Pub Date : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000149
V. Holmes, S. Kleban, David J. Miller, C. Pavlakos, C. Poore, R. Vandewart, C. Crowley
At Sandia National Laboratories, a Data Services system has been developed to provide web-based access to high-performance computing clusters that host a set of post-processing applications for very large-scale data manipulation and visualization. A three-tier architecture provides a meta-framework for a collection of smaller frameworks, each of which satisfies a particular aspect of the overall system, including frameworks for a common data model, distributed resource management, component-based software on the cluster, and security. A prototype implementation has been completed which demonstrates the use of all of these frameworks in an integrated environment to provide end users the ability to manage and understand simulation results for very large, complex problems.
{"title":"An architecture and implementation to support large-scale data access in scientific simulation environments","authors":"V. Holmes, S. Kleban, David J. Miller, C. Pavlakos, C. Poore, R. Vandewart, C. Crowley","doi":"10.1109/SIMSYM.2002.1000149","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000149","url":null,"abstract":"At Sandia National Laboratories, a Data Services system has been developed to provide web-based access to high-performance computing clusters that host a set of post-processing applications for very large-scale data manipulation and visualization. A three-tier architecture provides a meta-framework for a collection of smaller frameworks, each of which satisfies a particular aspect of the overall system, including frameworks for a common data model, distributed resource management, component-based software on the cluster, and security. A prototype implementation has been completed which demonstrates the use of all of these frameworks in an integrated environment to provide end users the ability to manage and understand simulation results for very large, complex problems.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131962008","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000155
Ali Maqousi, S. Tater, F. Ball
In this paper we describe the development of a measurement based flow acceptance control mechanism that will support guaranteed services in multiservice packet switched networks. Using simulation models we present simulation experiments with two monitoring techniques. One that monitors the percentile occupancy of queue and the other monitors the mean and variance of packet inter-arrival times and packet lengths of a continuous media packet stream. Both these techniques are considered in the development of the measurement based flow acceptance mechanism.
{"title":"Traffic monitoring techniques for measurement based flow acceptance control","authors":"Ali Maqousi, S. Tater, F. Ball","doi":"10.1109/SIMSYM.2002.1000155","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000155","url":null,"abstract":"In this paper we describe the development of a measurement based flow acceptance control mechanism that will support guaranteed services in multiservice packet switched networks. Using simulation models we present simulation experiments with two monitoring techniques. One that monitors the percentile occupancy of queue and the other monitors the mean and variance of packet inter-arrival times and packet lengths of a continuous media packet stream. Both these techniques are considered in the development of the measurement based flow acceptance mechanism.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130813383","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000105
W. M. Zuberek
The performance of modern computer systems is increasingly limited by long latencies of accesses to their memory systems. Instruction-level multithreading is a technique to tolerate long latencies of memory accesses by switching from one instruction thread to another. The paper shows that the simulation-based performance evaluation of distributed-memory multithreaded multiprocessor systems can be significantly simplified by using approximate models, composed of only a few processors, but with some parameters adjusted to represent the behavior of the original system.
{"title":"Approximate simulation of distributed-memory multithreaded multiprocessors","authors":"W. M. Zuberek","doi":"10.1109/SIMSYM.2002.1000105","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000105","url":null,"abstract":"The performance of modern computer systems is increasingly limited by long latencies of accesses to their memory systems. Instruction-level multithreading is a technique to tolerate long latencies of memory accesses by switching from one instruction thread to another. The paper shows that the simulation-based performance evaluation of distributed-memory multithreaded multiprocessor systems can be significantly simplified by using approximate models, composed of only a few processors, but with some parameters adjusted to represent the behavior of the original system.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"71 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114040109","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000136
H. Karatza, Ralph C. Hilzer
Efficient scheduling of jobs on parallel processors is essential for good performance. However, design of such schedulers is challenging because of the complex interaction between system and workload parameters. This paper studies the performance of a partitionable parallel system in which job scheduling depends on job characteristics. Jobs consist of a different number of tasks and are characterized as sequential or parallel depending on whether the tasks are processed sequentially on the same processor or at different processors. Jobs that consist of parallel tasks are called gangs, that is, they have to be scheduled to execute concurrently on processor partitions, where each task starts at the same time and computes at the same pace. The goal is to achieve good performance of sequential and parallel jobs. The performance of different scheduling schemes is compared over various workloads. Simulated results indicate that sequential jobs should not arbitrary overtake the execution of parallel jobs.
