Pub Date : 1993-07-20DOI: 10.1109/HPDC.1993.263831
P. Dowd, K. Bogineni, K. A. Aly, J. A. Perreault
This paper introduces a hierarchical optical structure for processor interconnection and evaluates its performance. The architecture is based on wavelength division multiplexing (WDM) which enables multiple multi-access channels to be realized on a single optical fiber. The objective of the hierarchical architecture is to achieve scalability yet avoid the requirement of multiple wavelength tunable devices per node as with the WDM-based hypercube interconnection scheme. Furthermore, single-hop communication is achieved: a packet remains in the optical form from source to destination and does not require cross dimensional intermediate routing. The wavelength multiplexed hierarchical structure features wavelength channel re-use at each level, allowing scalability to very large system sizes. It employs acousto-optic tunable filters in conjunction with passive couplers to partition the traffic between different levels of the hierarchy without electronic intervention. A significant advantage of the proposed structure is its ability to dynamically vary the bandwidth provided to different levels of the hierarchy. The architecture is compared to a wavelength-flat architecture in terms of physical and performance scalability.<>
{"title":"Design and analysis of a hierarchical scalable photonic architecture","authors":"P. Dowd, K. Bogineni, K. A. Aly, J. A. Perreault","doi":"10.1109/HPDC.1993.263831","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263831","url":null,"abstract":"This paper introduces a hierarchical optical structure for processor interconnection and evaluates its performance. The architecture is based on wavelength division multiplexing (WDM) which enables multiple multi-access channels to be realized on a single optical fiber. The objective of the hierarchical architecture is to achieve scalability yet avoid the requirement of multiple wavelength tunable devices per node as with the WDM-based hypercube interconnection scheme. Furthermore, single-hop communication is achieved: a packet remains in the optical form from source to destination and does not require cross dimensional intermediate routing. The wavelength multiplexed hierarchical structure features wavelength channel re-use at each level, allowing scalability to very large system sizes. It employs acousto-optic tunable filters in conjunction with passive couplers to partition the traffic between different levels of the hierarchy without electronic intervention. A significant advantage of the proposed structure is its ability to dynamically vary the bandwidth provided to different levels of the hierarchy. The architecture is compared to a wavelength-flat architecture in terms of physical and performance scalability.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117086370","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263842
Patrick T. Homer, R. Schlichting
The numerical propulsion system simulation (NPSS) project has been initiated by NASA to expand the use of computer simulation in the development of new aircraft engines. A major goal is to study interactions between engine components using multiple computational codes, each modeling a separate component and potentially executing on a different machine in a network. Thus, a simulation run is a heterogeneous distributed program controlled by a simulation executive. This paper describes a prototype executive composed of the AVS visualization system and the Schooner heterogeneous remote procedure call (RPC) facility. In addition, the match between Schooner's capabilities and the needs of NPSS is evaluated based on the authors experience with a collection of test codes. This discussion not only documents the evolution of Schooner, but also serves to highlight the practical problems that can be encountered when dealing with heterogeneity and distribution in such applications.<>
{"title":"Support heterogeneity and distribution in the numerical propulsion system simulation project","authors":"Patrick T. Homer, R. Schlichting","doi":"10.1109/HPDC.1993.263842","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263842","url":null,"abstract":"The numerical propulsion system simulation (NPSS) project has been initiated by NASA to expand the use of computer simulation in the development of new aircraft engines. A major goal is to study interactions between engine components using multiple computational codes, each modeling a separate component and potentially executing on a different machine in a network. Thus, a simulation run is a heterogeneous distributed program controlled by a simulation executive. This paper describes a prototype executive composed of the AVS visualization system and the Schooner heterogeneous remote procedure call (RPC) facility. In addition, the match between Schooner's capabilities and the needs of NPSS is evaluated based on the authors experience with a collection of test codes. This discussion not only documents the evolution of Schooner, but also serves to highlight the practical problems that can be encountered when dealing with heterogeneity and distribution in such applications.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126297814","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263848
G. Minden, Joseph B. Evans, D. Petr, V. Frost
This paper describes a gigabit LAN/WAN gateway being developed for the MAGIC gigabit testbed. The gateway interfaces a gigabit LAN developed by Digital's Systems Research Center and the MAGIC SONET/ATM wide area network. The gateway provides 622 Mb/s throughput between the LAN and WAN environments, and supports either a single STS-12c or four STS-3c tributaries. Traffic measurement capability and support for multiple bandwidth management schemes are provided by this architecture.<>
{"title":"An ATM WAN/LAN gateway architecture","authors":"G. Minden, Joseph B. Evans, D. Petr, V. Frost","doi":"10.1109/HPDC.1993.263848","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263848","url":null,"abstract":"This paper describes a gigabit LAN/WAN gateway being developed for the MAGIC gigabit testbed. The gateway interfaces a gigabit LAN developed by Digital's Systems Research Center and the MAGIC SONET/ATM wide area network. The gateway provides 622 Mb/s throughput between the LAN and WAN environments, and supports either a single STS-12c or four STS-3c tributaries. Traffic measurement capability and support for multiple bandwidth management schemes are provided by this architecture.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"237 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127046651","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263825
A. Banerji, D. Kulkarni, J. Tracey, P. M. Greenawalt, D. Cohn
