number of units. The first test demonstrated heterogeneous programming, or parallel pipes. Results are provided for a parallel pipe using various mapping combinations. The second test demonstrated I/O between parallel programs and secondary storage. Performance figures are given.<>
{"title":"nCUBE parallel I/O software","authors":"E. Debenedictis, J. M. D. Del Rosario","doi":"10.1109/PCCC.1992.200547","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200547","url":null,"abstract":"Describes input/output (I/O) system software that makes I/O on a massively parallel computer as scalable as computing. The analysis is centered around mapping functions, which form an intellectual framework from which to understand parallel I/O. The I/O system not only provides the raw capability of doing parallel I/O, but is also convenient to use and compatible with Unix. These features are in release 3 of the nCUBE system software. This system will transfer data in parallel between scalable programs and/or I/O devices with any number of units. The first test demonstrated heterogeneous programming, or parallel pipes. Results are provided for a parallel pipe using various mapping combinations. The second test demonstrated I/O between parallel programs and secondary storage. Performance figures are given.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121309185","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200518
H. Yen
The author composes a unified approach for dealing with the race detection problem for two entirely different models, namely, parallel programs and asynchronous circuits. It is shown that the problem of determining whether two transitions in a one-bounded conflict-free Petri net can become enabled simultaneously is solvable in polynomial time. This is referred to as the pairwise concurrency problem. It is then shown that the race detection problem for parallel programs (asynchronous circuits) and the pairwise concurrency problem for Petri nets are closely related to each other. As a result, race conditions can be detected efficiently for those parallel programs and asynchronous circuits that can be modeled by one-bounded conflict-free Petri nets.<>
{"title":"Applications of conflict-free Petri nets to parallel programs and asynchronous circuits","authors":"H. Yen","doi":"10.1109/PCCC.1992.200518","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200518","url":null,"abstract":"The author composes a unified approach for dealing with the race detection problem for two entirely different models, namely, parallel programs and asynchronous circuits. It is shown that the problem of determining whether two transitions in a one-bounded conflict-free Petri net can become enabled simultaneously is solvable in polynomial time. This is referred to as the pairwise concurrency problem. It is then shown that the race detection problem for parallel programs (asynchronous circuits) and the pairwise concurrency problem for Petri nets are closely related to each other. As a result, race conditions can be detected efficiently for those parallel programs and asynchronous circuits that can be modeled by one-bounded conflict-free Petri nets.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"212 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116113541","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}
Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200509
D. Simmons, N. Ellis, J. Stanley
A distributed knowledge-based system (KBS) designed to help computer network users and administrators use, manage, and maintain computer networks is described. The initial version of the system emphasizes the types of local area networks that are typically found in large industrial, governmental, or educational organizations. Knowledge used by the system is elicited from experts, generated from logical and physical network connectivity topology, and created by analyzing data gathered by simple network management protocol (SNMP) agents, system log agents, error message daemons, and interexpert system communication daemons. Knowledge is then shared by transferring chunks of knowledge between loosely coupled KBSs. Examples of knowledge sharing between KBSs are given.<>
{"title":"Knowledge sharing between distributed knowledge based systems","authors":"D. Simmons, N. Ellis, J. Stanley","doi":"10.1109/PCCC.1992.200509","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200509","url":null,"abstract":"A distributed knowledge-based system (KBS) designed to help computer network users and administrators use, manage, and maintain computer networks is described. The initial version of the system emphasizes the types of local area networks that are typically found in large industrial, governmental, or educational organizations. Knowledge used by the system is elicited from experts, generated from logical and physical network connectivity topology, and created by analyzing data gathered by simple network management protocol (SNMP) agents, system log agents, error message daemons, and interexpert system communication daemons. Knowledge is then shared by transferring chunks of knowledge between loosely coupled KBSs. Examples of knowledge sharing between KBSs are given.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125312590","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：