Pub Date : 1998-07-19DOI: 10.1109/MASCOT.1998.693672
A. Helmy, D. Estrin
We propose a method for using simulation to analyze the robustness of multiparty (multicast-based) protocols in a systematic fashion. We call our method Systematic Testing of Robustness by Examination of Selected Scenarios (STRESS). STRESS aims to cut the time and effort needed to explore pathological cases of a protocol during its design. This paper has two goals: (1) to describe the method, and (2) to serve as a case study of robustness analysis of multicast routing protocols. We aim to offer design tools similar to those used in CAD and VLSI design, and demonstrate how effective systematic simulation can be in studying protocol robustness.
{"title":"Simulation-based 'STRESS' testing case study: a multicast routing protocol","authors":"A. Helmy, D. Estrin","doi":"10.1109/MASCOT.1998.693672","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693672","url":null,"abstract":"We propose a method for using simulation to analyze the robustness of multiparty (multicast-based) protocols in a systematic fashion. We call our method Systematic Testing of Robustness by Examination of Selected Scenarios (STRESS). STRESS aims to cut the time and effort needed to explore pathological cases of a protocol during its design. This paper has two goals: (1) to describe the method, and (2) to serve as a case study of robustness analysis of multicast routing protocols. We aim to offer design tools similar to those used in CAD and VLSI design, and demonstrate how effective systematic simulation can be in studying protocol robustness.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114435165","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693705
S. Borst, S. A. Grandhi, Colin L. Kahn, K. Kumaran, B. Lubachevsky, Donna M. Sand
We describe the simulation of a new dynamic channel assignment algorithm in FDMA/TDMA wireless networks. The algorithm relies on periodic interference measurements by each of the base stations on the inactive frequencies, so as to identify appropriate candidate channels. The adaptive nature provides automatic configuration at the time of system initialization and adaptation to system expansion and traffic patterns with spatial or temporal variations. By eliminating the manual frequency planning process inherent to today's fixed channel assignment procedures, the self-organizing capability guarantees ease of operation for service providers, while increasing both capacity and voice quality. Our simulation experiments demonstrate stability of the algorithm and confirm its self-organizing capability. They also indicate a significant decrease of call blocking and dropping and other quality-of-service improvements.
{"title":"Simulation of self-organizing spectrum management in wireless networks","authors":"S. Borst, S. A. Grandhi, Colin L. Kahn, K. Kumaran, B. Lubachevsky, Donna M. Sand","doi":"10.1109/MASCOT.1998.693705","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693705","url":null,"abstract":"We describe the simulation of a new dynamic channel assignment algorithm in FDMA/TDMA wireless networks. The algorithm relies on periodic interference measurements by each of the base stations on the inactive frequencies, so as to identify appropriate candidate channels. The adaptive nature provides automatic configuration at the time of system initialization and adaptation to system expansion and traffic patterns with spatial or temporal variations. By eliminating the manual frequency planning process inherent to today's fixed channel assignment procedures, the self-organizing capability guarantees ease of operation for service providers, while increasing both capacity and voice quality. Our simulation experiments demonstrate stability of the algorithm and confirm its self-organizing capability. They also indicate a significant decrease of call blocking and dropping and other quality-of-service improvements.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130575556","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693711
P. Raghavan, H. Shachnai, Mira Yaniv
Speculative execution of code is becoming a key technique for enhancing the performance of pipeline processors. We study schemes that predict the execution path of a program based on the history of branch executions. Building on previous work, we present a model for analyzing the effective speedup from pipelining using various schemes for speculative execution. We follow this with stochastic analyses of various speculative execution schemes. Finally, we conclude with simulations covering several of the settings we study.
{"title":"Dynamic schemes for speculative execution of code","authors":"P. Raghavan, H. Shachnai, Mira Yaniv","doi":"10.1109/MASCOT.1998.693711","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693711","url":null,"abstract":"Speculative execution of code is becoming a key technique for enhancing the performance of pipeline processors. We study schemes that predict the execution path of a program based on the history of branch executions. Building on previous work, we present a model for analyzing the effective speedup from pipelining using various schemes for speculative execution. We follow this with stochastic analyses of various speculative execution schemes. Finally, we conclude with simulations covering several of the settings we study.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115803650","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693689
G. Ravindran, M. Stumm
This paper proposes and evaluates prioritized direct shared-memory multiprocessor networks. We use three components to implement prioritized networks, namely, priority-based link arbitration, priority inheritance, and dynamic virtual channels. The two major results from our study are: (i) adding priorities to direct shared-memory multiprocessor networks can lead to reduced average transaction latencies and increased system throughput when running traditional parallel applications, and (ii) a prioritized multiprocessor network can be used to reduce the worst-case latencies of time-constrained traffic when it co-exists with best-effort traffic, without penalizing the average performance of best-effort traffic.