{"title":"Scheduling a job mix in a partitionable parallel system","authors":"H. Karatza, Ralph C. Hilzer","doi":"10.1109/SIMSYM.2002.1000136","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000136","url":null,"abstract":"Efficient scheduling of jobs on parallel processors is essential for good performance. However, design of such schedulers is challenging because of the complex interaction between system and workload parameters. This paper studies the performance of a partitionable parallel system in which job scheduling depends on job characteristics. Jobs consist of a different number of tasks and are characterized as sequential or parallel depending on whether the tasks are processed sequentially on the same processor or at different processors. Jobs that consist of parallel tasks are called gangs, that is, they have to be scheduled to execute concurrently on processor partitions, where each task starts at the same time and computes at the same pace. The goal is to achieve good performance of sequential and parallel jobs. The performance of different scheduling schemes is compared over various workloads. Simulated results indicate that sequential jobs should not arbitrary overtake the execution of parallel jobs.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114103411","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000159
H. Karatza
Clusters of workstations have emerged as a cost effective solution to the high performance computing problem. To take advantage of any opportunities, however, effective scheduling techniques are necessary that enable parallel applications to dynamically share workstations with their owners. In this paper a special type of parallel applications called gangs are considered. Gangs are jobs that consist of a number of interacting tasks scheduled to run simultaneously on separate and distinct processors. A simulation model is used to address performance issues associated with gang scheduling on a non-dedicated workstation cluster for various workloads. Simulated results indicate that the relative performance of the gang scheduling policies that we examine depends on the workload characteristics.
{"title":"Gang scheduling performance on a cluster of non-dedicated workstations","authors":"H. Karatza","doi":"10.1109/SIMSYM.2002.1000159","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000159","url":null,"abstract":"Clusters of workstations have emerged as a cost effective solution to the high performance computing problem. To take advantage of any opportunities, however, effective scheduling techniques are necessary that enable parallel applications to dynamically share workstations with their owners. In this paper a special type of parallel applications called gangs are considered. Gangs are jobs that consist of a number of interacting tasks scheduled to run simultaneously on separate and distinct processors. A simulation model is used to address performance issues associated with gang scheduling on a non-dedicated workstation cluster for various workloads. Simulated results indicate that the relative performance of the gang scheduling policies that we examine depends on the workload characteristics.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"80 2-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123567654","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000077
Shu Li, R. Melhem, T. Znati
Multicast networking is poised to play a prominent role in the future deployment of multimedia applications. Multimedia applications are usually resource intensive, have stringent quality of service requirements, and in many cases involve large multicast groups. Multicasting enables these applications to scale to a large number of users without overloading the network and server resources. This paper focuses on the design and analysis of a new heuristic for building low-cost, delay-bounded multicast trees to support multimedia applications. The approach used by the proposed heuristic to "optimize" the multicast tree limits its paths computation to paths which originate from the multicast destinations instead of all pairs of paths, as is the case in other well-known algorithms. Moreover, the path finding procedure, based on Dijkstra's algorithm, results in the selection of better paths than those discovered the k-shortest path based procedures. The simulation results show that the proposed heuristic outperforms on average other known heuristics.
{"title":"On the performance of STAR: an efficient delay-bound, low-cost multicast algorithm","authors":"Shu Li, R. Melhem, T. Znati","doi":"10.1109/SIMSYM.2002.1000077","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000077","url":null,"abstract":"Multicast networking is poised to play a prominent role in the future deployment of multimedia applications. Multimedia applications are usually resource intensive, have stringent quality of service requirements, and in many cases involve large multicast groups. Multicasting enables these applications to scale to a large number of users without overloading the network and server resources. This paper focuses on the design and analysis of a new heuristic for building low-cost, delay-bounded multicast trees to support multimedia applications. The approach used by the proposed heuristic to \"optimize\" the multicast tree limits its paths computation to paths which originate from the multicast destinations instead of all pairs of paths, as is the case in other well-known algorithms. Moreover, the path finding procedure, based on Dijkstra's algorithm, results in the selection of better paths than those discovered the k-shortest path based procedures. The simulation results show that the proposed heuristic outperforms on average other known heuristics.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132137273","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000177
D. Jiang, Zhiguo Li, Zhaoqi Wang, Gao Wen
In this paper, the principle of facial animation compatible with the MPEG-4 standard is introduced. Then the algorithm of calculating the displacements of face mesh vertices within the influence of facial animation parameters (FAPs) is discussed and improved. At last, a method of constructing FaceDefTables, which is one field of facial definition parameters (FDPs), is presented Using this technique, realistic facial animation can be generated.
