Pub Date : 1992-04-14DOI: 10.1109/FTDCS.1992.217475
S. Chang, A. Tantawy, H. Meleis
This paper discusses the impact of various design and implementation factors on the performance of a communication subsystem. Measurements obtained from two different software implementations of the same protocol (ISO 8802-2 logical link control protocol type 2) over three different experimental hardware platforms are used as a basis for comparison. The impact of exploiting parallelism is especially emphasized. The effects of software structure and optimized hand coding are also discussed. Although some results pertain to only one specific protocol, similarities with other connection-oriented protocols can be drawn.<>
{"title":"Parallelism and performance in communication subsystems","authors":"S. Chang, A. Tantawy, H. Meleis","doi":"10.1109/FTDCS.1992.217475","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217475","url":null,"abstract":"This paper discusses the impact of various design and implementation factors on the performance of a communication subsystem. Measurements obtained from two different software implementations of the same protocol (ISO 8802-2 logical link control protocol type 2) over three different experimental hardware platforms are used as a basis for comparison. The impact of exploiting parallelism is especially emphasized. The effects of software structure and optimized hand coding are also discussed. Although some results pertain to only one specific protocol, similarities with other connection-oriented protocols can be drawn.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124084061","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217493
P. Egloff, E. Moeller, A. Scheller, G. Schurmann
Within the BERliner KOMmunikationssystem (BERKOM) a Reference Model has been developed which can be used as a framework to specify, design and describe future oriented telecommunication services. In this paper the principles and the first two levels of refinement are described as a taxonomy of characteristics of distributed applications.<>
{"title":"The BERKOM Reference Model: the base for a taxonomy of characteristics of distributed applications","authors":"P. Egloff, E. Moeller, A. Scheller, G. Schurmann","doi":"10.1109/FTDCS.1992.217493","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217493","url":null,"abstract":"Within the BERliner KOMmunikationssystem (BERKOM) a Reference Model has been developed which can be used as a framework to specify, design and describe future oriented telecommunication services. In this paper the principles and the first two levels of refinement are described as a taxonomy of characteristics of distributed applications.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128747699","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217505
V. Tschammer, A. Wolisz, M. Walch
The authors consider the case of trading in an environment of autonomous components. Trading is the process of matching a service request with the offers to support that particular service made by potential servers. In the case of multiple matching offers a selection of the most suitable server can be made according to the properties of the server. Among the possible selection policies the authors concentrate on those taking into account the actual load of the server. The selection process is usually delegated to a specialised type of component, called the trader. Various aspects influence the performance of the traders, including the delay of the information on the server load, the selection strategy, and the number of concurrent traders. The authors investigate several trading strategies in a scenario where traders receive the load information periodically and where multiple traders operate concurrently.<>
{"title":"The performance of multiple traders operating in the same domain","authors":"V. Tschammer, A. Wolisz, M. Walch","doi":"10.1109/FTDCS.1992.217505","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217505","url":null,"abstract":"The authors consider the case of trading in an environment of autonomous components. Trading is the process of matching a service request with the offers to support that particular service made by potential servers. In the case of multiple matching offers a selection of the most suitable server can be made according to the properties of the server. Among the possible selection policies the authors concentrate on those taking into account the actual load of the server. The selection process is usually delegated to a specialised type of component, called the trader. Various aspects influence the performance of the traders, including the delay of the information on the server load, the selection strategy, and the number of concurrent traders. The authors investigate several trading strategies in a scenario where traders receive the load information periodically and where multiple traders operate concurrently.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"41 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127654794","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217465
S. Nishimura, R. Mukai, T. Kunii
This paper describes a parallel computer architecture for real-time image synthesis. The architecture is based on a loosely-coupled array of general purpose processors equipped with a novel frame buffer subsystem called a conflict-free multiport frame buffer (CFMFB) which enables every processor to write any region of the screen without access conflicts. An efficient polygon rendering method using the CFMFB is also described. The method assigns a subset of the polygons to each processor, which independently calculates the images of the assigned polygons with the Z-buffer algorithm. The performance of the system is estimated through simulation experiments with sample scenes.<>