{"title":"Prioritized multiprocessor networks: design and performance","authors":"G. Ravindran, M. Stumm","doi":"10.1109/MASCOT.1998.693689","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693689","url":null,"abstract":"This paper proposes and evaluates prioritized direct shared-memory multiprocessor networks. We use three components to implement prioritized networks, namely, priority-based link arbitration, priority inheritance, and dynamic virtual channels. The two major results from our study are: (i) adding priorities to direct shared-memory multiprocessor networks can lead to reduced average transaction latencies and increased system throughput when running traditional parallel applications, and (ii) a prioritized multiprocessor network can be used to reduce the worst-case latencies of time-constrained traffic when it co-exists with best-effort traffic, without penalizing the average performance of best-effort traffic.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125686354","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693697
Guang-Liang Li, Jun-hong Cui, Bo Li, Fang-Ming Li
Conventional analysis techniques of queueing systems typically assume that the stochastic process under study is already in steady state. This assumption is, however, not valid if the life cycle of the process is not large enough. Previous work in transient analysis of queueing systems usually focuses on Markov models. This paper, in contrast, presents an analysis technique for investigating transient performance of queueing systems that are not necessarily Markovian.
{"title":"A novel analysis technique for investigating transient performance of queueing systems","authors":"Guang-Liang Li, Jun-hong Cui, Bo Li, Fang-Ming Li","doi":"10.1109/MASCOT.1998.693697","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693697","url":null,"abstract":"Conventional analysis techniques of queueing systems typically assume that the stochastic process under study is already in steady state. This assumption is, however, not valid if the life cycle of the process is not large enough. Previous work in transient analysis of queueing systems usually focuses on Markov models. This paper, in contrast, presents an analysis technique for investigating transient performance of queueing systems that are not necessarily Markovian.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132490374","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693676
P. Mishra, M. Saksena
In this paper, we examine the effect of the buffer management policies, used at the IP/ATM gateway, on the end-to-end performance seen by IP traffic when using the ATM ABR service class. The ABR service class uses feedback-based flow control at the ATM layer to dynamically partition bandwidth among active ABR virtual circuits. It is likely that the ABR service will be operated in a manner designed to achieve nearly loss free operation in the core of the ATM network, causing most of the buffering requirements to be pushed to the ingress points of the ATM network. In our traffic model, an ingress IP/ATM gateway is responsible for setting up ATM virtual circuits and mapping IP packets onto ATM virtual circuits. In this model of network transport, the IP/ATM gateways serve as ABR source and destination end-points. Since the buffering available at an IP/ATM gateway will typically be small relative to the worst case buffer buildups that can occur due to transient overloads in the ATM network. Therefore, the buffer management policy can significantly impact the end to end performance.
{"title":"Effect of gateway buffer management policies on TCP over ATM performance","authors":"P. Mishra, M. Saksena","doi":"10.1109/MASCOT.1998.693676","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693676","url":null,"abstract":"In this paper, we examine the effect of the buffer management policies, used at the IP/ATM gateway, on the end-to-end performance seen by IP traffic when using the ATM ABR service class. The ABR service class uses feedback-based flow control at the ATM layer to dynamically partition bandwidth among active ABR virtual circuits. It is likely that the ABR service will be operated in a manner designed to achieve nearly loss free operation in the core of the ATM network, causing most of the buffering requirements to be pushed to the ingress points of the ATM network. In our traffic model, an ingress IP/ATM gateway is responsible for setting up ATM virtual circuits and mapping IP packets onto ATM virtual circuits. In this model of network transport, the IP/ATM gateways serve as ABR source and destination end-points. Since the buffering available at an IP/ATM gateway will typically be small relative to the worst case buffer buildups that can occur due to transient overloads in the ATM network. Therefore, the buffer management policy can significantly impact the end to end performance.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"98 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114271285","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693702
L. Tao
We present the design and implementation of an efficient online simulator for wormhole routing networks, which is an important part of the Concordia Parallel Systems Simulator (CPSS), a simulator for wormhole routed multicomputers. The ultimate purpose of the CPSS is to provide a parallel programming environment which allows users to study impacts of system and software factors on program performance and to locate performance bottlenecks in parallel programs. Our simulator can accurately simulate a large range of regular topologies that represent the communication structures of most wormhole routed networks. Users are given the flexibility of changing communication and computation parameters as often as needed without recompilation. It is unique in its integrated parallel simulation of the communication process and the execution of user applications. This makes possible real time evaluation of network performance in realistic application domains.