In order to exploit the latest advances in hardware technology, application developers need high-performance, easy-to-use cooperation tools that spun interconnections of standard hardware. Distributed shared memory has been proposed as such a cooperation tool, but performance problems have limited its usefulness. This paper argues that a new approach to distributed shared memory implementation can make it an effective tool in its own right and a foundation for other tools. It describes a prototype implementation that allows sharing of memory resources in workstation cluster. The prototype is based on an innovative, low-overhead messaging protocol which utilizes the high bandwidth of the underlying hardware, while adding very little latency overhead. Finally, the interface exported by this software is designed to function effectively as a substrate for a variety of cooperation tools.<>
{"title":"High-performance distributed shared memory substrate for workstation clusters","authors":"A. Banerji, D. Kulkarni, J. Tracey, P. M. Greenawalt, D. Cohn","doi":"10.1109/HPDC.1993.263825","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263825","url":null,"abstract":"In order to exploit the latest advances in hardware technology, application developers need high-performance, easy-to-use cooperation tools that spun interconnections of standard hardware. Distributed shared memory has been proposed as such a cooperation tool, but performance problems have limited its usefulness. This paper argues that a new approach to distributed shared memory implementation can make it an effective tool in its own right and a foundation for other tools. It describes a prototype implementation that allows sharing of memory resources in workstation cluster. The prototype is based on an innovative, low-overhead messaging protocol which utilizes the high bandwidth of the underlying hardware, while adding very little latency overhead. Finally, the interface exported by this software is designed to function effectively as a substrate for a variety of cooperation tools.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131934761","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263832
A. Nakamura, M. Takizawa
The authors discuss a distributed broadcast protocol which provides priority-based receipt ordering of protocol data units (PDUs) for the application entities by using the high-speed single-channel network in the presence of the loss of PDUs. There is a starvation problem, i.e. lower-priority PDUs can be left waiting indefinitely in the receipt queue since higher-priority PDUs jump over lower-priority ones. They present a method by which even lower-priority PDUs are delivered to the application entities in some pre-defined time by partitioning the receipt sequence of PDUs into runs, where each runs is priority-based ordered.<>
{"title":"Starvation-prevented priority-based total ordering broadcast protocol on high-speed single channel network","authors":"A. Nakamura, M. Takizawa","doi":"10.1109/HPDC.1993.263832","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263832","url":null,"abstract":"The authors discuss a distributed broadcast protocol which provides priority-based receipt ordering of protocol data units (PDUs) for the application entities by using the high-speed single-channel network in the presence of the loss of PDUs. There is a starvation problem, i.e. lower-priority PDUs can be left waiting indefinitely in the receipt queue since higher-priority PDUs jump over lower-priority ones. They present a method by which even lower-priority PDUs are delivered to the application entities in some pre-defined time by partitioning the receipt sequence of PDUs into runs, where each runs is priority-based ordered.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"370 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124635515","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263854
S. Hariri, Jong Park, Fang-Kuo Yu, M. Parashar, G. Fox
The proliferation of high performance workstations and the emergence of high speed networks have attracted a lot of interest in parallel and distributed computing (PDC). The authors envision that PDC environments with supercomputing capabilities will be available in the near future. However, a number of hardware and software issues have to be resolved before the full potential of these PDC environments can be exploited. The presented research has the following objectives: (1) to characterize the message-passing primitives used in parallel and distributed computing; (2) to develop a communication protocol that supports PDC; and (3) to develop an architectural support for PDC over gigabit networks.<>
{"title":"A message passing interface for parallel and distributed computing","authors":"S. Hariri, Jong Park, Fang-Kuo Yu, M. Parashar, G. Fox","doi":"10.1109/HPDC.1993.263854","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263854","url":null,"abstract":"The proliferation of high performance workstations and the emergence of high speed networks have attracted a lot of interest in parallel and distributed computing (PDC). The authors envision that PDC environments with supercomputing capabilities will be available in the near future. However, a number of hardware and software issues have to be resolved before the full potential of these PDC environments can be exploited. The presented research has the following objectives: (1) to characterize the message-passing primitives used in parallel and distributed computing; (2) to develop a communication protocol that supports PDC; and (3) to develop an architectural support for PDC over gigabit networks.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041528","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263830
A. Tripathi, Surya P. Koneru, Clifton Nock, Renu Tewari, Neeran M. Karnik, V. Bandi, Khaled Day, T. Noonan
This paper describes the approach taken for configuration management in the Nexus distributed operating system. Nexus uses kernel-level support for monitoring status of distributed components of an application. Periodic user-level messages are no longer required for status monitoring. Group and dependency relationships between such components can be defined by the programmer for the purpose of configuration monitoring and management. An object belonging to a distributed application can be monitored by its host kernel for some system-defined exception conditions. When any of these conditions arise, other objects are notified through signals or messages, as specified by the programmer.<>