{"title":"A loosely-coupled parallel graphics architecture based on a conflict-free multiport frame buffer","authors":"S. Nishimura, R. Mukai, T. Kunii","doi":"10.1109/FTDCS.1992.217465","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217465","url":null,"abstract":"This paper describes a parallel computer architecture for real-time image synthesis. The architecture is based on a loosely-coupled array of general purpose processors equipped with a novel frame buffer subsystem called a conflict-free multiport frame buffer (CFMFB) which enables every processor to write any region of the screen without access conflicts. An efficient polygon rendering method using the CFMFB is also described. The method assigns a subset of the polygons to each processor, which independently calculates the images of the assigned polygons with the Z-buffer algorithm. The performance of the system is estimated through simulation experiments with sample scenes.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130145266","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217480
S. Sheu, Jinchun Ho, J. Juang
This paper describes a program decomposition scheme that decomposes a C++ program into a set of concurrent tasks to support fault tolerant computing in distributed environments. This scheme consists of a C++ analyzer for program decomposition and a set of mechanisms to perform run-time object backup and error recovery. The analyzer uses a weighted-object approach to decompose an object into a set of concurrent tasks or combines a set of objects into a single task. The analyzer guarantees that the resulting decomposition will not violate system resource constraints. A reliable message passing protocol is also generated by the program analyzer for remote object references. Run time supports for fault tolerant computing based on the decomposed objects are discussed, which consist of an interface, a reliable message passing mechanism and a recovery mechanism. The message passing mechanism updates backup storage whenever a message is passed to avoid Domino effect.<>
{"title":"Decomposition of object-oriented programs for fault tolerant computing in distributed environment","authors":"S. Sheu, Jinchun Ho, J. Juang","doi":"10.1109/FTDCS.1992.217480","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217480","url":null,"abstract":"This paper describes a program decomposition scheme that decomposes a C++ program into a set of concurrent tasks to support fault tolerant computing in distributed environments. This scheme consists of a C++ analyzer for program decomposition and a set of mechanisms to perform run-time object backup and error recovery. The analyzer uses a weighted-object approach to decompose an object into a set of concurrent tasks or combines a set of objects into a single task. The analyzer guarantees that the resulting decomposition will not violate system resource constraints. A reliable message passing protocol is also generated by the program analyzer for remote object references. Run time supports for fault tolerant computing based on the decomposed objects are discussed, which consist of an interface, a reliable message passing mechanism and a recovery mechanism. The message passing mechanism updates backup storage whenever a message is passed to avoid Domino effect.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130414874","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217506
L. F. Pires, M. V. van Sinderen, C. Vissers
This paper introduces the concept of pre-defined implementation constructs (PDICs) as a method for distributed systems design. It discusses how PDICs should be selected and used, and shows the applicability of this method on basis of a middle size design example: the implementation of a sliding window protocol.<>
{"title":"On the use of pre-defined implementation constructs in distributed systems design","authors":"L. F. Pires, M. V. van Sinderen, C. Vissers","doi":"10.1109/FTDCS.1992.217506","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217506","url":null,"abstract":"This paper introduces the concept of pre-defined implementation constructs (PDICs) as a method for distributed systems design. It discusses how PDICs should be selected and used, and shows the applicability of this method on basis of a middle size design example: the implementation of a sliding window protocol.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133863395","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217478
M. Pan, Shi-Kuo Chang, Chien-Chiao Yang
A multidatabase system (MDBS) is a system that integrates the operational data of several autonomous database systems and provides a uniform interface and control mechanisms to control access to those data. To efficiently retrieve and manipulate the data stored in MDBS, a metadata dictionary is needed as a repository of essential information for reasoning, controlling, and maintaining the retrieval/manipulation processes. The authors develop a two-level active metadata dictionary approach based on logic for building a metadata dictionary, query processing, and maintenance in MDBS. The low-level metadata dictionaries (LLMDs) keep metadata for each corresponding local database in MDBS, respectively. The high-level metadata dictionary (HLMD) integrates the metadata about all LLMDs.<>
{"title":"Semantic query processing in multidatabase systems: a logic-based approach","authors":"M. Pan, Shi-Kuo Chang, Chien-Chiao Yang","doi":"10.1109/FTDCS.1992.217478","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217478","url":null,"abstract":"A multidatabase system (MDBS) is a system that integrates the operational data of several autonomous database systems and provides a uniform interface and control mechanisms to control access to those data. To efficiently retrieve and manipulate the data stored in MDBS, a metadata dictionary is needed as a repository of essential information for reasoning, controlling, and maintaining the retrieval/manipulation processes. The authors develop a two-level active metadata dictionary approach based on logic for building a metadata dictionary, query processing, and maintenance in MDBS. The low-level metadata dictionaries (LLMDs) keep metadata for each corresponding local database in MDBS, respectively. The high-level metadata dictionary (HLMD) integrates the metadata about all LLMDs.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122350896","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217494