{"title":"An on-line simulator for wormhole routing networks","authors":"L. Tao","doi":"10.1109/MASCOT.1998.693702","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693702","url":null,"abstract":"We present the design and implementation of an efficient online simulator for wormhole routing networks, which is an important part of the Concordia Parallel Systems Simulator (CPSS), a simulator for wormhole routed multicomputers. The ultimate purpose of the CPSS is to provide a parallel programming environment which allows users to study impacts of system and software factors on program performance and to locate performance bottlenecks in parallel programs. Our simulator can accurately simulate a large range of regular topologies that represent the communication structures of most wormhole routed networks. Users are given the flexibility of changing communication and computation parameters as often as needed without recompilation. It is unique in its integrated parallel simulation of the communication process and the execution of user applications. This makes possible real time evaluation of network performance in realistic application domains.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123205143","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693671
A. Tanaka
The paper extends the definition of the working set for modeling spatial locality in program behavior, and it presents theoretical results. One of the theoretical results is that the working set based hit ratio can be given by the time or ensemble averages of the distributions of the interreference interval. We also present, as a theorem, that the average number of unique blocks in the extended working set can be given by the sum of the miss ratios. We derive a mathematical formula to calculate the hit ratio for Markov Chains. A kind of random walk is examined as an example of program behavior. The average number of unique blocks of a given block size in the extended working set is used for comparison with other empirical observations. The comparison had good agreement with our random walk model of program behavior and the empirical observations.
{"title":"Extension of the working set for modeling spatial locality in program behavior","authors":"A. Tanaka","doi":"10.1109/MASCOT.1998.693671","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693671","url":null,"abstract":"The paper extends the definition of the working set for modeling spatial locality in program behavior, and it presents theoretical results. One of the theoretical results is that the working set based hit ratio can be given by the time or ensemble averages of the distributions of the interreference interval. We also present, as a theorem, that the average number of unique blocks in the extended working set can be given by the sum of the miss ratios. We derive a mathematical formula to calculate the hit ratio for Markov Chains. A kind of random walk is examined as an example of program behavior. The average number of unique blocks of a given block size in the extended working set is used for comparison with other empirical observations. The comparison had good agreement with our random walk model of program behavior and the empirical observations.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122153514","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693704
R. A. Meyer, R. Bagrodia
Simulation of large sets of mobile computers or other wireless communication devices is difficult because of the computationally intensive models of wireless channels. Parallel simulation would seem to be applicable here because of the large computation granularity, but the location based communication topology makes conservative methods difficult to implement. This paper considers a novel approach to improving lookahead in conservative parallel simulations by differentiating between data flow paths in the simulation. An experimental study shows that for this application, the technique produces a 70% reduction in null message traffic, with only a 25% increase in null message computation overhead, and a consistent improvement in parallel performance.
{"title":"Improving lookahead in parallel wireless network simulation","authors":"R. A. Meyer, R. Bagrodia","doi":"10.1109/MASCOT.1998.693704","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693704","url":null,"abstract":"Simulation of large sets of mobile computers or other wireless communication devices is difficult because of the computationally intensive models of wireless channels. Parallel simulation would seem to be applicable here because of the large computation granularity, but the location based communication topology makes conservative methods difficult to implement. This paper considers a novel approach to improving lookahead in conservative parallel simulations by differentiating between data flow paths in the simulation. An experimental study shows that for this application, the technique produces a 70% reduction in null message traffic, with only a 25% increase in null message computation overhead, and a consistent improvement in parallel performance.","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127689663","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 : 1998-07-19DOI: 10.1109/MASCOT.1998.693688
A. Ferscha, James Johnson, Gabriele Anderst-Kotsis, C. Anglano
Self-managing systems able to dynamically re-configure with respect to time-varying workload mixes and changing system resource availability are of growing importance in heterogeneous multicomputer environments. Advanced performance evaluation techniques are needed to induce and assess the impact of such re-configurations where guaranteeing timeliness of reconfiguration activities is particularly challenging. A whole new class of methods supporting "pro-active" adaptivity based on the predicted system state at the re-configuration instant are needed to alleviate the shortcomings of "re-active" systems which bring reconfigurations in effect after the system state has changed. In this paper we argue for self-contained performance management of distributed applications, i.e. integrated performance tuning with the ability to automatically adapt the application behavior to the performance characteristics of the execution environment. Particularly, we study pro-active performance management for distributed simulation based on the Time Warp protocol executing on a network of workstations (NOWs).
{"title":"Pro-active performance management of distributed applications","authors":"A. Ferscha, James Johnson, Gabriele Anderst-Kotsis, C. Anglano","doi":"10.1109/MASCOT.1998.693688","DOIUrl":"https://doi.org/10.1109/MASCOT.1998.693688","url":null,"abstract":"Self-managing systems able to dynamically re-configure with respect to time-varying workload mixes and changing system resource availability are of growing importance in heterogeneous multicomputer environments. Advanced performance evaluation techniques are needed to induce and assess the impact of such re-configurations where guaranteeing timeliness of reconfiguration activities is particularly challenging. A whole new class of methods supporting \"pro-active\" adaptivity based on the predicted system state at the re-configuration instant are needed to alleviate the shortcomings of \"re-active\" systems which bring reconfigurations in effect after the system state has changed. In this paper we argue for self-contained performance management of distributed applications, i.e. integrated performance tuning with the ability to automatically adapt the application behavior to the performance characteristics of the execution environment. Particularly, we study pro-active performance management for distributed simulation based on the Time Warp protocol executing on a network of workstations (NOWs).","PeriodicalId":272859,"journal":{"name":"Proceedings. Sixth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.98TB100247)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966025","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：