{"title":"Reliable management of distributed computations in Nexus","authors":"A. Tripathi, Surya P. Koneru, Clifton Nock, Renu Tewari, Neeran M. Karnik, V. Bandi, Khaled Day, T. Noonan","doi":"10.1109/HPDC.1993.263830","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263830","url":null,"abstract":"This paper describes the approach taken for configuration management in the Nexus distributed operating system. Nexus uses kernel-level support for monitoring status of distributed components of an application. Periodic user-level messages are no longer required for status monitoring. Group and dependency relationships between such components can be defined by the programmer for the purpose of configuration monitoring and management. An object belonging to a distributed application can be monitored by its host kernel for some system-defined exception conditions. When any of these conditions arise, other objects are notified through signals or messages, as specified by the programmer.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133789794","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263826
N. Sharma, D. Agrawal
Design of a large distributed system (DS) is becoming increasing important and with its added popularity, it is crucial to define its topology based on some objective function. This paper introduces a reliability-based systematic approach for defining the topology of a DS network in a hierarchical form, given the traffic requirements, a set of cluster topologies and the cost constraints. The authors scheme first identifies a group of permissible inter-cluster links which yields the maximum network reliability to cost ratio and then selects the gateways within each cluster for balancing the traffic through the inter-cluster links and the node degrees within each cluster. The usefulness of their method lies in a simultaneous consideration of the cost and the network reliability. Some examples are included to illustrate their design procedure.<>
{"title":"Hierarchical distributed system network design with cost-performance tradeoffs","authors":"N. Sharma, D. Agrawal","doi":"10.1109/HPDC.1993.263826","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263826","url":null,"abstract":"Design of a large distributed system (DS) is becoming increasing important and with its added popularity, it is crucial to define its topology based on some objective function. This paper introduces a reliability-based systematic approach for defining the topology of a DS network in a hierarchical form, given the traffic requirements, a set of cluster topologies and the cost constraints. The authors scheme first identifies a group of permissible inter-cluster links which yields the maximum network reliability to cost ratio and then selects the gateways within each cluster for balancing the traffic through the inter-cluster links and the node degrees within each cluster. The usefulness of their method lies in a simultaneous consideration of the cost and the network reliability. Some examples are included to illustrate their design procedure.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125193334","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263855
T. Braun, C. Schmidt
Requirements of emerging applications together with rapid changes in networking technology towards gigabit speeds require new adequate transport systems. Integrated designs of transport services, protocol architecture, and implementation platforms are needed for the requirements of forthcoming applications in high-speed network environments. The transport subsystem PATROCLOS (Parallel Transport subsystem for cell based high speed networks) is designed with special emphasis on a high degree of inherent parallelism to allow efficient implementations on multiprocessor architectures combined with specialised hardware for very time critical functions. The paper presents transport system design guidelines based on experiences gained with parallel implementations of transport and network layer protocols on transputer networks, an implementation architecture for PATROCLOS based on transputer networks and results of a performance evaluation, which indicate promising throughput values.<>
{"title":"Implementation of a parallel transport subsystem on a multiprocessor architecture","authors":"T. Braun, C. Schmidt","doi":"10.1109/HPDC.1993.263855","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263855","url":null,"abstract":"Requirements of emerging applications together with rapid changes in networking technology towards gigabit speeds require new adequate transport systems. Integrated designs of transport services, protocol architecture, and implementation platforms are needed for the requirements of forthcoming applications in high-speed network environments. The transport subsystem PATROCLOS (Parallel Transport subsystem for cell based high speed networks) is designed with special emphasis on a high degree of inherent parallelism to allow efficient implementations on multiprocessor architectures combined with specialised hardware for very time critical functions. The paper presents transport system design guidelines based on experiences gained with parallel implementations of transport and network layer protocols on transputer networks, an implementation architecture for PATROCLOS based on transputer networks and results of a performance evaluation, which indicate promising throughput values.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128811203","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 : 1993-07-20DOI: 10.1109/HPDC.1993.263864
H. T. Kung
Summary form only given. This paper argues that, for high-speed networks such as ATM, it is important to use link-by-link flow control on a per virtual circuit (VC) basis. It can effectively control congestion and maximize network utilization. Three progressively memory-efficient, credit-based flow control schemes, called N123, N123+ and N23, are described, and simulation results of these schemes are presented. An ATM switch, which supports credit-based flow control, is under joint development by BNR and Harvard.<>
{"title":"New flow control methods for high-speed networks","authors":"H. T. Kung","doi":"10.1109/HPDC.1993.263864","DOIUrl":"https://doi.org/10.1109/HPDC.1993.263864","url":null,"abstract":"Summary form only given. This paper argues that, for high-speed networks such as ATM, it is important to use link-by-link flow control on a per virtual circuit (VC) basis. It can effectively control congestion and maximize network utilization. Three progressively memory-efficient, credit-based flow control schemes, called N123, N123+ and N23, are described, and simulation results of these schemes are presented. An ATM switch, which supports credit-based flow control, is under joint development by BNR and Harvard.<<ETX>>","PeriodicalId":226280,"journal":{"name":"[1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117344365","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：