{"title":"Animating 3D facial models with MPEG-4 FaceDefTables","authors":"D. Jiang, Zhiguo Li, Zhaoqi Wang, Gao Wen","doi":"10.1109/SIMSYM.2002.1000177","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000177","url":null,"abstract":"In this paper, the principle of facial animation compatible with the MPEG-4 standard is introduced. Then the algorithm of calculating the displacements of face mesh vertices within the influence of facial animation parameters (FAPs) is discussed and improved. At last, a method of constructing FaceDefTables, which is one field of facial definition parameters (FDPs), is presented Using this technique, realistic facial animation can be generated.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114198748","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000171
Jing Tian, J. Hähner, C. Becker, I. Stepanov, K. Rothermel
Imagine a world where people constantly try to pass through walls and cars suddenly leave the roads and drive into rivers. Although this is unrealistic, most simulations for mobile ad hoc networks so far are based on the so called "random walk" of mobile objects, which are not constrained by their surrounding spatial environments. In this paper we propose a novel graph-based mobility model, which provides a more realistic movement than the random walk model by reflecting the spatial constraints in the real world. We analyzed three commonly used ad hoc network routing protocols, DSDV, DSR and AODV with both a random walk-based and our graph-based mobility model. Our simulation results show that the spatial constraints have a strong impact on the performance of ad hoc routing protocols.
{"title":"Graph-based mobility model for mobile ad hoc network simulation","authors":"Jing Tian, J. Hähner, C. Becker, I. Stepanov, K. Rothermel","doi":"10.1109/SIMSYM.2002.1000171","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000171","url":null,"abstract":"Imagine a world where people constantly try to pass through walls and cars suddenly leave the roads and drive into rivers. Although this is unrealistic, most simulations for mobile ad hoc networks so far are based on the so called \"random walk\" of mobile objects, which are not constrained by their surrounding spatial environments. In this paper we propose a novel graph-based mobility model, which provides a more realistic movement than the random walk model by reflecting the spatial constraints in the real world. We analyzed three commonly used ad hoc network routing protocols, DSDV, DSR and AODV with both a random walk-based and our graph-based mobility model. Our simulation results show that the spatial constraints have a strong impact on the performance of ad hoc routing protocols.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123468158","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000147
Shu Chen, P. Olson, S. A. Morrison
Graphical user interfaces can provide interactive and intuitive visual communication to fault simulation and analysis application programs, enhancing the capabilities of engineers to conduct studies with ease and flexibility. Unfortunately, such benefits often come at the price of efficient CPU utilization and more complicated maintenance activities. Employing a distributed architecture can mitigate these costs by trading the one-time cost of more complex design activities for the long term benefits of ease of use and efficient resource utilization. TUFTsim, a multi-level concurrent simulation system, has been designed to address these concerns and demonstrates that an extensible, distributed architecture can be created without incurring excessive cost in processor and resource consumption. In addition, the investment in this architecture has also yielded benefits with respect to long-term maintenance and other software engineering considerations.
{"title":"A distributed graphical environment for interactive fault simulation and analysis","authors":"Shu Chen, P. Olson, S. A. Morrison","doi":"10.1109/SIMSYM.2002.1000147","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000147","url":null,"abstract":"Graphical user interfaces can provide interactive and intuitive visual communication to fault simulation and analysis application programs, enhancing the capabilities of engineers to conduct studies with ease and flexibility. Unfortunately, such benefits often come at the price of efficient CPU utilization and more complicated maintenance activities. Employing a distributed architecture can mitigate these costs by trading the one-time cost of more complex design activities for the long term benefits of ease of use and efficient resource utilization. TUFTsim, a multi-level concurrent simulation system, has been designed to address these concerns and demonstrates that an extensible, distributed architecture can be created without incurring excessive cost in processor and resource consumption. In addition, the investment in this architecture has also yielded benefits with respect to long-term maintenance and other software engineering considerations.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126499057","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000161
S. Kim, W. Tranter, S. Midkiff
Simulations of physical layer communication systems using Monte Carlo methods usually require long execution times, because of the slow convergence of the performance estimator. By utilizing reconfigurable hardware and other processing elements such as programmable DSPs, the overall runtime of the simulation can be greatly reduced compared to traditional simulations involving general-purpose processors. To form a flexible simulation environment, it is necessary to have a method of interconnecting the various processing elements, whether within a single computer or distributed over network. In this paper, an example of a reconfigurable simulator is presented. Also, middleware for distributed reconfigurable simulation is presented. First, a detailed architecture is illustrated. Then the simulation process and applications using the middleware are discussed.
{"title":"Middleware for a distributed reconfigurable simulator","authors":"S. Kim, W. Tranter, S. Midkiff","doi":"10.1109/SIMSYM.2002.1000161","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000161","url":null,"abstract":"Simulations of physical layer communication systems using Monte Carlo methods usually require long execution times, because of the slow convergence of the performance estimator. By utilizing reconfigurable hardware and other processing elements such as programmable DSPs, the overall runtime of the simulation can be greatly reduced compared to traditional simulations involving general-purpose processors. To form a flexible simulation environment, it is necessary to have a method of interconnecting the various processing elements, whether within a single computer or distributed over network. In this paper, an example of a reconfigurable simulator is presented. Also, middleware for distributed reconfigurable simulation is presented. First, a detailed architecture is illustrated. Then the simulation process and applications using the middleware are discussed.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115705078","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：