T. Magedanz
A number of different concepts has been developed for the provision of future open service environments. The most important concepts identified in this context are the intelligent network (IN) architecture, which allows for the flexible and uniform provision of a variety of future telecommunication services by the definition of functional network elements and a set of generic service building blocks, and CCITT's telecommunication management network (TMN) providing a range of management functions above a set of support systems, needed to operate, control and maintain future telecommunication networks and services. Based on the management related aspects of future IN-structured telecommunication networks, this paper examines the issues and relations of both concepts focussing on a possible integration of both concepts into a common telecommunication platform.<>
{"title":"IN and TMN-key concepts for future telecom networks","authors":"T. Magedanz","doi":"10.1109/FTDCS.1992.217494","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217494","url":null,"abstract":"A number of different concepts has been developed for the provision of future open service environments. The most important concepts identified in this context are the intelligent network (IN) architecture, which allows for the flexible and uniform provision of a variety of future telecommunication services by the definition of functional network elements and a set of generic service building blocks, and CCITT's telecommunication management network (TMN) providing a range of management functions above a set of support systems, needed to operate, control and maintain future telecommunication networks and services. Based on the management related aspects of future IN-structured telecommunication networks, this paper examines the issues and relations of both concepts focussing on a possible integration of both concepts into a common telecommunication platform.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121286906","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217491
H. Dediu, C. Chang, H. K. Azzam
The authors consider a class of processes which is characterized by very long running times and very large data dependencies. Such processes exploit the availability of all system resources on the executing host. The long running times imply a need for undivided CPU bandwidth as well as an intolerance for system faults. The authors consider the problem of supporting the execution of such heavyweight processes on small systems whose reliability and availability cannot be guaranteed. The support mechanism uses process migration and redundant execution with checkpointing to guarantee process completion.<>
{"title":"Heavyweight process migration","authors":"H. Dediu, C. Chang, H. K. Azzam","doi":"10.1109/FTDCS.1992.217491","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217491","url":null,"abstract":"The authors consider a class of processes which is characterized by very long running times and very large data dependencies. Such processes exploit the availability of all system resources on the executing host. The long running times imply a need for undivided CPU bandwidth as well as an intolerance for system faults. The authors consider the problem of supporting the execution of such heavyweight processes on small systems whose reliability and availability cannot be guaranteed. The support mechanism uses process migration and redundant execution with checkpointing to guarantee process completion.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114848172","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 : 1992-04-14DOI: 10.1109/FTDCS.1992.217517
A. Benslimane
Realizing the need for a precise model of computer communications protocols, many different approaches are being investigated. The author presents an algebraic approach to formally specify protocols composed of many modules. The protocols studied are described in the model of finite state machine and then transformed into a set of process equations. The main concept consists in carrying out transformations on these equations in order to prove some properties. The reachability analysis can then be defined in the form of algebraic transformation rules applied to the global system states. The properties to verify during the communication between processes are the detection of some logical errors such as deadlocks, blocking or unspecified receptions.<>
{"title":"An algebraic approach to validate communication protocols","authors":"A. Benslimane","doi":"10.1109/FTDCS.1992.217517","DOIUrl":"https://doi.org/10.1109/FTDCS.1992.217517","url":null,"abstract":"Realizing the need for a precise model of computer communications protocols, many different approaches are being investigated. The author presents an algebraic approach to formally specify protocols composed of many modules. The protocols studied are described in the model of finite state machine and then transformed into a set of process equations. The main concept consists in carrying out transformations on these equations in order to prove some properties. The reachability analysis can then be defined in the form of algebraic transformation rules applied to the global system states. The properties to verify during the communication between processes are the detection of some logical errors such as deadlocks, blocking or unspecified receptions.<<ETX>>","PeriodicalId":186762,"journal":{"name":"Proceedings of the Third Workshop on Future Trends of Distributed Computing Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125383483","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：